style: Fix final import sorting in provider_test.py

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

docs/concepts/knowledge.mdx

@@ -91,7 +91,7 @@ result = crew.kickoff(inputs={"question": "What city does John live in and how o
 ```
 
 
-Here's another example with the `CrewDoclingSource`. The CrewDoclingSource is actually quite versatile and can handle multiple file formats including TXT, PDF, DOCX, HTML, and more. 
+Here's another example with the `CrewDoclingSource`. The CrewDoclingSource is actually quite versatile and can handle multiple file formats including MD, PDF, DOCX, HTML, and more. 
 
 <Note>
   You need to install `docling` for the following example to work: `uv add docling`
@@ -152,10 +152,10 @@ Here are examples of how to use different types of knowledge sources:
 
 ### Text File Knowledge Source
 ```python
-from crewai.knowledge.source.crew_docling_source import CrewDoclingSource
+from crewai.knowledge.source.text_file_knowledge_source import TextFileKnowledgeSource
 
 # Create a text file knowledge source
-text_source = CrewDoclingSource(
+text_source = TextFileKnowledgeSource(
     file_paths=["document.txt", "another.txt"]
 )
 

docs/concepts/memory.mdx

@@ -282,6 +282,19 @@ my_crew = Crew(
 
 ### Using Google AI embeddings
 
+#### Prerequisites
+Before using Google AI embeddings, ensure you have:
+- Access to the Gemini API
+- The necessary API keys and permissions
+
+You will need to update your *pyproject.toml* dependencies:
+```YAML
+dependencies = [
+    "google-generativeai>=0.8.4", #main version in January/2025 - crewai v.0.100.0 and crewai-tools 0.33.0
+    "crewai[tools]>=0.100.0,<1.0.0"
+]
+```
+
 ```python Code
 from crewai import Crew, Agent, Task, Process
 
@@ -434,6 +447,38 @@ my_crew = Crew(
 )
 ```
 
+### Using Amazon Bedrock embeddings
+
+```python Code
+# Note: Ensure you have installed `boto3` for Bedrock embeddings to work.
+
+import os
+import boto3
+from crewai import Crew, Agent, Task, Process
+
+boto3_session = boto3.Session(
+    region_name=os.environ.get("AWS_REGION_NAME"),
+    aws_access_key_id=os.environ.get("AWS_ACCESS_KEY_ID"),
+    aws_secret_access_key=os.environ.get("AWS_SECRET_ACCESS_KEY")
+)
+
+my_crew = Crew(
+    agents=[...],
+    tasks=[...],
+    process=Process.sequential,
+    memory=True,
+    embedder={
+    "provider": "bedrock",
+        "config":{
+            "session": boto3_session,
+            "model": "amazon.titan-embed-text-v2:0",
+            "vector_dimension": 1024
+        }
+    }
+    verbose=True
+)
+```
+
 ### Adding Custom Embedding Function
 
 ```python Code

docs/concepts/tasks.mdx

@@ -268,7 +268,7 @@ analysis_task = Task(
 
 Task guardrails provide a way to validate and transform task outputs before they
 are passed to the next task. This feature helps ensure data quality and provides
-efeedback to agents when their output doesn't meet specific criteria.
+feedback to agents when their output doesn't meet specific criteria.
 
 ### Using Task Guardrails
 

docs/how-to/langfuse-observability.mdx

@@ -0,0 +1,98 @@
+---
+title: Agent Monitoring with Langfuse
+description: Learn how to integrate Langfuse with CrewAI via OpenTelemetry using OpenLit
+icon: magnifying-glass-chart
+---
+
+# Integrate Langfuse with CrewAI
+
+This notebook demonstrates how to integrate **Langfuse** with **CrewAI** using OpenTelemetry via the **OpenLit** SDK. By the end of this notebook, you will be able to trace your CrewAI applications with Langfuse for improved observability and debugging.
+
+> **What is Langfuse?** [Langfuse](https://langfuse.com) is an open-source LLM engineering platform. It provides tracing and monitoring capabilities for LLM applications, helping developers debug, analyze, and optimize their AI systems. Langfuse integrates with various tools and frameworks via native integrations, OpenTelemetry, and APIs/SDKs.
+
+## Get Started
+
+We'll walk through a simple example of using CrewAI and integrating it with Langfuse via OpenTelemetry using OpenLit.
+
+### Step 1: Install Dependencies
+
+
+```python
+%pip install langfuse openlit crewai crewai_tools
+```
+
+### Step 2: Set Up Environment Variables
+
+Set your Langfuse API keys and configure OpenTelemetry export settings to send traces to Langfuse. Please refer to the [Langfuse OpenTelemetry Docs](https://langfuse.com/docs/opentelemetry/get-started) for more information on the Langfuse OpenTelemetry endpoint `/api/public/otel` and authentication.
+
+
+```python
+import os
+import base64
+
+LANGFUSE_PUBLIC_KEY="pk-lf-..."
+LANGFUSE_SECRET_KEY="sk-lf-..."
+LANGFUSE_AUTH=base64.b64encode(f"{LANGFUSE_PUBLIC_KEY}:{LANGFUSE_SECRET_KEY}".encode()).decode()
+
+os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "https://cloud.langfuse.com/api/public/otel" # EU data region
+# os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "https://us.cloud.langfuse.com/api/public/otel" # US data region
+os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = f"Authorization=Basic {LANGFUSE_AUTH}"
+
+# your openai key
+os.environ["OPENAI_API_KEY"] = "sk-..."
+```
+
+### Step 3: Initialize OpenLit
+
+Initialize the OpenLit OpenTelemetry instrumentation SDK to start capturing OpenTelemetry traces.
+
+
+```python
+import openlit
+
+openlit.init()
+```
+
+### Step 4: Create a Simple CrewAI Application
+
+We'll create a simple CrewAI application where multiple agents collaborate to answer a user's question.
+
+
+```python
+from crewai import Agent, Task, Crew
+
+from crewai_tools import (
+    WebsiteSearchTool
+)
+
+web_rag_tool = WebsiteSearchTool()
+
+writer = Agent(
+        role="Writer",
+        goal="You make math engaging and understandable for young children through poetry",
+        backstory="You're an expert in writing haikus but you know nothing of math.",
+        tools=[web_rag_tool],  
+    )
+
+task = Task(description=("What is {multiplication}?"),
+            expected_output=("Compose a haiku that includes the answer."),
+            agent=writer)
+
+crew = Crew(
+  agents=[writer],
+  tasks=[task],
+  share_crew=False
+)
+```
+
+### Step 5: See Traces in Langfuse
+
+After running the agent, you can view the traces generated by your CrewAI application in [Langfuse](https://cloud.langfuse.com). You should see detailed steps of the LLM interactions, which can help you debug and optimize your AI agent.
+
+![CrewAI example trace in Langfuse](https://langfuse.com/images/cookbook/integration_crewai/crewai-example-trace.png)
+
+_[Public example trace in Langfuse](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/e2cf380ffc8d47d28da98f136140642b?timestamp=2025-02-05T15%3A12%3A02.717Z&observation=3b32338ee6a5d9af)_
+
+## References
+
+- [Langfuse OpenTelemetry Docs](https://langfuse.com/docs/opentelemetry/get-started)

docs/how-to/portkey-observability-and-guardrails.mdx

@@ -1,211 +0,0 @@
-# Portkey Integration with CrewAI
-<img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-CrewAI.png" alt="Portkey CrewAI Header Image" width="70%" />
-
-
-[Portkey](https://portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai) is a 2-line upgrade to make your CrewAI agents reliable, cost-efficient, and fast.
-
-Portkey adds 4 core production capabilities to any CrewAI agent:
-1. Routing to **200+ LLMs**
-2. Making each LLM call more robust
-3. Full-stack tracing & cost, performance analytics
-4. Real-time guardrails to enforce behavior
-
-
-
-
-
-## Getting Started
-
-1. **Install Required Packages:**
-
-```bash
-pip install -qU crewai portkey-ai
-```
-
-2. **Configure the LLM Client:**
-
-To build CrewAI Agents with Portkey, you'll need two keys:
-- **Portkey API Key**: Sign up on the [Portkey app](https://app.portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai) and copy your API key
-- **Virtual Key**: Virtual Keys securely manage your LLM API keys in one place. Store your LLM provider API keys securely in Portkey's vault
-
-```python
-from crewai import LLM
-from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
-
-gpt_llm = LLM(
-    model="gpt-4",
-    base_url=PORTKEY_GATEWAY_URL,
-    api_key="dummy", # We are using Virtual key
-    extra_headers=createHeaders(
-        api_key="YOUR_PORTKEY_API_KEY",
-        virtual_key="YOUR_VIRTUAL_KEY", # Enter your Virtual key from Portkey
-    )
-)
-```
-
-3. **Create and Run Your First Agent:**
-
-```python
-from crewai import Agent, Task, Crew
-
-# Define your agents with roles and goals
-coder = Agent(
-    role='Software developer',
-    goal='Write clear, concise code on demand',
-    backstory='An expert coder with a keen eye for software trends.',
-    llm=gpt_llm
-)
-
-# Create tasks for your agents
-task1 = Task(
-    description="Define the HTML for making a simple website with heading- Hello World! Portkey is working!",
-    expected_output="A clear and concise HTML code",
-    agent=coder
-)
-
-# Instantiate your crew
-crew = Crew(
-    agents=[coder],
-    tasks=[task1],
-)
-
-result = crew.kickoff()
-print(result)
-```
-
-
-## Key Features
-
-| Feature | Description |
-|---------|-------------|
-| 🌐 Multi-LLM Support | Access OpenAI, Anthropic, Gemini, Azure, and 250+ providers through a unified interface |
-| 🛡️ Production Reliability | Implement retries, timeouts, load balancing, and fallbacks |
-| 📊 Advanced Observability | Track 40+ metrics including costs, tokens, latency, and custom metadata |
-| 🔍 Comprehensive Logging | Debug with detailed execution traces and function call logs |
-| 🚧 Security Controls | Set budget limits and implement role-based access control |
-| 🔄 Performance Analytics | Capture and analyze feedback for continuous improvement |
-| 💾 Intelligent Caching | Reduce costs and latency with semantic or simple caching |
-
-
-## Production Features with Portkey Configs
-
-All features mentioned below are through Portkey's Config system. Portkey's Config system allows you to define routing strategies using simple JSON objects in your LLM API calls. You can create and manage Configs directly in your code or through the Portkey Dashboard. Each Config has a unique ID for easy reference.
-
-<Frame>
-    <img src="https://raw.githubusercontent.com/Portkey-AI/docs-core/refs/heads/main/images/libraries/libraries-3.avif"/>
-</Frame>
-
-
-### 1. Use 250+ LLMs
-Access various LLMs like Anthropic, Gemini, Mistral, Azure OpenAI, and more with minimal code changes. Switch between providers or use them together seamlessly. [Learn more about Universal API](https://portkey.ai/docs/product/ai-gateway/universal-api)
-
-
-Easily switch between different LLM providers:
-
-```python
-# Anthropic Configuration
-anthropic_llm = LLM(
-    model="claude-3-5-sonnet-latest",
-    base_url=PORTKEY_GATEWAY_URL,
-    api_key="dummy",
-    extra_headers=createHeaders(
-        api_key="YOUR_PORTKEY_API_KEY",
-        virtual_key="YOUR_ANTHROPIC_VIRTUAL_KEY", #You don't need provider when using Virtual keys
-        trace_id="anthropic_agent"
-    )
-)
-
-# Azure OpenAI Configuration
-azure_llm = LLM(
-    model="gpt-4",
-    base_url=PORTKEY_GATEWAY_URL,
-    api_key="dummy",
-    extra_headers=createHeaders(
-        api_key="YOUR_PORTKEY_API_KEY",
-        virtual_key="YOUR_AZURE_VIRTUAL_KEY", #You don't need provider when using Virtual keys
-        trace_id="azure_agent"
-    )
-)
-```
-
-
-### 2. Caching
-Improve response times and reduce costs with two powerful caching modes:
-- **Simple Cache**: Perfect for exact matches
-- **Semantic Cache**: Matches responses for requests that are semantically similar
-[Learn more about Caching](https://portkey.ai/docs/product/ai-gateway/cache-simple-and-semantic)
-
-```py
-config = {
-    "cache": {
-        "mode": "semantic",  # or "simple" for exact matching
-    }
-}
-```
-
-### 3. Production Reliability
-Portkey provides comprehensive reliability features:
-- **Automatic Retries**: Handle temporary failures gracefully
-- **Request Timeouts**: Prevent hanging operations
-- **Conditional Routing**: Route requests based on specific conditions
-- **Fallbacks**: Set up automatic provider failovers
-- **Load Balancing**: Distribute requests efficiently
-
-[Learn more about Reliability Features](https://portkey.ai/docs/product/ai-gateway/)
-
-
-
-### 4. Metrics
-
-Agent runs are complex. Portkey automatically logs **40+ comprehensive metrics** for your AI agents, including cost, tokens used, latency, etc. Whether you need a broad overview or granular insights into your agent runs, Portkey's customizable filters provide the metrics you need.
-
-
-- Cost per agent interaction
-- Response times and latency
-- Token usage and efficiency
-- Success/failure rates
-- Cache hit rates
-
-<img src="https://github.com/siddharthsambharia-portkey/Portkey-Product-Images/blob/main/Portkey-Dashboard.png?raw=true" width="70%" alt="Portkey Dashboard" />
-
-### 5. Detailed Logging
-Logs are essential for understanding agent behavior, diagnosing issues, and improving performance. They provide a detailed record of agent activities and tool use, which is crucial for debugging and optimizing processes.
-
-
-Access a dedicated section to view records of agent executions, including parameters, outcomes, function calls, and errors. Filter logs based on multiple parameters such as trace ID, model, tokens used, and metadata.
-
-<details>
-  <summary><b>Traces</b></summary>
-  <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-Traces.png" alt="Portkey Traces" width="70%" />
-</details>
-
-<details>
-  <summary><b>Logs</b></summary>
-  <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-Logs.png" alt="Portkey Logs" width="70%" />
-</details>
-
-### 6. Enterprise Security Features
-- Set budget limit and rate limts per Virtual Key (disposable API keys)
-- Implement role-based access control
-- Track system changes with audit logs
-- Configure data retention policies
-
-
-
-For detailed information on creating and managing Configs, visit the [Portkey documentation](https://docs.portkey.ai/product/ai-gateway/configs).
-
-## Resources
-
-- [📘 Portkey Documentation](https://docs.portkey.ai)
-- [📊 Portkey Dashboard](https://app.portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai)
-- [🐦 Twitter](https://twitter.com/portkeyai)
-- [💬 Discord Community](https://discord.gg/DD7vgKK299)
-
-
-
-
-
-
-
-
-

docs/how-to/portkey-observability.mdx

@@ -1,5 +1,5 @@
 ---
-title: Portkey Observability and Guardrails
+title: Agent Monitoring with Portkey
 description: How to use Portkey with CrewAI
 icon: key
 ---

docs/mint.json

@@ -103,7 +103,8 @@
         "how-to/langtrace-observability",
         "how-to/mlflow-observability",
         "how-to/openlit-observability",
-        "how-to/portkey-observability"
+        "how-to/portkey-observability",
+        "how-to/langfuse-observability"
       ]
     },
     {

src/crewai/cli/provider.py

@@ -1,4 +1,5 @@
 import json
+import os
 import time
 from collections import defaultdict
 from pathlib import Path
@@ -153,6 +154,56 @@ def read_cache_file(cache_file):
         return None
 
 
+def validate_response(response):
+    """
+    Validates the response content type.
+
+    Args:
+    - response: The HTTP response object.
+
+    Returns:
+    - bool: True if the content type is valid, False otherwise.
+    """
+    content_type = response.headers.get('content-type', '').lower()
+    valid_types = ['application/json', 'application/json; charset=utf-8']
+    if not any(content_type.startswith(t) for t in valid_types):
+        click.secho(f"Error: Expected JSON response but got {content_type}", fg="red")
+        return False
+    return True
+
+def handle_provider_error(error, error_type="fetch"):
+    """
+    Handles provider data errors with consistent messaging.
+
+    Args:
+    - error: The error object.
+    - error_type: Type of error for message selection.
+
+    Returns:
+    - None: Always returns None to indicate error.
+    """
+    error_messages = {
+        "fetch": "Error fetching provider data",
+        "parse": "Error parsing provider data",
+        "unexpected": "Unexpected error"
+    }
+    base_message = error_messages.get(error_type, "Error")
+    click.secho(f"{base_message}: {str(error)}", fg="red")
+    return None
+
+def invalidate_cache(cache_file):
+    """
+    Invalidates the cache file in error scenarios.
+
+    Args:
+    - cache_file: Path to the cache file.
+    """
+    try:
+        if os.path.exists(cache_file):
+            os.remove(cache_file)
+    except OSError as e:
+        click.secho(f"Warning: Could not clear cache file: {e}", fg="yellow")
+
 def fetch_provider_data(cache_file):
     """
     Fetches provider data from a specified URL and caches it to a file.
@@ -166,15 +217,24 @@ def fetch_provider_data(cache_file):
     try:
         response = requests.get(JSON_URL, stream=True, timeout=60)
         response.raise_for_status()
+        
+        if not validate_response(response):
+            invalidate_cache(cache_file)
+            return None
+            
         data = download_data(response)
         with open(cache_file, "w") as f:
             json.dump(data, f)
         return data
     except requests.RequestException as e:
-        click.secho(f"Error fetching provider data: {e}", fg="red")
-    except json.JSONDecodeError:
-        click.secho("Error parsing provider data. Invalid JSON format.", fg="red")
-    return None
+        invalidate_cache(cache_file)
+        return handle_provider_error(e, "fetch")
+    except json.JSONDecodeError as e:
+        invalidate_cache(cache_file)
+        return handle_provider_error(e, "parse")
+    except Exception as e:
+        invalidate_cache(cache_file)
+        return handle_provider_error(e, "unexpected")
 
 
 def download_data(response):
@@ -206,7 +266,7 @@ def get_provider_data():
     Retrieves provider data from a cache file, filters out models based on provider criteria, and returns a dictionary of providers mapped to their models.
 
     Returns:
-    - dict or None: A dictionary of providers mapped to their models or None if the operation fails.
+    - dict: A dictionary of providers mapped to their models, using default providers if fetch fails.
     """
     cache_dir = Path.home() / ".crewai"
     cache_dir.mkdir(exist_ok=True)
@@ -215,7 +275,9 @@ def get_provider_data():
 
     data = load_provider_data(cache_file, cache_expiry)
     if not data:
-        return None
+        # Return default providers if fetch fails
+        return {provider.lower(): MODELS.get(provider.lower(), []) 
+                for provider in PROVIDERS}
 
     provider_models = defaultdict(list)
     for model_name, properties in data.items():

src/crewai/crew.py

@@ -1147,32 +1147,20 @@ class Crew(BaseModel):
 
     def test(
         self,
-        n_iterations: int = 1,
+        n_iterations: int,
         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.
-
-        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 and evaluate the Crew with the given inputs for n iterations concurrently using concurrent.futures."""
         test_crew = self.copy()
 
         self._test_execution_span = test_crew._telemetry.test_execution_span(
             test_crew,
             n_iterations,
             inputs,
-            str(model_to_use.model),
-        )
-        evaluator = CrewEvaluator(test_crew, model_to_use)
+            openai_model_name,  # type: ignore[arg-type]
+        )  # type: ignore[arg-type]
+        evaluator = CrewEvaluator(test_crew, openai_model_name)  # type: ignore[arg-type]
 
         for i in range(1, n_iterations + 1):
             evaluator.set_iteration(i)
@@ -1180,28 +1168,6 @@ 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/flow/flow.py

@@ -1,4 +1,5 @@
 import asyncio
+import copy
 import inspect
 import logging
 from typing import (
@@ -394,7 +395,6 @@ class FlowMeta(type):
                 or hasattr(attr_value, "__trigger_methods__")
                 or hasattr(attr_value, "__is_router__")
             ):
-
                 # Register start methods
                 if hasattr(attr_value, "__is_start_method__"):
                     start_methods.append(attr_name)
@@ -569,6 +569,9 @@ class Flow(Generic[T], metaclass=FlowMeta):
             f"Initial state must be dict or BaseModel, got {type(self.initial_state)}"
         )
 
+    def _copy_state(self) -> T:
+        return copy.deepcopy(self._state)
+
     @property
     def state(self) -> T:
         return self._state
@@ -740,6 +743,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
             event=FlowStartedEvent(
                 type="flow_started",
                 flow_name=self.__class__.__name__,
+                inputs=inputs,
             ),
         )
         self._log_flow_event(
@@ -803,6 +807,18 @@ class Flow(Generic[T], metaclass=FlowMeta):
     async def _execute_method(
         self, method_name: str, method: Callable, *args: Any, **kwargs: Any
     ) -> Any:
+        dumped_params = {f"_{i}": arg for i, arg in enumerate(args)} | (kwargs or {})
+        self.event_emitter.send(
+            self,
+            event=MethodExecutionStartedEvent(
+                type="method_execution_started",
+                method_name=method_name,
+                flow_name=self.__class__.__name__,
+                params=dumped_params,
+                state=self._copy_state(),
+            ),
+        )
+
         result = (
             await method(*args, **kwargs)
             if asyncio.iscoroutinefunction(method)
@@ -812,6 +828,18 @@ class Flow(Generic[T], metaclass=FlowMeta):
         self._method_execution_counts[method_name] = (
             self._method_execution_counts.get(method_name, 0) + 1
         )
+
+        self.event_emitter.send(
+            self,
+            event=MethodExecutionFinishedEvent(
+                type="method_execution_finished",
+                method_name=method_name,
+                flow_name=self.__class__.__name__,
+                state=self._copy_state(),
+                result=result,
+            ),
+        )
+
         return result
 
     async def _execute_listeners(self, trigger_method: str, result: Any) -> None:
@@ -950,16 +978,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
         """
         try:
             method = self._methods[listener_name]
-
-            self.event_emitter.send(
-                self,
-                event=MethodExecutionStartedEvent(
-                    type="method_execution_started",
-                    method_name=listener_name,
-                    flow_name=self.__class__.__name__,
-                ),
-            )
-
             sig = inspect.signature(method)
             params = list(sig.parameters.values())
             method_params = [p for p in params if p.name != "self"]
@@ -971,15 +989,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
             else:
                 listener_result = await self._execute_method(listener_name, method)
 
-            self.event_emitter.send(
-                self,
-                event=MethodExecutionFinishedEvent(
-                    type="method_execution_finished",
-                    method_name=listener_name,
-                    flow_name=self.__class__.__name__,
-                ),
-            )
-
             # Execute listeners (and possibly routers) of this listener
             await self._execute_listeners(listener_name, listener_result)
 

src/crewai/flow/flow_events.py

@@ -1,6 +1,8 @@
 from dataclasses import dataclass, field
 from datetime import datetime
-from typing import Any, Optional
+from typing import Any, Dict, Optional, Union
+
+from pydantic import BaseModel
 
 
 @dataclass
@@ -15,17 +17,21 @@ class Event:
 
 @dataclass
 class FlowStartedEvent(Event):
-    pass
+    inputs: Optional[Dict[str, Any]] = None
 
 
 @dataclass
 class MethodExecutionStartedEvent(Event):
     method_name: str
+    state: Union[Dict[str, Any], BaseModel]
+    params: Optional[Dict[str, Any]] = None
 
 
 @dataclass
 class MethodExecutionFinishedEvent(Event):
     method_name: str
+    state: Union[Dict[str, Any], BaseModel]
+    result: Any = None
 
 
 @dataclass

src/crewai/knowledge/source/excel_knowledge_source.py

@@ -1,28 +1,138 @@
 from pathlib import Path
-from typing import Dict, List
+from typing import Dict, Iterator, List, Optional, Union
+from urllib.parse import urlparse
 
-from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
+from pydantic import Field, field_validator
+
+from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
+from crewai.utilities.constants import KNOWLEDGE_DIRECTORY
+from crewai.utilities.logger import Logger
 
 
-class ExcelKnowledgeSource(BaseFileKnowledgeSource):
+class ExcelKnowledgeSource(BaseKnowledgeSource):
     """A knowledge source that stores and queries Excel file content using embeddings."""
 
-    def load_content(self) -> Dict[Path, str]:
-        """Load and preprocess Excel file content."""
-        pd = self._import_dependencies()
+    # override content to be a dict of file paths to sheet names to csv content
 
+    _logger: Logger = Logger(verbose=True)
+
+    file_path: Optional[Union[Path, List[Path], str, List[str]]] = Field(
+        default=None,
+        description="[Deprecated] The path to the file. Use file_paths instead.",
+    )
+    file_paths: Optional[Union[Path, List[Path], str, List[str]]] = Field(
+        default_factory=list, description="The path to the file"
+    )
+    chunks: List[str] = Field(default_factory=list)
+    content: Dict[Path, Dict[str, str]] = Field(default_factory=dict)
+    safe_file_paths: List[Path] = Field(default_factory=list)
+
+    @field_validator("file_path", "file_paths", mode="before")
+    def validate_file_path(cls, v, info):
+        """Validate that at least one of file_path or file_paths is provided."""
+        # Single check if both are None, O(1) instead of nested conditions
+        if (
+            v is None
+            and info.data.get(
+                "file_path" if info.field_name == "file_paths" else "file_paths"
+            )
+            is None
+        ):
+            raise ValueError("Either file_path or file_paths must be provided")
+        return v
+
+    def _process_file_paths(self) -> List[Path]:
+        """Convert file_path to a list of Path objects."""
+
+        if hasattr(self, "file_path") and self.file_path is not None:
+            self._logger.log(
+                "warning",
+                "The 'file_path' attribute is deprecated and will be removed in a future version. Please use 'file_paths' instead.",
+                color="yellow",
+            )
+            self.file_paths = self.file_path
+
+        if self.file_paths is None:
+            raise ValueError("Your source must be provided with a file_paths: []")
+
+        # Convert single path to list
+        path_list: List[Union[Path, str]] = (
+            [self.file_paths]
+            if isinstance(self.file_paths, (str, Path))
+            else list(self.file_paths)
+            if isinstance(self.file_paths, list)
+            else []
+        )
+
+        if not path_list:
+            raise ValueError(
+                "file_path/file_paths must be a Path, str, or a list of these types"
+            )
+
+        return [self.convert_to_path(path) for path in path_list]
+
+    def validate_content(self):
+        """Validate the paths."""
+        for path in self.safe_file_paths:
+            if not path.exists():
+                self._logger.log(
+                    "error",
+                    f"File not found: {path}. Try adding sources to the knowledge directory. If it's inside the knowledge directory, use the relative path.",
+                    color="red",
+                )
+                raise FileNotFoundError(f"File not found: {path}")
+            if not path.is_file():
+                self._logger.log(
+                    "error",
+                    f"Path is not a file: {path}",
+                    color="red",
+                )
+
+    def model_post_init(self, _) -> None:
+        if self.file_path:
+            self._logger.log(
+                "warning",
+                "The 'file_path' attribute is deprecated and will be removed in a future version. Please use 'file_paths' instead.",
+                color="yellow",
+            )
+            self.file_paths = self.file_path
+        self.safe_file_paths = self._process_file_paths()
+        self.validate_content()
+        self.content = self._load_content()
+
+    def _load_content(self) -> Dict[Path, Dict[str, str]]:
+        """Load and preprocess Excel file content from multiple sheets.
+
+        Each sheet's content is converted to CSV format and stored.
+
+        Returns:
+            Dict[Path, Dict[str, str]]: A mapping of file paths to their respective sheet contents.
+
+        Raises:
+            ImportError: If required dependencies are missing.
+            FileNotFoundError: If the specified Excel file cannot be opened.
+        """
+        pd = self._import_dependencies()
         content_dict = {}
         for file_path in self.safe_file_paths:
             file_path = self.convert_to_path(file_path)
-            df = pd.read_excel(file_path)
-            content = df.to_csv(index=False)
-            content_dict[file_path] = content
+            with pd.ExcelFile(file_path) as xl:
+                sheet_dict = {
+                    str(sheet_name): str(
+                        pd.read_excel(xl, sheet_name).to_csv(index=False)
+                    )
+                    for sheet_name in xl.sheet_names
+                }
+            content_dict[file_path] = sheet_dict
         return content_dict
 
+    def convert_to_path(self, path: Union[Path, str]) -> Path:
+        """Convert a path to a Path object."""
+        return Path(KNOWLEDGE_DIRECTORY + "/" + path) if isinstance(path, str) else path
+
     def _import_dependencies(self):
         """Dynamically import dependencies."""
         try:
-            import openpyxl  # noqa
             import pandas as pd
 
             return pd
@@ -38,10 +148,14 @@ class ExcelKnowledgeSource(BaseFileKnowledgeSource):
         and save the embeddings.
         """
         # Convert dictionary values to a single string if content is a dictionary
-        if isinstance(self.content, dict):
-            content_str = "\n".join(str(value) for value in self.content.values())
-        else:
-            content_str = str(self.content)
+        # Updated to account for .xlsx workbooks with multiple tabs/sheets
+        content_str = ""
+        for value in self.content.values():
+            if isinstance(value, dict):
+                for sheet_value in value.values():
+                    content_str += str(sheet_value) + "\n"
+            else:
+                content_str += str(value) + "\n"
 
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -1,5 +1,4 @@
 from collections import defaultdict
-from typing import Union
 
 from pydantic import BaseModel, Field
 from rich.box import HEAVY_EDGE
@@ -7,7 +6,6 @@ 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
@@ -34,9 +32,9 @@ class CrewEvaluator:
     run_execution_times: defaultdict = defaultdict(list)
     iteration: int = 0
 
-    def __init__(self, crew, llm: Union[str, LLM]):
+    def __init__(self, crew, openai_model_name: str):
         self.crew = crew
-        self.llm = LLM(model=llm) if isinstance(llm, str) else llm
+        self.openai_model_name = openai_model_name
         self._telemetry = Telemetry()
         self._setup_for_evaluating()
 
@@ -53,7 +51,7 @@ 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.llm,
+            llm=self.openai_model_name,
         )
 
     def _evaluation_task(
@@ -183,7 +181,7 @@ class CrewEvaluator:
                 self.crew,
                 evaluation_result.pydantic.quality,
                 current_task.execution_duration,
-                self.llm.model,
+                self.openai_model_name,
             )
             self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
             self.run_execution_times[self.iteration].append(

tests/agent_test.py

@@ -78,6 +78,18 @@ def test_agent_default_values():
     assert agent.llm.model == "gpt-4o-mini"
     assert agent.allow_delegation is False
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_creation_without_model_prices():
+    with patch('crewai.cli.provider.get_provider_data') as mock_get:
+        mock_get.return_value = None
+        agent = Agent(
+            role="test role",
+            goal="test goal",
+            backstory="test backstory"
+        )
+        assert agent is not None
+        assert agent.role == "test role"
+
 
 def test_custom_llm():
     agent = Agent(

tests/cli/provider_test.py

@@ -0,0 +1,47 @@
+from unittest.mock import Mock, patch
+
+import json
+import os
+import pytest
+import requests
+import time
+
+from crewai.cli.constants import JSON_URL, MODELS, PROVIDERS
+from crewai.cli.provider import fetch_provider_data, get_provider_data
+
+def test_fetch_provider_data_timeout():
+    with patch('requests.get') as mock_get:
+        mock_get.side_effect = requests.exceptions.Timeout
+        result = fetch_provider_data('/tmp/cache.json')
+        assert result is None
+
+def test_fetch_provider_data_wrong_content_type():
+    with patch('requests.get') as mock_get:
+        mock_response = Mock()
+        mock_response.headers = {'content-type': 'text/plain'}
+        mock_get.return_value = mock_response
+        result = fetch_provider_data('/tmp/cache.json')
+        assert result is None
+
+def test_fetch_provider_data_success():
+    mock_data = {"model1": {"provider": "test"}}
+    with patch('requests.get') as mock_get:
+        mock_response = Mock()
+        mock_response.headers = {'content-type': 'application/json'}
+        mock_response.json.return_value = mock_data
+        mock_response.iter_content.return_value = [json.dumps(mock_data).encode()]
+        mock_get.return_value = mock_response
+        result = fetch_provider_data('/tmp/cache.json')
+        assert result == mock_data
+
+def test_cache_expiry():
+    with patch('os.path.getmtime') as mock_time:
+        mock_time.return_value = time.time() - (25 * 60 * 60)  # 25 hours old
+        with patch('crewai.cli.provider.load_provider_data') as mock_load:
+            mock_load.return_value = None
+            result = get_provider_data()
+            assert result is not None
+            assert all(provider.lower() in result for provider in PROVIDERS)
+            # Verify that each provider has its models from MODELS
+            for provider in PROVIDERS:
+                assert result[provider.lower()] == MODELS.get(provider.lower(), [])

tests/crew_test.py

@@ -51,6 +51,7 @@ 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
 
@@ -82,6 +83,7 @@ def test_crew_with_only_conditional_tasks_raises_error():
             tasks=[conditional1, conditional2, conditional3],
         )
 
+
 def test_crew_config_conditional_requirement():
     with pytest.raises(ValueError):
         Crew(process=Process.sequential)
@@ -589,12 +591,12 @@ def test_crew_with_delegating_agents_should_not_override_task_tools():
         _, kwargs = mock_execute_sync.call_args
         tools = kwargs["tools"]
 
-        assert any(isinstance(tool, TestTool) for tool in tools), (
-            "TestTool should be present"
-        )
-        assert any("delegate" in tool.name.lower() for tool in tools), (
-            "Delegation tool should be present"
-        )
+        assert any(
+            isinstance(tool, TestTool) for tool in tools
+        ), "TestTool should be present"
+        assert any(
+            "delegate" in tool.name.lower() for tool in tools
+        ), "Delegation tool should be present"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -653,12 +655,12 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
         _, kwargs = mock_execute_sync.call_args
         tools = kwargs["tools"]
 
-        assert any(isinstance(tool, TestTool) for tool in new_ceo.tools), (
-            "TestTool should be present"
-        )
-        assert any("delegate" in tool.name.lower() for tool in tools), (
-            "Delegation tool should be present"
-        )
+        assert any(
+            isinstance(tool, TestTool) for tool in new_ceo.tools
+        ), "TestTool should be present"
+        assert any(
+            "delegate" in tool.name.lower() for tool in tools
+        ), "Delegation tool should be present"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -782,17 +784,17 @@ def test_task_tools_override_agent_tools_with_allow_delegation():
         used_tools = kwargs["tools"]
 
         # Confirm AnotherTestTool is present but TestTool is not
-        assert any(isinstance(tool, AnotherTestTool) for tool in used_tools), (
-            "AnotherTestTool should be present"
-        )
-        assert not any(isinstance(tool, TestTool) for tool in used_tools), (
-            "TestTool should not be present among used tools"
-        )
+        assert any(
+            isinstance(tool, AnotherTestTool) for tool in used_tools
+        ), "AnotherTestTool should be present"
+        assert not any(
+            isinstance(tool, TestTool) for tool in used_tools
+        ), "TestTool should not be present among used tools"
 
         # Confirm delegation tool(s) are present
-        assert any("delegate" in tool.name.lower() for tool in used_tools), (
-            "Delegation tool should be present"
-        )
+        assert any(
+            "delegate" in tool.name.lower() for tool in used_tools
+        ), "Delegation tool should be present"
 
     # Finally, make sure the agent's original tools remain unchanged
     assert len(researcher_with_delegation.tools) == 1
@@ -1593,9 +1595,9 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
 
         # Verify that exactly one tool was used and it was a CodeInterpreterTool
         assert len(used_tools) == 1, "Should have exactly one tool"
-        assert isinstance(used_tools[0], CodeInterpreterTool), (
-            "Tool should be CodeInterpreterTool"
-        )
+        assert isinstance(
+            used_tools[0], CodeInterpreterTool
+        ), "Tool should be CodeInterpreterTool"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -1952,6 +1954,7 @@ def test_task_callback_on_crew():
 
 def test_task_callback_both_on_task_and_crew():
     from unittest.mock import MagicMock, patch
+
     mock_callback_on_task = MagicMock()
     mock_callback_on_crew = MagicMock()
 
@@ -2101,21 +2104,22 @@ def test_conditional_task_uses_last_output():
         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",
@@ -2134,35 +2138,37 @@ def test_conditional_task_uses_last_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
+
+            # Verify outputs collection:
+            # First executed task output, followed by an automatically generated (skipped) output, then the conditional execution
             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
+            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():
@@ -2172,20 +2178,20 @@ def test_conditional_tasks_result_collection():
         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",
@@ -2204,35 +2210,46 @@ def test_conditional_tasks_result_collection():
         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:
+            # There should be three outputs: normal task, skipped conditional task (empty output),
+            # and the conditional task that executed.
+            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
+
             # 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
+            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():
@@ -2242,20 +2259,20 @@ def test_multiple_conditional_tasks():
         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",
@@ -2274,7 +2291,7 @@ def test_multiple_conditional_tasks():
         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()
@@ -2282,6 +2299,7 @@ def test_multiple_conditional_tasks():
         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
@@ -3306,7 +3324,8 @@ def test_conditional_should_execute():
 
 @mock.patch("crewai.crew.CrewEvaluator")
 @mock.patch("crewai.crew.Crew.copy")
-def test_crew_testing_function(copy_mock, crew_evaluator_mock):
+@mock.patch("crewai.crew.Crew.kickoff")
+def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
     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.",
@@ -3318,28 +3337,25 @@ def test_crew_testing_function(copy_mock, crew_evaluator_mock):
         tasks=[task],
     )
 
-    # 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
+    # Create a mock for the copied crew
+    copy_mock.return_value = crew
 
     n_iterations = 2
     crew.test(n_iterations, openai_model_name="gpt-4o-mini", inputs={"topic": "AI"})
 
     # Ensure kickoff is called on the copied crew
-    copied_crew.kickoff.assert_has_calls(
+    kickoff_mock.assert_has_calls(
         [mock.call(inputs={"topic": "AI"}), mock.call(inputs={"topic": "AI"})]
     )
 
-    # 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()
+    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(),
+        ]
+    )
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -3402,9 +3418,9 @@ def test_fetch_inputs():
     expected_placeholders = {"role_detail", "topic", "field"}
     actual_placeholders = crew.fetch_inputs()
 
-    assert actual_placeholders == expected_placeholders, (
-        f"Expected {expected_placeholders}, but got {actual_placeholders}"
-    )
+    assert (
+        actual_placeholders == expected_placeholders
+    ), f"Expected {expected_placeholders}, but got {actual_placeholders}"
 
 
 def test_task_tools_preserve_code_execution_tools():
@@ -3477,20 +3493,20 @@ def test_task_tools_preserve_code_execution_tools():
         used_tools = kwargs["tools"]
 
         # Verify all expected tools are present
-        assert any(isinstance(tool, TestTool) for tool in used_tools), (
-            "Task's TestTool should be present"
-        )
-        assert any(isinstance(tool, CodeInterpreterTool) for tool in used_tools), (
-            "CodeInterpreterTool should be present"
-        )
-        assert any("delegate" in tool.name.lower() for tool in used_tools), (
-            "Delegation tool should be present"
-        )
+        assert any(
+            isinstance(tool, TestTool) for tool in used_tools
+        ), "Task's TestTool should be present"
+        assert any(
+            isinstance(tool, CodeInterpreterTool) for tool in used_tools
+        ), "CodeInterpreterTool should be present"
+        assert any(
+            "delegate" in tool.name.lower() for tool in used_tools
+        ), "Delegation tool should be present"
 
         # Verify the total number of tools (TestTool + CodeInterpreter + 2 delegation tools)
-        assert len(used_tools) == 4, (
-            "Should have TestTool, CodeInterpreter, and 2 delegation tools"
-        )
+        assert (
+            len(used_tools) == 4
+        ), "Should have TestTool, CodeInterpreter, and 2 delegation tools"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -3534,9 +3550,9 @@ def test_multimodal_flag_adds_multimodal_tools():
         used_tools = kwargs["tools"]
 
         # Check that the multimodal tool was added
-        assert any(isinstance(tool, AddImageTool) for tool in used_tools), (
-            "AddImageTool should be present when agent is multimodal"
-        )
+        assert any(
+            isinstance(tool, AddImageTool) for tool in used_tools
+        ), "AddImageTool should be present when agent is multimodal"
 
         # Verify we have exactly one tool (just the AddImageTool)
         assert len(used_tools) == 1, "Should only have the AddImageTool"
@@ -3762,9 +3778,9 @@ def test_crew_guardrail_feedback_in_context():
     assert len(execution_contexts) > 1, "Task should have been executed multiple times"
 
     # Verify that the second execution included the guardrail feedback
-    assert "Output must contain the keyword 'IMPORTANT'" in execution_contexts[1], (
-        "Guardrail feedback should be included in retry context"
-    )
+    assert (
+        "Output must contain the keyword 'IMPORTANT'" in execution_contexts[1]
+    ), "Guardrail feedback should be included in retry context"
 
     # Verify final output meets guardrail requirements
     assert "IMPORTANT" in result.raw, "Final output should contain required keyword"

tests/flow_test.py

@@ -1,11 +1,18 @@
 """Test Flow creation and execution basic functionality."""
 
 import asyncio
+from datetime import datetime
 
 import pytest
 from pydantic import BaseModel
 
 from crewai.flow.flow import Flow, and_, listen, or_, router, start
+from crewai.flow.flow_events import (
+    FlowFinishedEvent,
+    FlowStartedEvent,
+    MethodExecutionFinishedEvent,
+    MethodExecutionStartedEvent,
+)
 
 
 def test_simple_sequential_flow():
@@ -398,3 +405,218 @@ def test_router_with_multiple_conditions():
 
     # final_step should run after router_and
     assert execution_order.index("log_final_step") > execution_order.index("router_and")
+
+
+def test_unstructured_flow_event_emission():
+    """Test that the correct events are emitted during unstructured flow
+    execution with all fields validated."""
+
+    class PoemFlow(Flow):
+        @start()
+        def prepare_flower(self):
+            self.state["flower"] = "roses"
+            return "foo"
+
+        @start()
+        def prepare_color(self):
+            self.state["color"] = "red"
+            return "bar"
+
+        @listen(prepare_color)
+        def write_first_sentence(self):
+            return f"{self.state["flower"]} are {self.state["color"]}"
+
+        @listen(write_first_sentence)
+        def finish_poem(self, first_sentence):
+            separator = self.state.get("separator", "\n")
+            return separator.join([first_sentence, "violets are blue"])
+
+        @listen(finish_poem)
+        def save_poem_to_database(self):
+            # A method without args/kwargs to ensure events are sent correctly
+            pass
+
+    event_log = []
+
+    def handle_event(_, event):
+        event_log.append(event)
+
+    flow = PoemFlow()
+    flow.event_emitter.connect(handle_event)
+    flow.kickoff(inputs={"separator": ", "})
+
+    assert isinstance(event_log[0], FlowStartedEvent)
+    assert event_log[0].flow_name == "PoemFlow"
+    assert event_log[0].inputs == {"separator": ", "}
+    assert isinstance(event_log[0].timestamp, datetime)
+
+    # Asserting for concurrent start method executions in a for loop as you
+    # can't guarantee ordering in asynchronous executions
+    for i in range(1, 5):
+        event = event_log[i]
+        assert isinstance(event.state, dict)
+        assert isinstance(event.state["id"], str)
+
+        if event.method_name == "prepare_flower":
+            if isinstance(event, MethodExecutionStartedEvent):
+                assert event.params == {}
+                assert event.state["separator"] == ", "
+            elif isinstance(event, MethodExecutionFinishedEvent):
+                assert event.result == "foo"
+                assert event.state["flower"] == "roses"
+                assert event.state["separator"] == ", "
+            else:
+                assert False, "Unexpected event type for prepare_flower"
+        elif event.method_name == "prepare_color":
+            if isinstance(event, MethodExecutionStartedEvent):
+                assert event.params == {}
+                assert event.state["separator"] == ", "
+            elif isinstance(event, MethodExecutionFinishedEvent):
+                assert event.result == "bar"
+                assert event.state["color"] == "red"
+                assert event.state["separator"] == ", "
+            else:
+                assert False, "Unexpected event type for prepare_color"
+        else:
+            assert False, f"Unexpected method {event.method_name} in prepare events"
+
+    assert isinstance(event_log[5], MethodExecutionStartedEvent)
+    assert event_log[5].method_name == "write_first_sentence"
+    assert event_log[5].params == {}
+    assert isinstance(event_log[5].state, dict)
+    assert event_log[5].state["flower"] == "roses"
+    assert event_log[5].state["color"] == "red"
+    assert event_log[5].state["separator"] == ", "
+
+    assert isinstance(event_log[6], MethodExecutionFinishedEvent)
+    assert event_log[6].method_name == "write_first_sentence"
+    assert event_log[6].result == "roses are red"
+
+    assert isinstance(event_log[7], MethodExecutionStartedEvent)
+    assert event_log[7].method_name == "finish_poem"
+    assert event_log[7].params == {"_0": "roses are red"}
+    assert isinstance(event_log[7].state, dict)
+    assert event_log[7].state["flower"] == "roses"
+    assert event_log[7].state["color"] == "red"
+
+    assert isinstance(event_log[8], MethodExecutionFinishedEvent)
+    assert event_log[8].method_name == "finish_poem"
+    assert event_log[8].result == "roses are red, violets are blue"
+
+    assert isinstance(event_log[9], MethodExecutionStartedEvent)
+    assert event_log[9].method_name == "save_poem_to_database"
+    assert event_log[9].params == {}
+    assert isinstance(event_log[9].state, dict)
+    assert event_log[9].state["flower"] == "roses"
+    assert event_log[9].state["color"] == "red"
+
+    assert isinstance(event_log[10], MethodExecutionFinishedEvent)
+    assert event_log[10].method_name == "save_poem_to_database"
+    assert event_log[10].result is None
+
+    assert isinstance(event_log[11], FlowFinishedEvent)
+    assert event_log[11].flow_name == "PoemFlow"
+    assert event_log[11].result is None
+    assert isinstance(event_log[11].timestamp, datetime)
+
+
+def test_structured_flow_event_emission():
+    """Test that the correct events are emitted during structured flow
+    execution with all fields validated."""
+
+    class OnboardingState(BaseModel):
+        name: str = ""
+        sent: bool = False
+
+    class OnboardingFlow(Flow[OnboardingState]):
+        @start()
+        def user_signs_up(self):
+            self.state.sent = False
+
+        @listen(user_signs_up)
+        def send_welcome_message(self):
+            self.state.sent = True
+            return f"Welcome, {self.state.name}!"
+
+    event_log = []
+
+    def handle_event(_, event):
+        event_log.append(event)
+
+    flow = OnboardingFlow()
+    flow.event_emitter.connect(handle_event)
+    flow.kickoff(inputs={"name": "Anakin"})
+
+    assert isinstance(event_log[0], FlowStartedEvent)
+    assert event_log[0].flow_name == "OnboardingFlow"
+    assert event_log[0].inputs == {"name": "Anakin"}
+    assert isinstance(event_log[0].timestamp, datetime)
+
+    assert isinstance(event_log[1], MethodExecutionStartedEvent)
+    assert event_log[1].method_name == "user_signs_up"
+
+    assert isinstance(event_log[2], MethodExecutionFinishedEvent)
+    assert event_log[2].method_name == "user_signs_up"
+
+    assert isinstance(event_log[3], MethodExecutionStartedEvent)
+    assert event_log[3].method_name == "send_welcome_message"
+    assert event_log[3].params == {}
+    assert getattr(event_log[3].state, "sent") is False
+
+    assert isinstance(event_log[4], MethodExecutionFinishedEvent)
+    assert event_log[4].method_name == "send_welcome_message"
+    assert getattr(event_log[4].state, "sent") is True
+    assert event_log[4].result == "Welcome, Anakin!"
+
+    assert isinstance(event_log[5], FlowFinishedEvent)
+    assert event_log[5].flow_name == "OnboardingFlow"
+    assert event_log[5].result == "Welcome, Anakin!"
+    assert isinstance(event_log[5].timestamp, datetime)
+
+
+def test_stateless_flow_event_emission():
+    """Test that the correct events are emitted stateless during flow execution
+    with all fields validated."""
+
+    class StatelessFlow(Flow):
+        @start()
+        def init(self):
+            pass
+
+        @listen(init)
+        def process(self):
+            return "Deeds will not be less valiant because they are unpraised."
+
+    event_log = []
+
+    def handle_event(_, event):
+        event_log.append(event)
+
+    flow = StatelessFlow()
+    flow.event_emitter.connect(handle_event)
+    flow.kickoff()
+
+    assert isinstance(event_log[0], FlowStartedEvent)
+    assert event_log[0].flow_name == "StatelessFlow"
+    assert event_log[0].inputs is None
+    assert isinstance(event_log[0].timestamp, datetime)
+
+    assert isinstance(event_log[1], MethodExecutionStartedEvent)
+    assert event_log[1].method_name == "init"
+
+    assert isinstance(event_log[2], MethodExecutionFinishedEvent)
+    assert event_log[2].method_name == "init"
+
+    assert isinstance(event_log[3], MethodExecutionStartedEvent)
+    assert event_log[3].method_name == "process"
+
+    assert isinstance(event_log[4], MethodExecutionFinishedEvent)
+    assert event_log[4].method_name == "process"
+
+    assert isinstance(event_log[5], FlowFinishedEvent)
+    assert event_log[5].flow_name == "StatelessFlow"
+    assert (
+        event_log[5].result
+        == "Deeds will not be less valiant because they are unpraised."
+    )
+    assert isinstance(event_log[5].timestamp, datetime)

tests/utilities/evaluators/cassettes/test_crew_test_with_custom_llm.yaml

@@ -1,942 +0,0 @@
-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

@@ -1,71 +0,0 @@
-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