drop record new episodes

* Suppressed userWarnings from litellm pydantic issues

* change litellm version

* Fix failling ollama tasks

README.md

@@ -4,7 +4,7 @@
 
 # **CrewAI**
 
-🤖 **CrewAI**: Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
+🤖 **CrewAI**: Production-grade framework for orchestrating sophisticated AI agent systems. From simple automations to complex real-world applications, CrewAI provides precise control and deep customization. By fostering collaborative intelligence through flexible, production-ready architecture, CrewAI empowers agents to work together seamlessly, tackling complex business challenges with predictable, consistent results.
 
 <h3>
 
@@ -22,13 +22,17 @@
 - [Why CrewAI?](#why-crewai)
 - [Getting Started](#getting-started)
 - [Key Features](#key-features)
+- [Understanding Flows and Crews](#understanding-flows-and-crews)
+- [CrewAI vs LangGraph](#how-crewai-compares)
 - [Examples](#examples)
   - [Quick Tutorial](#quick-tutorial)
   - [Write Job Descriptions](#write-job-descriptions)
   - [Trip Planner](#trip-planner)
   - [Stock Analysis](#stock-analysis)
+  - [Using Crews and Flows Together](#using-crews-and-flows-together)
 - [Connecting Your Crew to a Model](#connecting-your-crew-to-a-model)
 - [How CrewAI Compares](#how-crewai-compares)
+- [Frequently Asked Questions (FAQ)](#frequently-asked-questions-faq)
 - [Contribution](#contribution)
 - [Telemetry](#telemetry)
 - [License](#license)
@@ -36,10 +40,40 @@
 ## Why CrewAI?
 
 The power of AI collaboration has too much to offer.
-CrewAI is designed to enable AI agents to assume roles, share goals, and operate in a cohesive unit - much like a well-oiled crew. Whether you're building a smart assistant platform, an automated customer service ensemble, or a multi-agent research team, CrewAI provides the backbone for sophisticated multi-agent interactions.
+CrewAI is a standalone framework, built from the ground up without dependencies on Langchain or other agent frameworks. It's designed to enable AI agents to assume roles, share goals, and operate in a cohesive unit - much like a well-oiled crew. Whether you're building a smart assistant platform, an automated customer service ensemble, or a multi-agent research team, CrewAI provides the backbone for sophisticated multi-agent interactions.
 
 ## Getting Started
 
+### Learning Resources
+
+Learn CrewAI through our comprehensive courses:
+- [Multi AI Agent Systems with CrewAI](https://www.deeplearning.ai/short-courses/multi-ai-agent-systems-with-crewai/) - Master the fundamentals of multi-agent systems
+- [Practical Multi AI Agents and Advanced Use Cases](https://www.deeplearning.ai/short-courses/practical-multi-ai-agents-and-advanced-use-cases-with-crewai/) - Deep dive into advanced implementations
+
+### Understanding Flows and Crews
+
+CrewAI offers two powerful, complementary approaches that work seamlessly together to build sophisticated AI applications:
+
+1. **Crews**: Teams of AI agents with true autonomy and agency, working together to accomplish complex tasks through role-based collaboration. Crews enable:
+   - Natural, autonomous decision-making between agents
+   - Dynamic task delegation and collaboration
+   - Specialized roles with defined goals and expertise
+   - Flexible problem-solving approaches
+
+2. **Flows**: Production-ready, event-driven workflows that deliver precise control over complex automations. Flows provide:
+   - Fine-grained control over execution paths for real-world scenarios
+   - Secure, consistent state management between tasks
+   - Clean integration of AI agents with production Python code
+   - Conditional branching for complex business logic
+
+The true power of CrewAI emerges when combining Crews and Flows. This synergy allows you to:
+- Build complex, production-grade applications
+- Balance autonomy with precise control
+- Handle sophisticated real-world scenarios
+- Maintain clean, maintainable code structure
+
+### Getting Started with Installation
+
 To get started with CrewAI, follow these simple steps:
 
 ### 1. Installation
@@ -51,7 +85,6 @@ First, install CrewAI:
 ```shell
 pip install crewai
 ```
-
 If you want to install the 'crewai' package along with its optional features that include additional tools for agents, you can do so by using the following command:
 
 ```shell
@@ -59,6 +92,22 @@ pip install 'crewai[tools]'
 ```
 The command above installs the basic package and also adds extra components which require more dependencies to function.
 
+### Troubleshooting Dependencies
+
+If you encounter issues during installation or usage, here are some common solutions:
+
+#### Common Issues
+
+1. **ModuleNotFoundError: No module named 'tiktoken'**
+   - Install tiktoken explicitly: `pip install 'crewai[embeddings]'`
+   - If using embedchain or other tools: `pip install 'crewai[tools]'`
+
+2. **Failed building wheel for tiktoken**
+   - Ensure Rust compiler is installed (see installation steps above)
+   - For Windows: Verify Visual C++ Build Tools are installed
+   - Try upgrading pip: `pip install --upgrade pip`
+   - If issues persist, use a pre-built wheel: `pip install tiktoken --prefer-binary`
+
 ### 2. Setting Up Your Crew with the YAML Configuration
 
 To create a new CrewAI project, run the following CLI (Command Line Interface) command:
@@ -264,13 +313,16 @@ In addition to the sequential process, you can use the hierarchical process, whi
 
 ## Key Features
 
-- **Role-Based Agent Design**: Customize agents with specific roles, goals, and tools.
-- **Autonomous Inter-Agent Delegation**: Agents can autonomously delegate tasks and inquire amongst themselves, enhancing problem-solving efficiency.
-- **Flexible Task Management**: Define tasks with customizable tools and assign them to agents dynamically.
-- **Processes Driven**: Currently only supports `sequential` task execution and `hierarchical` processes, but more complex processes like consensual and autonomous are being worked on.
-- **Save output as file**: Save the output of individual tasks as a file, so you can use it later.
-- **Parse output as Pydantic or Json**: Parse the output of individual tasks as a Pydantic model or as a Json if you want to.
-- **Works with Open Source Models**: Run your crew using Open AI or open source models refer to the [Connect CrewAI to LLMs](https://docs.crewai.com/how-to/LLM-Connections/) page for details on configuring your agents' connections to models, even ones running locally!
+**Note**: CrewAI is a standalone framework built from the ground up, without dependencies on Langchain or other agent frameworks.
+
+- **Deep Customization**: Build sophisticated agents with full control over the system - from overriding inner prompts to accessing low-level APIs. Customize roles, goals, tools, and behaviors while maintaining clean abstractions.
+- **Autonomous Inter-Agent Delegation**: Agents can autonomously delegate tasks and inquire amongst themselves, enabling complex problem-solving in real-world scenarios.
+- **Flexible Task Management**: Define and customize tasks with granular control, from simple operations to complex multi-step processes.
+- **Production-Grade Architecture**: Support for both high-level abstractions and low-level customization, with robust error handling and state management.
+- **Predictable Results**: Ensure consistent, accurate outputs through programmatic guardrails, agent training capabilities, and flow-based execution control. See our [documentation on guardrails](https://docs.crewai.com/how-to/guardrails/) for implementation details.
+- **Model Flexibility**: Run your crew using OpenAI or open source models with production-ready integrations. See [Connect CrewAI to LLMs](https://docs.crewai.com/how-to/LLM-Connections/) for detailed configuration options.
+- **Event-Driven Flows**: Build complex, real-world workflows with precise control over execution paths, state management, and conditional logic.
+- **Process Orchestration**: Achieve any workflow pattern through flows - from simple sequential and hierarchical processes to complex, custom orchestration patterns with conditional branching and parallel execution.
 
 ![CrewAI Mind Map](./docs/crewAI-mindmap.png "CrewAI Mind Map")
 
@@ -305,6 +357,98 @@ You can test different real life examples of AI crews in the [CrewAI-examples re
 
 [![Stock Analysis](https://img.youtube.com/vi/e0Uj4yWdaAg/maxresdefault.jpg)](https://www.youtube.com/watch?v=e0Uj4yWdaAg "Stock Analysis")
 
+### Using Crews and Flows Together
+
+CrewAI's power truly shines when combining Crews with Flows to create sophisticated automation pipelines. Here's how you can orchestrate multiple Crews within a Flow:
+
+```python
+from crewai.flow.flow import Flow, listen, start, router
+from crewai import Crew, Agent, Task
+from pydantic import BaseModel
+
+# Define structured state for precise control
+class MarketState(BaseModel):
+    sentiment: str = "neutral"
+    confidence: float = 0.0
+    recommendations: list = []
+
+class AdvancedAnalysisFlow(Flow[MarketState]):
+    @start()
+    def fetch_market_data(self):
+        # Demonstrate low-level control with structured state
+        self.state.sentiment = "analyzing"
+        return {"sector": "tech", "timeframe": "1W"}  # These parameters match the task description template
+
+    @listen(fetch_market_data)
+    def analyze_with_crew(self, market_data):
+        # Show crew agency through specialized roles
+        analyst = Agent(
+            role="Senior Market Analyst",
+            goal="Conduct deep market analysis with expert insight",
+            backstory="You're a veteran analyst known for identifying subtle market patterns"
+        )
+        researcher = Agent(
+            role="Data Researcher",
+            goal="Gather and validate supporting market data",
+            backstory="You excel at finding and correlating multiple data sources"
+        )
+        
+        analysis_task = Task(
+            description="Analyze {sector} sector data for the past {timeframe}",
+            expected_output="Detailed market analysis with confidence score",
+            agent=analyst
+        )
+        research_task = Task(
+            description="Find supporting data to validate the analysis",
+            expected_output="Corroborating evidence and potential contradictions",
+            agent=researcher
+        )
+        
+        # Demonstrate crew autonomy
+        analysis_crew = Crew(
+            agents=[analyst, researcher],
+            tasks=[analysis_task, research_task],
+            process=Process.sequential,
+            verbose=True
+        )
+        return analysis_crew.kickoff(inputs=market_data)  # Pass market_data as named inputs
+
+    @router(analyze_with_crew)
+    def determine_next_steps(self):
+        # Show flow control with conditional routing
+        if self.state.confidence > 0.8:
+            return "high_confidence"
+        elif self.state.confidence > 0.5:
+            return "medium_confidence"
+        return "low_confidence"
+
+    @listen("high_confidence")
+    def execute_strategy(self):
+        # Demonstrate complex decision making
+        strategy_crew = Crew(
+            agents=[
+                Agent(role="Strategy Expert",
+                      goal="Develop optimal market strategy")
+            ],
+            tasks=[
+                Task(description="Create detailed strategy based on analysis",
+                     expected_output="Step-by-step action plan")
+            ]
+        )
+        return strategy_crew.kickoff()
+
+    @listen("medium_confidence", "low_confidence")
+    def request_additional_analysis(self):
+        self.state.recommendations.append("Gather more data")
+        return "Additional analysis required"
+```
+
+This example demonstrates how to:
+1. Use Python code for basic data operations
+2. Create and execute Crews as steps in your workflow
+3. Use Flow decorators to manage the sequence of operations
+4. Implement conditional branching based on Crew results
+
 ## Connecting Your Crew to a Model
 
 CrewAI supports using various LLMs through a variety of connection options. By default your agents will use the OpenAI API when querying the model. However, there are several other ways to allow your agents to connect to models. For example, you can configure your agents to use a local model via the Ollama tool.
@@ -313,9 +457,13 @@ Please refer to the [Connect CrewAI to LLMs](https://docs.crewai.com/how-to/LLM-
 
 ## How CrewAI Compares
 
-**CrewAI's Advantage**: CrewAI is built with production in mind. It offers the flexibility of Autogen's conversational agents and the structured process approach of ChatDev, but without the rigidity. CrewAI's processes are designed to be dynamic and adaptable, fitting seamlessly into both development and production workflows.
+**CrewAI's Advantage**: CrewAI combines autonomous agent intelligence with precise workflow control through its unique Crews and Flows architecture. The framework excels at both high-level orchestration and low-level customization, enabling complex, production-grade systems with granular control.
 
-- **Autogen**: While Autogen does good in creating conversational agents capable of working together, it lacks an inherent concept of process. In Autogen, orchestrating agents' interactions requires additional programming, which can become complex and cumbersome as the scale of tasks grows.
+- **LangGraph**: While LangGraph provides a foundation for building agent workflows, its approach requires significant boilerplate code and complex state management patterns. The framework's tight coupling with LangChain can limit flexibility when implementing custom agent behaviors or integrating with external systems.
+
+*P.S. CrewAI demonstrates significant performance advantages over LangGraph, executing 5.76x faster in certain cases like this QA task example ([see comparison](https://github.com/crewAIInc/crewAI-examples/tree/main/Notebooks/CrewAI%20Flows%20%26%20Langgraph/QA%20Agent)) while achieving higher evaluation scores with faster completion times in certain coding tasks, like in this example ([detailed analysis](https://github.com/crewAIInc/crewAI-examples/blob/main/Notebooks/CrewAI%20Flows%20%26%20Langgraph/Coding%20Assistant/coding_assistant_eval.ipynb)).*
+
+- **Autogen**: While Autogen excels at creating conversational agents capable of working together, it lacks an inherent concept of process. In Autogen, orchestrating agents' interactions requires additional programming, which can become complex and cumbersome as the scale of tasks grows.
 
 - **ChatDev**: ChatDev introduced the idea of processes into the realm of AI agents, but its implementation is quite rigid. Customizations in ChatDev are limited and not geared towards production environments, which can hinder scalability and flexibility in real-world applications.
 
@@ -440,5 +588,8 @@ A: CrewAI uses anonymous telemetry to collect usage data for improvement purpose
 ### Q: Where can I find examples of CrewAI in action?
 A: You can find various real-life examples in the [CrewAI-examples repository](https://github.com/crewAIInc/crewAI-examples), including trip planners, stock analysis tools, and more.
 
+### Q: What is the difference between Crews and Flows?
+A: Crews and Flows serve different but complementary purposes in CrewAI. Crews are teams of AI agents working together to accomplish specific tasks through role-based collaboration, delivering accurate and predictable results. Flows, on the other hand, are event-driven workflows that can orchestrate both Crews and regular Python code, allowing you to build complex automation pipelines with secure state management and conditional execution paths.
+
 ### Q: How can I contribute to CrewAI?
 A: Contributions are welcome! You can fork the repository, create a new branch for your feature, add your improvement, and send a pull request. Check the Contribution section in the README for more details.

docs/concepts/knowledge.mdx

@@ -79,6 +79,55 @@ crew = Crew(
 result = crew.kickoff(inputs={"question": "What city does John live in and how old is he?"})
 ```
 
+
+Here's another example with the `CrewDoclingSource`
+```python Code
+from crewai import LLM, Agent, Crew, Process, Task
+from crewai.knowledge.source.crew_docling_source import CrewDoclingSource
+
+# Create a knowledge source
+content_source = CrewDoclingSource(
+    file_paths=[
+        "https://lilianweng.github.io/posts/2024-11-28-reward-hacking",
+        "https://lilianweng.github.io/posts/2024-07-07-hallucination",
+    ],
+)
+
+# Create an LLM with a temperature of 0 to ensure deterministic outputs
+llm = LLM(model="gpt-4o-mini", temperature=0)
+
+# Create an agent with the knowledge store
+agent = Agent(
+    role="About papers",
+    goal="You know everything about the papers.",
+    backstory="""You are a master at understanding papers and their content.""",
+    verbose=True,
+    allow_delegation=False,
+    llm=llm,
+)
+task = Task(
+    description="Answer the following questions about the papers: {question}",
+    expected_output="An answer to the question.",
+    agent=agent,
+)
+
+crew = Crew(
+    agents=[agent],
+    tasks=[task],
+    verbose=True,
+    process=Process.sequential,
+    knowledge_sources=[
+        content_source
+    ],  # Enable knowledge by adding the sources here. You can also add more sources to the sources list.
+)
+
+result = crew.kickoff(
+    inputs={
+        "question": "What is the reward hacking paper about? Be sure to provide sources."
+    }
+)
+```
+
 ## Knowledge Configuration
 
 ### Chunking Configuration
@@ -122,6 +171,58 @@ crewai reset-memories --knowledge
 
 This is useful when you've updated your knowledge sources and want to ensure that the agents are using the most recent information.
 
+## Agent-Specific Knowledge
+
+While knowledge can be provided at the crew level using `crew.knowledge_sources`, individual agents can also have their own knowledge sources using the `knowledge_sources` parameter:
+
+```python Code
+from crewai import Agent, Task, Crew
+from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
+
+# Create agent-specific knowledge about a product
+product_specs = StringKnowledgeSource(
+    content="""The XPS 13 laptop features:
+    - 13.4-inch 4K display
+    - Intel Core i7 processor
+    - 16GB RAM
+    - 512GB SSD storage
+    - 12-hour battery life""",
+    metadata={"category": "product_specs"}
+)
+
+# Create a support agent with product knowledge
+support_agent = Agent(
+    role="Technical Support Specialist",
+    goal="Provide accurate product information and support.",
+    backstory="You are an expert on our laptop products and specifications.",
+    knowledge_sources=[product_specs]  # Agent-specific knowledge
+)
+
+# Create a task that requires product knowledge
+support_task = Task(
+    description="Answer this customer question: {question}",
+    agent=support_agent
+)
+
+# Create and run the crew
+crew = Crew(
+    agents=[support_agent],
+    tasks=[support_task]
+)
+
+# Get answer about the laptop's specifications
+result = crew.kickoff(
+    inputs={"question": "What is the storage capacity of the XPS 13?"}
+)
+```
+
+<Info>
+  Benefits of agent-specific knowledge:
+  - Give agents specialized information for their roles
+  - Maintain separation of concerns between agents
+  - Combine with crew-level knowledge for layered information access
+</Info>
+
 ## Custom Knowledge Sources
 
 CrewAI allows you to create custom knowledge sources for any type of data by extending the `BaseKnowledgeSource` class. Let's create a practical example that fetches and processes space news articles.

docs/concepts/llms.mdx

@@ -29,7 +29,7 @@ Large Language Models (LLMs) are the core intelligence behind CrewAI agents. The
 
 ## Available Models and Their Capabilities
 
-Here's a detailed breakdown of supported models and their capabilities, you can compare performance at [lmarena.ai](https://lmarena.ai/):
+Here's a detailed breakdown of supported models and their capabilities, you can compare performance at [lmarena.ai](https://lmarena.ai/?leaderboard) and [artificialanalysis.ai](https://artificialanalysis.ai/):
 
 <Tabs>
   <Tab title="OpenAI">
@@ -121,12 +121,18 @@ Here's a detailed breakdown of supported models and their capabilities, you can
   <Tab title="Gemini">
     | Model | Context Window | Best For |
     |-------|---------------|-----------|
-    | Gemini 1.5 Flash | 1M tokens | Balanced multimodal model, good for most tasks |
-    | Gemini 1.5 Flash 8B | 1M tokens | Fastest, most cost-efficient, good for high-frequency tasks |
-    | Gemini 1.5 Pro | 2M tokens | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
+    | gemini-2.0-flash-exp | 1M tokens | Higher quality at faster speed, multimodal model, good for most tasks |
+    | gemini-1.5-flash | 1M tokens | Balanced multimodal model, good for most tasks |
+    | gemini-1.5-flash-8B | 1M tokens | Fastest, most cost-efficient, good for high-frequency tasks |
+    | gemini-1.5-pro | 2M tokens | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
 
     <Tip>
       Google's Gemini models are all multimodal, supporting audio, images, video and text, supporting context caching, json schema, function calling, etc.
+
+      These models are available via API_KEY from 
+      [The Gemini API](https://ai.google.dev/gemini-api/docs) and also from 
+      [Google Cloud Vertex](https://cloud.google.com/vertex-ai/generative-ai/docs/migrate/migrate-google-ai) as part of the
+      [Model Garden](https://cloud.google.com/vertex-ai/generative-ai/docs/model-garden/explore-models).
     </Tip>
   </Tab>
   <Tab title="Groq">
@@ -135,7 +141,6 @@ Here's a detailed breakdown of supported models and their capabilities, you can
     | Llama 3.1 70B/8B | 131,072 tokens | High-performance, large context tasks |
     | Llama 3.2 Series | 8,192 tokens | General-purpose tasks |
     | Mixtral 8x7B | 32,768 tokens | Balanced performance and context |
-    | Gemma Series | 8,192 tokens | Efficient, smaller-scale tasks |
 
     <Tip>
       Groq is known for its fast inference speeds, making it suitable for real-time applications.
@@ -146,7 +151,7 @@ Here's a detailed breakdown of supported models and their capabilities, you can
     |----------|---------------|--------------|
     | Deepseek Chat | 128,000 tokens | Specialized in technical discussions |
     | Claude 3 | Up to 200K tokens | Strong reasoning, code understanding |
-    | Gemini | Varies by model | Multimodal capabilities |
+    | Gemma Series | 8,192 tokens | Efficient, smaller-scale tasks |
 
     <Info>
       Provider selection should consider factors like:

docs/concepts/tasks.mdx

@@ -6,7 +6,7 @@ icon: list-check
 
 ## Overview of a Task
 
-In the CrewAI framework, a `Task` is a specific assignment completed by an `Agent`. 
+In the CrewAI framework, a `Task` is a specific assignment completed by an `Agent`.
 
 Tasks provide all necessary details for execution, such as a description, the agent responsible, required tools, and more, facilitating a wide range of action complexities.
 
@@ -263,8 +263,148 @@ analysis_task = Task(
 )
 ```
 
+## Task Guardrails
+
+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.
+
+### Using Task Guardrails
+
+To add a guardrail to a task, provide a validation function through the `guardrail` parameter:
+
+```python Code
+from typing import Tuple, Union, Dict, Any
+
+def validate_blog_content(result: str) -> Tuple[bool, Union[Dict[str, Any], str]]:
+    """Validate blog content meets requirements."""
+    try:
+        # Check word count
+        word_count = len(result.split())
+        if word_count > 200:
+            return (False, {
+                "error": "Blog content exceeds 200 words",
+                "code": "WORD_COUNT_ERROR",
+                "context": {"word_count": word_count}
+            })
+
+        # Additional validation logic here
+        return (True, result.strip())
+    except Exception as e:
+        return (False, {
+            "error": "Unexpected error during validation",
+            "code": "SYSTEM_ERROR"
+        })
+
+blog_task = Task(
+    description="Write a blog post about AI",
+    expected_output="A blog post under 200 words",
+    agent=blog_agent,
+    guardrail=validate_blog_content  # Add the guardrail function
+)
+```
+
+### Guardrail Function Requirements
+
+1. **Function Signature**:
+   - Must accept exactly one parameter (the task output)
+   - Should return a tuple of `(bool, Any)`
+   - Type hints are recommended but optional
+
+2. **Return Values**:
+   - Success: Return `(True, validated_result)`
+   - Failure: Return `(False, error_details)`
+
+### Error Handling Best Practices
+
+1. **Structured Error Responses**:
+```python Code
+def validate_with_context(result: str) -> Tuple[bool, Union[Dict[str, Any], str]]:
+    try:
+        # Main validation logic
+        validated_data = perform_validation(result)
+        return (True, validated_data)
+    except ValidationError as e:
+        return (False, {
+            "error": str(e),
+            "code": "VALIDATION_ERROR",
+            "context": {"input": result}
+        })
+    except Exception as e:
+        return (False, {
+            "error": "Unexpected error",
+            "code": "SYSTEM_ERROR"
+        })
+```
+
+2. **Error Categories**:
+   - Use specific error codes
+   - Include relevant context
+   - Provide actionable feedback
+
+3. **Validation Chain**:
+```python Code
+from typing import Any, Dict, List, Tuple, Union
+
+def complex_validation(result: str) -> Tuple[bool, Union[str, Dict[str, Any]]]:
+    """Chain multiple validation steps."""
+    # Step 1: Basic validation
+    if not result:
+        return (False, {"error": "Empty result", "code": "EMPTY_INPUT"})
+
+    # Step 2: Content validation
+    try:
+        validated = validate_content(result)
+        if not validated:
+            return (False, {"error": "Invalid content", "code": "CONTENT_ERROR"})
+
+        # Step 3: Format validation
+        formatted = format_output(validated)
+        return (True, formatted)
+    except Exception as e:
+        return (False, {
+            "error": str(e),
+            "code": "VALIDATION_ERROR",
+            "context": {"step": "content_validation"}
+        })
+```
+
+### Handling Guardrail Results
+
+When a guardrail returns `(False, error)`:
+1. The error is sent back to the agent
+2. The agent attempts to fix the issue
+3. The process repeats until:
+   - The guardrail returns `(True, result)`
+   - Maximum retries are reached
+
+Example with retry handling:
+```python Code
+from typing import Optional, Tuple, Union
+
+def validate_json_output(result: str) -> Tuple[bool, Union[Dict[str, Any], str]]:
+    """Validate and parse JSON output."""
+    try:
+        # Try to parse as JSON
+        data = json.loads(result)
+        return (True, data)
+    except json.JSONDecodeError as e:
+        return (False, {
+            "error": "Invalid JSON format",
+            "code": "JSON_ERROR",
+            "context": {"line": e.lineno, "column": e.colno}
+        })
+
+task = Task(
+    description="Generate a JSON report",
+    expected_output="A valid JSON object",
+    agent=analyst,
+    guardrail=validate_json_output,
+    max_retries=3  # Limit retry attempts
+)
+```
+
 ## Getting Structured Consistent Outputs from Tasks
-When you need to ensure that a task outputs a structured and consistent format, you can use the `output_pydantic` or `output_json` properties on a task. These properties allow you to define the expected output structure, making it easier to parse and utilize the results in your application. 
 
 <Note>
 It's also important to note that the output of the final task of a crew becomes the final output of the actual crew itself.
@@ -608,6 +748,114 @@ While creating and executing tasks, certain validation mechanisms are in place t
 
 These validations help in maintaining the consistency and reliability of task executions within the crewAI framework.
 
+## Task Guardrails
+
+Task guardrails provide a powerful way to validate, transform, or filter task outputs before they are passed to the next task. Guardrails are optional functions that execute before the next task starts, allowing you to ensure that task outputs meet specific requirements or formats.
+
+### Basic Usage
+
+```python Code
+from typing import Tuple, Union
+from crewai import Task
+
+def validate_json_output(result: str) -> Tuple[bool, Union[dict, str]]:
+    """Validate that the output is valid JSON."""
+    try:
+        json_data = json.loads(result)
+        return (True, json_data)
+    except json.JSONDecodeError:
+        return (False, "Output must be valid JSON")
+
+task = Task(
+    description="Generate JSON data",
+    expected_output="Valid JSON object",
+    guardrail=validate_json_output
+)
+```
+
+### How Guardrails Work
+
+1. **Optional Attribute**: Guardrails are an optional attribute at the task level, allowing you to add validation only where needed.
+2. **Execution Timing**: The guardrail function is executed before the next task starts, ensuring valid data flow between tasks.
+3. **Return Format**: Guardrails must return a tuple of `(success, data)`:
+   - If `success` is `True`, `data` is the validated/transformed result
+   - If `success` is `False`, `data` is the error message
+4. **Result Routing**:
+   - On success (`True`), the result is automatically passed to the next task
+   - On failure (`False`), the error is sent back to the agent to generate a new answer
+
+### Common Use Cases
+
+#### Data Format Validation
+```python Code
+def validate_email_format(result: str) -> Tuple[bool, Union[str, str]]:
+    """Ensure the output contains a valid email address."""
+    import re
+    email_pattern = r'^[\w\.-]+@[\w\.-]+\.\w+$'
+    if re.match(email_pattern, result.strip()):
+        return (True, result.strip())
+    return (False, "Output must be a valid email address")
+```
+
+#### Content Filtering
+```python Code
+def filter_sensitive_info(result: str) -> Tuple[bool, Union[str, str]]:
+    """Remove or validate sensitive information."""
+    sensitive_patterns = ['SSN:', 'password:', 'secret:']
+    for pattern in sensitive_patterns:
+        if pattern.lower() in result.lower():
+            return (False, f"Output contains sensitive information ({pattern})")
+    return (True, result)
+```
+
+#### Data Transformation
+```python Code
+def normalize_phone_number(result: str) -> Tuple[bool, Union[str, str]]:
+    """Ensure phone numbers are in a consistent format."""
+    import re
+    digits = re.sub(r'\D', '', result)
+    if len(digits) == 10:
+        formatted = f"({digits[:3]}) {digits[3:6]}-{digits[6:]}"
+        return (True, formatted)
+    return (False, "Output must be a 10-digit phone number")
+```
+
+### Advanced Features
+
+#### Chaining Multiple Validations
+```python Code
+def chain_validations(*validators):
+    """Chain multiple validators together."""
+    def combined_validator(result):
+        for validator in validators:
+            success, data = validator(result)
+            if not success:
+                return (False, data)
+            result = data
+        return (True, result)
+    return combined_validator
+
+# Usage
+task = Task(
+    description="Get user contact info",
+    expected_output="Email and phone",
+    guardrail=chain_validations(
+        validate_email_format,
+        filter_sensitive_info
+    )
+)
+```
+
+#### Custom Retry Logic
+```python Code
+task = Task(
+    description="Generate data",
+    expected_output="Valid data",
+    guardrail=validate_data,
+    max_retries=5  # Override default retry limit
+)
+```
+
 ## Creating Directories when Saving Files
 
 You can now specify if a task should create directories when saving its output to a file. This is particularly useful for organizing outputs and ensuring that file paths are correctly structured.
@@ -629,7 +877,7 @@ save_output_task = Task(
 
 ## Conclusion
 
-Tasks are the driving force behind the actions of agents in CrewAI. 
-By properly defining tasks and their outcomes, you set the stage for your AI agents to work effectively, either independently or as a collaborative unit. 
-Equipping tasks with appropriate tools, understanding the execution process, and following robust validation practices are crucial for maximizing CrewAI's potential, 
+Tasks are the driving force behind the actions of agents in CrewAI.
+By properly defining tasks and their outcomes, you set the stage for your AI agents to work effectively, either independently or as a collaborative unit.
+Equipping tasks with appropriate tools, understanding the execution process, and following robust validation practices are crucial for maximizing CrewAI's potential,
 ensuring agents are effectively prepared for their assignments and that tasks are executed as intended.

docs/how-to/Portkey-Observability-and-Guardrails.md

@@ -0,0 +1,211 @@
+# 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/multimodal-agents.mdx

@@ -0,0 +1,138 @@
+---
+title: Using Multimodal Agents
+description: Learn how to enable and use multimodal capabilities in your agents for processing images and other non-text content within the CrewAI framework.
+icon: image
+---
+
+# Using Multimodal Agents
+
+CrewAI supports multimodal agents that can process both text and non-text content like images. This guide will show you how to enable and use multimodal capabilities in your agents.
+
+## Enabling Multimodal Capabilities
+
+To create a multimodal agent, simply set the `multimodal` parameter to `True` when initializing your agent:
+
+```python
+from crewai import Agent
+
+agent = Agent(
+    role="Image Analyst",
+    goal="Analyze and extract insights from images",
+    backstory="An expert in visual content interpretation with years of experience in image analysis",
+    multimodal=True  # This enables multimodal capabilities
+)
+```
+
+When you set `multimodal=True`, the agent is automatically configured with the necessary tools for handling non-text content, including the `AddImageTool`.
+
+## Working with Images
+
+The multimodal agent comes pre-configured with the `AddImageTool`, which allows it to process images. You don't need to manually add this tool - it's automatically included when you enable multimodal capabilities.
+
+Here's a complete example showing how to use a multimodal agent to analyze an image:
+
+```python
+from crewai import Agent, Task, Crew
+
+# Create a multimodal agent
+image_analyst = Agent(
+    role="Product Analyst",
+    goal="Analyze product images and provide detailed descriptions",
+    backstory="Expert in visual product analysis with deep knowledge of design and features",
+    multimodal=True
+)
+
+# Create a task for image analysis
+task = Task(
+    description="Analyze the product image at https://example.com/product.jpg and provide a detailed description",
+    agent=image_analyst
+)
+
+# Create and run the crew
+crew = Crew(
+    agents=[image_analyst],
+    tasks=[task]
+)
+
+result = crew.kickoff()
+```
+
+### Advanced Usage with Context
+
+You can provide additional context or specific questions about the image when creating tasks for multimodal agents. The task description can include specific aspects you want the agent to focus on:
+
+```python
+from crewai import Agent, Task, Crew
+
+# Create a multimodal agent for detailed analysis
+expert_analyst = Agent(
+    role="Visual Quality Inspector",
+    goal="Perform detailed quality analysis of product images",
+    backstory="Senior quality control expert with expertise in visual inspection",
+    multimodal=True  # AddImageTool is automatically included
+)
+
+# Create a task with specific analysis requirements
+inspection_task = Task(
+    description="""
+    Analyze the product image at https://example.com/product.jpg with focus on:
+    1. Quality of materials
+    2. Manufacturing defects
+    3. Compliance with standards
+    Provide a detailed report highlighting any issues found.
+    """,
+    agent=expert_analyst
+)
+
+# Create and run the crew
+crew = Crew(
+    agents=[expert_analyst],
+    tasks=[inspection_task]
+)
+
+result = crew.kickoff()
+```
+
+### Tool Details
+
+When working with multimodal agents, the `AddImageTool` is automatically configured with the following schema:
+
+```python
+class AddImageToolSchema:
+    image_url: str  # Required: The URL or path of the image to process
+    action: Optional[str] = None  # Optional: Additional context or specific questions about the image
+```
+
+The multimodal agent will automatically handle the image processing through its built-in tools, allowing it to:
+- Access images via URLs or local file paths
+- Process image content with optional context or specific questions
+- Provide analysis and insights based on the visual information and task requirements
+
+## Best Practices
+
+When working with multimodal agents, keep these best practices in mind:
+
+1. **Image Access**
+   - Ensure your images are accessible via URLs that the agent can reach
+   - For local images, consider hosting them temporarily or using absolute file paths
+   - Verify that image URLs are valid and accessible before running tasks
+
+2. **Task Description**
+   - Be specific about what aspects of the image you want the agent to analyze
+   - Include clear questions or requirements in the task description
+   - Consider using the optional `action` parameter for focused analysis
+
+3. **Resource Management**
+   - Image processing may require more computational resources than text-only tasks
+   - Some language models may require base64 encoding for image data
+   - Consider batch processing for multiple images to optimize performance
+
+4. **Environment Setup**
+   - Verify that your environment has the necessary dependencies for image processing
+   - Ensure your language model supports multimodal capabilities
+   - Test with small images first to validate your setup
+
+5. **Error Handling**
+   - Implement proper error handling for image loading failures
+   - Have fallback strategies for when image processing fails
+   - Monitor and log image processing operations for debugging

pyproject.toml

@@ -8,27 +8,38 @@ authors = [
     { name = "Joao Moura", email = "joao@crewai.com" }
 ]
 dependencies = [
+    # Core Dependencies
     "pydantic>=2.4.2",
     "openai>=1.13.3",
+    "litellm>=1.44.22",
+    "instructor>=1.3.3",
+    
+    # Text Processing
+    "pdfplumber>=0.11.4",
+    "regex>=2024.9.11",
+    
+    # Telemetry and Monitoring
     "opentelemetry-api>=1.22.0",
     "opentelemetry-sdk>=1.22.0",
     "opentelemetry-exporter-otlp-proto-http>=1.22.0",
-    "instructor>=1.3.3",
-    "regex>=2024.9.11",
-    "click>=8.1.7",
+    
+    # Data Handling
+    "chromadb>=0.5.23",
+    "openpyxl>=3.1.5",
+    "pyvis>=0.3.2",
+    
+    # Authentication and Security
+    "auth0-python>=4.7.1",
     "python-dotenv>=1.0.0",
+    
+    # Configuration and Utils
+    "click>=8.1.7",
     "appdirs>=1.4.4",
     "jsonref>=1.1.0",
     "json-repair>=0.25.2",
-    "auth0-python>=4.7.1",
-    "litellm>=1.44.22",
-    "pyvis>=0.3.2",
     "uv>=0.4.25",
     "tomli-w>=1.1.0",
     "tomli>=2.0.2",
-    "chromadb>=0.5.23",
-    "pdfplumber>=0.11.4",
-    "openpyxl>=3.1.5",
     "blinker>=1.9.0",
 ]
 
@@ -39,6 +50,9 @@ Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
 tools = ["crewai-tools>=0.17.0"]
+embeddings = [
+    "tiktoken~=0.7.0"
+]
 agentops = ["agentops>=0.3.0"]
 fastembed = ["fastembed>=0.4.1"]
 pdfplumber = [
@@ -51,6 +65,9 @@ openpyxl = [
     "openpyxl>=3.1.5",
 ]
 mem0 = ["mem0ai>=0.1.29"]
+docling = [
+    "docling>=2.12.0",
+]
 
 [tool.uv]
 dev-dependencies = [
@@ -64,7 +81,6 @@ dev-dependencies = [
     "mkdocs-material-extensions>=1.3.1",
     "pillow>=10.2.0",
     "cairosvg>=2.7.1",
-    "crewai-tools>=0.17.0",
     "pytest>=8.0.0",
     "pytest-vcr>=1.0.2",
     "python-dotenv>=1.0.0",

src/crewai/agent.py

@@ -17,6 +17,7 @@ from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.task import Task
 from crewai.tools import BaseTool
 from crewai.tools.agent_tools.agent_tools import AgentTools
+from crewai.tools.base_tool import Tool
 from crewai.utilities import Converter, Prompts
 from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
 from crewai.utilities.converter import generate_model_description
@@ -114,6 +115,10 @@ class Agent(BaseAgent):
         default=2,
         description="Maximum number of retries for an agent to execute a task when an error occurs.",
     )
+    multimodal: bool = Field(
+        default=False,
+        description="Whether the agent is multimodal.",
+    )
     code_execution_mode: Literal["safe", "unsafe"] = Field(
         default="safe",
         description="Mode for code execution: 'safe' (using Docker) or 'unsafe' (direct execution).",
@@ -406,6 +411,10 @@ class Agent(BaseAgent):
         tools = agent_tools.tools()
         return tools
 
+    def get_multimodal_tools(self) -> List[Tool]:
+        from crewai.tools.agent_tools.add_image_tool import AddImageTool
+        return [AddImageTool()]
+
     def get_code_execution_tools(self):
         try:
             from crewai_tools import CodeInterpreterTool

src/crewai/agents/crew_agent_executor.py

@@ -143,10 +143,20 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         tool_result = self._execute_tool_and_check_finality(
                             formatted_answer
                         )
-                        if self.step_callback:
-                            self.step_callback(tool_result)
 
-                        formatted_answer.text += f"\nObservation: {tool_result.result}"
+                        # Directly append the result to the messages if the
+                        # tool is "Add image to content" in case of multimodal
+                        # agents
+                        if formatted_answer.tool == self._i18n.tools("add_image")["name"]:
+                            self.messages.append(tool_result.result)
+                            continue
+
+                        else:
+                            if self.step_callback:
+                                self.step_callback(tool_result)
+
+                            formatted_answer.text += f"\nObservation: {tool_result.result}"
+
                         formatted_answer.result = tool_result.result
                         if tool_result.result_as_answer:
                             return AgentFinish(

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

@@ -18,3 +18,6 @@ test = "{{folder_name}}.main:test"
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"
+
+[tool.crewai]
+type = "crew"

src/crewai/cli/templates/flow/main.py

@@ -5,7 +5,7 @@ from pydantic import BaseModel
 
 from crewai.flow.flow import Flow, listen, start
 
-from .crews.poem_crew.poem_crew import PoemCrew
+from {{folder_name}}.crews.poem_crew.poem_crew import PoemCrew
 
 
 class PoemState(BaseModel):

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

@@ -15,3 +15,6 @@ plot = "{{folder_name}}.main:plot"
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"
+
+[tool.crewai]
+type = "flow"

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

@@ -8,3 +8,5 @@ dependencies = [
     "crewai[tools]>=0.86.0"
 ]
 
+[tool.crewai]
+type = "tool"

src/crewai/crew.py

@@ -35,6 +35,7 @@ from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry import Telemetry
 from crewai.tools.agent_tools.agent_tools import AgentTools
+from crewai.tools.base_tool import Tool
 from crewai.types.usage_metrics import UsageMetrics
 from crewai.utilities import I18N, FileHandler, Logger, RPMController
 from crewai.utilities.constants import TRAINING_DATA_FILE
@@ -533,9 +534,6 @@ class Crew(BaseModel):
             if not agent.function_calling_llm:  # type: ignore # "BaseAgent" has no attribute "function_calling_llm"
                 agent.function_calling_llm = self.function_calling_llm  # type: ignore # "BaseAgent" has no attribute "function_calling_llm"
 
-            if agent.allow_code_execution:  # type: ignore # BaseAgent" has no attribute "allow_code_execution"
-                agent.tools += agent.get_code_execution_tools()  # type: ignore # "BaseAgent" has no attribute "get_code_execution_tools"; maybe "get_delegation_tools"?
-
             if not agent.step_callback:  # type: ignore # "BaseAgent" has no attribute "step_callback"
                 agent.step_callback = self.step_callback  # type: ignore # "BaseAgent" has no attribute "step_callback"
 
@@ -672,7 +670,6 @@ class Crew(BaseModel):
                 )
                 manager.tools = []
                 raise Exception("Manager agent should not have tools")
-            manager.tools = self.manager_agent.get_delegation_tools(self.agents)
         else:
             self.manager_llm = (
                 getattr(self.manager_llm, "model_name", None)
@@ -684,6 +681,7 @@ class Crew(BaseModel):
                 goal=i18n.retrieve("hierarchical_manager_agent", "goal"),
                 backstory=i18n.retrieve("hierarchical_manager_agent", "backstory"),
                 tools=AgentTools(agents=self.agents).tools(),
+                allow_delegation=True,
                 llm=self.manager_llm,
                 verbose=self.verbose,
             )
@@ -726,7 +724,10 @@ class Crew(BaseModel):
                     f"No agent available for task: {task.description}. Ensure that either the task has an assigned agent or a manager agent is provided."
                 )
 
-            self._prepare_agent_tools(task)
+            # Determine which tools to use - task tools take precedence over agent tools
+            tools_for_task = task.tools or agent_to_use.tools or []
+            tools_for_task = self._prepare_tools(agent_to_use, task, tools_for_task)
+
             self._log_task_start(task, agent_to_use.role)
 
             if isinstance(task, ConditionalTask):
@@ -743,7 +744,7 @@ class Crew(BaseModel):
                 future = task.execute_async(
                     agent=agent_to_use,
                     context=context,
-                    tools=agent_to_use.tools,
+                    tools=tools_for_task,
                 )
                 futures.append((task, future, task_index))
             else:
@@ -755,7 +756,7 @@ class Crew(BaseModel):
                 task_output = task.execute_sync(
                     agent=agent_to_use,
                     context=context,
-                    tools=agent_to_use.tools,
+                    tools=tools_for_task,
                 )
                 task_outputs = [task_output]
                 self._process_task_result(task, task_output)
@@ -792,45 +793,77 @@ class Crew(BaseModel):
             return skipped_task_output
         return None
 
-    def _prepare_agent_tools(self, task: Task):
-        if self.process == Process.hierarchical:
-            if self.manager_agent:
-                self._update_manager_tools(task)
-            else:
-                raise ValueError("Manager agent is required for hierarchical process.")
-        elif task.agent and task.agent.allow_delegation:
-            self._add_delegation_tools(task)
+    def _prepare_tools(
+        self, agent: BaseAgent, task: Task, tools: List[Tool]
+    ) -> List[Tool]:
+        # Add delegation tools if agent allows delegation
+        if agent.allow_delegation:
+            if self.process == Process.hierarchical:
+                if self.manager_agent:
+                    tools = self._update_manager_tools(task, tools)
+                else:
+                    raise ValueError(
+                        "Manager agent is required for hierarchical process."
+                    )
+
+            elif agent and agent.allow_delegation:
+                tools = self._add_delegation_tools(task, tools)
+
+        # Add code execution tools if agent allows code execution
+        if agent.allow_code_execution:
+            tools = self._add_code_execution_tools(agent, tools)
+
+        if agent and agent.multimodal:
+            tools = self._add_multimodal_tools(agent, tools)
+
+        return tools
 
     def _get_agent_to_use(self, task: Task) -> Optional[BaseAgent]:
         if self.process == Process.hierarchical:
             return self.manager_agent
         return task.agent
 
-    def _add_delegation_tools(self, task: Task):
+    def _merge_tools(
+        self, existing_tools: List[Tool], new_tools: List[Tool]
+    ) -> List[Tool]:
+        """Merge new tools into existing tools list, avoiding duplicates by tool name."""
+        if not new_tools:
+            return existing_tools
+
+        # Create mapping of tool names to new tools
+        new_tool_map = {tool.name: tool for tool in new_tools}
+
+        # Remove any existing tools that will be replaced
+        tools = [tool for tool in existing_tools if tool.name not in new_tool_map]
+
+        # Add all new tools
+        tools.extend(new_tools)
+
+        return tools
+
+    def _inject_delegation_tools(
+        self, tools: List[Tool], task_agent: BaseAgent, agents: List[BaseAgent]
+    ):
+        delegation_tools = task_agent.get_delegation_tools(agents)
+        return self._merge_tools(tools, delegation_tools)
+
+    def _add_multimodal_tools(self, agent: BaseAgent, tools: List[Tool]):
+        multimodal_tools = agent.get_multimodal_tools()
+        return self._merge_tools(tools, multimodal_tools)
+
+    def _add_code_execution_tools(self, agent: BaseAgent, tools: List[Tool]):
+        code_tools = agent.get_code_execution_tools()
+        return self._merge_tools(tools, code_tools)
+
+    def _add_delegation_tools(self, task: Task, tools: List[Tool]):
         agents_for_delegation = [agent for agent in self.agents if agent != task.agent]
         if len(self.agents) > 1 and len(agents_for_delegation) > 0 and task.agent:
-            delegation_tools = task.agent.get_delegation_tools(agents_for_delegation)
-
-            # Add tools if they are not already in task.tools
-            for new_tool in delegation_tools:
-                # Find the index of the tool with the same name
-                existing_tool_index = next(
-                    (
-                        index
-                        for index, tool in enumerate(task.tools or [])
-                        if tool.name == new_tool.name
-                    ),
-                    None,
-                )
-                if not task.tools:
-                    task.tools = []
-
-                if existing_tool_index is not None:
-                    # Replace the existing tool
-                    task.tools[existing_tool_index] = new_tool
-                else:
-                    # Add the new tool
-                    task.tools.append(new_tool)
+            if not tools:
+                tools = []
+            tools = self._inject_delegation_tools(
+                tools, task.agent, agents_for_delegation
+            )
+        return tools
 
     def _log_task_start(self, task: Task, role: str = "None"):
         if self.output_log_file:
@@ -838,14 +871,15 @@ class Crew(BaseModel):
                 task_name=task.name, task=task.description, agent=role, status="started"
             )
 
-    def _update_manager_tools(self, task: Task):
+    def _update_manager_tools(self, task: Task, tools: List[Tool]):
         if self.manager_agent:
             if task.agent:
-                self.manager_agent.tools = task.agent.get_delegation_tools([task.agent])
+                tools = self._inject_delegation_tools(tools, task.agent, [task.agent])
             else:
-                self.manager_agent.tools = self.manager_agent.get_delegation_tools(
-                    self.agents
+                tools = self._inject_delegation_tools(
+                    tools, self.manager_agent, self.agents
                 )
+        return tools
 
     def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
         context = (

src/crewai/flow/flow.py

@@ -30,7 +30,47 @@ from crewai.telemetry import Telemetry
 T = TypeVar("T", bound=Union[BaseModel, Dict[str, Any]])
 
 
-def start(condition=None):
+def start(condition: Optional[Union[str, dict, Callable]] = None) -> Callable:
+    """
+    Marks a method as a flow's starting point.
+
+    This decorator designates a method as an entry point for the flow execution.
+    It can optionally specify conditions that trigger the start based on other
+    method executions.
+
+    Parameters
+    ----------
+    condition : Optional[Union[str, dict, Callable]], optional
+        Defines when the start method should execute. Can be:
+        - str: Name of a method that triggers this start
+        - dict: Contains "type" ("AND"/"OR") and "methods" (list of triggers)
+        - Callable: A method reference that triggers this start
+        Default is None, meaning unconditional start.
+
+    Returns
+    -------
+    Callable
+        A decorator function that marks the method as a flow start point.
+
+    Raises
+    ------
+    ValueError
+        If the condition format is invalid.
+
+    Examples
+    --------
+    >>> @start()  # Unconditional start
+    >>> def begin_flow(self):
+    ...     pass
+
+    >>> @start("method_name")  # Start after specific method
+    >>> def conditional_start(self):
+    ...     pass
+
+    >>> @start(and_("method1", "method2"))  # Start after multiple methods
+    >>> def complex_start(self):
+    ...     pass
+    """
     def decorator(func):
         func.__is_start_method__ = True
         if condition is not None:
@@ -55,8 +95,42 @@ def start(condition=None):
 
     return decorator
 
+def listen(condition: Union[str, dict, Callable]) -> Callable:
+    """
+    Creates a listener that executes when specified conditions are met.
 
-def listen(condition):
+    This decorator sets up a method to execute in response to other method
+    executions in the flow. It supports both simple and complex triggering
+    conditions.
+
+    Parameters
+    ----------
+    condition : Union[str, dict, Callable]
+        Specifies when the listener should execute. Can be:
+        - str: Name of a method that triggers this listener
+        - dict: Contains "type" ("AND"/"OR") and "methods" (list of triggers)
+        - Callable: A method reference that triggers this listener
+
+    Returns
+    -------
+    Callable
+        A decorator function that sets up the method as a listener.
+
+    Raises
+    ------
+    ValueError
+        If the condition format is invalid.
+
+    Examples
+    --------
+    >>> @listen("process_data")  # Listen to single method
+    >>> def handle_processed_data(self):
+    ...     pass
+
+    >>> @listen(or_("success", "failure"))  # Listen to multiple methods
+    >>> def handle_completion(self):
+    ...     pass
+    """
     def decorator(func):
         if isinstance(condition, str):
             func.__trigger_methods__ = [condition]
@@ -80,16 +154,103 @@ def listen(condition):
     return decorator
 
 
-def router(method):
+def router(condition: Union[str, dict, Callable]) -> Callable:
+    """
+    Creates a routing method that directs flow execution based on conditions.
+
+    This decorator marks a method as a router, which can dynamically determine
+    the next steps in the flow based on its return value. Routers are triggered
+    by specified conditions and can return constants that determine which path
+    the flow should take.
+
+    Parameters
+    ----------
+    condition : Union[str, dict, Callable]
+        Specifies when the router should execute. Can be:
+        - str: Name of a method that triggers this router
+        - dict: Contains "type" ("AND"/"OR") and "methods" (list of triggers)
+        - Callable: A method reference that triggers this router
+
+    Returns
+    -------
+    Callable
+        A decorator function that sets up the method as a router.
+
+    Raises
+    ------
+    ValueError
+        If the condition format is invalid.
+
+    Examples
+    --------
+    >>> @router("check_status")
+    >>> def route_based_on_status(self):
+    ...     if self.state.status == "success":
+    ...         return SUCCESS
+    ...     return FAILURE
+
+    >>> @router(and_("validate", "process"))
+    >>> def complex_routing(self):
+    ...     if all([self.state.valid, self.state.processed]):
+    ...         return CONTINUE
+    ...     return STOP
+    """
     def decorator(func):
         func.__is_router__ = True
-        func.__router_for__ = method.__name__
+        if isinstance(condition, str):
+            func.__trigger_methods__ = [condition]
+            func.__condition_type__ = "OR"
+        elif (
+            isinstance(condition, dict)
+            and "type" in condition
+            and "methods" in condition
+        ):
+            func.__trigger_methods__ = condition["methods"]
+            func.__condition_type__ = condition["type"]
+        elif callable(condition) and hasattr(condition, "__name__"):
+            func.__trigger_methods__ = [condition.__name__]
+            func.__condition_type__ = "OR"
+        else:
+            raise ValueError(
+                "Condition must be a method, string, or a result of or_() or and_()"
+            )
         return func
 
     return decorator
 
+def or_(*conditions: Union[str, dict, Callable]) -> dict:
+    """
+    Combines multiple conditions with OR logic for flow control.
 
-def or_(*conditions):
+    Creates a condition that is satisfied when any of the specified conditions
+    are met. This is used with @start, @listen, or @router decorators to create
+    complex triggering conditions.
+
+    Parameters
+    ----------
+    *conditions : Union[str, dict, Callable]
+        Variable number of conditions that can be:
+        - str: Method names
+        - dict: Existing condition dictionaries
+        - Callable: Method references
+
+    Returns
+    -------
+    dict
+        A condition dictionary with format:
+        {"type": "OR", "methods": list_of_method_names}
+
+    Raises
+    ------
+    ValueError
+        If any condition is invalid.
+
+    Examples
+    --------
+    >>> @listen(or_("success", "timeout"))
+    >>> def handle_completion(self):
+    ...     pass
+    """
     methods = []
     for condition in conditions:
         if isinstance(condition, dict) and "methods" in condition:
@@ -103,7 +264,39 @@ def or_(*conditions):
     return {"type": "OR", "methods": methods}
 
 
-def and_(*conditions):
+def and_(*conditions: Union[str, dict, Callable]) -> dict:
+    """
+    Combines multiple conditions with AND logic for flow control.
+
+    Creates a condition that is satisfied only when all specified conditions
+    are met. This is used with @start, @listen, or @router decorators to create
+    complex triggering conditions.
+
+    Parameters
+    ----------
+    *conditions : Union[str, dict, Callable]
+        Variable number of conditions that can be:
+        - str: Method names
+        - dict: Existing condition dictionaries
+        - Callable: Method references
+
+    Returns
+    -------
+    dict
+        A condition dictionary with format:
+        {"type": "AND", "methods": list_of_method_names}
+
+    Raises
+    ------
+    ValueError
+        If any condition is invalid.
+
+    Examples
+    --------
+    >>> @listen(and_("validated", "processed"))
+    >>> def handle_complete_data(self):
+    ...     pass
+    """
     methods = []
     for condition in conditions:
         if isinstance(condition, dict) and "methods" in condition:
@@ -123,8 +316,8 @@ class FlowMeta(type):
 
         start_methods = []
         listeners = {}
-        routers = {}
         router_paths = {}
+        routers = set()
 
         for attr_name, attr_value in dct.items():
             if hasattr(attr_value, "__is_start_method__"):
@@ -137,18 +330,11 @@ class FlowMeta(type):
                 methods = attr_value.__trigger_methods__
                 condition_type = getattr(attr_value, "__condition_type__", "OR")
                 listeners[attr_name] = (condition_type, methods)
-
-            elif hasattr(attr_value, "__is_router__"):
-                routers[attr_value.__router_for__] = attr_name
-                possible_returns = get_possible_return_constants(attr_value)
-                if possible_returns:
-                    router_paths[attr_name] = possible_returns
-
-                # Register router as a listener to its triggering method
-                trigger_method_name = attr_value.__router_for__
-                methods = [trigger_method_name]
-                condition_type = "OR"
-                listeners[attr_name] = (condition_type, methods)
+                if hasattr(attr_value, "__is_router__") and attr_value.__is_router__:
+                    routers.add(attr_name)
+                    possible_returns = get_possible_return_constants(attr_value)
+                    if possible_returns:
+                        router_paths[attr_name] = possible_returns
 
         setattr(cls, "_start_methods", start_methods)
         setattr(cls, "_listeners", listeners)
@@ -163,7 +349,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
 
     _start_methods: List[str] = []
     _listeners: Dict[str, tuple[str, List[str]]] = {}
-    _routers: Dict[str, str] = {}
+    _routers: Set[str] = set()
     _router_paths: Dict[str, List[str]] = {}
     initial_state: Union[Type[T], T, None] = None
     event_emitter = Signal("event_emitter")
@@ -210,20 +396,10 @@ class Flow(Generic[T], metaclass=FlowMeta):
         return self._method_outputs
 
     def _initialize_state(self, inputs: Dict[str, Any]) -> None:
-        """
-        Initializes or updates the state with the provided inputs.
-
-        Args:
-            inputs: Dictionary of inputs to initialize or update the state.
-
-        Raises:
-            ValueError: If inputs do not match the structured state model.
-            TypeError: If state is neither a BaseModel instance nor a dictionary.
-        """
         if isinstance(self._state, BaseModel):
-            # Structured state management
+            # Structured state
             try:
-                # Define a function to create the dynamic class
+
                 def create_model_with_extra_forbid(
                     base_model: Type[BaseModel],
                 ) -> Type[BaseModel]:
@@ -233,34 +409,20 @@ class Flow(Generic[T], metaclass=FlowMeta):
 
                     return ModelWithExtraForbid
 
-                # Create the dynamic class
                 ModelWithExtraForbid = create_model_with_extra_forbid(
                     self._state.__class__
                 )
-
-                # Create a new instance using the combined state and inputs
                 self._state = cast(
                     T, ModelWithExtraForbid(**{**self._state.model_dump(), **inputs})
                 )
-
             except ValidationError as e:
                 raise ValueError(f"Invalid inputs for structured state: {e}") from e
         elif isinstance(self._state, dict):
-            # Unstructured state management
             self._state.update(inputs)
         else:
             raise TypeError("State must be a BaseModel instance or a dictionary.")
 
     def kickoff(self, inputs: Optional[Dict[str, Any]] = None) -> Any:
-        """
-        Starts the execution of the flow synchronously.
-
-        Args:
-            inputs: Optional dictionary of inputs to initialize or update the state.
-
-        Returns:
-            The final output from the flow execution.
-        """
         self.event_emitter.send(
             self,
             event=FlowStartedEvent(
@@ -274,15 +436,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
         return asyncio.run(self.kickoff_async())
 
     async def kickoff_async(self, inputs: Optional[Dict[str, Any]] = None) -> Any:
-        """
-        Starts the execution of the flow asynchronously.
-
-        Args:
-            inputs: Optional dictionary of inputs to initialize or update the state.
-
-        Returns:
-            The final output from the flow execution.
-        """
         if not self._start_methods:
             raise ValueError("No start method defined")
 
@@ -290,16 +443,12 @@ class Flow(Generic[T], metaclass=FlowMeta):
             self.__class__.__name__, list(self._methods.keys())
         )
 
-        # Create tasks for all start methods
         tasks = [
             self._execute_start_method(start_method)
             for start_method in self._start_methods
         ]
-
-        # Run all start methods concurrently
         await asyncio.gather(*tasks)
 
-        # Determine the final output (from the last executed method)
         final_output = self._method_outputs[-1] if self._method_outputs else None
 
         self.event_emitter.send(
@@ -310,10 +459,26 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 result=final_output,
             ),
         )
-
         return final_output
 
     async def _execute_start_method(self, start_method_name: str) -> None:
+        """
+        Executes a flow's start method and its triggered listeners.
+
+        This internal method handles the execution of methods marked with @start
+        decorator and manages the subsequent chain of listener executions.
+
+        Parameters
+        ----------
+        start_method_name : str
+            The name of the start method to execute.
+
+        Notes
+        -----
+        - Executes the start method and captures its result
+        - Triggers execution of any listeners waiting on this start method
+        - Part of the flow's initialization sequence
+        """
         result = await self._execute_method(
             start_method_name, self._methods[start_method_name]
         )
@@ -327,51 +492,146 @@ class Flow(Generic[T], metaclass=FlowMeta):
             if asyncio.iscoroutinefunction(method)
             else method(*args, **kwargs)
         )
-        self._method_outputs.append(result)  # Store the output
-
-        # Track method execution counts
+        self._method_outputs.append(result)
         self._method_execution_counts[method_name] = (
             self._method_execution_counts.get(method_name, 0) + 1
         )
-
         return result
 
     async def _execute_listeners(self, trigger_method: str, result: Any) -> None:
-        listener_tasks = []
+        """
+        Executes all listeners and routers triggered by a method completion.
 
-        if trigger_method in self._routers:
-            router_method = self._methods[self._routers[trigger_method]]
-            path = await self._execute_method(
-                self._routers[trigger_method], router_method
+        This internal method manages the execution flow by:
+        1. First executing all triggered routers sequentially
+        2. Then executing all triggered listeners in parallel
+
+        Parameters
+        ----------
+        trigger_method : str
+            The name of the method that triggered these listeners.
+        result : Any
+            The result from the triggering method, passed to listeners
+            that accept parameters.
+
+        Notes
+        -----
+        - Routers are executed sequentially to maintain flow control
+        - Each router's result becomes the new trigger_method
+        - Normal listeners are executed in parallel for efficiency
+        - Listeners can receive the trigger method's result as a parameter
+        """
+        # First, handle routers repeatedly until no router triggers anymore
+        while True:
+            routers_triggered = self._find_triggered_methods(
+                trigger_method, router_only=True
             )
-            trigger_method = path
+            if not routers_triggered:
+                break
+            for router_name in routers_triggered:
+                await self._execute_single_listener(router_name, result)
+                # After executing router, the router's result is the path
+                # The last router executed sets the trigger_method
+                # The router result is the last element in self._method_outputs
+                trigger_method = self._method_outputs[-1]
 
+        # Now that no more routers are triggered by current trigger_method,
+        # execute normal listeners
+        listeners_triggered = self._find_triggered_methods(
+            trigger_method, router_only=False
+        )
+        if listeners_triggered:
+            tasks = [
+                self._execute_single_listener(listener_name, result)
+                for listener_name in listeners_triggered
+            ]
+            await asyncio.gather(*tasks)
+
+    def _find_triggered_methods(
+        self, trigger_method: str, router_only: bool
+    ) -> List[str]:
+        """
+        Finds all methods that should be triggered based on conditions.
+
+        This internal method evaluates both OR and AND conditions to determine
+        which methods should be executed next in the flow.
+
+        Parameters
+        ----------
+        trigger_method : str
+            The name of the method that just completed execution.
+        router_only : bool
+            If True, only consider router methods.
+            If False, only consider non-router methods.
+
+        Returns
+        -------
+        List[str]
+            Names of methods that should be triggered.
+
+        Notes
+        -----
+        - Handles both OR and AND conditions:
+          * OR: Triggers if any condition is met
+          * AND: Triggers only when all conditions are met
+        - Maintains state for AND conditions using _pending_and_listeners
+        - Separates router and normal listener evaluation
+        """
+        triggered = []
         for listener_name, (condition_type, methods) in self._listeners.items():
+            is_router = listener_name in self._routers
+
+            if router_only != is_router:
+                continue
+
             if condition_type == "OR":
+                # If the trigger_method matches any in methods, run this
                 if trigger_method in methods:
-                    # Schedule the listener without preventing re-execution
-                    listener_tasks.append(
-                        self._execute_single_listener(listener_name, result)
-                    )
+                    triggered.append(listener_name)
             elif condition_type == "AND":
                 # Initialize pending methods for this listener if not already done
                 if listener_name not in self._pending_and_listeners:
                     self._pending_and_listeners[listener_name] = set(methods)
                 # Remove the trigger method from pending methods
-                self._pending_and_listeners[listener_name].discard(trigger_method)
+                if trigger_method in self._pending_and_listeners[listener_name]:
+                    self._pending_and_listeners[listener_name].discard(trigger_method)
+
                 if not self._pending_and_listeners[listener_name]:
                     # All required methods have been executed
-                    listener_tasks.append(
-                        self._execute_single_listener(listener_name, result)
-                    )
+                    triggered.append(listener_name)
                     # Reset pending methods for this listener
                     self._pending_and_listeners.pop(listener_name, None)
 
-        # Run all listener tasks concurrently and wait for them to complete
-        if listener_tasks:
-            await asyncio.gather(*listener_tasks)
+        return triggered
 
     async def _execute_single_listener(self, listener_name: str, result: Any) -> None:
+        """
+        Executes a single listener method with proper event handling.
+
+        This internal method manages the execution of an individual listener,
+        including parameter inspection, event emission, and error handling.
+
+        Parameters
+        ----------
+        listener_name : str
+            The name of the listener method to execute.
+        result : Any
+            The result from the triggering method, which may be passed
+            to the listener if it accepts parameters.
+
+        Notes
+        -----
+        - Inspects method signature to determine if it accepts the trigger result
+        - Emits events for method execution start and finish
+        - Handles errors gracefully with detailed logging
+        - Recursively triggers listeners of this listener
+        - Supports both parameterized and parameter-less listeners
+
+        Error Handling
+        -------------
+        Catches and logs any exceptions during execution, preventing
+        individual listener failures from breaking the entire flow.
+        """
         try:
             method = self._methods[listener_name]
 
@@ -386,17 +646,13 @@ class Flow(Generic[T], metaclass=FlowMeta):
 
             sig = inspect.signature(method)
             params = list(sig.parameters.values())
-
-            # Exclude 'self' parameter
             method_params = [p for p in params if p.name != "self"]
 
             if method_params:
-                # If listener expects parameters, pass the result
                 listener_result = await self._execute_method(
                     listener_name, method, result
                 )
             else:
-                # If listener does not expect parameters, call without arguments
                 listener_result = await self._execute_method(listener_name, method)
 
             self.event_emitter.send(
@@ -408,8 +664,9 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 ),
             )
 
-            # Execute listeners of this listener
+            # Execute listeners (and possibly routers) of this listener
             await self._execute_listeners(listener_name, listener_result)
+
         except Exception as e:
             print(
                 f"[Flow._execute_single_listener] Error in method {listener_name}: {e}"
@@ -422,5 +679,4 @@ class Flow(Generic[T], metaclass=FlowMeta):
         self._telemetry.flow_plotting_span(
             self.__class__.__name__, list(self._methods.keys())
         )
-
         plot_flow(self, filename)

src/crewai/flow/flow_visualizer.py

@@ -1,12 +1,14 @@
 # flow_visualizer.py
 
 import os
+from pathlib import Path
 
 from pyvis.network import Network
 
 from crewai.flow.config import COLORS, NODE_STYLES
 from crewai.flow.html_template_handler import HTMLTemplateHandler
 from crewai.flow.legend_generator import generate_legend_items_html, get_legend_items
+from crewai.flow.path_utils import safe_path_join, validate_path_exists
 from crewai.flow.utils import calculate_node_levels
 from crewai.flow.visualization_utils import (
     add_edges,
@@ -16,89 +18,209 @@ from crewai.flow.visualization_utils import (
 
 
 class FlowPlot:
+    """Handles the creation and rendering of flow visualization diagrams."""
+
     def __init__(self, flow):
+        """
+        Initialize FlowPlot with a flow object.
+
+        Parameters
+        ----------
+        flow : Flow
+            A Flow instance to visualize.
+
+        Raises
+        ------
+        ValueError
+            If flow object is invalid or missing required attributes.
+        """
+        if not hasattr(flow, '_methods'):
+            raise ValueError("Invalid flow object: missing '_methods' attribute")
+        if not hasattr(flow, '_listeners'):
+            raise ValueError("Invalid flow object: missing '_listeners' attribute")
+        if not hasattr(flow, '_start_methods'):
+            raise ValueError("Invalid flow object: missing '_start_methods' attribute")
+            
         self.flow = flow
         self.colors = COLORS
         self.node_styles = NODE_STYLES
 
     def plot(self, filename):
-        net = Network(
-            directed=True,
-            height="750px",
-            width="100%",
-            bgcolor=self.colors["bg"],
-            layout=None,
-        )
-
-        # Set options to disable physics
-        net.set_options(
-            """
-            var options = {
-                "nodes": {
-                    "font": {
-                        "multi": "html"
-                    }
-                },
-                "physics": {
-                    "enabled": false
-                }
-            }
         """
-        )
+        Generate and save an HTML visualization of the flow.
 
-        # Calculate levels for nodes
-        node_levels = calculate_node_levels(self.flow)
+        Parameters
+        ----------
+        filename : str
+            Name of the output file (without extension).
 
-        # Compute positions
-        node_positions = compute_positions(self.flow, node_levels)
+        Raises
+        ------
+        ValueError
+            If filename is invalid or network generation fails.
+        IOError
+            If file operations fail or visualization cannot be generated.
+        RuntimeError
+            If network visualization generation fails.
+        """
+        if not filename or not isinstance(filename, str):
+            raise ValueError("Filename must be a non-empty string")
+            
+        try:
+            # Initialize network
+            net = Network(
+                directed=True,
+                height="750px",
+                width="100%",
+                bgcolor=self.colors["bg"],
+                layout=None,
+            )
 
-        # Add nodes to the network
-        add_nodes_to_network(net, self.flow, node_positions, self.node_styles)
+            # Set options to disable physics
+            net.set_options(
+                """
+                var options = {
+                    "nodes": {
+                        "font": {
+                            "multi": "html"
+                        }
+                    },
+                    "physics": {
+                        "enabled": false
+                    }
+                }
+            """
+            )
 
-        # Add edges to the network
-        add_edges(net, self.flow, node_positions, self.colors)
+            # Calculate levels for nodes
+            try:
+                node_levels = calculate_node_levels(self.flow)
+            except Exception as e:
+                raise ValueError(f"Failed to calculate node levels: {str(e)}")
 
-        network_html = net.generate_html()
-        final_html_content = self._generate_final_html(network_html)
+            # Compute positions
+            try:
+                node_positions = compute_positions(self.flow, node_levels)
+            except Exception as e:
+                raise ValueError(f"Failed to compute node positions: {str(e)}")
 
-        # Save the final HTML content to the file
-        with open(f"{filename}.html", "w", encoding="utf-8") as f:
-            f.write(final_html_content)
-        print(f"Plot saved as {filename}.html")
+            # Add nodes to the network
+            try:
+                add_nodes_to_network(net, self.flow, node_positions, self.node_styles)
+            except Exception as e:
+                raise RuntimeError(f"Failed to add nodes to network: {str(e)}")
 
-        self._cleanup_pyvis_lib()
+            # Add edges to the network
+            try:
+                add_edges(net, self.flow, node_positions, self.colors)
+            except Exception as e:
+                raise RuntimeError(f"Failed to add edges to network: {str(e)}")
+
+            # Generate HTML
+            try:
+                network_html = net.generate_html()
+                final_html_content = self._generate_final_html(network_html)
+            except Exception as e:
+                raise RuntimeError(f"Failed to generate network visualization: {str(e)}")
+
+            # Save the final HTML content to the file
+            try:
+                with open(f"{filename}.html", "w", encoding="utf-8") as f:
+                    f.write(final_html_content)
+                print(f"Plot saved as {filename}.html")
+            except IOError as e:
+                raise IOError(f"Failed to save flow visualization to {filename}.html: {str(e)}")
+
+        except (ValueError, RuntimeError, IOError) as e:
+            raise e
+        except Exception as e:
+            raise RuntimeError(f"Unexpected error during flow visualization: {str(e)}")
+        finally:
+            self._cleanup_pyvis_lib()
 
     def _generate_final_html(self, network_html):
-        # Extract just the body content from the generated HTML
-        current_dir = os.path.dirname(__file__)
-        template_path = os.path.join(
-            current_dir, "assets", "crewai_flow_visual_template.html"
-        )
-        logo_path = os.path.join(current_dir, "assets", "crewai_logo.svg")
+        """
+        Generate the final HTML content with network visualization and legend.
 
-        html_handler = HTMLTemplateHandler(template_path, logo_path)
-        network_body = html_handler.extract_body_content(network_html)
+        Parameters
+        ----------
+        network_html : str
+            HTML content generated by pyvis Network.
 
-        # Generate the legend items HTML
-        legend_items = get_legend_items(self.colors)
-        legend_items_html = generate_legend_items_html(legend_items)
-        final_html_content = html_handler.generate_final_html(
-            network_body, legend_items_html
-        )
-        return final_html_content
+        Returns
+        -------
+        str
+            Complete HTML content with styling and legend.
+
+        Raises
+        ------
+        IOError
+            If template or logo files cannot be accessed.
+        ValueError
+            If network_html is invalid.
+        """
+        if not network_html:
+            raise ValueError("Invalid network HTML content")
+
+        try:
+            # Extract just the body content from the generated HTML
+            current_dir = os.path.dirname(__file__)
+            template_path = safe_path_join("assets", "crewai_flow_visual_template.html", root=current_dir)
+            logo_path = safe_path_join("assets", "crewai_logo.svg", root=current_dir)
+
+            if not os.path.exists(template_path):
+                raise IOError(f"Template file not found: {template_path}")
+            if not os.path.exists(logo_path):
+                raise IOError(f"Logo file not found: {logo_path}")
+
+            html_handler = HTMLTemplateHandler(template_path, logo_path)
+            network_body = html_handler.extract_body_content(network_html)
+
+            # Generate the legend items HTML
+            legend_items = get_legend_items(self.colors)
+            legend_items_html = generate_legend_items_html(legend_items)
+            final_html_content = html_handler.generate_final_html(
+                network_body, legend_items_html
+            )
+            return final_html_content
+        except Exception as e:
+            raise IOError(f"Failed to generate visualization HTML: {str(e)}")
 
     def _cleanup_pyvis_lib(self):
-        # Clean up the generated lib folder
-        lib_folder = os.path.join(os.getcwd(), "lib")
+        """
+        Clean up the generated lib folder from pyvis.
+
+        This method safely removes the temporary lib directory created by pyvis
+        during network visualization generation.
+        """
         try:
+            lib_folder = safe_path_join("lib", root=os.getcwd())
             if os.path.exists(lib_folder) and os.path.isdir(lib_folder):
                 import shutil
-
                 shutil.rmtree(lib_folder)
+        except ValueError as e:
+            print(f"Error validating lib folder path: {e}")
         except Exception as e:
-            print(f"Error cleaning up {lib_folder}: {e}")
+            print(f"Error cleaning up lib folder: {e}")
 
 
 def plot_flow(flow, filename="flow_plot"):
+    """
+    Convenience function to create and save a flow visualization.
+
+    Parameters
+    ----------
+    flow : Flow
+        Flow instance to visualize.
+    filename : str, optional
+        Output filename without extension, by default "flow_plot".
+
+    Raises
+    ------
+    ValueError
+        If flow object or filename is invalid.
+    IOError
+        If file operations fail.
+    """
     visualizer = FlowPlot(flow)
     visualizer.plot(filename)

src/crewai/flow/html_template_handler.py

@@ -1,26 +1,53 @@
 import base64
 import re
+from pathlib import Path
+
+from crewai.flow.path_utils import safe_path_join, validate_path_exists
 
 
 class HTMLTemplateHandler:
+    """Handles HTML template processing and generation for flow visualization diagrams."""
+
     def __init__(self, template_path, logo_path):
-        self.template_path = template_path
-        self.logo_path = logo_path
+        """
+        Initialize HTMLTemplateHandler with validated template and logo paths.
+
+        Parameters
+        ----------
+        template_path : str
+            Path to the HTML template file.
+        logo_path : str
+            Path to the logo image file.
+
+        Raises
+        ------
+        ValueError
+            If template or logo paths are invalid or files don't exist.
+        """
+        try:
+            self.template_path = validate_path_exists(template_path, "file")
+            self.logo_path = validate_path_exists(logo_path, "file")
+        except ValueError as e:
+            raise ValueError(f"Invalid template or logo path: {e}")
 
     def read_template(self):
+        """Read and return the HTML template file contents."""
         with open(self.template_path, "r", encoding="utf-8") as f:
             return f.read()
 
     def encode_logo(self):
+        """Convert the logo SVG file to base64 encoded string."""
         with open(self.logo_path, "rb") as logo_file:
             logo_svg_data = logo_file.read()
             return base64.b64encode(logo_svg_data).decode("utf-8")
 
     def extract_body_content(self, html):
+        """Extract and return content between body tags from HTML string."""
         match = re.search("<body.*?>(.*?)</body>", html, re.DOTALL)
         return match.group(1) if match else ""
 
     def generate_legend_items_html(self, legend_items):
+        """Generate HTML markup for the legend items."""
         legend_items_html = ""
         for item in legend_items:
             if "border" in item:
@@ -48,6 +75,7 @@ class HTMLTemplateHandler:
         return legend_items_html
 
     def generate_final_html(self, network_body, legend_items_html, title="Flow Plot"):
+        """Combine all components into final HTML document with network visualization."""
         html_template = self.read_template()
         logo_svg_base64 = self.encode_logo()
 

src/crewai/flow/legend_generator.py

@@ -1,3 +1,4 @@
+
 def get_legend_items(colors):
     return [
         {"label": "Start Method", "color": colors["start"]},

src/crewai/flow/path_utils.py

@@ -0,0 +1,135 @@
+"""
+Path utilities for secure file operations in CrewAI flow module.
+
+This module provides utilities for secure path handling to prevent directory
+traversal attacks and ensure paths remain within allowed boundaries.
+"""
+
+import os
+from pathlib import Path
+from typing import List, Union
+
+
+def safe_path_join(*parts: str, root: Union[str, Path, None] = None) -> str:
+    """
+    Safely join path components and ensure the result is within allowed boundaries.
+
+    Parameters
+    ----------
+    *parts : str
+        Variable number of path components to join.
+    root : Union[str, Path, None], optional
+        Root directory to use as base. If None, uses current working directory.
+
+    Returns
+    -------
+    str
+        String representation of the resolved path.
+
+    Raises
+    ------
+    ValueError
+        If the resulting path would be outside the root directory
+        or if any path component is invalid.
+    """
+    if not parts:
+        raise ValueError("No path components provided")
+
+    try:
+        # Convert all parts to strings and clean them
+        clean_parts = [str(part).strip() for part in parts if part]
+        if not clean_parts:
+            raise ValueError("No valid path components provided")
+
+        # Establish root directory
+        root_path = Path(root).resolve() if root else Path.cwd()
+        
+        # Join and resolve the full path
+        full_path = Path(root_path, *clean_parts).resolve()
+        
+        # Check if the resolved path is within root
+        if not str(full_path).startswith(str(root_path)):
+            raise ValueError(
+                f"Invalid path: Potential directory traversal. Path must be within {root_path}"
+            )
+            
+        return str(full_path)
+        
+    except Exception as e:
+        if isinstance(e, ValueError):
+            raise
+        raise ValueError(f"Invalid path components: {str(e)}")
+
+
+def validate_path_exists(path: Union[str, Path], file_type: str = "file") -> str:
+    """
+    Validate that a path exists and is of the expected type.
+
+    Parameters
+    ----------
+    path : Union[str, Path]
+        Path to validate.
+    file_type : str, optional
+        Expected type ('file' or 'directory'), by default 'file'.
+
+    Returns
+    -------
+    str
+        Validated path as string.
+
+    Raises
+    ------
+    ValueError
+        If path doesn't exist or is not of expected type.
+    """
+    try:
+        path_obj = Path(path).resolve()
+        
+        if not path_obj.exists():
+            raise ValueError(f"Path does not exist: {path}")
+            
+        if file_type == "file" and not path_obj.is_file():
+            raise ValueError(f"Path is not a file: {path}")
+        elif file_type == "directory" and not path_obj.is_dir():
+            raise ValueError(f"Path is not a directory: {path}")
+            
+        return str(path_obj)
+        
+    except Exception as e:
+        if isinstance(e, ValueError):
+            raise
+        raise ValueError(f"Invalid path: {str(e)}")
+
+
+def list_files(directory: Union[str, Path], pattern: str = "*") -> List[str]:
+    """
+    Safely list files in a directory matching a pattern.
+
+    Parameters
+    ----------
+    directory : Union[str, Path]
+        Directory to search in.
+    pattern : str, optional
+        Glob pattern to match files against, by default "*".
+
+    Returns
+    -------
+    List[str]
+        List of matching file paths.
+
+    Raises
+    ------
+    ValueError
+        If directory is invalid or inaccessible.
+    """
+    try:
+        dir_path = Path(directory).resolve()
+        if not dir_path.is_dir():
+            raise ValueError(f"Not a directory: {directory}")
+            
+        return [str(p) for p in dir_path.glob(pattern) if p.is_file()]
+        
+    except Exception as e:
+        if isinstance(e, ValueError):
+            raise
+        raise ValueError(f"Error listing files: {str(e)}")

src/crewai/flow/utils.py

@@ -1,9 +1,25 @@
+"""
+Utility functions for flow visualization and dependency analysis.
+
+This module provides core functionality for analyzing and manipulating flow structures,
+including node level calculation, ancestor tracking, and return value analysis.
+Functions in this module are primarily used by the visualization system to create
+accurate and informative flow diagrams.
+
+Example
+-------
+>>> flow = Flow()
+>>> node_levels = calculate_node_levels(flow)
+>>> ancestors = build_ancestor_dict(flow)
+"""
+
 import ast
 import inspect
 import textwrap
+from typing import Any, Dict, List, Optional, Set, Union
 
 
-def get_possible_return_constants(function):
+def get_possible_return_constants(function: Any) -> Optional[List[str]]:
     try:
         source = inspect.getsource(function)
     except OSError:
@@ -31,23 +47,80 @@ def get_possible_return_constants(function):
         print(f"Source code:\n{source}")
         return None
 
-    return_values = []
+    return_values = set()
+    dict_definitions = {}
+
+    class DictionaryAssignmentVisitor(ast.NodeVisitor):
+        def visit_Assign(self, node):
+            # Check if this assignment is assigning a dictionary literal to a variable
+            if isinstance(node.value, ast.Dict) and len(node.targets) == 1:
+                target = node.targets[0]
+                if isinstance(target, ast.Name):
+                    var_name = target.id
+                    dict_values = []
+                    # Extract string values from the dictionary
+                    for val in node.value.values:
+                        if isinstance(val, ast.Constant) and isinstance(val.value, str):
+                            dict_values.append(val.value)
+                        # If non-string, skip or just ignore
+                    if dict_values:
+                        dict_definitions[var_name] = dict_values
+            self.generic_visit(node)
 
     class ReturnVisitor(ast.NodeVisitor):
         def visit_Return(self, node):
-            # Check if the return value is a constant (Python 3.8+)
-            if isinstance(node.value, ast.Constant):
-                return_values.append(node.value.value)
+            # Direct string return
+            if isinstance(node.value, ast.Constant) and isinstance(
+                node.value.value, str
+            ):
+                return_values.add(node.value.value)
+            # Dictionary-based return, like return paths[result]
+            elif isinstance(node.value, ast.Subscript):
+                # Check if we're subscripting a known dictionary variable
+                if isinstance(node.value.value, ast.Name):
+                    var_name = node.value.value.id
+                    if var_name in dict_definitions:
+                        # Add all possible dictionary values
+                        for v in dict_definitions[var_name]:
+                            return_values.add(v)
+            self.generic_visit(node)
 
+    # First pass: identify dictionary assignments
+    DictionaryAssignmentVisitor().visit(code_ast)
+    # Second pass: identify returns
     ReturnVisitor().visit(code_ast)
-    return return_values
+
+    return list(return_values) if return_values else None
 
 
-def calculate_node_levels(flow):
-    levels = {}
-    queue = []
-    visited = set()
-    pending_and_listeners = {}
+def calculate_node_levels(flow: Any) -> Dict[str, int]:
+    """
+    Calculate the hierarchical level of each node in the flow.
+
+    Performs a breadth-first traversal of the flow graph to assign levels
+    to nodes, starting with start methods at level 0.
+
+    Parameters
+    ----------
+    flow : Any
+        The flow instance containing methods, listeners, and router configurations.
+
+    Returns
+    -------
+    Dict[str, int]
+        Dictionary mapping method names to their hierarchical levels.
+
+    Notes
+    -----
+    - Start methods are assigned level 0
+    - Each subsequent connected node is assigned level = parent_level + 1
+    - Handles both OR and AND conditions for listeners
+    - Processes router paths separately
+    """
+    levels: Dict[str, int] = {}
+    queue: List[str] = []
+    visited: Set[str] = set()
+    pending_and_listeners: Dict[str, Set[str]] = {}
 
     # Make all start methods at level 0
     for method_name, method in flow._methods.items():
@@ -61,10 +134,7 @@ def calculate_node_levels(flow):
         current_level = levels[current]
         visited.add(current)
 
-        for listener_name, (
-            condition_type,
-            trigger_methods,
-        ) in flow._listeners.items():
+        for listener_name, (condition_type, trigger_methods) in flow._listeners.items():
             if condition_type == "OR":
                 if current in trigger_methods:
                     if (
@@ -89,7 +159,7 @@ def calculate_node_levels(flow):
                             queue.append(listener_name)
 
         # Handle router connections
-        if current in flow._routers.values():
+        if current in flow._routers:
             router_method_name = current
             paths = flow._router_paths.get(router_method_name, [])
             for path in paths:
@@ -105,10 +175,24 @@ def calculate_node_levels(flow):
                             levels[listener_name] = current_level + 1
                             if listener_name not in visited:
                                 queue.append(listener_name)
+
     return levels
 
 
-def count_outgoing_edges(flow):
+def count_outgoing_edges(flow: Any) -> Dict[str, int]:
+    """
+    Count the number of outgoing edges for each method in the flow.
+
+    Parameters
+    ----------
+    flow : Any
+        The flow instance to analyze.
+
+    Returns
+    -------
+    Dict[str, int]
+        Dictionary mapping method names to their outgoing edge count.
+    """
     counts = {}
     for method_name in flow._methods:
         counts[method_name] = 0
@@ -120,16 +204,53 @@ def count_outgoing_edges(flow):
     return counts
 
 
-def build_ancestor_dict(flow):
-    ancestors = {node: set() for node in flow._methods}
-    visited = set()
+def build_ancestor_dict(flow: Any) -> Dict[str, Set[str]]:
+    """
+    Build a dictionary mapping each node to its ancestor nodes.
+
+    Parameters
+    ----------
+    flow : Any
+        The flow instance to analyze.
+
+    Returns
+    -------
+    Dict[str, Set[str]]
+        Dictionary mapping each node to a set of its ancestor nodes.
+    """
+    ancestors: Dict[str, Set[str]] = {node: set() for node in flow._methods}
+    visited: Set[str] = set()
     for node in flow._methods:
         if node not in visited:
             dfs_ancestors(node, ancestors, visited, flow)
     return ancestors
 
 
-def dfs_ancestors(node, ancestors, visited, flow):
+def dfs_ancestors(
+    node: str,
+    ancestors: Dict[str, Set[str]],
+    visited: Set[str],
+    flow: Any
+) -> None:
+    """
+    Perform depth-first search to build ancestor relationships.
+
+    Parameters
+    ----------
+    node : str
+        Current node being processed.
+    ancestors : Dict[str, Set[str]]
+        Dictionary tracking ancestor relationships.
+    visited : Set[str]
+        Set of already visited nodes.
+    flow : Any
+        The flow instance being analyzed.
+
+    Notes
+    -----
+    This function modifies the ancestors dictionary in-place to build
+    the complete ancestor graph.
+    """
     if node in visited:
         return
     visited.add(node)
@@ -142,7 +263,7 @@ def dfs_ancestors(node, ancestors, visited, flow):
             dfs_ancestors(listener_name, ancestors, visited, flow)
 
     # Handle router methods separately
-    if node in flow._routers.values():
+    if node in flow._routers:
         router_method_name = node
         paths = flow._router_paths.get(router_method_name, [])
         for path in paths:
@@ -153,12 +274,48 @@ def dfs_ancestors(node, ancestors, visited, flow):
                     dfs_ancestors(listener_name, ancestors, visited, flow)
 
 
-def is_ancestor(node, ancestor_candidate, ancestors):
+def is_ancestor(node: str, ancestor_candidate: str, ancestors: Dict[str, Set[str]]) -> bool:
+    """
+    Check if one node is an ancestor of another.
+
+    Parameters
+    ----------
+    node : str
+        The node to check ancestors for.
+    ancestor_candidate : str
+        The potential ancestor node.
+    ancestors : Dict[str, Set[str]]
+        Dictionary containing ancestor relationships.
+
+    Returns
+    -------
+    bool
+        True if ancestor_candidate is an ancestor of node, False otherwise.
+    """
     return ancestor_candidate in ancestors.get(node, set())
 
 
-def build_parent_children_dict(flow):
-    parent_children = {}
+def build_parent_children_dict(flow: Any) -> Dict[str, List[str]]:
+    """
+    Build a dictionary mapping parent nodes to their children.
+
+    Parameters
+    ----------
+    flow : Any
+        The flow instance to analyze.
+
+    Returns
+    -------
+    Dict[str, List[str]]
+        Dictionary mapping parent method names to lists of their child method names.
+
+    Notes
+    -----
+    - Maps listeners to their trigger methods
+    - Maps router methods to their paths and listeners
+    - Children lists are sorted for consistent ordering
+    """
+    parent_children: Dict[str, List[str]] = {}
 
     # Map listeners to their trigger methods
     for listener_name, (_, trigger_methods) in flow._listeners.items():
@@ -182,7 +339,24 @@ def build_parent_children_dict(flow):
     return parent_children
 
 
-def get_child_index(parent, child, parent_children):
+def get_child_index(parent: str, child: str, parent_children: Dict[str, List[str]]) -> int:
+    """
+    Get the index of a child node in its parent's sorted children list.
+
+    Parameters
+    ----------
+    parent : str
+        The parent node name.
+    child : str
+        The child node name to find the index for.
+    parent_children : Dict[str, List[str]]
+        Dictionary mapping parents to their children lists.
+
+    Returns
+    -------
+    int
+        Zero-based index of the child in its parent's sorted children list.
+    """
     children = parent_children.get(parent, [])
     children.sort()
     return children.index(child)

src/crewai/flow/visualization_utils.py

@@ -1,5 +1,23 @@
+"""
+Utilities for creating visual representations of flow structures.
+
+This module provides functions for generating network visualizations of flows,
+including node placement, edge creation, and visual styling. It handles the
+conversion of flow structures into visual network graphs with appropriate
+styling and layout.
+
+Example
+-------
+>>> flow = Flow()
+>>> net = Network(directed=True)
+>>> node_positions = compute_positions(flow, node_levels)
+>>> add_nodes_to_network(net, flow, node_positions, node_styles)
+>>> add_edges(net, flow, node_positions, colors)
+"""
+
 import ast
 import inspect
+from typing import Any, Dict, List, Optional, Tuple, Union
 
 from .utils import (
     build_ancestor_dict,
@@ -9,8 +27,25 @@ from .utils import (
 )
 
 
-def method_calls_crew(method):
-    """Check if the method calls `.crew()`."""
+def method_calls_crew(method: Any) -> bool:
+    """
+    Check if the method contains a call to `.crew()`.
+
+    Parameters
+    ----------
+    method : Any
+        The method to analyze for crew() calls.
+
+    Returns
+    -------
+    bool
+        True if the method calls .crew(), False otherwise.
+
+    Notes
+    -----
+    Uses AST analysis to detect method calls, specifically looking for
+    attribute access of 'crew'.
+    """
     try:
         source = inspect.getsource(method)
         source = inspect.cleandoc(source)
@@ -20,6 +55,7 @@ def method_calls_crew(method):
         return False
 
     class CrewCallVisitor(ast.NodeVisitor):
+        """AST visitor to detect .crew() method calls."""
         def __init__(self):
             self.found = False
 
@@ -34,7 +70,34 @@ def method_calls_crew(method):
     return visitor.found
 
 
-def add_nodes_to_network(net, flow, node_positions, node_styles):
+def add_nodes_to_network(
+    net: Any,
+    flow: Any,
+    node_positions: Dict[str, Tuple[float, float]],
+    node_styles: Dict[str, Dict[str, Any]]
+) -> None:
+    """
+    Add nodes to the network visualization with appropriate styling.
+
+    Parameters
+    ----------
+    net : Any
+        The pyvis Network instance to add nodes to.
+    flow : Any
+        The flow instance containing method information.
+    node_positions : Dict[str, Tuple[float, float]]
+        Dictionary mapping node names to their (x, y) positions.
+    node_styles : Dict[str, Dict[str, Any]]
+        Dictionary containing style configurations for different node types.
+
+    Notes
+    -----
+    Node types include:
+    - Start methods
+    - Router methods
+    - Crew methods
+    - Regular methods
+    """
     def human_friendly_label(method_name):
         return method_name.replace("_", " ").title()
 
@@ -73,9 +136,33 @@ def add_nodes_to_network(net, flow, node_positions, node_styles):
         )
 
 
-def compute_positions(flow, node_levels, y_spacing=150, x_spacing=150):
-    level_nodes = {}
-    node_positions = {}
+def compute_positions(
+    flow: Any,
+    node_levels: Dict[str, int],
+    y_spacing: float = 150,
+    x_spacing: float = 150
+) -> Dict[str, Tuple[float, float]]:
+    """
+    Compute the (x, y) positions for each node in the flow graph.
+
+    Parameters
+    ----------
+    flow : Any
+        The flow instance to compute positions for.
+    node_levels : Dict[str, int]
+        Dictionary mapping node names to their hierarchical levels.
+    y_spacing : float, optional
+        Vertical spacing between levels, by default 150.
+    x_spacing : float, optional
+        Horizontal spacing between nodes, by default 150.
+
+    Returns
+    -------
+    Dict[str, Tuple[float, float]]
+        Dictionary mapping node names to their (x, y) coordinates.
+    """
+    level_nodes: Dict[int, List[str]] = {}
+    node_positions: Dict[str, Tuple[float, float]] = {}
 
     for method_name, level in node_levels.items():
         level_nodes.setdefault(level, []).append(method_name)
@@ -90,16 +177,44 @@ def compute_positions(flow, node_levels, y_spacing=150, x_spacing=150):
     return node_positions
 
 
-def add_edges(net, flow, node_positions, colors):
+def add_edges(
+    net: Any,
+    flow: Any,
+    node_positions: Dict[str, Tuple[float, float]],
+    colors: Dict[str, str]
+) -> None:
+    edge_smooth: Dict[str, Union[str, float]] = {"type": "continuous"}  # Default value
+    """
+    Add edges to the network visualization with appropriate styling.
+
+    Parameters
+    ----------
+    net : Any
+        The pyvis Network instance to add edges to.
+    flow : Any
+        The flow instance containing edge information.
+    node_positions : Dict[str, Tuple[float, float]]
+        Dictionary mapping node names to their positions.
+    colors : Dict[str, str]
+        Dictionary mapping edge types to their colors.
+
+    Notes
+    -----
+    - Handles both normal listener edges and router edges
+    - Applies appropriate styling (color, dashes) based on edge type
+    - Adds curvature to edges when needed (cycles or multiple children)
+    """
     ancestors = build_ancestor_dict(flow)
     parent_children = build_parent_children_dict(flow)
 
+    # Edges for normal listeners
     for method_name in flow._listeners:
         condition_type, trigger_methods = flow._listeners[method_name]
         is_and_condition = condition_type == "AND"
 
         for trigger in trigger_methods:
-            if trigger in flow._methods or trigger in flow._routers.values():
+            # Check if nodes exist before adding edges
+            if trigger in node_positions and method_name in node_positions:
                 is_router_edge = any(
                     trigger in paths for paths in flow._router_paths.values()
                 )
@@ -124,7 +239,7 @@ def add_edges(net, flow, node_positions, colors):
                     else:
                         edge_smooth = {"type": "cubicBezier"}
                 else:
-                    edge_smooth = False
+                    edge_smooth.update({"type": "continuous"})
 
                 edge_style = {
                     "color": edge_color,
@@ -135,7 +250,22 @@ def add_edges(net, flow, node_positions, colors):
                 }
 
                 net.add_edge(trigger, method_name, **edge_style)
+            else:
+                # Nodes not found in node_positions. Check if it's a known router outcome and a known method.
+                is_router_edge = any(
+                    trigger in paths for paths in flow._router_paths.values()
+                )
+                # Check if method_name is a known method
+                method_known = method_name in flow._methods
 
+                # If it's a known router edge and the method is known, don't warn.
+                # This means the path is legitimate, just not reflected as nodes here.
+                if not (is_router_edge and method_known):
+                    print(
+                        f"Warning: No node found for '{trigger}' or '{method_name}'. Skipping edge."
+                    )
+
+    # Edges for router return paths
     for router_method_name, paths in flow._router_paths.items():
         for path in paths:
             for listener_name, (
@@ -143,36 +273,49 @@ def add_edges(net, flow, node_positions, colors):
                 trigger_methods,
             ) in flow._listeners.items():
                 if path in trigger_methods:
-                    is_cycle_edge = is_ancestor(trigger, method_name, ancestors)
-                    parent_has_multiple_children = (
-                        len(parent_children.get(router_method_name, [])) > 1
-                    )
-                    needs_curvature = is_cycle_edge or parent_has_multiple_children
+                    if (
+                        router_method_name in node_positions
+                        and listener_name in node_positions
+                    ):
+                        is_cycle_edge = is_ancestor(
+                            router_method_name, listener_name, ancestors
+                        )
+                        parent_has_multiple_children = (
+                            len(parent_children.get(router_method_name, [])) > 1
+                        )
+                        needs_curvature = is_cycle_edge or parent_has_multiple_children
 
-                    if needs_curvature:
-                        source_pos = node_positions.get(router_method_name)
-                        target_pos = node_positions.get(listener_name)
+                        if needs_curvature:
+                            source_pos = node_positions.get(router_method_name)
+                            target_pos = node_positions.get(listener_name)
 
-                        if source_pos and target_pos:
-                            dx = target_pos[0] - source_pos[0]
-                            smooth_type = "curvedCCW" if dx <= 0 else "curvedCW"
-                            index = get_child_index(
-                                router_method_name, listener_name, parent_children
-                            )
-                            edge_smooth = {
-                                "type": smooth_type,
-                                "roundness": 0.2 + (0.1 * index),
-                            }
+                            if source_pos and target_pos:
+                                dx = target_pos[0] - source_pos[0]
+                                smooth_type = "curvedCCW" if dx <= 0 else "curvedCW"
+                                index = get_child_index(
+                                    router_method_name, listener_name, parent_children
+                                )
+                                edge_smooth = {
+                                    "type": smooth_type,
+                                    "roundness": 0.2 + (0.1 * index),
+                                }
+                            else:
+                                edge_smooth = {"type": "cubicBezier"}
                         else:
-                            edge_smooth = {"type": "cubicBezier"}
-                    else:
-                        edge_smooth = False
+                            edge_smooth.update({"type": "continuous"})
 
-                    edge_style = {
-                        "color": colors["router_edge"],
-                        "width": 2,
-                        "arrows": "to",
-                        "dashes": True,
-                        "smooth": edge_smooth,
-                    }
-                    net.add_edge(router_method_name, listener_name, **edge_style)
+                        edge_style = {
+                            "color": colors["router_edge"],
+                            "width": 2,
+                            "arrows": "to",
+                            "dashes": True,
+                            "smooth": edge_smooth,
+                        }
+                        net.add_edge(router_method_name, listener_name, **edge_style)
+                    else:
+                        # Same check here: known router edge and known method?
+                        method_known = listener_name in flow._methods
+                        if not method_known:
+                            print(
+                                f"Warning: No node found for '{router_method_name}' or '{listener_name}'. Skipping edge."
+                            )

src/crewai/knowledge/knowledge.py

@@ -14,13 +14,13 @@ class Knowledge(BaseModel):
     Knowledge is a collection of sources and setup for the vector store to save and query relevant context.
     Args:
         sources: List[BaseKnowledgeSource] = Field(default_factory=list)
-        storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+        storage: Optional[KnowledgeStorage] = Field(default=None)
         embedder_config: Optional[Dict[str, Any]] = None
     """
 
     sources: List[BaseKnowledgeSource] = Field(default_factory=list)
     model_config = ConfigDict(arbitrary_types_allowed=True)
-    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    storage: Optional[KnowledgeStorage] = Field(default=None)
     embedder_config: Optional[Dict[str, Any]] = None
     collection_name: Optional[str] = None
 
@@ -49,8 +49,13 @@ class Knowledge(BaseModel):
         """
         Query across all knowledge sources to find the most relevant information.
         Returns the top_k most relevant chunks.
+        
+        Raises:
+            ValueError: If storage is not initialized.
         """
-
+        if self.storage is None:
+            raise ValueError("Storage is not initialized.")
+            
         results = self.storage.search(
             query,
             limit,

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -1,8 +1,8 @@
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Dict, List, Union
+from typing import Dict, List, Optional, Union
 
-from pydantic import Field
+from pydantic import Field, field_validator
 
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
@@ -14,17 +14,29 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
     """Base class for knowledge sources that load content from files."""
 
     _logger: Logger = Logger(verbose=True)
-    file_path: Union[Path, List[Path], str, List[str]] = Field(
-        ..., description="The path to the file"
+    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"
     )
     content: Dict[Path, str] = Field(init=False, default_factory=dict)
-    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    storage: Optional[KnowledgeStorage] = Field(default=None)
     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 model_post_init(self, _):
         """Post-initialization method to load content."""
         self.safe_file_paths = self._process_file_paths()
-        self.validate_paths()
+        self.validate_content()
         self.content = self.load_content()
 
     @abstractmethod
@@ -32,7 +44,7 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
         """Load and preprocess file content. Should be overridden by subclasses. Assume that the file path is relative to the project root in the knowledge directory."""
         pass
 
-    def validate_paths(self):
+    def validate_content(self):
         """Validate the paths."""
         for path in self.safe_file_paths:
             if not path.exists():
@@ -51,7 +63,10 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
 
     def _save_documents(self):
         """Save the documents to the storage."""
-        self.storage.save(self.chunks)
+        if self.storage:
+            self.storage.save(self.chunks)
+        else:
+            raise ValueError("No storage found to save documents.")
 
     def convert_to_path(self, path: Union[Path, str]) -> Path:
         """Convert a path to a Path object."""
@@ -59,13 +74,30 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
 
     def _process_file_paths(self) -> List[Path]:
         """Convert file_path to a list of Path objects."""
-        paths = (
-            [self.file_path]
-            if isinstance(self.file_path, (str, Path))
-            else self.file_path
+
+        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 isinstance(paths, list):
-            raise ValueError("file_path must be a Path, str, or a list of these types")
+        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 paths]
+        return [self.convert_to_path(path) for path in path_list]

src/crewai/knowledge/source/base_knowledge_source.py

@@ -16,12 +16,12 @@ class BaseKnowledgeSource(BaseModel, ABC):
     chunk_embeddings: List[np.ndarray] = Field(default_factory=list)
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
-    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    storage: Optional[KnowledgeStorage] = Field(default=None)
     metadata: Dict[str, Any] = Field(default_factory=dict)  # Currently unused
     collection_name: Optional[str] = Field(default=None)
 
     @abstractmethod
-    def load_content(self) -> Dict[Any, str]:
+    def validate_content(self) -> Any:
         """Load and preprocess content from the source."""
         pass
 
@@ -46,4 +46,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
         Save the documents to the storage.
         This method should be called after the chunks and embeddings are generated.
         """
-        self.storage.save(self.chunks)
+        if self.storage:
+            self.storage.save(self.chunks)
+        else:
+            raise ValueError("No storage found to save documents.")

src/crewai/knowledge/source/crew_docling_source.py

@@ -0,0 +1,120 @@
+from pathlib import Path
+from typing import Iterator, List, Optional, Union
+from urllib.parse import urlparse
+
+from docling.datamodel.base_models import InputFormat
+from docling.document_converter import DocumentConverter
+from docling.exceptions import ConversionError
+from docling_core.transforms.chunker.hierarchical_chunker import HierarchicalChunker
+from docling_core.types.doc.document import DoclingDocument
+from pydantic import Field
+
+from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
+from crewai.utilities.constants import KNOWLEDGE_DIRECTORY
+from crewai.utilities.logger import Logger
+
+
+class CrewDoclingSource(BaseKnowledgeSource):
+    """Default Source class for converting documents to markdown or json
+    This will auto support PDF, DOCX, and TXT, XLSX, Images, and HTML files without any additional dependencies and follows the docling package as the source of truth.
+    """
+
+    _logger: Logger = Logger(verbose=True)
+
+    file_path: Optional[List[Union[Path, str]]] = Field(default=None)
+    file_paths: List[Union[Path, str]] = Field(default_factory=list)
+    chunks: List[str] = Field(default_factory=list)
+    safe_file_paths: List[Union[Path, str]] = Field(default_factory=list)
+    content: List[DoclingDocument] = Field(default_factory=list)
+    document_converter: DocumentConverter = Field(
+        default_factory=lambda: DocumentConverter(
+            allowed_formats=[
+                InputFormat.MD,
+                InputFormat.ASCIIDOC,
+                InputFormat.PDF,
+                InputFormat.DOCX,
+                InputFormat.HTML,
+                InputFormat.IMAGE,
+                InputFormat.XLSX,
+                InputFormat.PPTX,
+            ]
+        )
+    )
+
+    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.validate_content()
+        self.content = self._load_content()
+
+    def _load_content(self) -> List[DoclingDocument]:
+        try:
+            return self._convert_source_to_docling_documents()
+        except ConversionError as e:
+            self._logger.log(
+                "error",
+                f"Error loading content: {e}. Supported formats: {self.document_converter.allowed_formats}",
+                "red",
+            )
+            raise e
+        except Exception as e:
+            self._logger.log("error", f"Error loading content: {e}")
+            raise e
+
+    def add(self) -> None:
+        if self.content is None:
+            return
+        for doc in self.content:
+            new_chunks_iterable = self._chunk_doc(doc)
+            self.chunks.extend(list(new_chunks_iterable))
+        self._save_documents()
+
+    def _convert_source_to_docling_documents(self) -> List[DoclingDocument]:
+        conv_results_iter = self.document_converter.convert_all(self.safe_file_paths)
+        return [result.document for result in conv_results_iter]
+
+    def _chunk_doc(self, doc: DoclingDocument) -> Iterator[str]:
+        chunker = HierarchicalChunker()
+        for chunk in chunker.chunk(doc):
+            yield chunk.text
+
+    def validate_content(self) -> List[Union[Path, str]]:
+        processed_paths: List[Union[Path, str]] = []
+        for path in self.file_paths:
+            if isinstance(path, str):
+                if path.startswith(("http://", "https://")):
+                    try:
+                        if self._validate_url(path):
+                            processed_paths.append(path)
+                        else:
+                            raise ValueError(f"Invalid URL format: {path}")
+                    except Exception as e:
+                        raise ValueError(f"Invalid URL: {path}. Error: {str(e)}")
+                else:
+                    local_path = Path(KNOWLEDGE_DIRECTORY + "/" + path)
+                    if local_path.exists():
+                        processed_paths.append(local_path)
+                    else:
+                        raise FileNotFoundError(f"File not found: {local_path}")
+            else:
+                # this is an instance of Path
+                processed_paths.append(path)
+        return processed_paths
+
+    def _validate_url(self, url: str) -> bool:
+        try:
+            result = urlparse(url)
+            return all(
+                [
+                    result.scheme in ("http", "https"),
+                    result.netloc,
+                    len(result.netloc.split(".")) >= 2,  # Ensure domain has TLD
+                ]
+            )
+        except Exception:
+            return False

src/crewai/knowledge/source/string_knowledge_source.py

@@ -13,9 +13,9 @@ class StringKnowledgeSource(BaseKnowledgeSource):
 
     def model_post_init(self, _):
         """Post-initialization method to validate content."""
-        self.load_content()
+        self.validate_content()
 
-    def load_content(self):
+    def validate_content(self):
         """Validate string content."""
         if not isinstance(self.content, str):
             raise ValueError("StringKnowledgeSource only accepts string content")

src/crewai/llm.py

@@ -6,8 +6,10 @@ import warnings
 from contextlib import contextmanager
 from typing import Any, Dict, List, Optional, Union
 
-import litellm
-from litellm import get_supported_openai_params
+with warnings.catch_warnings():
+    warnings.simplefilter("ignore", UserWarning)
+    import litellm
+    from litellm import get_supported_openai_params
 
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
@@ -44,6 +46,7 @@ LLM_CONTEXT_WINDOW_SIZES = {
     "o1-preview": 128000,
     "o1-mini": 128000,
     # gemini
+    "gemini-2.0-flash": 1048576,
     "gemini-1.5-pro": 2097152,
     "gemini-1.5-flash": 1048576,
     "gemini-1.5-flash-8b": 1048576,
@@ -63,6 +66,8 @@ LLM_CONTEXT_WINDOW_SIZES = {
     "llama3-70b-8192": 8192,
     "llama3-8b-8192": 8192,
     "mixtral-8x7b-32768": 32768,
+    "llama-3.3-70b-versatile": 128000,
+    "llama-3.3-70b-instruct": 128000,
 }
 
 DEFAULT_CONTEXT_WINDOW_SIZE = 8192
@@ -135,7 +140,7 @@ class LLM:
         self.kwargs = kwargs
 
         litellm.drop_params = True
-        litellm.set_verbose = False
+
         self.set_callbacks(callbacks)
         self.set_env_callbacks()
 

src/crewai/task.py

@@ -1,12 +1,25 @@
 import datetime
+import inspect
 import json
+import logging
 import threading
 import uuid
 from concurrent.futures import Future
 from copy import copy
 from hashlib import md5
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Set, Tuple, Type, Union
+from typing import (
+    Any,
+    Callable,
+    ClassVar,
+    Dict,
+    List,
+    Optional,
+    Set,
+    Tuple,
+    Type,
+    Union,
+)
 
 from opentelemetry.trace import Span
 from pydantic import (
@@ -20,6 +33,7 @@ from pydantic import (
 from pydantic_core import PydanticCustomError
 
 from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.tasks.guardrail_result import GuardrailResult
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry.telemetry import Telemetry
@@ -49,6 +63,7 @@ class Task(BaseModel):
     """
 
     __hash__ = object.__hash__  # type: ignore
+    logger: ClassVar[logging.Logger] = logging.getLogger(__name__)
     used_tools: int = 0
     tools_errors: int = 0
     delegations: int = 0
@@ -110,11 +125,61 @@ class Task(BaseModel):
         default=None,
     )
     processed_by_agents: Set[str] = Field(default_factory=set)
+    guardrail: Optional[Callable[[TaskOutput], Tuple[bool, Any]]] = Field(
+        default=None,
+        description="Function to validate task output before proceeding to next task"
+    )
+    max_retries: int = Field(
+        default=3,
+        description="Maximum number of retries when guardrail fails"
+    )
+    retry_count: int = Field(
+        default=0,
+        description="Current number of retries"
+    )
+
+    @field_validator("guardrail")
+    @classmethod
+    def validate_guardrail_function(cls, v: Optional[Callable]) -> Optional[Callable]:
+        """Validate that the guardrail function has the correct signature and behavior.
+        
+        While type hints provide static checking, this validator ensures runtime safety by:
+        1. Verifying the function accepts exactly one parameter (the TaskOutput)
+        2. Checking return type annotations match Tuple[bool, Any] if present
+        3. Providing clear, immediate error messages for debugging
+        
+        This runtime validation is crucial because:
+        - Type hints are optional and can be ignored at runtime
+        - Function signatures need immediate validation before task execution
+        - Clear error messages help users debug guardrail implementation issues
+        
+        Args:
+            v: The guardrail function to validate
+            
+        Returns:
+            The validated guardrail function
+            
+        Raises:
+            ValueError: If the function signature is invalid or return annotation
+                       doesn't match Tuple[bool, Any]
+        """
+        if v is not None:
+            sig = inspect.signature(v)
+            if len(sig.parameters) != 1:
+                raise ValueError("Guardrail function must accept exactly one parameter")
+
+            # Check return annotation if present, but don't require it
+            return_annotation = sig.return_annotation
+            if return_annotation != inspect.Signature.empty:
+                if not (return_annotation == Tuple[bool, Any] or str(return_annotation) == 'Tuple[bool, Any]'):
+                    raise ValueError("If return type is annotated, it must be Tuple[bool, Any]")
+        return v
 
     _telemetry: Telemetry = PrivateAttr(default_factory=Telemetry)
     _execution_span: Optional[Span] = PrivateAttr(default=None)
     _original_description: Optional[str] = PrivateAttr(default=None)
     _original_expected_output: Optional[str] = PrivateAttr(default=None)
+    _original_output_file: Optional[str] = PrivateAttr(default=None)
     _thread: Optional[threading.Thread] = PrivateAttr(default=None)
     _execution_time: Optional[float] = PrivateAttr(default=None)
 
@@ -149,8 +214,46 @@ class Task(BaseModel):
 
     @field_validator("output_file")
     @classmethod
-    def output_file_validation(cls, value: str) -> str:
-        """Validate the output file path by removing the / from the beginning of the path."""
+    def output_file_validation(cls, value: Optional[str]) -> Optional[str]:
+        """Validate the output file path.
+        
+        Args:
+            value: The output file path to validate. Can be None or a string.
+                  If the path contains template variables (e.g. {var}), leading slashes are preserved.
+                  For regular paths, leading slashes are stripped.
+        
+        Returns:
+            The validated and potentially modified path, or None if no path was provided.
+            
+        Raises:
+            ValueError: If the path contains invalid characters, path traversal attempts,
+                      or other security concerns.
+        """
+        if value is None:
+            return None
+
+        # Basic security checks
+        if ".." in value:
+            raise ValueError("Path traversal attempts are not allowed in output_file paths")
+        
+        # Check for shell expansion first
+        if value.startswith('~') or value.startswith('$'):
+            raise ValueError("Shell expansion characters are not allowed in output_file paths")
+            
+        # Then check other shell special characters
+        if any(char in value for char in ['|', '>', '<', '&', ';']):
+            raise ValueError("Shell special characters are not allowed in output_file paths")
+
+        # Don't strip leading slash if it's a template path with variables
+        if "{" in value or "}" in value: 
+            # Validate template variable format
+            template_vars = [part.split("}")[0] for part in value.split("{")[1:]]
+            for var in template_vars:
+                if not var.isidentifier():
+                    raise ValueError(f"Invalid template variable name: {var}")
+            return value
+
+        # Strip leading slash for regular paths
         if value.startswith("/"):
             return value[1:]
         return value
@@ -254,7 +357,6 @@ class Task(BaseModel):
         )
 
         pydantic_output, json_output = self._export_output(result)
-
         task_output = TaskOutput(
             name=self.name,
             description=self.description,
@@ -265,6 +367,37 @@ class Task(BaseModel):
             agent=agent.role,
             output_format=self._get_output_format(),
         )
+
+        if self.guardrail:
+            guardrail_result = GuardrailResult.from_tuple(self.guardrail(task_output))
+            if not guardrail_result.success:
+                if self.retry_count >= self.max_retries:
+                    raise Exception(
+                        f"Task failed guardrail validation after {self.max_retries} retries. "
+                        f"Last error: {guardrail_result.error}"
+                    )
+
+                self.retry_count += 1
+                context = (
+                    f"### Previous attempt failed validation: {guardrail_result.error}\n\n\n"
+                    f"### Previous result:\n{task_output.raw}\n\n\n"
+                    "Try again, making sure to address the validation error."
+                )
+                return self._execute_core(agent, context, tools)
+
+            if guardrail_result.result is None:
+                raise Exception(
+                    "Task guardrail returned None as result. This is not allowed."
+                )
+
+            if isinstance(guardrail_result.result, str):
+                task_output.raw = guardrail_result.result
+                pydantic_output, json_output = self._export_output(guardrail_result.result)
+                task_output.pydantic = pydantic_output
+                task_output.json_dict = json_output
+            elif isinstance(guardrail_result.result, TaskOutput):
+                task_output = guardrail_result.result
+
         self.output = task_output
 
         self._set_end_execution_time(start_time)
@@ -299,16 +432,89 @@ class Task(BaseModel):
         tasks_slices = [self.description, output]
         return "\n".join(tasks_slices)
 
-    def interpolate_inputs(self, inputs: Dict[str, Any]) -> None:
-        """Interpolate inputs into the task description and expected output."""
+    def interpolate_inputs(self, inputs: Dict[str, Union[str, int, float]]) -> None:
+        """Interpolate inputs into the task description, expected output, and output file path.
+        
+        Args:
+            inputs: Dictionary mapping template variables to their values.
+                   Supported value types are strings, integers, and floats.
+        
+        Raises:
+            ValueError: If a required template variable is missing from inputs.
+        """
         if self._original_description is None:
             self._original_description = self.description
         if self._original_expected_output is None:
             self._original_expected_output = self.expected_output
+        if self.output_file is not None and self._original_output_file is None:
+            self._original_output_file = self.output_file
 
-        if inputs:
+        if not inputs:
+            return
+
+        try:
             self.description = self._original_description.format(**inputs)
-            self.expected_output = self._original_expected_output.format(**inputs)
+        except KeyError as e:
+            raise ValueError(f"Missing required template variable '{e.args[0]}' in description") from e
+        except ValueError as e:
+            raise ValueError(f"Error interpolating description: {str(e)}") from e
+
+        try:
+            self.expected_output = self.interpolate_only(
+                input_string=self._original_expected_output, inputs=inputs
+            )
+        except (KeyError, ValueError) as e:
+            raise ValueError(f"Error interpolating expected_output: {str(e)}") from e
+
+        if self.output_file is not None:
+            try:
+                self.output_file = self.interpolate_only(
+                    input_string=self._original_output_file, inputs=inputs
+                )
+            except (KeyError, ValueError) as e:
+                raise ValueError(f"Error interpolating output_file path: {str(e)}") from e
+
+    def interpolate_only(self, input_string: Optional[str], inputs: Dict[str, Union[str, int, float]]) -> str:
+        """Interpolate placeholders (e.g., {key}) in a string while leaving JSON untouched.
+        
+        Args:
+            input_string: The string containing template variables to interpolate.
+                         Can be None or empty, in which case an empty string is returned.
+            inputs: Dictionary mapping template variables to their values.
+                   Supported value types are strings, integers, and floats.
+                   If input_string is empty or has no placeholders, inputs can be empty.
+        
+        Returns:
+            The interpolated string with all template variables replaced with their values.
+            Empty string if input_string is None or empty.
+            
+        Raises:
+            ValueError: If a required template variable is missing from inputs.
+            KeyError: If a template variable is not found in the inputs dictionary.
+        """
+        if input_string is None or not input_string:
+            return ""
+        if "{" not in input_string and "}" not in input_string:
+            return input_string
+        if not inputs:
+            raise ValueError("Inputs dictionary cannot be empty when interpolating variables")
+
+        try:
+            # Validate input types
+            for key, value in inputs.items():
+                if not isinstance(value, (str, int, float)):
+                    raise ValueError(f"Value for key '{key}' must be a string, integer, or float, got {type(value).__name__}")
+
+            escaped_string = input_string.replace("{", "{{").replace("}", "}}")
+
+            for key in inputs.keys():
+                escaped_string = escaped_string.replace(f"{{{{{key}}}}}", f"{{{key}}}")
+
+            return escaped_string.format(**inputs)
+        except KeyError as e:
+            raise KeyError(f"Template variable '{e.args[0]}' not found in inputs dictionary") from e
+        except ValueError as e:
+            raise ValueError(f"Error during string interpolation: {str(e)}") from e
 
     def increment_tools_errors(self) -> None:
         """Increment the tools errors counter."""
@@ -390,22 +596,33 @@ class Task(BaseModel):
         return OutputFormat.RAW
 
     def _save_file(self, result: Any) -> None:
+        """Save task output to a file.
+        
+        Args:
+            result: The result to save to the file. Can be a dict or any stringifiable object.
+            
+        Raises:
+            ValueError: If output_file is not set
+            RuntimeError: If there is an error writing to the file
+        """
         if self.output_file is None:
             raise ValueError("output_file is not set.")
 
-        resolved_path = Path(self.output_file).expanduser().resolve()
-        directory = resolved_path.parent
+        try:
+            resolved_path = Path(self.output_file).expanduser().resolve()
+            directory = resolved_path.parent
 
-        if not directory.exists():
-            directory.mkdir(parents=True, exist_ok=True)
+            if not directory.exists():
+                directory.mkdir(parents=True, exist_ok=True)
 
-        with resolved_path.open("w", encoding="utf-8") as file:
-            if isinstance(result, dict):
-                import json
-
-                json.dump(result, file, ensure_ascii=False, indent=2)
-            else:
-                file.write(str(result))
+            with resolved_path.open("w", encoding="utf-8") as file:
+                if isinstance(result, dict):
+                    import json
+                    json.dump(result, file, ensure_ascii=False, indent=2)
+                else:
+                    file.write(str(result))
+        except (OSError, IOError) as e:
+            raise RuntimeError(f"Failed to save output file: {e}")
         return None
 
     def __repr__(self):

src/crewai/tasks/guardrail_result.py

@@ -0,0 +1,56 @@
+"""
+Module for handling task guardrail validation results.
+
+This module provides the GuardrailResult class which standardizes
+the way task guardrails return their validation results.
+"""
+
+from typing import Any, Optional, Tuple, Union
+
+from pydantic import BaseModel, field_validator
+
+
+class GuardrailResult(BaseModel):
+    """Result from a task guardrail execution.
+
+    This class standardizes the return format of task guardrails,
+    converting tuple responses into a structured format that can
+    be easily handled by the task execution system.
+
+    Attributes:
+        success (bool): Whether the guardrail validation passed
+        result (Any, optional): The validated/transformed result if successful
+        error (str, optional): Error message if validation failed
+    """
+    success: bool
+    result: Optional[Any] = None
+    error: Optional[str] = None
+
+    @field_validator("result", "error")
+    @classmethod
+    def validate_result_error_exclusivity(cls, v: Any, info) -> Any:
+        values = info.data
+        if "success" in values:
+            if values["success"] and v and "error" in values and values["error"]:
+                raise ValueError("Cannot have both result and error when success is True")
+            if not values["success"] and v and "result" in values and values["result"]:
+                raise ValueError("Cannot have both result and error when success is False")
+        return v
+
+    @classmethod
+    def from_tuple(cls, result: Tuple[bool, Union[Any, str]]) -> "GuardrailResult":
+        """Create a GuardrailResult from a validation tuple.
+
+        Args:
+            result: A tuple of (success, data) where data is either
+                   the validated result or error message.
+
+        Returns:
+            GuardrailResult: A new instance with the tuple data.
+        """
+        success, data = result
+        return cls(
+            success=success,
+            result=data if success else None,
+            error=data if not success else None
+        )

src/crewai/tools/agent_tools/add_image_tool.py

@@ -0,0 +1,45 @@
+from typing import Dict, Optional, Union
+
+from pydantic import BaseModel, Field
+
+from crewai.tools.base_tool import BaseTool
+from crewai.utilities import I18N
+
+i18n = I18N()
+
+class AddImageToolSchema(BaseModel):
+    image_url: str = Field(..., description="The URL or path of the image to add")
+    action: Optional[str] = Field(
+        default=None,
+        description="Optional context or question about the image"
+    )
+
+
+class AddImageTool(BaseTool):
+    """Tool for adding images to the content"""
+
+    name: str = Field(default_factory=lambda: i18n.tools("add_image")["name"])  # type: ignore
+    description: str = Field(default_factory=lambda: i18n.tools("add_image")["description"])  # type: ignore
+    args_schema: type[BaseModel] = AddImageToolSchema
+
+    def _run(
+        self,
+        image_url: str,
+        action: Optional[str] = None,
+        **kwargs,
+    ) -> dict:
+        action = action or i18n.tools("add_image")["default_action"]  # type: ignore
+        content = [
+            {"type": "text", "text": action},
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": image_url,
+                },
+            }
+        ]
+
+        return {
+            "role": "user",
+            "content": content
+        }

src/crewai/tools/agent_tools/agent_tools.py

@@ -20,13 +20,13 @@ class AgentTools:
         delegate_tool = DelegateWorkTool(
             agents=self.agents,
             i18n=self.i18n,
-            description=self.i18n.tools("delegate_work").format(coworkers=coworkers),
+            description=self.i18n.tools("delegate_work").format(coworkers=coworkers),  # type: ignore
         )
 
         ask_tool = AskQuestionTool(
             agents=self.agents,
             i18n=self.i18n,
-            description=self.i18n.tools("ask_question").format(coworkers=coworkers),
+            description=self.i18n.tools("ask_question").format(coworkers=coworkers),  # type: ignore
         )
 
         return [delegate_tool, ask_tool]

src/crewai/tools/agent_tools/base_agent_tools.py

@@ -1,3 +1,4 @@
+import logging
 from typing import Optional, Union
 
 from pydantic import Field
@@ -7,6 +8,8 @@ from crewai.task import Task
 from crewai.tools.base_tool import BaseTool
 from crewai.utilities import I18N
 
+logger = logging.getLogger(__name__)
+
 
 class BaseAgentTool(BaseTool):
     """Base class for agent-related tools"""
@@ -16,6 +19,25 @@ class BaseAgentTool(BaseTool):
         default_factory=I18N, description="Internationalization settings"
     )
 
+    def sanitize_agent_name(self, name: str) -> str:
+        """
+        Sanitize agent role name by normalizing whitespace and setting to lowercase.
+        Converts all whitespace (including newlines) to single spaces and removes quotes.
+
+        Args:
+            name (str): The agent role name to sanitize
+
+        Returns:
+            str: The sanitized agent role name, with whitespace normalized,
+                 converted to lowercase, and quotes removed
+        """
+        if not name:
+            return ""
+        # Normalize all whitespace (including newlines) to single spaces
+        normalized = " ".join(name.split())
+        # Remove quotes and convert to lowercase
+        return normalized.replace('"', "").casefold()
+
     def _get_coworker(self, coworker: Optional[str], **kwargs) -> Optional[str]:
         coworker = coworker or kwargs.get("co_worker") or kwargs.get("coworker")
         if coworker:
@@ -25,11 +47,27 @@ class BaseAgentTool(BaseTool):
         return coworker
 
     def _execute(
-        self, agent_name: Union[str, None], task: str, context: Union[str, None]
+        self,
+        agent_name: Optional[str],
+        task: str,
+        context: Optional[str] = None
     ) -> str:
+        """
+        Execute delegation to an agent with case-insensitive and whitespace-tolerant matching.
+        
+        Args:
+            agent_name: Name/role of the agent to delegate to (case-insensitive)
+            task: The specific question or task to delegate
+            context: Optional additional context for the task execution
+            
+        Returns:
+            str: The execution result from the delegated agent or an error message
+                 if the agent cannot be found
+        """
         try:
             if agent_name is None:
                 agent_name = ""
+                logger.debug("No agent name provided, using empty string")
 
             # It is important to remove the quotes from the agent name.
             # The reason we have to do this is because less-powerful LLM's
@@ -38,31 +76,49 @@ class BaseAgentTool(BaseTool):
             # {"task": "....", "coworker": "....
             # when it should look like this:
             # {"task": "....", "coworker": "...."}
-            agent_name = agent_name.casefold().replace('"', "").replace("\n", "")
+            sanitized_name = self.sanitize_agent_name(agent_name)
+            logger.debug(f"Sanitized agent name from '{agent_name}' to '{sanitized_name}'")
+
+            available_agents = [agent.role for agent in self.agents]
+            logger.debug(f"Available agents: {available_agents}")
+
             agent = [  # type: ignore # Incompatible types in assignment (expression has type "list[BaseAgent]", variable has type "str | None")
                 available_agent
                 for available_agent in self.agents
-                if available_agent.role.casefold().replace("\n", "") == agent_name
+                if self.sanitize_agent_name(available_agent.role) == sanitized_name
             ]
-        except Exception as _:
+            logger.debug(f"Found {len(agent)} matching agents for role '{sanitized_name}'")
+        except (AttributeError, ValueError) as e:
+            # Handle specific exceptions that might occur during role name processing
             return self.i18n.errors("agent_tool_unexisting_coworker").format(
                 coworkers="\n".join(
-                    [f"- {agent.role.casefold()}" for agent in self.agents]
-                )
+                    [f"- {self.sanitize_agent_name(agent.role)}" for agent in self.agents]
+                ),
+                error=str(e)
             )
 
         if not agent:
+            # No matching agent found after sanitization
             return self.i18n.errors("agent_tool_unexisting_coworker").format(
                 coworkers="\n".join(
-                    [f"- {agent.role.casefold()}" for agent in self.agents]
-                )
+                    [f"- {self.sanitize_agent_name(agent.role)}" for agent in self.agents]
+                ),
+                error=f"No agent found with role '{sanitized_name}'"
             )
 
         agent = agent[0]
-        task_with_assigned_agent = Task(  # type: ignore # Incompatible types in assignment (expression has type "Task", variable has type "str")
-            description=task,
-            agent=agent,
-            expected_output=agent.i18n.slice("manager_request"),
-            i18n=agent.i18n,
-        )
-        return agent.execute_task(task_with_assigned_agent, context)
+        try:
+            task_with_assigned_agent = Task(
+                description=task,
+                agent=agent,
+                expected_output=agent.i18n.slice("manager_request"),
+                i18n=agent.i18n,
+            )
+            logger.debug(f"Created task for agent '{self.sanitize_agent_name(agent.role)}': {task}")
+            return agent.execute_task(task_with_assigned_agent, context)
+        except Exception as e:
+            # Handle task creation or execution errors
+            return self.i18n.errors("agent_tool_execution_error").format(
+                agent_role=self.sanitize_agent_name(agent.role),
+                error=str(e)
+            )

src/crewai/tools/tool_usage.py

@@ -10,6 +10,7 @@ from crewai.agents.tools_handler import ToolsHandler
 from crewai.task import Task
 from crewai.telemetry import Telemetry
 from crewai.tools import BaseTool
+from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.tools.tool_calling import InstructorToolCalling, ToolCalling
 from crewai.tools.tool_usage_events import ToolUsageError, ToolUsageFinished
 from crewai.utilities import I18N, Converter, ConverterError, Printer
@@ -18,8 +19,7 @@ try:
     import agentops  # type: ignore
 except ImportError:
     agentops = None
-
-OPENAI_BIGGER_MODELS = ["gpt-4", "gpt-4o", "o1-preview", "o1-mini"]
+OPENAI_BIGGER_MODELS = ["gpt-4", "gpt-4o", "o1-preview", "o1-mini", "o1", "o3", "o3-mini"]
 
 
 class ToolUsageErrorException(Exception):
@@ -103,6 +103,19 @@ class ToolUsage:
             if self.agent.verbose:
                 self._printer.print(content=f"\n\n{error}\n", color="red")
             return error
+
+        if isinstance(tool, CrewStructuredTool) and tool.name == self._i18n.tools("add_image")["name"]:  # type: ignore
+            try:
+                result = self._use(tool_string=tool_string, tool=tool, calling=calling)
+                return result
+
+            except Exception as e:
+                error = getattr(e, "message", str(e))
+                self.task.increment_tools_errors()
+                if self.agent.verbose:
+                    self._printer.print(content=f"\n\n{error}\n", color="red")
+                return error
+
         return f"{self._use(tool_string=tool_string, tool=tool, calling=calling)}"  # type: ignore # BUG?: "_use" of "ToolUsage" does not return a value (it only ever returns None)
 
     def _use(

src/crewai/translations/en.json

@@ -12,7 +12,7 @@
     "tools": "\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\n{tools}\n\nUse the following format:\n\nThought: you should always think about what to do\nAction: the action to take, only one name of [{tool_names}], just the name, exactly as it's written.\nAction Input: the input to the action, just a simple python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce all necessary information is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n",
     "no_tools": "\nTo give my best complete final answer to the task use the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!",
     "format": "I MUST either use a tool (use one at time) OR give my best final answer not both at the same time. To Use the following format:\n\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action, dictionary enclosed in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action Input/Result can repeat N times)\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described\n\n",
-    "final_answer_format": "If you don't need to use any more tools, you must give your best complete final answer, make sure it satisfy the expect criteria, use the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer: my best complete final answer to the task.\n\n",
+    "final_answer_format": "If you don't need to use any more tools, you must give your best complete final answer, make sure it satisfies the expected criteria, use the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer: my best complete final answer to the task.\n\n",
     "format_without_tools": "\nSorry, I didn't use the right format. I MUST either use a tool (among the available ones), OR give my best final answer.\nI just remembered the expected format I must follow:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Result can repeat N times)\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described\n\n",
     "task_with_context": "{task}\n\nThis is the context you're working with:\n{context}",
     "expected_output": "\nThis is the expect criteria for your final answer: {expected_output}\nyou MUST return the actual complete content as the final answer, not a summary.",
@@ -33,10 +33,16 @@
     "tool_usage_error": "I encountered an error: {error}",
     "tool_arguments_error": "Error: the Action Input is not a valid key, value dictionary.",
     "wrong_tool_name": "You tried to use the tool {tool}, but it doesn't exist. You must use one of the following tools, use one at time: {tools}.",
-    "tool_usage_exception": "I encountered an error while trying to use the tool. This was the error: {error}.\n Tool {tool} accepts these inputs: {tool_inputs}"
+    "tool_usage_exception": "I encountered an error while trying to use the tool. This was the error: {error}.\n Tool {tool} accepts these inputs: {tool_inputs}",
+    "agent_tool_execution_error": "Error executing task with agent '{agent_role}'. Error: {error}"
   },
   "tools": {
     "delegate_work": "Delegate a specific task to one of the following coworkers: {coworkers}\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolute everything you know, don't reference things but instead explain them.",
-    "ask_question": "Ask a specific question to one of the following coworkers: {coworkers}\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolute everything you know, don't reference things but instead explain them."
+    "ask_question": "Ask a specific question to one of the following coworkers: {coworkers}\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolute everything you know, don't reference things but instead explain them.",
+    "add_image": {
+      "name": "Add image to content",
+      "description": "See image to understand it's content, you can optionally ask a question about the image",
+      "default_action": "Please provide a detailed description of this image, including all visual elements, context, and any notable details you can observe."
+    }
   }
 }

src/crewai/utilities/i18n.py

@@ -1,6 +1,6 @@
 import json
 import os
-from typing import Dict, Optional
+from typing import Dict, Optional, Union
 
 from pydantic import BaseModel, Field, PrivateAttr, model_validator
 
@@ -41,8 +41,8 @@ class I18N(BaseModel):
     def errors(self, error: str) -> str:
         return self.retrieve("errors", error)
 
-    def tools(self, error: str) -> str:
-        return self.retrieve("tools", error)
+    def tools(self, tool: str) -> Union[str, Dict[str, str]]:
+        return self.retrieve("tools", tool)
 
     def retrieve(self, kind, key) -> str:
         try:

src/crewai/utilities/internal_instructor.py

@@ -1,3 +1,4 @@
+import warnings
 from typing import Any, Optional, Type
 
 
@@ -25,9 +26,10 @@ class InternalInstructor:
         if self.agent and not self.llm:
             self.llm = self.agent.function_calling_llm or self.agent.llm
 
-        # Lazy import
-        import instructor
-        from litellm import completion
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", UserWarning)
+            import instructor
+            from litellm import completion
 
         self._client = instructor.from_litellm(
             completion,

src/crewai/utilities/planning_handler.py

@@ -1,3 +1,5 @@
+import json
+import logging
 from typing import Any, List, Optional
 
 from pydantic import BaseModel, Field
@@ -5,6 +7,8 @@ from pydantic import BaseModel, Field
 from crewai.agent import Agent
 from crewai.task import Task
 
+logger = logging.getLogger(__name__)
+
 
 class PlanPerTask(BaseModel):
     task: str = Field(..., description="The task for which the plan is created")
@@ -68,19 +72,39 @@ class CrewPlanner:
             output_pydantic=PlannerTaskPydanticOutput,
         )
 
+    def _get_agent_knowledge(self, task: Task) -> List[str]:
+        """
+        Safely retrieve knowledge source content from the task's agent.
+        
+        Args:
+            task: The task containing an agent with potential knowledge sources
+            
+        Returns:
+            List[str]: A list of knowledge source strings
+        """
+        try:
+            if task.agent and task.agent.knowledge_sources:
+                return [source.content for source in task.agent.knowledge_sources]
+        except AttributeError:
+            logger.warning("Error accessing agent knowledge sources")
+        return []
+
     def _create_tasks_summary(self) -> str:
         """Creates a summary of all tasks."""
         tasks_summary = []
         for idx, task in enumerate(self.tasks):
-            tasks_summary.append(
-                f"""
+            knowledge_list = self._get_agent_knowledge(task)
+            task_summary = f"""
                 Task Number {idx + 1} - {task.description}
                 "task_description": {task.description}
                 "task_expected_output": {task.expected_output}
                 "agent": {task.agent.role if task.agent else "None"}
                 "agent_goal": {task.agent.goal if task.agent else "None"}
                 "task_tools": {task.tools}
-                "agent_tools": {task.agent.tools if task.agent else "None"}
-                """
-            )
+                "agent_tools": %s%s""" % (
+                    f"[{', '.join(str(tool) for tool in task.agent.tools)}]" if task.agent and task.agent.tools else '"agent has no tools"',
+                    f',\n                "agent_knowledge": "[\\"{knowledge_list[0]}\\"]"' if knowledge_list and str(knowledge_list) != "None" else ""
+                )
+            
+            tasks_summary.append(task_summary)
         return " ".join(tasks_summary)

src/crewai/utilities/token_counter_callback.py

@@ -1,3 +1,5 @@
+import warnings
+
 from litellm.integrations.custom_logger import CustomLogger
 from litellm.types.utils import Usage
 
@@ -12,11 +14,13 @@ class TokenCalcHandler(CustomLogger):
         if self.token_cost_process is None:
             return
 
-        usage: Usage = response_obj["usage"]
-        self.token_cost_process.sum_successful_requests(1)
-        self.token_cost_process.sum_prompt_tokens(usage.prompt_tokens)
-        self.token_cost_process.sum_completion_tokens(usage.completion_tokens)
-        if usage.prompt_tokens_details:
-            self.token_cost_process.sum_cached_prompt_tokens(
-                usage.prompt_tokens_details.cached_tokens
-            )
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", UserWarning)
+            usage: Usage = response_obj["usage"]
+            self.token_cost_process.sum_successful_requests(1)
+            self.token_cost_process.sum_prompt_tokens(usage.prompt_tokens)
+            self.token_cost_process.sum_completion_tokens(usage.completion_tokens)
+            if usage.prompt_tokens_details:
+                self.token_cost_process.sum_cached_prompt_tokens(
+                    usage.prompt_tokens_details.cached_tokens
+                )

tests/agent_test.py

@@ -1445,44 +1445,43 @@ def test_llm_call_with_all_attributes():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_agent_with_ollama_gemma():
+def test_agent_with_ollama_llama3():
     agent = Agent(
         role="test role",
         goal="test goal",
         backstory="test backstory",
-        llm=LLM(
-            model="ollama/gemma2:latest",
-            base_url="http://localhost:8080",
-        ),
+        llm=LLM(model="ollama/llama3.2:3b", base_url="http://localhost:11434"),
     )
 
     assert isinstance(agent.llm, LLM)
-    assert agent.llm.model == "ollama/gemma2:latest"
-    assert agent.llm.base_url == "http://localhost:8080"
+    assert agent.llm.model == "ollama/llama3.2:3b"
+    assert agent.llm.base_url == "http://localhost:11434"
 
-    task = "Respond in 20 words. Who are you?"
+    task = "Respond in 20 words. Which model are you?"
     response = agent.llm.call([{"role": "user", "content": task}])
 
     assert response
     assert len(response.split()) <= 25  # Allow a little flexibility in word count
-    assert "Gemma" in response or "AI" in response or "language model" in response
+    assert "Llama3" in response or "AI" in response or "language model" in response
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_llm_call_with_ollama_gemma():
+def test_llm_call_with_ollama_llama3():
     llm = LLM(
-        model="ollama/gemma2:latest",
-        base_url="http://localhost:8080",
+        model="ollama/llama3.2:3b",
+        base_url="http://localhost:11434",
         temperature=0.7,
         max_tokens=30,
     )
-    messages = [{"role": "user", "content": "Respond in 20 words. Who are you?"}]
+    messages = [
+        {"role": "user", "content": "Respond in 20 words. Which model are you?"}
+    ]
 
     response = llm.call(messages)
 
     assert response
     assert len(response.split()) <= 25  # Allow a little flexibility in word count
-    assert "Gemma" in response or "AI" in response or "language model" in response
+    assert "Llama3" in response or "AI" in response or "language model" in response
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -1578,7 +1577,7 @@ def test_agent_execute_task_with_ollama():
         role="test role",
         goal="test goal",
         backstory="test backstory",
-        llm=LLM(model="ollama/gemma2:latest", base_url="http://localhost:8080"),
+        llm=LLM(model="ollama/llama3.2:3b", base_url="http://localhost:11434"),
     )
 
     task = Task(

tests/cassettes/test_agent_execute_task_with_ollama.yaml

@@ -1,42 +1,6 @@
 interactions:
 - request:
-    body: !!binary |
-      CrcCCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSjgIKEgoQY3Jld2FpLnRl
-      bGVtZXRyeRJoChA/Q8UW5bidCRtKvri5fOaNEgh5qLzvLvZJkioQVG9vbCBVc2FnZSBFcnJvcjAB
-      OYjFVQr1TPgXQXCXhwr1TPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMHoCGAGFAQABAAAS
-      jQEKEChQTWQ07t26ELkZmP5RresSCHEivRGBpsP7KgpUb29sIFVzYWdlMAE5sKkbC/VM+BdB8MIc
-      C/VM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShkKCXRvb2xfbmFtZRIMCgpkdW1teV90
-      b29sSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAA=
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '314'
-      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:
-      - Tue, 24 Sep 2024 21:57:54 GMT
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gemma2:latest", "prompt": "### System:\nYou are test role. test
+    body: '{"model": "llama3.2:3b", "prompt": "### System:\nYou are test role. test
       backstory\nYour personal goal is: test goal\nTo give my best complete final
       answer to the task use the exact following format:\n\nThought: I now can give
       a great answer\nFinal Answer: Your final answer must be the great and the most
@@ -46,7 +10,7 @@ interactions:
       explanation of AI\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:\n\n",
-      "options": {}, "stream": false}'
+      "options": {"stop": ["\nObservation:"]}, "stream": false}'
     headers:
       Accept:
       - '*/*'
@@ -55,26 +19,26 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '815'
+      - '839'
       Content-Type:
       - application/json
       User-Agent:
-      - python-requests/2.31.0
+      - python-requests/2.32.3
     method: POST
-    uri: http://localhost:8080/api/generate
+    uri: http://localhost:11434/api/generate
   response:
     body:
-      string: '{"model":"gemma2:latest","created_at":"2024-09-24T21:57:55.835715Z","response":"Thought:
-        I can explain AI in one sentence. \n\nFinal Answer: Artificial intelligence
-        (AI) is the ability of computer systems to perform tasks that typically require
-        human intelligence, such as learning, problem-solving, and decision-making.  \n","done":true,"done_reason":"stop","context":[106,1645,108,6176,1479,235292,108,2045,708,2121,4731,235265,2121,135147,108,6922,3749,6789,603,235292,2121,6789,108,1469,2734,970,1963,3407,2048,3448,577,573,6911,1281,573,5463,2412,5920,235292,109,65366,235292,590,1490,798,2734,476,1775,3448,108,11263,10358,235292,3883,2048,3448,2004,614,573,1775,578,573,1546,3407,685,3077,235269,665,2004,614,17526,6547,235265,109,235285,44472,1281,1450,32808,235269,970,3356,12014,611,665,235341,109,6176,4926,235292,109,6846,12297,235292,36576,1212,16481,603,575,974,13060,109,1596,603,573,5246,12830,604,861,2048,3448,235292,586,974,235290,47366,15844,576,16481,108,4747,44472,2203,573,5579,3407,3381,685,573,2048,3448,235269,780,476,13367,235265,109,12694,235341,1417,603,50471,2845,577,692,235269,1281,573,8112,2506,578,2734,861,1963,14124,10358,235269,861,3356,12014,611,665,235341,109,65366,235292,109,107,108,106,2516,108,65366,235292,590,798,10200,16481,575,974,13060,235265,235248,109,11263,10358,235292,42456,17273,591,11716,235275,603,573,7374,576,6875,5188,577,3114,13333,674,15976,2817,3515,17273,235269,1582,685,6044,235269,3210,235290,60495,235269,578,4530,235290,14577,235265,139,108],"total_duration":3370959792,"load_duration":20611750,"prompt_eval_count":173,"prompt_eval_duration":688036000,"eval_count":51,"eval_duration":2660291000}'
+      string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:05:52.24992Z","response":"Final
+        Answer: Artificial Intelligence (AI) refers to the development of computer
+        systems capable of performing tasks that typically require human intelligence,
+        such as learning, problem-solving, decision-making, and perception.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,744,512,2675,527,1296,3560,13,1296,93371,198,7927,4443,5915,374,25,1296,5915,198,1271,3041,856,1888,4686,1620,4320,311,279,3465,1005,279,4839,2768,3645,1473,85269,25,358,1457,649,3041,264,2294,4320,198,19918,22559,25,4718,1620,4320,2011,387,279,2294,323,279,1455,4686,439,3284,11,433,2011,387,15632,7633,382,40,28832,1005,1521,20447,11,856,2683,14117,389,433,2268,14711,2724,1473,5520,5546,25,83017,1148,15592,374,304,832,11914,271,2028,374,279,1755,13186,369,701,1620,4320,25,362,832,1355,18886,16540,315,15592,198,9514,28832,471,279,5150,4686,2262,439,279,1620,4320,11,539,264,12399,382,11382,0,1115,374,48174,3062,311,499,11,1005,279,7526,2561,323,3041,701,1888,13321,22559,11,701,2683,14117,389,433,2268,85269,1473,128009,128006,78191,128007,271,19918,22559,25,59294,22107,320,15836,8,19813,311,279,4500,315,6500,6067,13171,315,16785,9256,430,11383,1397,3823,11478,11,1778,439,6975,11,3575,99246,11,5597,28846,11,323,21063,13],"total_duration":1461909875,"load_duration":39886208,"prompt_eval_count":181,"prompt_eval_duration":701000000,"eval_count":39,"eval_duration":719000000}'
     headers:
       Content-Length:
-      - '1662'
+      - '1537'
       Content-Type:
       - application/json; charset=utf-8
       Date:
-      - Tue, 24 Sep 2024 21:57:55 GMT
+      - Thu, 02 Jan 2025 20:05:52 GMT
     status:
       code: 200
       message: OK

tests/cassettes/test_agent_function_calling_llm.yaml

@@ -26237,7 +26237,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}], "model": "gpt-4o"}'
     headers:
@@ -26590,7 +26590,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -26941,7 +26941,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -27292,7 +27292,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -27647,7 +27647,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -28005,7 +28005,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -28364,7 +28364,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -28718,7 +28718,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -29082,7 +29082,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -29441,7 +29441,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -29802,7 +29802,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -30170,7 +30170,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -30533,7 +30533,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -30907,7 +30907,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -31273,7 +31273,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -31644,7 +31644,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -32015,7 +32015,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the

tests/cassettes/test_agent_powered_by_new_o_model_family_that_allows_skipping_tool.yaml

@@ -247,7 +247,7 @@ interactions:
       {"role": "user", "content": "I did it wrong. Invalid Format: I missed the ''Action:''
       after ''Thought:''. I will do right next, and don''t use a tool I have already
       used.\n\nIf you don''t need to use any more tools, you must give your best complete
-      final answer, make sure it satisfy the expect criteria, use the EXACT format
+      final answer, make sure it satisfies the expected criteria, use the EXACT format
       below:\n\nThought: I now can give a great answer\nFinal Answer: my best complete
       final answer to the task.\n\n"}], "model": "o1-preview"}'
     headers:

tests/cassettes/test_agent_with_ollama_gemma.yaml

@@ -1,397 +0,0 @@
-interactions:
-- request:
-    body: !!binary |
-      CumTAQokCiIKDHNlcnZpY2UubmFtZRISChBjcmV3QUktdGVsZW1ldHJ5Er+TAQoSChBjcmV3YWku
-      dGVsZW1ldHJ5EqoHChDvqD2QZooz9BkEwtbWjp4OEgjxh72KACHvZSoMQ3JldyBDcmVhdGVkMAE5
-      qMhNnvBM+BdBcO9PnvBM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShoKDnB5dGhvbl92
-      ZXJzaW9uEggKBjMuMTEuN0ouCghjcmV3X2tleRIiCiBkNTUxMTNiZTRhYTQxYmE2NDNkMzI2MDQy
-      YjJmMDNmMUoxCgdjcmV3X2lkEiYKJGY4YTA1OTA1LTk0OGEtNDQ0YS04NmJmLTJiNTNiNDkyYjgy
-      MkocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jl
-      d19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFKxwIKC2Ny
-      ZXdfYWdlbnRzErcCCrQCW3sia2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1ODJi
-      IiwgImlkIjogIjg1MGJjNWUwLTk4NTctNDhkOC1iNWZlLTJmZjk2OWExYTU3YiIsICJyb2xlIjog
-      InRlc3Qgcm9sZSIsICJ2ZXJib3NlPyI6IHRydWUsICJtYXhfaXRlciI6IDQsICJtYXhfcnBtIjog
-      MTAsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00byIsICJkZWxlZ2F0
-      aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1h
-      eF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1KkAIKCmNyZXdfdGFza3MSgQIK
-      /gFbeyJrZXkiOiAiNGEzMWI4NTEzM2EzYTI5NGM2ODUzZGE3NTdkNGJhZTciLCAiaWQiOiAiOTc1
-      ZDgwMjItMWJkMS00NjBlLTg2NmEtYjJmZGNiYjA4ZDliIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBm
-      YWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJ0ZXN0IHJvbGUiLCAi
-      YWdlbnRfa2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1ODJiIiwgInRvb2xzX25h
-      bWVzIjogWyJnZXRfZmluYWxfYW5zd2VyIl19XXoCGAGFAQABAAASjgIKEP9UYSAOFQbZquSppN1j
-      IeUSCAgZmXUoJKFmKgxUYXNrIENyZWF0ZWQwATloPV+e8Ez4F0GYsl+e8Ez4F0ouCghjcmV3X2tl
-      eRIiCiBkNTUxMTNiZTRhYTQxYmE2NDNkMzI2MDQyYjJmMDNmMUoxCgdjcmV3X2lkEiYKJGY4YTA1
-      OTA1LTk0OGEtNDQ0YS04NmJmLTJiNTNiNDkyYjgyMkouCgh0YXNrX2tleRIiCiA0YTMxYjg1MTMz
-      YTNhMjk0YzY4NTNkYTc1N2Q0YmFlN0oxCgd0YXNrX2lkEiYKJDk3NWQ4MDIyLTFiZDEtNDYwZS04
-      NjZhLWIyZmRjYmIwOGQ5YnoCGAGFAQABAAASkwEKEEfiywgqgiUXE3KoUbrnHDQSCGmv+iM7Wc1Z
-      KgpUb29sIFVzYWdlMAE5kOybnvBM+BdBIM+cnvBM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42
-      MS4wSh8KCXRvb2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGF
-      AQABAAASkwEKEH7AHXpfmvwIkA45HB8YyY0SCAFRC+uJpsEZKgpUb29sIFVzYWdlMAE56PLdnvBM
-      +BdBYFbfnvBM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wSh8KCXRvb2xfbmFtZRISChBn
-      ZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASkwEKEIDKKEbYU4lcJF+a
-      WsAVZwESCI+/La7oL86MKgpUb29sIFVzYWdlMAE5yIkgn/BM+BdBWGwhn/BM+BdKGgoOY3Jld2Fp
-      X3ZlcnNpb24SCAoGMC42MS4wSh8KCXRvb2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0
-      dGVtcHRzEgIYAXoCGAGFAQABAAASnAEKEMTZ2IhpLz6J2hJhHBQ8/M4SCEuWz+vjzYifKhNUb29s
-      IFJlcGVhdGVkIFVzYWdlMAE5mAVhn/BM+BdBKOhhn/BM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoG
-      MC42MS4wSh8KCXRvb2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoC
-      GAGFAQABAAASkAIKED8C+t95p855kLcXs5Nnt/sSCM4XAhL6u8O8Kg5UYXNrIEV4ZWN1dGlvbjAB
-      OdD8X57wTPgXQUgno5/wTPgXSi4KCGNyZXdfa2V5EiIKIGQ1NTExM2JlNGFhNDFiYTY0M2QzMjYw
-      NDJiMmYwM2YxSjEKB2NyZXdfaWQSJgokZjhhMDU5MDUtOTQ4YS00NDRhLTg2YmYtMmI1M2I0OTJi
-      ODIySi4KCHRhc2tfa2V5EiIKIDRhMzFiODUxMzNhM2EyOTRjNjg1M2RhNzU3ZDRiYWU3SjEKB3Rh
-      c2tfaWQSJgokOTc1ZDgwMjItMWJkMS00NjBlLTg2NmEtYjJmZGNiYjA4ZDliegIYAYUBAAEAABLO
-      CwoQFlnZCfbZ3Dj0L9TAE5LrLBIIoFr7BZErFNgqDENyZXcgQ3JlYXRlZDABOVhDDaDwTPgXQSg/
-      D6DwTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMEoaCg5weXRob25fdmVyc2lvbhIICgYz
-      LjExLjdKLgoIY3Jld19rZXkSIgogOTRjMzBkNmMzYjJhYzhmYjk0YjJkY2ZjNTcyZDBmNTlKMQoH
-      Y3Jld19pZBImCiQyMzM2MzRjNi1lNmQ2LTQ5ZTYtODhhZS1lYWUxYTM5YjBlMGZKHAoMY3Jld19w
-      cm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29m
-      X3Rhc2tzEgIYAkobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSv4ECgtjcmV3X2FnZW50cxLu
-      BArrBFt7ImtleSI6ICJlMTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJpZCI6ICI0
-      MjAzZjIyYi0wNWM3LTRiNjUtODBjMS1kM2Y0YmFlNzZhNDYiLCAicm9sZSI6ICJ0ZXN0IHJvbGUi
-      LCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAyLCAibWF4X3JwbSI6IDEwLCAiZnVuY3Rp
-      b25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVk
-      PyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGlt
-      aXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX0sIHsia2V5IjogImU3ZThlZWE4ODZiY2I4ZjEwNDVh
-      YmVlY2YxNDI1ZGI3IiwgImlkIjogImZjOTZjOTQ1LTY4ZDUtNDIxMy05NmNkLTNmYTAwNmUyZTYz
-      MCIsICJyb2xlIjogInRlc3Qgcm9sZTIiLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAx
-      LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdw
-      dC00byIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlv
-      bj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/QMK
-      CmNyZXdfdGFza3MS7gMK6wNbeyJrZXkiOiAiMzIyZGRhZTNiYzgwYzFkNDViODVmYTc3NTZkYjg2
-      NjUiLCAiaWQiOiAiOTVjYTg4NDItNmExMi00MGQ5LWIwZDItNGI0MzYxYmJlNTZkIiwgImFzeW5j
-      X2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6
-      ICJ0ZXN0IHJvbGUiLCAiYWdlbnRfa2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1
-      ODJiIiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICI1ZTljYTdkNjRiNDIwNWJiN2M0N2Uw
-      YjNmY2I1ZDIxZiIsICJpZCI6ICI5NzI5MTg2Yy1kN2JlLTRkYjQtYTk0ZS02OWU5OTk2NTI3MDAi
-      LCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2Vu
-      dF9yb2xlIjogInRlc3Qgcm9sZTIiLCAiYWdlbnRfa2V5IjogImU3ZThlZWE4ODZiY2I4ZjEwNDVh
-      YmVlY2YxNDI1ZGI3IiwgInRvb2xzX25hbWVzIjogWyJnZXRfZmluYWxfYW5zd2VyIl19XXoCGAGF
-      AQABAAASjgIKEC/YM2OukRrSg+ZAev4VhGESCOQ5RvzSS5IEKgxUYXNrIENyZWF0ZWQwATmQJx6g
-      8Ez4F0EgjR6g8Ez4F0ouCghjcmV3X2tleRIiCiA5NGMzMGQ2YzNiMmFjOGZiOTRiMmRjZmM1NzJk
-      MGY1OUoxCgdjcmV3X2lkEiYKJDIzMzYzNGM2LWU2ZDYtNDllNi04OGFlLWVhZTFhMzliMGUwZkou
-      Cgh0YXNrX2tleRIiCiAzMjJkZGFlM2JjODBjMWQ0NWI4NWZhNzc1NmRiODY2NUoxCgd0YXNrX2lk
-      EiYKJDk1Y2E4ODQyLTZhMTItNDBkOS1iMGQyLTRiNDM2MWJiZTU2ZHoCGAGFAQABAAASkAIKEHqZ
-      L8s3clXQyVTemNcTCcQSCA0tzK95agRQKg5UYXNrIEV4ZWN1dGlvbjABOQC8HqDwTPgXQdgNSqDw
-      TPgXSi4KCGNyZXdfa2V5EiIKIDk0YzMwZDZjM2IyYWM4ZmI5NGIyZGNmYzU3MmQwZjU5SjEKB2Ny
-      ZXdfaWQSJgokMjMzNjM0YzYtZTZkNi00OWU2LTg4YWUtZWFlMWEzOWIwZTBmSi4KCHRhc2tfa2V5
-      EiIKIDMyMmRkYWUzYmM4MGMxZDQ1Yjg1ZmE3NzU2ZGI4NjY1SjEKB3Rhc2tfaWQSJgokOTVjYTg4
-      NDItNmExMi00MGQ5LWIwZDItNGI0MzYxYmJlNTZkegIYAYUBAAEAABKOAgoQjhKzodMUmQ8NWtdy
-      Uj99whIIBsGtAymZibwqDFRhc2sgQ3JlYXRlZDABOXjVVaDwTPgXQXhSVqDwTPgXSi4KCGNyZXdf
-      a2V5EiIKIDk0YzMwZDZjM2IyYWM4ZmI5NGIyZGNmYzU3MmQwZjU5SjEKB2NyZXdfaWQSJgokMjMz
-      NjM0YzYtZTZkNi00OWU2LTg4YWUtZWFlMWEzOWIwZTBmSi4KCHRhc2tfa2V5EiIKIDVlOWNhN2Q2
-      NGI0MjA1YmI3YzQ3ZTBiM2ZjYjVkMjFmSjEKB3Rhc2tfaWQSJgokOTcyOTE4NmMtZDdiZS00ZGI0
-      LWE5NGUtNjllOTk5NjUyNzAwegIYAYUBAAEAABKTAQoQx5IUsjAFMGNUaz5MHy20OBIIzl2tr25P
-      LL8qClRvb2wgVXNhZ2UwATkgt5Sg8Ez4F0GwFpag8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYw
-      LjYxLjBKHwoJdG9vbF9uYW1lEhIKEGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1wdHMSAhgBegIY
-      AYUBAAEAABKQAgoQEkfcfCrzTYIM6GQXhknlexIIa/oxeT78OL8qDlRhc2sgRXhlY3V0aW9uMAE5
-      WIFWoPBM+BdBuL/GoPBM+BdKLgoIY3Jld19rZXkSIgogOTRjMzBkNmMzYjJhYzhmYjk0YjJkY2Zj
-      NTcyZDBmNTlKMQoHY3Jld19pZBImCiQyMzM2MzRjNi1lNmQ2LTQ5ZTYtODhhZS1lYWUxYTM5YjBl
-      MGZKLgoIdGFza19rZXkSIgogNWU5Y2E3ZDY0YjQyMDViYjdjNDdlMGIzZmNiNWQyMWZKMQoHdGFz
-      a19pZBImCiQ5NzI5MTg2Yy1kN2JlLTRkYjQtYTk0ZS02OWU5OTk2NTI3MDB6AhgBhQEAAQAAEqwH
-      ChDrKBdEe+Z5276g9fgg6VzjEgiJfnDwsv1SrCoMQ3JldyBDcmVhdGVkMAE5MLQYofBM+BdBQFIa
-      ofBM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMu
-      MTEuN0ouCghjcmV3X2tleRIiCiA3M2FhYzI4NWU2NzQ2NjY3Zjc1MTQ3NjcwMDAzNDExMEoxCgdj
-      cmV3X2lkEiYKJDg0NDY0YjhlLTRiZjctNDRiYy05MmUxLWE4ZDE1NGZlNWZkN0ocCgxjcmV3X3By
-      b2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2Zf
-      dGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFKyQIKC2NyZXdfYWdlbnRzErkC
-      CrYCW3sia2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1ODJiIiwgImlkIjogIjk4
-      YmIwNGYxLTBhZGMtNGZiNC04YzM2LWM3M2Q1MzQ1ZGRhZCIsICJyb2xlIjogInRlc3Qgcm9sZSIs
-      ICJ2ZXJib3NlPyI6IHRydWUsICJtYXhfaXRlciI6IDEsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0
-      aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvIiwgImRlbGVnYXRpb25fZW5hYmxl
-      ZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xp
-      bWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUqQAgoKY3Jld190YXNrcxKBAgr+AVt7ImtleSI6
-      ICJmN2E5ZjdiYjFhZWU0YjZlZjJjNTI2ZDBhOGMyZjJhYyIsICJpZCI6ICIxZjRhYzJhYS03YmQ4
-      LTQ1NWQtODgyMC1jMzZmMjJjMDY4MzciLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVt
-      YW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogInRlc3Qgcm9sZSIsICJhZ2VudF9rZXki
-      OiAiZTE0OGU1MzIwMjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAidG9vbHNfbmFtZXMiOiBbImdl
-      dF9maW5hbF9hbnN3ZXIiXX1degIYAYUBAAEAABKOAgoQ0/vrakH7zD0uSvmVBUV8lxIIYe4YKcYG
-      hNgqDFRhc2sgQ3JlYXRlZDABOdBXKqHwTPgXQcCtKqHwTPgXSi4KCGNyZXdfa2V5EiIKIDczYWFj
-      Mjg1ZTY3NDY2NjdmNzUxNDc2NzAwMDM0MTEwSjEKB2NyZXdfaWQSJgokODQ0NjRiOGUtNGJmNy00
-      NGJjLTkyZTEtYThkMTU0ZmU1ZmQ3Si4KCHRhc2tfa2V5EiIKIGY3YTlmN2JiMWFlZTRiNmVmMmM1
-      MjZkMGE4YzJmMmFjSjEKB3Rhc2tfaWQSJgokMWY0YWMyYWEtN2JkOC00NTVkLTg4MjAtYzM2ZjIy
-      YzA2ODM3egIYAYUBAAEAABKkAQoQ5GDzHNlSdlcVDdxsI3abfRIIhYu8fZS3iA4qClRvb2wgVXNh
-      Z2UwATnIi2eh8Ez4F0FYbmih8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBKHwoJdG9v
-      bF9uYW1lEhIKEGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1wdHMSAhgBSg8KA2xsbRIICgZncHQt
-      NG96AhgBhQEAAQAAEpACChAy85Jfr/EEIe1THU8koXoYEgjlkNn7xfysjioOVGFzayBFeGVjdXRp
-      b24wATm42Cqh8Ez4F0GgxZah8Ez4F0ouCghjcmV3X2tleRIiCiA3M2FhYzI4NWU2NzQ2NjY3Zjc1
-      MTQ3NjcwMDAzNDExMEoxCgdjcmV3X2lkEiYKJDg0NDY0YjhlLTRiZjctNDRiYy05MmUxLWE4ZDE1
-      NGZlNWZkN0ouCgh0YXNrX2tleRIiCiBmN2E5ZjdiYjFhZWU0YjZlZjJjNTI2ZDBhOGMyZjJhY0ox
-      Cgd0YXNrX2lkEiYKJDFmNGFjMmFhLTdiZDgtNDU1ZC04ODIwLWMzNmYyMmMwNjgzN3oCGAGFAQAB
-      AAASrAcKEG0ZVq5Ww+/A0wOY3HmKgq4SCMe0ooxqjqBlKgxDcmV3IENyZWF0ZWQwATlwmISi8Ez4
-      F0HYUYai8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBKGgoOcHl0aG9uX3ZlcnNpb24S
-      CAoGMy4xMS43Si4KCGNyZXdfa2V5EiIKIGQ1NTExM2JlNGFhNDFiYTY0M2QzMjYwNDJiMmYwM2Yx
-      SjEKB2NyZXdfaWQSJgokNzkyMWVlYmItMWI4NS00MzNjLWIxMDAtZDU4MmMyOTg5MzBkShwKDGNy
-      ZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJl
-      cl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrJAgoLY3Jld19hZ2Vu
-      dHMSuQIKtgJbeyJrZXkiOiAiZTE0OGU1MzIwMjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAiaWQi
-      OiAiZmRiZDI1MWYtYzUwOC00YmFhLTkwNjctN2U5YzQ2ZGZiZTJhIiwgInJvbGUiOiAidGVzdCBy
-      b2xlIiwgInZlcmJvc2U/IjogdHJ1ZSwgIm1heF9pdGVyIjogNiwgIm1heF9ycG0iOiBudWxsLCAi
-      ZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9l
-      bmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0
-      cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSpACCgpjcmV3X3Rhc2tzEoECCv4BW3si
-      a2V5IjogIjRhMzFiODUxMzNhM2EyOTRjNjg1M2RhNzU3ZDRiYWU3IiwgImlkIjogIjA2YWFmM2Y1
-      LTE5ODctNDAxYS05Yzk0LWY3ZjM1YmQzMDg3OSIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2Us
-      ICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAidGVzdCByb2xlIiwgImFnZW50
-      X2tleSI6ICJlMTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJ0b29sc19uYW1lcyI6
-      IFsiZ2V0X2ZpbmFsX2Fuc3dlciJdfV16AhgBhQEAAQAAEo4CChDT+zPZHwfacDilkzaZJ9uGEgip
-      Kr5r62JB+ioMVGFzayBDcmVhdGVkMAE56KeTovBM+BdB8PmTovBM+BdKLgoIY3Jld19rZXkSIgog
-      ZDU1MTEzYmU0YWE0MWJhNjQzZDMyNjA0MmIyZjAzZjFKMQoHY3Jld19pZBImCiQ3OTIxZWViYi0x
-      Yjg1LTQzM2MtYjEwMC1kNTgyYzI5ODkzMGRKLgoIdGFza19rZXkSIgogNGEzMWI4NTEzM2EzYTI5
-      NGM2ODUzZGE3NTdkNGJhZTdKMQoHdGFza19pZBImCiQwNmFhZjNmNS0xOTg3LTQwMWEtOWM5NC1m
-      N2YzNWJkMzA4Nzl6AhgBhQEAAQAAEpMBChCl85ZcL2Fa0N5QTl6EsIfnEghyDo3bxT+AkyoKVG9v
-      bCBVc2FnZTABOVBA2aLwTPgXQYAy2qLwTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMEof
-      Cgl0b29sX25hbWUSEgoQZ2V0X2ZpbmFsX2Fuc3dlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
-      EpwBChB22uwKhaur9zmeoeEMaRKzEgjrtSEzMbRdIioTVG9vbCBSZXBlYXRlZCBVc2FnZTABOQga
-      C6PwTPgXQaDRC6PwTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMEofCgl0b29sX25hbWUS
-      EgoQZ2V0X2ZpbmFsX2Fuc3dlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpMBChArAfcRpE+W
-      02oszyzccbaWEghTAO9J3zq/kyoKVG9vbCBVc2FnZTABORBRTqPwTPgXQegnT6PwTPgXShoKDmNy
-      ZXdhaV92ZXJzaW9uEggKBjAuNjEuMEofCgl0b29sX25hbWUSEgoQZ2V0X2ZpbmFsX2Fuc3dlckoO
-      CghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpwBChBdtM3p3aqT7wTGaXi6el/4Egie6lFQpa+AfioT
-      VG9vbCBSZXBlYXRlZCBVc2FnZTABOdBg2KPwTPgXQehW2aPwTPgXShoKDmNyZXdhaV92ZXJzaW9u
-      EggKBjAuNjEuMEofCgl0b29sX25hbWUSEgoQZ2V0X2ZpbmFsX2Fuc3dlckoOCghhdHRlbXB0cxIC
-      GAF6AhgBhQEAAQAAEpMBChDq4OuaUKkNoi6jlMyahPJpEgg1MFDHktBxNSoKVG9vbCBVc2FnZTAB
-      ORD/K6TwTPgXQZgMLaTwTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMEofCgl0b29sX25h
-      bWUSEgoQZ2V0X2ZpbmFsX2Fuc3dlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpACChBhvTmu
-      QWP+bx9JMmGpt+w5Egh1J17yki7s8ioOVGFzayBFeGVjdXRpb24wATnoJJSi8Ez4F0HwNX6k8Ez4
-      F0ouCghjcmV3X2tleRIiCiBkNTUxMTNiZTRhYTQxYmE2NDNkMzI2MDQyYjJmMDNmMUoxCgdjcmV3
-      X2lkEiYKJDc5MjFlZWJiLTFiODUtNDMzYy1iMTAwLWQ1ODJjMjk4OTMwZEouCgh0YXNrX2tleRIi
-      CiA0YTMxYjg1MTMzYTNhMjk0YzY4NTNkYTc1N2Q0YmFlN0oxCgd0YXNrX2lkEiYKJDA2YWFmM2Y1
-      LTE5ODctNDAxYS05Yzk0LWY3ZjM1YmQzMDg3OXoCGAGFAQABAAASrg0KEOJZEqiJ7LTTX/J+tuLR
-      stQSCHKjy4tIcmKEKgxDcmV3IENyZWF0ZWQwATmIEuGk8Ez4F0FYDuOk8Ez4F0oaCg5jcmV3YWlf
-      dmVyc2lvbhIICgYwLjYxLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMS43Si4KCGNyZXdfa2V5
-      EiIKIDExMWI4NzJkOGYwY2Y3MDNmMmVmZWYwNGNmM2FjNzk4SjEKB2NyZXdfaWQSJgokYWFiYmU5
-      MmQtYjg3NC00NTZmLWE0NzAtM2FmMDc4ZTdjYThlShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50
-      aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGANKGwoVY3Jl
-      d19udW1iZXJfb2ZfYWdlbnRzEgIYAkqEBQoLY3Jld19hZ2VudHMS9AQK8QRbeyJrZXkiOiAiZTE0
-      OGU1MzIwMjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAiaWQiOiAiZmYzOTE0OGEtZWI2NS00Nzkx
-      LWI3MTMtM2Q4ZmE1YWQ5NTJlIiwgInJvbGUiOiAidGVzdCByb2xlIiwgInZlcmJvc2U/IjogZmFs
-      c2UsICJtYXhfaXRlciI6IDE1LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xs
-      bSI6ICIiLCAibGxtIjogImdwdC00byIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJh
-      bGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29s
-      c19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiZTdlOGVlYTg4NmJjYjhmMTA0NWFiZWVjZjE0MjVkYjci
-      LCAiaWQiOiAiYzYyNDJmNDMtNmQ2Mi00N2U4LTliYmMtNjM0ZDQwYWI4YTQ2IiwgInJvbGUiOiAi
-      dGVzdCByb2xlMiIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAxNSwgIm1heF9ycG0i
-      OiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVs
-      ZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2Us
-      ICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dStcFCgpjcmV3X3Rhc2tz
-      EsgFCsUFW3sia2V5IjogIjMyMmRkYWUzYmM4MGMxZDQ1Yjg1ZmE3NzU2ZGI4NjY1IiwgImlkIjog
-      IjRmZDZhZDdiLTFjNWMtNDE1ZC1hMWQ4LTgwYzExZGNjMTY4NiIsICJhc3luY19leGVjdXRpb24/
-      IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAidGVzdCByb2xl
-      IiwgImFnZW50X2tleSI6ICJlMTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJ0b29s
-      c19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiY2M0ODc2ZjZlNTg4ZTcxMzQ5YmJkM2E2NTg4OGMzZTki
-      LCAiaWQiOiAiOTFlYWFhMWMtMWI4ZC00MDcxLTk2ZmQtM2QxZWVkMjhjMzZjIiwgImFzeW5jX2V4
-      ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJ0
-      ZXN0IHJvbGUiLCAiYWdlbnRfa2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1ODJi
-      IiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICJlMGIxM2UxMGQ3YTE0NmRjYzRjNDg4ZmNm
-      OGQ3NDhhMCIsICJpZCI6ICI4NjExZjhjZS1jNDVlLTQ2OTgtYWEyMS1jMGJkNzdhOGY2ZWYiLCAi
-      YXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9y
-      b2xlIjogInRlc3Qgcm9sZTIiLCAiYWdlbnRfa2V5IjogImU3ZThlZWE4ODZiY2I4ZjEwNDVhYmVl
-      Y2YxNDI1ZGI3IiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEMbX6YsWK7RRf4L1
-      NBRKD6cSCFLJiNmspsyjKgxUYXNrIENyZWF0ZWQwATnonPGk8Ez4F0EotvKk8Ez4F0ouCghjcmV3
-      X2tleRIiCiAxMTFiODcyZDhmMGNmNzAzZjJlZmVmMDRjZjNhYzc5OEoxCgdjcmV3X2lkEiYKJGFh
-      YmJlOTJkLWI4NzQtNDU2Zi1hNDcwLTNhZjA3OGU3Y2E4ZUouCgh0YXNrX2tleRIiCiAzMjJkZGFl
-      M2JjODBjMWQ0NWI4NWZhNzc1NmRiODY2NUoxCgd0YXNrX2lkEiYKJDRmZDZhZDdiLTFjNWMtNDE1
-      ZC1hMWQ4LTgwYzExZGNjMTY4NnoCGAGFAQABAAASkAIKEM9JnUNanFbE9AtnSxqA7H8SCBWlG0WJ
-      sMgKKg5UYXNrIEV4ZWN1dGlvbjABOfDo8qTwTPgXQWhEH6XwTPgXSi4KCGNyZXdfa2V5EiIKIDEx
-      MWI4NzJkOGYwY2Y3MDNmMmVmZWYwNGNmM2FjNzk4SjEKB2NyZXdfaWQSJgokYWFiYmU5MmQtYjg3
-      NC00NTZmLWE0NzAtM2FmMDc4ZTdjYThlSi4KCHRhc2tfa2V5EiIKIDMyMmRkYWUzYmM4MGMxZDQ1
-      Yjg1ZmE3NzU2ZGI4NjY1SjEKB3Rhc2tfaWQSJgokNGZkNmFkN2ItMWM1Yy00MTVkLWExZDgtODBj
-      MTFkY2MxNjg2egIYAYUBAAEAABKOAgoQaQALCJNe5ByN4Wu7FE0kABIIYW/UfVfnYscqDFRhc2sg
-      Q3JlYXRlZDABOWhzLKXwTPgXQSD8LKXwTPgXSi4KCGNyZXdfa2V5EiIKIDExMWI4NzJkOGYwY2Y3
-      MDNmMmVmZWYwNGNmM2FjNzk4SjEKB2NyZXdfaWQSJgokYWFiYmU5MmQtYjg3NC00NTZmLWE0NzAt
-      M2FmMDc4ZTdjYThlSi4KCHRhc2tfa2V5EiIKIGNjNDg3NmY2ZTU4OGU3MTM0OWJiZDNhNjU4ODhj
-      M2U5SjEKB3Rhc2tfaWQSJgokOTFlYWFhMWMtMWI4ZC00MDcxLTk2ZmQtM2QxZWVkMjhjMzZjegIY
-      AYUBAAEAABKQAgoQpPfkgFlpIsR/eN2zn+x3MRIILoWF4/HvceAqDlRhc2sgRXhlY3V0aW9uMAE5
-      GCctpfBM+BdBQLNapfBM+BdKLgoIY3Jld19rZXkSIgogMTExYjg3MmQ4ZjBjZjcwM2YyZWZlZjA0
-      Y2YzYWM3OThKMQoHY3Jld19pZBImCiRhYWJiZTkyZC1iODc0LTQ1NmYtYTQ3MC0zYWYwNzhlN2Nh
-      OGVKLgoIdGFza19rZXkSIgogY2M0ODc2ZjZlNTg4ZTcxMzQ5YmJkM2E2NTg4OGMzZTlKMQoHdGFz
-      a19pZBImCiQ5MWVhYWExYy0xYjhkLTQwNzEtOTZmZC0zZDFlZWQyOGMzNmN6AhgBhQEAAQAAEo4C
-      ChCdvXmXZRltDxEwZx2XkhWhEghoKdomHHhLGSoMVGFzayBDcmVhdGVkMAE54HpmpfBM+BdB4Pdm
-      pfBM+BdKLgoIY3Jld19rZXkSIgogMTExYjg3MmQ4ZjBjZjcwM2YyZWZlZjA0Y2YzYWM3OThKMQoH
-      Y3Jld19pZBImCiRhYWJiZTkyZC1iODc0LTQ1NmYtYTQ3MC0zYWYwNzhlN2NhOGVKLgoIdGFza19r
-      ZXkSIgogZTBiMTNlMTBkN2ExNDZkY2M0YzQ4OGZjZjhkNzQ4YTBKMQoHdGFza19pZBImCiQ4NjEx
-      ZjhjZS1jNDVlLTQ2OTgtYWEyMS1jMGJkNzdhOGY2ZWZ6AhgBhQEAAQAAEpACChAIvs/XQL53haTt
-      NV8fk6geEgicgSOcpcYulyoOVGFzayBFeGVjdXRpb24wATnYImel8Ez4F0Gw5ZSl8Ez4F0ouCghj
-      cmV3X2tleRIiCiAxMTFiODcyZDhmMGNmNzAzZjJlZmVmMDRjZjNhYzc5OEoxCgdjcmV3X2lkEiYK
-      JGFhYmJlOTJkLWI4NzQtNDU2Zi1hNDcwLTNhZjA3OGU3Y2E4ZUouCgh0YXNrX2tleRIiCiBlMGIx
-      M2UxMGQ3YTE0NmRjYzRjNDg4ZmNmOGQ3NDhhMEoxCgd0YXNrX2lkEiYKJDg2MTFmOGNlLWM0NWUt
-      NDY5OC1hYTIxLWMwYmQ3N2E4ZjZlZnoCGAGFAQABAAASvAcKEARTPn0s+U/k8GclUc+5rRoSCHF3
-      KCh8OS0FKgxDcmV3IENyZWF0ZWQwATlo+Pul8Ez4F0EQ0f2l8Ez4F0oaCg5jcmV3YWlfdmVyc2lv
-      bhIICgYwLjYxLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMS43Si4KCGNyZXdfa2V5EiIKIDQ5
-      NGYzNjU3MjM3YWQ4YTMwMzViMmYxYmVlY2RjNjc3SjEKB2NyZXdfaWQSJgokOWMwNzg3NWUtMTMz
-      Mi00MmMzLWFhZTEtZjNjMjc1YTQyNjYwShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEK
-      C2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1i
-      ZXJfb2ZfYWdlbnRzEgIYAUrbAgoLY3Jld19hZ2VudHMSywIKyAJbeyJrZXkiOiAiZTE0OGU1MzIw
-      MjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAiaWQiOiAiNGFkYzNmMmItN2IwNC00MDRlLWEwNDQt
-      N2JkNjVmYTMyZmE4IiwgInJvbGUiOiAidGVzdCByb2xlIiwgInZlcmJvc2U/IjogZmFsc2UsICJt
-      YXhfaXRlciI6IDE1LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIi
-      LCAibGxtIjogImdwdC00byIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19j
-      b2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1l
-      cyI6IFsibGVhcm5fYWJvdXRfYWkiXX1dSo4CCgpjcmV3X3Rhc2tzEv8BCvwBW3sia2V5IjogImYy
-      NTk3Yzc4NjdmYmUzMjRkYzY1ZGMwOGRmZGJmYzZjIiwgImlkIjogIjg2YzZiODE2LTgyOWMtNDUx
-      Zi1iMDZkLTUyZjQ4YTdhZWJiMyIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9p
-      bnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAidGVzdCByb2xlIiwgImFnZW50X2tleSI6ICJl
-      MTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJ0b29sc19uYW1lcyI6IFsibGVhcm5f
-      YWJvdXRfYWkiXX1degIYAYUBAAEAABKOAgoQZWSU3+i71QSqlD8iiLdyWBII1Pawtza2ZHsqDFRh
-      c2sgQ3JlYXRlZDABOdj2FKbwTPgXQZhUFabwTPgXSi4KCGNyZXdfa2V5EiIKIDQ5NGYzNjU3MjM3
-      YWQ4YTMwMzViMmYxYmVlY2RjNjc3SjEKB2NyZXdfaWQSJgokOWMwNzg3NWUtMTMzMi00MmMzLWFh
-      ZTEtZjNjMjc1YTQyNjYwSi4KCHRhc2tfa2V5EiIKIGYyNTk3Yzc4NjdmYmUzMjRkYzY1ZGMwOGRm
-      ZGJmYzZjSjEKB3Rhc2tfaWQSJgokODZjNmI4MTYtODI5Yy00NTFmLWIwNmQtNTJmNDhhN2FlYmIz
-      egIYAYUBAAEAABKRAQoQl3nNMLhrOg+OgsWWX6A9LxIINbCKrQzQ3JkqClRvb2wgVXNhZ2UwATlA
-      TlCm8Ez4F0FASFGm8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBKHQoJdG9vbF9uYW1l
-      EhAKDmxlYXJuX2Fib3V0X0FJSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASkAIKEL9YI/QwoVBJ
-      1HBkTLyQxOESCCcKWhev/Dc8Kg5UYXNrIEV4ZWN1dGlvbjABOXiDFabwTPgXQcjEfqbwTPgXSi4K
-      CGNyZXdfa2V5EiIKIDQ5NGYzNjU3MjM3YWQ4YTMwMzViMmYxYmVlY2RjNjc3SjEKB2NyZXdfaWQS
-      JgokOWMwNzg3NWUtMTMzMi00MmMzLWFhZTEtZjNjMjc1YTQyNjYwSi4KCHRhc2tfa2V5EiIKIGYy
-      NTk3Yzc4NjdmYmUzMjRkYzY1ZGMwOGRmZGJmYzZjSjEKB3Rhc2tfaWQSJgokODZjNmI4MTYtODI5
-      Yy00NTFmLWIwNmQtNTJmNDhhN2FlYmIzegIYAYUBAAEAABLBBwoQ0Le1256mT8wmcvnuLKYeNRII
-      IYBlVsTs+qEqDENyZXcgQ3JlYXRlZDABOYCBiKrwTPgXQRBeiqrwTPgXShoKDmNyZXdhaV92ZXJz
-      aW9uEggKBjAuNjEuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgog
-      NDk0ZjM2NTcyMzdhZDhhMzAzNWIyZjFiZWVjZGM2NzdKMQoHY3Jld19pZBImCiQyN2VlMGYyYy1h
-      ZjgwLTQxYWMtYjg3ZC0xNmViYWQyMTVhNTJKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxK
-      EQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251
-      bWJlcl9vZl9hZ2VudHMSAhgBSuACCgtjcmV3X2FnZW50cxLQAgrNAlt7ImtleSI6ICJlMTQ4ZTUz
-      MjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJpZCI6ICJmMTYyMTFjNS00YWJlLTRhZDAtOWI0
-      YS0yN2RmMTJhODkyN2UiLCAicm9sZSI6ICJ0ZXN0IHJvbGUiLCAidmVyYm9zZT8iOiBmYWxzZSwg
-      Im1heF9pdGVyIjogMiwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAi
-      Z3B0LTRvIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAi
-      YWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9v
-      bHNfbmFtZXMiOiBbImxlYXJuX2Fib3V0X2FpIl19XUqOAgoKY3Jld190YXNrcxL/AQr8AVt7Imtl
-      eSI6ICJmMjU5N2M3ODY3ZmJlMzI0ZGM2NWRjMDhkZmRiZmM2YyIsICJpZCI6ICJjN2FiOWRiYi0y
-      MTc4LTRmOGItOGFiNi1kYTU1YzE0YTBkMGMiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAi
-      aHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogInRlc3Qgcm9sZSIsICJhZ2VudF9r
-      ZXkiOiAiZTE0OGU1MzIwMjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAidG9vbHNfbmFtZXMiOiBb
-      ImxlYXJuX2Fib3V0X2FpIl19XXoCGAGFAQABAAASjgIKECr4ueCUCo/tMB7EuBQt6TcSCD/UepYl
-      WGqAKgxUYXNrIENyZWF0ZWQwATk4kpyq8Ez4F0Hg85yq8Ez4F0ouCghjcmV3X2tleRIiCiA0OTRm
-      MzY1NzIzN2FkOGEzMDM1YjJmMWJlZWNkYzY3N0oxCgdjcmV3X2lkEiYKJDI3ZWUwZjJjLWFmODAt
-      NDFhYy1iODdkLTE2ZWJhZDIxNWE1MkouCgh0YXNrX2tleRIiCiBmMjU5N2M3ODY3ZmJlMzI0ZGM2
-      NWRjMDhkZmRiZmM2Y0oxCgd0YXNrX2lkEiYKJGM3YWI5ZGJiLTIxNzgtNGY4Yi04YWI2LWRhNTVj
-      MTRhMGQwY3oCGAGFAQABAAASeQoQkj0vmbCBIZPi33W9KrvrYhIIM2g73dOAN9QqEFRvb2wgVXNh
-      Z2UgRXJyb3IwATnQgsyr8Ez4F0GghM2r8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBK
-      DwoDbGxtEggKBmdwdC00b3oCGAGFAQABAAASeQoQavr4/1SWr8x7HD5mAzlM0hIIXPx740Skkd0q
-      EFRvb2wgVXNhZ2UgRXJyb3IwATkouH9C8Uz4F0FQ1YBC8Uz4F0oaCg5jcmV3YWlfdmVyc2lvbhII
-      CgYwLjYxLjBKDwoDbGxtEggKBmdwdC00b3oCGAGFAQABAAASkAIKEIgmJ3QURJvSsEifMScSiUsS
-      CCyiPHcZT8AnKg5UYXNrIEV4ZWN1dGlvbjABOcAinarwTPgXQeBEynvxTPgXSi4KCGNyZXdfa2V5
-      EiIKIDQ5NGYzNjU3MjM3YWQ4YTMwMzViMmYxYmVlY2RjNjc3SjEKB2NyZXdfaWQSJgokMjdlZTBm
-      MmMtYWY4MC00MWFjLWI4N2QtMTZlYmFkMjE1YTUySi4KCHRhc2tfa2V5EiIKIGYyNTk3Yzc4Njdm
-      YmUzMjRkYzY1ZGMwOGRmZGJmYzZjSjEKB3Rhc2tfaWQSJgokYzdhYjlkYmItMjE3OC00ZjhiLThh
-      YjYtZGE1NWMxNGEwZDBjegIYAYUBAAEAABLEBwoQY+GZuYkP6mwdaVQQc11YuhII7ADKOlFZlzQq
-      DENyZXcgQ3JlYXRlZDABObCoi3zxTPgXQeCUjXzxTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAu
-      NjEuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogN2U2NjA4OTg5
-      ODU5YTY3ZWVjODhlZWY3ZmNlODUyMjVKMQoHY3Jld19pZBImCiQxMmE0OTFlNS00NDgwLTQ0MTYt
-      OTAxYi1iMmI1N2U1ZWU4ZThKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19t
-      ZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9h
-      Z2VudHMSAhgBSt8CCgtjcmV3X2FnZW50cxLPAgrMAlt7ImtleSI6ICIyMmFjZDYxMWU0NGVmNWZh
-      YzA1YjUzM2Q3NWU4ODkzYiIsICJpZCI6ICI5NjljZjhlMy0yZWEwLTQ5ZjgtODNlMS02MzEzYmE4
-      ODc1ZjUiLCAicm9sZSI6ICJEYXRhIFNjaWVudGlzdCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4
-      X2l0ZXIiOiAxNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwg
-      ImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29k
-      ZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMi
-      OiBbImdldCBncmVldGluZ3MiXX1dSpICCgpjcmV3X3Rhc2tzEoMCCoACW3sia2V5IjogImEyNzdi
-      MzRiMmMxNDZmMGM1NmM1ZTEzNTZlOGY4YTU3IiwgImlkIjogImIwMTg0NTI2LTJlOWItNDA0My1h
-      M2JiLTFiM2QzNWIxNTNhOCIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1
-      dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiRGF0YSBTY2llbnRpc3QiLCAiYWdlbnRfa2V5Ijog
-      IjIyYWNkNjExZTQ0ZWY1ZmFjMDViNTMzZDc1ZTg4OTNiIiwgInRvb2xzX25hbWVzIjogWyJnZXQg
-      Z3JlZXRpbmdzIl19XXoCGAGFAQABAAASjgIKEI/rrKkPz08VpVWNehfvxJ0SCIpeq76twGj3KgxU
-      YXNrIENyZWF0ZWQwATlA9aR88Uz4F0HoVqV88Uz4F0ouCghjcmV3X2tleRIiCiA3ZTY2MDg5ODk4
-      NTlhNjdlZWM4OGVlZjdmY2U4NTIyNUoxCgdjcmV3X2lkEiYKJDEyYTQ5MWU1LTQ0ODAtNDQxNi05
-      MDFiLWIyYjU3ZTVlZThlOEouCgh0YXNrX2tleRIiCiBhMjc3YjM0YjJjMTQ2ZjBjNTZjNWUxMzU2
-      ZThmOGE1N0oxCgd0YXNrX2lkEiYKJGIwMTg0NTI2LTJlOWItNDA0My1hM2JiLTFiM2QzNWIxNTNh
-      OHoCGAGFAQABAAASkAEKEKKr5LR8SkqfqqktFhniLdkSCPMnqI2ma9UoKgpUb29sIFVzYWdlMAE5
-      sCHgfPFM+BdB+A/hfPFM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShwKCXRvb2xfbmFt
-      ZRIPCg1HZXQgR3JlZXRpbmdzSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASkAIKEOj2bALdBlz6
-      1kP1MvHE5T0SCLw4D7D331IOKg5UYXNrIEV4ZWN1dGlvbjABOeCBpXzxTPgXQSjiEH3xTPgXSi4K
-      CGNyZXdfa2V5EiIKIDdlNjYwODk4OTg1OWE2N2VlYzg4ZWVmN2ZjZTg1MjI1SjEKB2NyZXdfaWQS
-      JgokMTJhNDkxZTUtNDQ4MC00NDE2LTkwMWItYjJiNTdlNWVlOGU4Si4KCHRhc2tfa2V5EiIKIGEy
-      NzdiMzRiMmMxNDZmMGM1NmM1ZTEzNTZlOGY4YTU3SjEKB3Rhc2tfaWQSJgokYjAxODQ1MjYtMmU5
-      Yi00MDQzLWEzYmItMWIzZDM1YjE1M2E4egIYAYUBAAEAABLQBwoQLjz7NWyGPgGU4tVFJ0sh9BII
-      N6EzU5f/sykqDENyZXcgQ3JlYXRlZDABOajOcX3xTPgXQUCAc33xTPgXShoKDmNyZXdhaV92ZXJz
-      aW9uEggKBjAuNjEuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgog
-      YzMwNzYwMDkzMjY3NjE0NDRkNTdjNzFkMWRhM2YyN2NKMQoHY3Jld19pZBImCiQ1N2Y0NjVhNC03
-      Zjk1LTQ5Y2MtODNmZC0zZTIwNWRhZDBjZTJKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxK
-      EQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251
-      bWJlcl9vZl9hZ2VudHMSAhgBSuUCCgtjcmV3X2FnZW50cxLVAgrSAlt7ImtleSI6ICI5OGYzYjFk
-      NDdjZTk2OWNmMDU3NzI3Yjc4NDE0MjVjZCIsICJpZCI6ICJjZjcyZDlkNy01MjQwLTRkMzEtYjA2
-      Mi0xMmNjMDU2OGNjM2MiLCAicm9sZSI6ICJGcmllbmRseSBOZWlnaGJvciIsICJ2ZXJib3NlPyI6
-      IGZhbHNlLCAibWF4X2l0ZXIiOiAxNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGlu
-      Z19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNl
-      LCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAi
-      dG9vbHNfbmFtZXMiOiBbImRlY2lkZSBncmVldGluZ3MiXX1dSpgCCgpjcmV3X3Rhc2tzEokCCoYC
-      W3sia2V5IjogIjgwZDdiY2Q0OTA5OTI5MDA4MzgzMmYwZTk4MzM4MGRmIiwgImlkIjogIjUxNTJk
-      MmQ2LWYwODYtNGIyMi1hOGMxLTMyODA5NzU1NjZhZCIsICJhc3luY19leGVjdXRpb24/IjogZmFs
-      c2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiRnJpZW5kbHkgTmVpZ2hi
-      b3IiLCAiYWdlbnRfa2V5IjogIjk4ZjNiMWQ0N2NlOTY5Y2YwNTc3MjdiNzg0MTQyNWNkIiwgInRv
-      b2xzX25hbWVzIjogWyJkZWNpZGUgZ3JlZXRpbmdzIl19XXoCGAGFAQABAAASjgIKEM+95r2LzVVg
-      kqAMolHjl9oSCN9WyhdF/ucVKgxUYXNrIENyZWF0ZWQwATnoCoJ98Uz4F0HwXIJ98Uz4F0ouCghj
-      cmV3X2tleRIiCiBjMzA3NjAwOTMyNjc2MTQ0NGQ1N2M3MWQxZGEzZjI3Y0oxCgdjcmV3X2lkEiYK
-      JDU3ZjQ2NWE0LTdmOTUtNDljYy04M2ZkLTNlMjA1ZGFkMGNlMkouCgh0YXNrX2tleRIiCiA4MGQ3
-      YmNkNDkwOTkyOTAwODM4MzJmMGU5ODMzODBkZkoxCgd0YXNrX2lkEiYKJDUxNTJkMmQ2LWYwODYt
-      NGIyMi1hOGMxLTMyODA5NzU1NjZhZHoCGAGFAQABAAASkwEKENJjTKn4eTP/P11ERMIGcdYSCIKF
-      bGEmcS7bKgpUb29sIFVzYWdlMAE5EFu5ffFM+BdBoD26ffFM+BdKGgoOY3Jld2FpX3ZlcnNpb24S
-      CAoGMC42MS4wSh8KCXRvb2xfbmFtZRISChBEZWNpZGUgR3JlZXRpbmdzSg4KCGF0dGVtcHRzEgIY
-      AXoCGAGFAQABAAASkAIKEG29htC06tLF7ihE5Yz6NyMSCAAsKzOcj25nKg5UYXNrIEV4ZWN1dGlv
-      bjABOQCEgn3xTPgXQfgg7X3xTPgXSi4KCGNyZXdfa2V5EiIKIGMzMDc2MDA5MzI2NzYxNDQ0ZDU3
-      YzcxZDFkYTNmMjdjSjEKB2NyZXdfaWQSJgokNTdmNDY1YTQtN2Y5NS00OWNjLTgzZmQtM2UyMDVk
-      YWQwY2UySi4KCHRhc2tfa2V5EiIKIDgwZDdiY2Q0OTA5OTI5MDA4MzgzMmYwZTk4MzM4MGRmSjEK
-      B3Rhc2tfaWQSJgokNTE1MmQyZDYtZjA4Ni00YjIyLWE4YzEtMzI4MDk3NTU2NmFkegIYAYUBAAEA
-      AA==
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '18925'
-      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:
-      - Tue, 24 Sep 2024 21:57:39 GMT
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gemma2:latest", "prompt": "### User:\nRespond in 20 words. Who
-      are you?\n\n", "options": {}, "stream": false}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '120'
-      Content-Type:
-      - application/json
-      User-Agent:
-      - python-requests/2.31.0
-    method: POST
-    uri: http://localhost:8080/api/generate
-  response:
-    body:
-      string: '{"model":"gemma2:latest","created_at":"2024-09-24T21:57:51.284303Z","response":"I
-        am Gemma, an open-weights AI assistant developed by Google DeepMind.  \n","done":true,"done_reason":"stop","context":[106,1645,108,6176,4926,235292,108,54657,575,235248,235284,235276,3907,235265,7702,708,692,235336,109,107,108,106,2516,108,235285,1144,137061,235269,671,2174,235290,30316,16481,20409,6990,731,6238,20555,35777,235265,139,108],"total_duration":14046647083,"load_duration":12942541833,"prompt_eval_count":25,"prompt_eval_duration":177695000,"eval_count":19,"eval_duration":923120000}'
-    headers:
-      Content-Length:
-      - '579'
-      Content-Type:
-      - application/json; charset=utf-8
-      Date:
-      - Tue, 24 Sep 2024 21:57:51 GMT
-    status:
-      code: 200
-      message: OK
-version: 1

tests/cassettes/test_agent_with_ollama_llama3.yaml

@@ -0,0 +1,36 @@
+interactions:
+- request:
+    body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Who
+      which model are you?\n\n", "options": {"stop": ["\nObservation:"]}, "stream":
+      false}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '156'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - python-requests/2.32.3
+    method: POST
+    uri: http://localhost:11434/api/generate
+  response:
+    body:
+      string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:07:07.623404Z","response":"I''m
+        an AI designed to assist and communicate with users, utilizing a combination
+        of natural language processing models.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,10699,902,1646,527,499,1980,128009,128006,78191,128007,271,40,2846,459,15592,6319,311,7945,323,19570,449,3932,11,35988,264,10824,315,5933,4221,8863,4211,13],"total_duration":1076617833,"load_duration":46505416,"prompt_eval_count":40,"prompt_eval_duration":626000000,"eval_count":22,"eval_duration":399000000}'
+    headers:
+      Content-Length:
+      - '690'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Thu, 02 Jan 2025 20:07:07 GMT
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_crew_output_file_end_to_end.yaml

@@ -0,0 +1,243 @@
+interactions:
+- request:
+    body: !!binary |
+      CuIcCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSuRwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKjBwoQXK7w4+uvyEkrI9D5qyvcJxII5UmQ7hmczdIqDENyZXcgQ3JlYXRlZDABOfxQ
+      /hs4jBUYQUi3DBw4jBUYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjEyLjdKLgoIY3Jld19rZXkSIgogYzk3YjVmZWI1ZDFiNjZiYjU5MDA2YWFhMDFh
+      MjljZDZKMQoHY3Jld19pZBImCiRkZjY3NGMwYi1hOTc0LTQ3NTAtYjlkMS0yZWQxNjM3MzFiNTZK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBStECCgtjcmV3
+      X2FnZW50cxLBAgq+Alt7ImtleSI6ICIwN2Q5OWI2MzA0MTFkMzVmZDkwNDdhNTMyZDUzZGRhNyIs
+      ICJpZCI6ICI5MDYwYTQ2Zi02MDY3LTQ1N2MtOGU3ZC04NjAyN2YzY2U5ZDUiLCAicm9sZSI6ICJS
+      ZXNlYXJjaGVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6
+      IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwg
+      ImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZh
+      bHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUr/AQoKY3Jld190
+      YXNrcxLwAQrtAVt7ImtleSI6ICI2Mzk5NjUxN2YzZjNmMWM5NGQ2YmI2MTdhYTBiMWM0ZiIsICJp
+      ZCI6ICJjYTA4ZjkyOS0yMmI0LTQyZmQtYjViMC05N2M3MjM0ZDk5OTEiLCAiYXN5bmNfZXhlY3V0
+      aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIlJlc2Vh
+      cmNoZXIiLCAiYWdlbnRfa2V5IjogIjA3ZDk5YjYzMDQxMWQzNWZkOTA0N2E1MzJkNTNkZGE3Iiwg
+      InRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEOTJZh9R45IwgGVg9cinZmISCJopKRMf
+      bpMJKgxUYXNrIENyZWF0ZWQwATlG+zQcOIwVGEHk0zUcOIwVGEouCghjcmV3X2tleRIiCiBjOTdi
+      NWZlYjVkMWI2NmJiNTkwMDZhYWEwMWEyOWNkNkoxCgdjcmV3X2lkEiYKJGRmNjc0YzBiLWE5NzQt
+      NDc1MC1iOWQxLTJlZDE2MzczMWI1NkouCgh0YXNrX2tleRIiCiA2Mzk5NjUxN2YzZjNmMWM5NGQ2
+      YmI2MTdhYTBiMWM0ZkoxCgd0YXNrX2lkEiYKJGNhMDhmOTI5LTIyYjQtNDJmZC1iNWIwLTk3Yzcy
+      MzRkOTk5MXoCGAGFAQABAAASowcKEEvwrN8+tNMIBwtnA+ip7jASCI78Hrh2wlsBKgxDcmV3IENy
+      ZWF0ZWQwATkcRqYeOIwVGEE8erQeOIwVGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKGgoO
+      cHl0aG9uX3ZlcnNpb24SCAoGMy4xMi43Si4KCGNyZXdfa2V5EiIKIDhjMjc1MmY0OWU1YjlkMmI2
+      OGNiMzVjYWM4ZmNjODZkSjEKB2NyZXdfaWQSJgokZmRkYzA4ZTMtNDUyNi00N2Q2LThlNWMtNjY0
+      YzIyMjc4ZDgyShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQ
+      AEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIY
+      AUrRAgoLY3Jld19hZ2VudHMSwQIKvgJbeyJrZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5
+      YzQ1NjNkNzUiLCAiaWQiOiAiY2UxNjA2YjktMjdiOS00ZDc4LWEyODctNDZiMDNlZDg3ZTA1Iiwg
+      InJvbGUiOiAiUmVzZWFyY2hlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwg
+      Im1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQt
+      NG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1
+      dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K
+      /wEKCmNyZXdfdGFza3MS8AEK7QFbeyJrZXkiOiAiMGQ2ODVhMjE5OTRkOTQ5MDk3YmM1YTU2ZDcz
+      N2U2ZDEiLCAiaWQiOiAiNDdkMzRjZjktMGYxZS00Y2JkLTgzMzItNzRjZjY0YWRlOThlIiwgImFz
+      eW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9s
+      ZSI6ICJSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6ICI4YmQyMTM5YjU5NzUxODE1MDZlNDFmZDlj
+      NDU2M2Q3NSIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChAf4TXS782b0PBJ4NSB
+      JXwsEgjXnd13GkMzlyoMVGFzayBDcmVhdGVkMAE5mb/cHjiMFRhBGRTiHjiMFRhKLgoIY3Jld19r
+      ZXkSIgogOGMyNzUyZjQ5ZTViOWQyYjY4Y2IzNWNhYzhmY2M4NmRKMQoHY3Jld19pZBImCiRmZGRj
+      MDhlMy00NTI2LTQ3ZDYtOGU1Yy02NjRjMjIyNzhkODJKLgoIdGFza19rZXkSIgogMGQ2ODVhMjE5
+      OTRkOTQ5MDk3YmM1YTU2ZDczN2U2ZDFKMQoHdGFza19pZBImCiQ0N2QzNGNmOS0wZjFlLTRjYmQt
+      ODMzMi03NGNmNjRhZGU5OGV6AhgBhQEAAQAAEqMHChAyBGKhzDhROB5pmAoXrikyEgj6SCwzj1dU
+      LyoMQ3JldyBDcmVhdGVkMAE5vkjTHziMFRhBRDbhHziMFRhKGgoOY3Jld2FpX3ZlcnNpb24SCAoG
+      MC44Ni4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTIuN0ouCghjcmV3X2tleRIiCiBiNjczNjg2
+      ZmM4MjJjMjAzYzdlODc5YzY3NTQyNDY5OUoxCgdjcmV3X2lkEiYKJGYyYWVlYTYzLTU2OWUtNDUz
+      NS1iZTY0LTRiZjYzZmU5NjhjN0ocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3
+      X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29m
+      X2FnZW50cxICGAFK0QIKC2NyZXdfYWdlbnRzEsECCr4CW3sia2V5IjogImI1OWNmNzdiNmU3NjU4
+      NDg3MGViMWMzODgyM2Q3ZTI4IiwgImlkIjogImJiZjNkM2E4LWEwMjUtNGI0ZC1hY2Q0LTFmNzcz
+      NTI3MWJmMCIsICJyb2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9p
+      dGVyIjogMjAsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJs
+      bG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3df
+      Y29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFt
+      ZXMiOiBbXX1dSv8BCgpjcmV3X3Rhc2tzEvABCu0BW3sia2V5IjogImE1ZTVjNThjZWExYjlkMDAz
+      MzJlNjg0NDFkMzI3YmRmIiwgImlkIjogIjBiOTRiMTY0LTM5NTktNGFmYS05Njg4LWJjNmEwZWMy
+      MWYzOCIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwg
+      ImFnZW50X3JvbGUiOiAiUmVzZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiYjU5Y2Y3N2I2ZTc2NTg0
+      ODcwZWIxYzM4ODIzZDdlMjgiLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKOAgoQyYfi
+      Ftim717svttBZY3p5hIIUxR5bBHzWWkqDFRhc2sgQ3JlYXRlZDABOV4OBiA4jBUYQbLjBiA4jBUY
+      Si4KCGNyZXdfa2V5EiIKIGI2NzM2ODZmYzgyMmMyMDNjN2U4NzljNjc1NDI0Njk5SjEKB2NyZXdf
+      aWQSJgokZjJhZWVhNjMtNTY5ZS00NTM1LWJlNjQtNGJmNjNmZTk2OGM3Si4KCHRhc2tfa2V5EiIK
+      IGE1ZTVjNThjZWExYjlkMDAzMzJlNjg0NDFkMzI3YmRmSjEKB3Rhc2tfaWQSJgokMGI5NGIxNjQt
+      Mzk1OS00YWZhLTk2ODgtYmM2YTBlYzIxZjM4egIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3685'
+      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, 29 Dec 2024 04:43:27 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You have
+      extensive AI research experience.\nYour personal goal is: Analyze AI topics\nTo
+      give my best complete final answer to the task use the exact following format:\n\nThought:
+      I now can give a great answer\nFinal Answer: Your final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent
+      Task: Explain the advantages of AI.\n\nThis is the expect criteria for your
+      final answer: A summary of the main advantages, bullet points recommended.\nyou
+      MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
+      This is VERY important to you, use the tools available and give your best Final
+      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '922'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=eff7OIkJ0zWRunpA6z67LHqscmSe6XjNxXiPw1R3xCc-1733770413538-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AjfR6FDuTw7NGzy8w7sxjvOkUQlru\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735447404,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer:  \\n**Advantages of AI**  \\n\\n1. **Increased Efficiency and Productivity**
+      \ \\n   - AI systems can process large amounts of data quickly and accurately,
+      leading to faster decision-making and increased productivity in various sectors.\\n\\n2.
+      **Cost Savings**  \\n   - Automation of repetitive and time-consuming tasks
+      reduces labor costs and increases operational efficiency, allowing businesses
+      to allocate resources more effectively.\\n\\n3. **Enhanced Data Analysis**  \\n
+      \  - AI excels at analyzing big data, identifying patterns, and providing insights
+      that support better strategic planning and business decision-making.\\n\\n4.
+      **24/7 Availability**  \\n   - AI solutions, such as chatbots and virtual assistants,
+      operate continuously without breaks, offering constant support and customer
+      service, enhancing user experience.\\n\\n5. **Personalization**  \\n   - AI
+      enables the customization of content, products, and services based on user preferences
+      and behaviors, leading to improved customer satisfaction and loyalty.\\n\\n6.
+      **Improved Accuracy**  \\n   - AI technologies, such as machine learning algorithms,
+      reduce the likelihood of human error in various processes, leading to greater
+      accuracy and reliability.\\n\\n7. **Enhanced Innovation**  \\n   - AI fosters
+      innovative solutions by providing new tools and approaches to problem-solving,
+      enabling companies to develop cutting-edge products and services.\\n\\n8. **Scalability**
+      \ \\n   - AI can be scaled to handle varying amounts of workloads without significant
+      changes to infrastructure, making it easier for organizations to expand operations.\\n\\n9.
+      **Predictive Capabilities**  \\n   - Advanced analytics powered by AI can anticipate
+      trends and outcomes, allowing businesses to proactively adjust strategies and
+      improve forecasting.\\n\\n10. **Health Benefits**  \\n    - In healthcare, AI
+      assists in diagnostics, personalized treatment plans, and predictive analytics,
+      leading to better patient care and improved health outcomes.\\n\\n11. **Safety
+      and Risk Mitigation**  \\n    - AI can enhance safety in various industries
+      by taking over dangerous tasks, monitoring for hazards, and predicting maintenance
+      needs for critical machinery, thereby preventing accidents.\\n\\n12. **Reduced
+      Environmental Impact**  \\n    - AI can optimize resource usage in areas such
+      as energy consumption and supply chain logistics, contributing to sustainability
+      efforts and reducing overall environmental footprints.\",\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 168,\n    \"completion_tokens\":
+      440,\n    \"total_tokens\": 608,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f9721053d1eb9f1-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 29 Dec 2024 04:43:32 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=5enubNIoQSGMYEgy8Q2FpzzhphA0y.0lXukRZrWFvMk-1735447412-1.0.1.1-FIK1sMkUl3YnW1gTC6ftDtb2mKsbosb4mwabdFAlWCfJ6pXeavYq.bPsfKNvzAb5WYq60yVGH5lHsJT05bhSgw;
+        path=/; expires=Sun, 29-Dec-24 05:13:32 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=63wmKMTuFamkLN8FBI4fP8JZWbjWiRxWm7wb3kz.z_A-1735447412038-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '7577'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999793'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_55b8d714656e8f10f4e23cbe9034d66b
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_crew_with_delegating_agents.yaml

@@ -3,223 +3,17 @@ interactions:
     body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
       time CEO of a content creation agency with a Senior Writer on the team. You''re
       now working on a new project and want to make sure the content produced is amazing.\nYour
-      personal goal is: Make sure the writers in your company produce amazing content.\nYou
-      ONLY have access to the following tools, and should NEVER make up tools that
-      are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
-      str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a
-      specific task to one of the following coworkers: Senior Writer\nThe input to
-      this tool should be the coworker, the task you want them to do, and ALL necessary
-      context to execute the task, they know nothing about the task, so share absolute
-      everything you know, don''t reference things but instead explain them.\nTool
-      Arguments: {''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'':
-      {''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
-      ''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
-      Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
-      = None, **kwargs)\nTool Description: Ask a specific question to one of the following
-      coworkers: Senior Writer\nThe input to this tool should be the coworker, the
-      question you have for them, and ALL necessary context to ask the question properly,
-      they know nothing about the question, so share absolute everything you know,
-      don''t reference things but instead explain them.\nTool Arguments: {''question'':
-      {''title'': ''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'',
-      ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
-      ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
-      format:\n\nThought: you should always think about what to do\nAction: the action
-      to take, only one name of [Delegate work to coworker, Ask question to coworker],
-      just the name, exactly as it''s written.\nAction Input: the input to the action,
-      just a simple python dictionary, enclosed in curly braces, using \" to wrap
-      keys and values.\nObservation: the result of the action\n\nOnce all necessary
-      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
-      the final answer to the original input question\n"}, {"role": "user", "content":
-      "\nCurrent Task: Produce and amazing 1 paragraph draft of an article about AI
-      Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
-      article about AI.\nyou MUST return the actual complete content as the final
-      answer, not a summary.\n\nBegin! This is VERY important to you, use the tools
-      available and give your best Final Answer, your job depends on it!\n\nThought:"}],
-      "model": "gpt-4o"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2762'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
-        _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.47.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.47.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-AB7ZvxqgeOayGTQWwR61ASlZp0s74\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1727214103,\n  \"model\": \"gpt-4o-2024-05-13\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Thought: To ensure the content is amazing,
-      I'll delegate the task of producing a one-paragraph draft of an article about
-      AI Agents to the Senior Writer with all necessary context.\\n\\nAction: Delegate
-      work to coworker\\nAction Input: \\n{\\n    \\\"coworker\\\": \\\"Senior Writer\\\",
-      \\n    \\\"task\\\": \\\"Produce a one paragraph draft of an article about AI
-      Agents\\\", \\n    \\\"context\\\": \\\"We need an amazing one-paragraph draft
-      as the beginning of a 4-paragraph article about AI Agents. This is for a high-stakes
-      project that critically impacts our company. The paragraph should highlight
-      what AI Agents are, their significance, and how they are transforming various
-      industries. The tone should be professional yet engaging. Make sure the content
-      is original, insightful, and thoroughly researched.\\\"\\n}\",\n        \"refusal\":
-      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
-      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 608,\n    \"completion_tokens\":
-      160,\n    \"total_tokens\": 768,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
-      0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8c85f0b038a71cf3-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 24 Sep 2024 21:41:45 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '1826'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '30000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '29999325'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 1ms
-      x-request-id:
-      - req_79054638deeb01da76c5bba273bffc28
-    http_version: HTTP/1.1
-    status_code: 200
-- request:
-    body: !!binary |
-      Cq8OCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkShg4KEgoQY3Jld2FpLnRl
-      bGVtZXRyeRKQAgoQg15EMIBbDpydrcK3GAUYfBII5VYz5B10kmgqDlRhc2sgRXhlY3V0aW9uMAE5
-      aGIpYwtM+BdBIO6VVRNM+BdKLgoIY3Jld19rZXkSIgogZTNmZGEwZjMxMTBmZTgwYjE4OTQ3YzAx
-      NDcxNDMwYTRKMQoHY3Jld19pZBImCiRjNzM1NzdhYi0xYThhLTQzMGYtYjYyZi01MTBlYWMyMWI3
-      MThKLgoIdGFza19rZXkSIgogNWZhNjVjMDZhOWUzMWYyYzY5NTQzMjY2OGFjZDYyZGRKMQoHdGFz
-      a19pZBImCiQ3MjAzMjYyMC0yMzJmLTQ5ZTMtOGMyNy0xYzBlOWJhNjFiZDB6AhgBhQEAAQAAEssJ
-      ChB+du4H1wHcku5blhLQBtuoEgiXVguc5KA1RyoMQ3JldyBDcmVhdGVkMAE54IJsVxNM+BdBcCN4
-      VxNM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMu
-      MTEuN0ouCghjcmV3X2tleRIiCiBlNjQ5NTczYTI2ZTU4NzkwY2FjMjFhMzdjZDQ0NDM3YUoxCgdj
-      cmV3X2lkEiYKJDI4ZTY0YmQ3LWNlYWMtNDYxOS04MmM3LTIzNmRkNTQxOGM4N0ocCgxjcmV3X3By
-      b2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2Zf
-      dGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAJKgAUKC2NyZXdfYWdlbnRzEvAE
-      Cu0EW3sia2V5IjogIjMyODIxN2I2YzI5NTliZGZjNDdjYWQwMGU4NDg5MGQwIiwgImlkIjogIjQ1
-      NjMxMmU3LThkMmMtNDcyMi1iNWNkLTlhMGRhMzg5MmM3OCIsICJyb2xlIjogIkNFTyIsICJ2ZXJi
-      b3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAxNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25f
-      Y2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6
-      IHRydWUsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6
-      IDIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiOWE1MDE1ZWY0ODk1ZGM2Mjc4ZDU0ODE4
-      YmE0NDZhZjciLCAiaWQiOiAiMTM0MDg5MjAtNzVjOC00MTk3LWIwNmQtY2I4MmNkZjhkZDhhIiwg
-      InJvbGUiOiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAx
-      NSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJn
-      cHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRp
-      b24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSvgB
-      CgpjcmV3X3Rhc2tzEukBCuYBW3sia2V5IjogIjBiOWQ2NWRiNmI3YWVkZmIzOThjNTllMmE5Zjcx
-      ZWM1IiwgImlkIjogImQ0YjVhZmE2LTczNTEtNDUxMy04NzY2LTIzOGNjYTk5ZjRlZiIsICJhc3lu
-      Y19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUi
-      OiAiQ0VPIiwgImFnZW50X2tleSI6ICIzMjgyMTdiNmMyOTU5YmRmYzQ3Y2FkMDBlODQ4OTBkMCIs
-      ICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChCLEGLGYlBkv0YucoYjY1NeEghRpGin
-      zpZUiSoMVGFzayBDcmVhdGVkMAE5KCA2WBNM+BdBaLw2WBNM+BdKLgoIY3Jld19rZXkSIgogZTY0
-      OTU3M2EyNmU1ODc5MGNhYzIxYTM3Y2Q0NDQzN2FKMQoHY3Jld19pZBImCiQyOGU2NGJkNy1jZWFj
-      LTQ2MTktODJjNy0yMzZkZDU0MThjODdKLgoIdGFza19rZXkSIgogMGI5ZDY1ZGI2YjdhZWRmYjM5
-      OGM1OWUyYTlmNzFlYzVKMQoHdGFza19pZBImCiRkNGI1YWZhNi03MzUxLTQ1MTMtODc2Ni0yMzhj
-      Y2E5OWY0ZWZ6AhgBhQEAAQAA
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '1842'
-      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:
-      - Tue, 24 Sep 2024 21:41:46 GMT
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are Senior Writer. You''re
-      a senior writer, specialized in technology, software engineering, AI and startups.
-      You work as a freelancer and are now working on writing content for a new customer.\nYour
-      personal goal is: Write the best content about AI and AI agents.\nTo give my
-      best complete final answer to the task use the exact following format:\n\nThought:
+      personal goal is: Make sure the writers in your company produce amazing content.\nTo
+      give my best complete final answer to the task use the exact following format:\n\nThought:
       I now can give a great answer\nFinal Answer: Your final answer must be the great
       and the most complete as possible, it must be outcome described.\n\nI MUST use
       these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent
-      Task: Produce a one paragraph draft of an article about AI Agents\n\nThis is
-      the expect criteria for your final answer: Your best answer to your coworker
-      asking you this, accounting for the context shared.\nyou MUST return the actual
-      complete content as the final answer, not a summary.\n\nThis is the context
-      you''re working with:\nWe need an amazing one-paragraph draft as the beginning
-      of a 4-paragraph article about AI Agents. This is for a high-stakes project
-      that critically impacts our company. The paragraph should highlight what AI
-      Agents are, their significance, and how they are transforming various industries.
-      The tone should be professional yet engaging. Make sure the content is original,
-      insightful, and thoroughly researched.\n\nBegin! This is VERY important to you,
-      use the tools available and give your best Final Answer, your job depends on
-      it!\n\nThought:"}], "model": "gpt-4o"}'
+      Task: Produce and amazing 1 paragraph draft of an article about AI Agents.\n\nThis
+      is the expect criteria for your final answer: A 4 paragraph article about AI.\nyou
+      MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
+      This is VERY important to you, use the tools available and give your best Final
+      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"], "stream": false}'
     headers:
       accept:
       - application/json
@@ -228,16 +22,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1545'
+      - '1105'
       content-type:
       - application/json
-      cookie:
-      - __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
-        _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.47.0
+      - OpenAI/Python 1.52.1
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -247,9 +38,11 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.47.0
+      - 1.52.1
       x-stainless-raw-response:
       - 'true'
+      x-stainless-retry-count:
+      - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -257,31 +50,51 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-AB7ZxDYcPlSiBZsftdRs2cWbUJllW\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1727214105,\n  \"model\": \"gpt-4o-2024-05-13\",\n
+    content: "{\n  \"id\": \"chatcmpl-Ahe7liUPejwfqxMe8aEWmKGJ837em\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734965705,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
       \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
       \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
-      Answer: Artificial Intelligence (AI) Agents are sophisticated computer programs
-      designed to perform tasks that typically require human intelligence, such as
-      decision making, problem-solving, and learning. These agents operate autonomously,
-      utilizing vast amounts of data, advanced algorithms, and machine learning techniques
-      to analyze their environment, adapt to new information, and improve their performance
-      over time. The significance of AI Agents lies in their transformative potential
-      across various industries. In healthcare, they assist in diagnosing diseases
-      with greater accuracy; in finance, they predict market trends and manage risks;
-      in customer service, they provide personalized and efficient responses. As these
-      AI-powered entities continue to evolve, they are not only enhancing operational
-      efficiencies but also driving innovation and creating new opportunities for
-      growth and development in every sector they penetrate.\",\n        \"refusal\":
-      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
-      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 297,\n    \"completion_tokens\":
-      160,\n    \"total_tokens\": 457,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
-      0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
+      Answer: In the rapidly evolving landscape of technology, AI agents have emerged
+      as formidable tools, revolutionizing how we interact with data and automate
+      tasks. These sophisticated systems leverage machine learning and natural language
+      processing to perform a myriad of functions, from virtual personal assistants
+      to complex decision-making companions in industries such as finance, healthcare,
+      and education. By mimicking human intelligence, AI agents can analyze massive
+      data sets at unparalleled speeds, enabling businesses to uncover valuable insights,
+      enhance productivity, and elevate user experiences to unprecedented levels.\\n\\nOne
+      of the most striking aspects of AI agents is their adaptability; they learn
+      from their interactions and continuously improve their performance over time.
+      This feature is particularly valuable in customer service where AI agents can
+      address inquiries, resolve issues, and provide personalized recommendations
+      without the limitations of human fatigue. Moreover, with intuitive interfaces,
+      AI agents enhance user interactions, making technology more accessible and user-friendly,
+      thereby breaking down barriers that have historically hindered digital engagement.\\n\\nDespite
+      their immense potential, the deployment of AI agents raises important ethical
+      and practical considerations. Issues related to privacy, data security, and
+      the potential for job displacement necessitate thoughtful dialogue and proactive
+      measures. Striking a balance between technological innovation and societal impact
+      will be crucial as organizations integrate these agents into their operations.
+      Additionally, ensuring transparency in AI decision-making processes is vital
+      to maintain public trust as AI agents become an integral part of daily life.\\n\\nLooking
+      ahead, the future of AI agents appears bright, with ongoing advancements promising
+      even greater capabilities. As we continue to harness the power of AI, we can
+      expect these agents to play a transformative role in shaping various sectors\u2014streamlining
+      workflows, enabling smarter decision-making, and fostering more personalized
+      experiences. Embracing this technology responsibly can lead to a future where
+      AI agents not only augment human effort but also inspire creativity and efficiency
+      across the board, ultimately redefining our interaction with the digital world.\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 208,\n    \"completion_tokens\":
+      382,\n    \"total_tokens\": 590,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8c85f0c0cf961cf3-GRU
+      - 8f6930c97a33ae54-GRU
       Connection:
       - keep-alive
       Content-Encoding:
@@ -289,45 +102,77 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 24 Sep 2024 21:41:48 GMT
+      - Mon, 23 Dec 2024 14:55:10 GMT
       Server:
       - cloudflare
+      Set-Cookie:
+      - __cf_bm=g58erGPkGAltcfYpDRU4IsdEEzb955dGmBOAZacFlPA-1734965710-1.0.1.1-IiodiX3uxbT5xSa4seI7M.gRM4Jj46h2d6ZW2wCkSUYUAX.ivRh_sGQN2hucEMzdG8O87pc00dCl7E5W8KkyEA;
+        path=/; expires=Mon, 23-Dec-24 15:25:10 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=eQzzWvIXDS8Me1OIBdCG5F1qFyVfAo3sumvYRE7J41E-1734965710778-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
       - nosniff
       access-control-expose-headers:
       - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '2468'
+      - '5401'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
       x-ratelimit-limit-requests:
-      - '10000'
+      - '30000'
       x-ratelimit-limit-tokens:
-      - '30000000'
+      - '150000000'
       x-ratelimit-remaining-requests:
-      - '9999'
+      - '29999'
       x-ratelimit-remaining-tokens:
-      - '29999625'
+      - '149999746'
       x-ratelimit-reset-requests:
-      - 6ms
+      - 2ms
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_66c8801b42ac865249246d98225c1492
+      - req_30791533923ae20626ef35a03ae66172
     http_version: HTTP/1.1
     status_code: 200
 - request:
     body: !!binary |
-      CtwBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSswEKEgoQY3Jld2FpLnRl
-      bGVtZXRyeRKcAQoQROg/k5NCUGdgfvfLrFlQDxIIlfh6oMbmqu0qClRvb2wgVXNhZ2UwATlws+Wj
-      FEz4F0EwBeijFEz4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBKKAoJdG9vbF9uYW1lEhsK
-      GURlbGVnYXRlIHdvcmsgdG8gY293b3JrZXJKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAAA==
+      CqYMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS/QsKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRLVCQoQLH3VghpS+l/DatJl8rrpvRIIUpNEm7ELU08qDENyZXcgQ3JlYXRlZDABObgs
+      nNId1hMYQfgVpdId1hMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogZTY0OTU3M2EyNmU1ODc5MGNhYzIxYTM3Y2Q0
+      NDQzN2FKMQoHY3Jld19pZBImCiQzYjVkNDFjNC1kZWJiLTQ2MzItYmIwMC1mNTdhNmM2M2QwMThK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSooFCgtjcmV3
+      X2FnZW50cxL6BAr3BFt7ImtleSI6ICIzMjgyMTdiNmMyOTU5YmRmYzQ3Y2FkMDBlODQ4OTBkMCIs
+      ICJpZCI6ICI1Yjk4NDA2OS03MjVlLTQxOWYtYjdiZS1mMDdjMTYyOGNkZjIiLCAicm9sZSI6ICJD
+      RU8iLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjAsICJtYXhfcnBtIjogbnVsbCwg
+      ImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdh
+      dGlvbl9lbmFibGVkPyI6IHRydWUsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1h
+      eF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiOWE1MDE1ZWY0
+      ODk1ZGM2Mjc4ZDU0ODE4YmE0NDZhZjciLCAiaWQiOiAiZjkwZWI0ZmItMzUyMC00ZDAyLTlhNDYt
+      NDE2ZTNlNTQ5NWYxIiwgInJvbGUiOiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJib3NlPyI6IGZhbHNl
+      LCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0i
+      OiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2Us
+      ICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0
+      b29sc19uYW1lcyI6IFtdfV1K+AEKCmNyZXdfdGFza3MS6QEK5gFbeyJrZXkiOiAiMGI5ZDY1ZGI2
+      YjdhZWRmYjM5OGM1OWUyYTlmNzFlYzUiLCAiaWQiOiAiNzdmNDY3MDYtNzRjZi00ZGVkLThlMDUt
+      NmRlZGM0MmYwZDliIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6
+      IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJDRU8iLCAiYWdlbnRfa2V5IjogIjMyODIxN2I2YzI5NTli
+      ZGZjNDdjYWQwMGU4NDg5MGQwIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEBvb
+      LkoAnHiD1gUnbftefpYSCNb1+4JxldizKgxUYXNrIENyZWF0ZWQwATmwYcTSHdYTGEEQz8TSHdYT
+      GEouCghjcmV3X2tleRIiCiBlNjQ5NTczYTI2ZTU4NzkwY2FjMjFhMzdjZDQ0NDM3YUoxCgdjcmV3
+      X2lkEiYKJDNiNWQ0MWM0LWRlYmItNDYzMi1iYjAwLWY1N2E2YzYzZDAxOEouCgh0YXNrX2tleRIi
+      CiAwYjlkNjVkYjZiN2FlZGZiMzk4YzU5ZTJhOWY3MWVjNUoxCgd0YXNrX2lkEiYKJDc3ZjQ2NzA2
+      LTc0Y2YtNGRlZC04ZTA1LTZkZWRjNDJmMGQ5YnoCGAGFAQABAAA=
     headers:
       Accept:
       - '*/*'
@@ -336,7 +181,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '223'
+      - '1577'
       Content-Type:
       - application/x-protobuf
       User-Agent:
@@ -352,213 +197,8 @@ interactions:
       Content-Type:
       - application/x-protobuf
       Date:
-      - Tue, 24 Sep 2024 21:41:51 GMT
+      - Mon, 23 Dec 2024 14:55:10 GMT
     status:
       code: 200
       message: OK
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
-      time CEO of a content creation agency with a Senior Writer on the team. You''re
-      now working on a new project and want to make sure the content produced is amazing.\nYour
-      personal goal is: Make sure the writers in your company produce amazing content.\nYou
-      ONLY have access to the following tools, and should NEVER make up tools that
-      are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
-      str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a
-      specific task to one of the following coworkers: Senior Writer\nThe input to
-      this tool should be the coworker, the task you want them to do, and ALL necessary
-      context to execute the task, they know nothing about the task, so share absolute
-      everything you know, don''t reference things but instead explain them.\nTool
-      Arguments: {''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'':
-      {''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
-      ''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
-      Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
-      = None, **kwargs)\nTool Description: Ask a specific question to one of the following
-      coworkers: Senior Writer\nThe input to this tool should be the coworker, the
-      question you have for them, and ALL necessary context to ask the question properly,
-      they know nothing about the question, so share absolute everything you know,
-      don''t reference things but instead explain them.\nTool Arguments: {''question'':
-      {''title'': ''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'',
-      ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
-      ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
-      format:\n\nThought: you should always think about what to do\nAction: the action
-      to take, only one name of [Delegate work to coworker, Ask question to coworker],
-      just the name, exactly as it''s written.\nAction Input: the input to the action,
-      just a simple python dictionary, enclosed in curly braces, using \" to wrap
-      keys and values.\nObservation: the result of the action\n\nOnce all necessary
-      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
-      the final answer to the original input question\n"}, {"role": "user", "content":
-      "\nCurrent Task: Produce and amazing 1 paragraph draft of an article about AI
-      Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
-      article about AI.\nyou MUST return the actual complete content as the final
-      answer, not a summary.\n\nBegin! This is VERY important to you, use the tools
-      available and give your best Final Answer, your job depends on it!\n\nThought:"},
-      {"role": "assistant", "content": "Thought: To ensure the content is amazing,
-      I''ll delegate the task of producing a one-paragraph draft of an article about
-      AI Agents to the Senior Writer with all necessary context.\n\nAction: Delegate
-      work to coworker\nAction Input: \n{\n    \"coworker\": \"Senior Writer\", \n    \"task\":
-      \"Produce a one paragraph draft of an article about AI Agents\", \n    \"context\":
-      \"We need an amazing one-paragraph draft as the beginning of a 4-paragraph article
-      about AI Agents. This is for a high-stakes project that critically impacts our
-      company. The paragraph should highlight what AI Agents are, their significance,
-      and how they are transforming various industries. The tone should be professional
-      yet engaging. Make sure the content is original, insightful, and thoroughly
-      researched.\"\n}\nObservation: Artificial Intelligence (AI) Agents are sophisticated
-      computer programs designed to perform tasks that typically require human intelligence,
-      such as decision making, problem-solving, and learning. These agents operate
-      autonomously, utilizing vast amounts of data, advanced algorithms, and machine
-      learning techniques to analyze their environment, adapt to new information,
-      and improve their performance over time. The significance of AI Agents lies
-      in their transformative potential across various industries. In healthcare,
-      they assist in diagnosing diseases with greater accuracy; in finance, they predict
-      market trends and manage risks; in customer service, they provide personalized
-      and efficient responses. As these AI-powered entities continue to evolve, they
-      are not only enhancing operational efficiencies but also driving innovation
-      and creating new opportunities for growth and development in every sector they
-      penetrate."}], "model": "gpt-4o"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '4536'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
-        _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.47.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.47.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-AB7a1PO3pMNybn76wXDFc5HE7ZRsL\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1727214109,\n  \"model\": \"gpt-4o-2024-05-13\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Thought: The paragraph provided by the
-      Senior Writer is well-detailed and engaging. I will now structure the 4-paragraph
-      article around this draft, adding an introduction, expanding on the specific
-      applications in various industries, and concluding with the potential future
-      impact of AI Agents.\\n\\nFinal Answer:\\n\\nArtificial Intelligence (AI) Agents
-      are sophisticated computer programs designed to perform tasks that typically
-      require human intelligence, such as decision making, problem-solving, and learning.
-      These agents operate autonomously, utilizing vast amounts of data, advanced
-      algorithms, and machine learning techniques to analyze their environment, adapt
-      to new information, and improve their performance over time.\\n\\nThe significance
-      of AI Agents lies in their transformative potential across various industries.
-      In healthcare, for example, they assist in diagnosing diseases with greater
-      accuracy and speed than human practitioners, offering personalized treatment
-      plans by analyzing patient data. In finance, AI Agents predict market trends,
-      manage risks, and even execute trades, contributing to more stable and profitable
-      financial systems. Customer service sectors benefit significantly from AI Agents,
-      as they provide personalized and efficient responses, often resolving issues
-      faster than traditional methods.\\n\\nMoreover, AI Agents are also making substantial
-      contributions in fields like education and manufacturing. In education, they
-      offer tailored learning experiences by assessing individual student needs and
-      adjusting teaching methods accordingly. They help educators identify students
-      who might need additional support and provide resources to enhance learning
-      outcomes. In manufacturing, AI Agents optimize production lines, predict equipment
-      failures, and improve supply chain management, thus boosting productivity and
-      reducing downtime.\\n\\nAs these AI-powered entities continue to evolve, they
-      are not only enhancing operational efficiencies but also driving innovation
-      and creating new opportunities for growth and development in every sector they
-      penetrate. The future of AI Agents looks promising, with the potential to revolutionize
-      the way we live and work, making processes more efficient, decisions more data-driven,
-      and solutions more innovative than ever before.\\n\\nThis is now a well-rounded,
-      four-paragraph article that comprehensively covers the topic of AI Agents.\\n\\nFinal
-      Answer: This is the complete content as specified:\\nArtificial Intelligence
-      (AI) Agents are sophisticated computer programs designed to perform tasks that
-      typically require human intelligence, such as decision making, problem-solving,
-      and learning. These agents operate autonomously, utilizing vast amounts of data,
-      advanced algorithms, and machine learning techniques to analyze their environment,
-      adapt to new information, and improve their performance over time.\\n\\nThe
-      significance of AI Agents lies in their transformative potential across various
-      industries. In healthcare, for example, they assist in diagnosing diseases with
-      greater accuracy and speed than human practitioners, offering personalized treatment
-      plans by analyzing patient data. In finance, AI Agents predict market trends,
-      manage risks, and even execute trades, contributing to more stable and profitable
-      financial systems. Customer service sectors benefit significantly from AI Agents,
-      as they provide personalized and efficient responses, often resolving issues
-      faster than traditional methods.\\n\\nMoreover, AI Agents are also making substantial
-      contributions in fields like education and manufacturing. In education, they
-      offer tailored learning experiences by assessing individual student needs and
-      adjusting teaching methods accordingly. They help educators identify students
-      who might need additional support and provide resources to enhance learning
-      outcomes. In manufacturing, AI Agents optimize production lines, predict equipment
-      failures, and improve supply chain management, thus boosting productivity and
-      reducing downtime.\\n\\nAs these AI-powered entities continue to evolve, they
-      are not only enhancing operational efficiencies but also driving innovation
-      and creating new opportunities for growth and development in every sector they
-      penetrate. The future of AI Agents looks promising, with the potential to revolutionize
-      the way we live and work, making processes more efficient, decisions more data-driven,
-      and solutions more innovative than ever before.\",\n        \"refusal\": null\n
-      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
-      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 923,\n    \"completion_tokens\":
-      715,\n    \"total_tokens\": 1638,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
-      0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8c85f0d2f90c1cf3-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 24 Sep 2024 21:41:58 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '8591'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '30000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '29998895'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 2ms
-      x-request-id:
-      - req_2b51b5cff02148d29b04284b40ca6081
-    http_version: HTTP/1.1
-    status_code: 200
 version: 1

tests/cassettes/test_crew_with_delegating_agents_should_not_override_agent_tools.yaml

@@ -0,0 +1,480 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
+      time CEO of a content creation agency with a Senior Writer on the team. You''re
+      now working on a new project and want to make sure the content produced is amazing.\nYour
+      personal goal is: Make sure the writers in your company produce amazing content.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
+      ''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
+      just returns the input\n\nUse the following format:\n\nThought: you should always
+      think about what to do\nAction: the action to take, only one name of [Test Tool],
+      just the name, exactly as it''s written.\nAction Input: the input to the action,
+      just a simple python dictionary, enclosed in curly braces, using \" to wrap
+      keys and values.\nObservation: the result of the action\n\nOnce all necessary
+      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
+      the final answer to the original input question"}, {"role": "user", "content":
+      "\nCurrent Task: Produce and amazing 1 paragraph draft of an article about AI
+      Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
+      article about AI.\nyou MUST return the actual complete content as the final
+      answer, not a summary.\n\nBegin! This is VERY important to you, use the tools
+      available and give your best Final Answer, your job depends on it!\n\nThought:"}],
+      "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1581'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhLsKP8xKkISk8ntUscyUKL30xRXW\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734895556,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I need to gather information to create
+      an amazing paragraph draft about AI Agents that aligns with the expected criteria
+      of a 4-paragraph article about AI. \\n\\nAction: Test Tool  \\nAction Input:
+      {\\\"query\\\": \\\"Write a captivating and informative paragraph about AI Agents,
+      focusing on their capabilities, applications, and significance in modern technology.\\\"}
+      \ \",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 309,\n    \"completion_tokens\":
+      68,\n    \"total_tokens\": 377,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f62802d0b3f00d5-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 22 Dec 2024 19:25:57 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=vwBNilrHRgMLd8ALWzYrBO5Lm8ieJzbQ3WCVOgmuJ.s-1734895557-1.0.1.1-z.QnDsynL_Ndu.JkWrh_wGMo57vvpK88nWDBTA8P.6prlSRmA91GQLpP62yRUbCW6yoKFbDxroSaYO6qrzZPRg;
+        path=/; expires=Sun, 22-Dec-24 19:55:57 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1075'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999630'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_80fbcef3505afac708a24ef167b701bb
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
+      time CEO of a content creation agency with a Senior Writer on the team. You''re
+      now working on a new project and want to make sure the content produced is amazing.\nYour
+      personal goal is: Make sure the writers in your company produce amazing content.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
+      ''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
+      just returns the input\n\nUse the following format:\n\nThought: you should always
+      think about what to do\nAction: the action to take, only one name of [Test Tool],
+      just the name, exactly as it''s written.\nAction Input: the input to the action,
+      just a simple python dictionary, enclosed in curly braces, using \" to wrap
+      keys and values.\nObservation: the result of the action\n\nOnce all necessary
+      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
+      the final answer to the original input question"}, {"role": "user", "content":
+      "\nCurrent Task: Produce and amazing 1 paragraph draft of an article about AI
+      Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
+      article about AI.\nyou MUST return the actual complete content as the final
+      answer, not a summary.\n\nBegin! This is VERY important to you, use the tools
+      available and give your best Final Answer, your job depends on it!\n\nThought:"},
+      {"role": "assistant", "content": "I need to gather information to create an
+      amazing paragraph draft about AI Agents that aligns with the expected criteria
+      of a 4-paragraph article about AI. \n\nAction: Test Tool  \nAction Input: {\"query\":
+      \"Write a captivating and informative paragraph about AI Agents, focusing on
+      their capabilities, applications, and significance in modern technology.\"}  \nObservation:
+      Processed: Write a captivating and informative paragraph about AI Agents, focusing
+      on their capabilities, applications, and significance in modern technology."}],
+      "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2153'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=vwBNilrHRgMLd8ALWzYrBO5Lm8ieJzbQ3WCVOgmuJ.s-1734895557-1.0.1.1-z.QnDsynL_Ndu.JkWrh_wGMo57vvpK88nWDBTA8P.6prlSRmA91GQLpP62yRUbCW6yoKFbDxroSaYO6qrzZPRg;
+        _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhLsMt1AgrzynC2TSJZZSwr9El8FV\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734895558,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I have received the content
+      related to AI Agents, which I need to now use as a foundation for creating a
+      complete 4-paragraph article about AI. \\n\\nAction: Test Tool  \\nAction Input:
+      {\\\"query\\\": \\\"Based on the previous paragraph about AI Agents, write a
+      4-paragraph article about AI, including an introduction, discussion of AI Agents,
+      their applications, and a conclusion on the future of AI.\\\"}  \",\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 409,\n    \"completion_tokens\":
+      88,\n    \"total_tokens\": 497,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f6280352b9400d5-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 22 Dec 2024 19:25:59 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1346'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999498'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_e25b377af34ef03b9a6955c9cfca5738
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CtoOCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSsQ4KEgoQY3Jld2FpLnRl
+      bGVtZXRyeRLrCQoQHzrcBLmZm6+CB9ZGtTnz1BIISnyRX3cExT4qDENyZXcgQ3JlYXRlZDABOdCK
+      UxFRlhMYQdiyWhFRlhMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogZTY0OTU3M2EyNmU1ODc5MGNhYzIxYTM3Y2Q0
+      NDQzN2FKMQoHY3Jld19pZBImCiQyYWFjYzYwZC0xYzE5LTRjZGYtYmJhNy1iM2RiMGM4YzFlZWZK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSpUFCgtjcmV3
+      X2FnZW50cxKFBQqCBVt7ImtleSI6ICIzMjgyMTdiNmMyOTU5YmRmYzQ3Y2FkMDBlODQ4OTBkMCIs
+      ICJpZCI6ICJlZmE4ZWRlNS0wN2IyLTQzOWUtYWQ4Yi1iNmQ0Nzg5NjBkNzkiLCAicm9sZSI6ICJD
+      RU8iLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjAsICJtYXhfcnBtIjogbnVsbCwg
+      ImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdh
+      dGlvbl9lbmFibGVkPyI6IHRydWUsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1h
+      eF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFsidGVzdCB0b29sIl19LCB7ImtleSI6
+      ICI5YTUwMTVlZjQ4OTVkYzYyNzhkNTQ4MThiYTQ0NmFmNyIsICJpZCI6ICIxMDE2MGEzMC0zM2U4
+      LTRlN2YtOTAzOC1lODU3Zjc2MzI0ZTUiLCAicm9sZSI6ICJTZW5pb3IgV3JpdGVyIiwgInZlcmJv
+      c2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9j
+      YWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxl
+      ZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xp
+      bWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUqDAgoKY3Jld190YXNrcxL0AQrxAVt7ImtleSI6
+      ICIwYjlkNjVkYjZiN2FlZGZiMzk4YzU5ZTJhOWY3MWVjNSIsICJpZCI6ICJiNjYyZWVkOS1kYzcy
+      LTQ1NTEtYTdmMC1kY2E4ZTk3MmU3NjciLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVt
+      YW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIkNFTyIsICJhZ2VudF9rZXkiOiAiMzI4
+      MjE3YjZjMjk1OWJkZmM0N2NhZDAwZTg0ODkwZDAiLCAidG9vbHNfbmFtZXMiOiBbInRlc3QgdG9v
+      bCJdfV16AhgBhQEAAQAAEo4CChDkOw+7vfeJwW1bc0PIIqxeEggzmQQt0SPl+ioMVGFzayBDcmVh
+      dGVkMAE5OBlxEVGWExhBwKlxEVGWExhKLgoIY3Jld19rZXkSIgogZTY0OTU3M2EyNmU1ODc5MGNh
+      YzIxYTM3Y2Q0NDQzN2FKMQoHY3Jld19pZBImCiQyYWFjYzYwZC0xYzE5LTRjZGYtYmJhNy1iM2Ri
+      MGM4YzFlZWZKLgoIdGFza19rZXkSIgogMGI5ZDY1ZGI2YjdhZWRmYjM5OGM1OWUyYTlmNzFlYzVK
+      MQoHdGFza19pZBImCiRiNjYyZWVkOS1kYzcyLTQ1NTEtYTdmMC1kY2E4ZTk3MmU3Njd6AhgBhQEA
+      AQAAEowBChDS1rm7Q+c0w96t+encwsGJEgjRF+jTQh1PCyoKVG9vbCBVc2FnZTABOaAiFGtRlhMY
+      QdiVImtRlhMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoYCgl0b29sX25hbWUSCwoJVGVz
+      dCBUb29sSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASjAEKECYGxNLnTRLCS76uAAOuzGwSCPmX
+      kSTjWKCcKgpUb29sIFVzYWdlMAE5CH3Wx1GWExhBGH/xx1GWExhKGgoOY3Jld2FpX3ZlcnNpb24S
+      CAoGMC44Ni4wShgKCXRvb2xfbmFtZRILCglUZXN0IFRvb2xKDgoIYXR0ZW1wdHMSAhgBegIYAYUB
+      AAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1885'
+      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, 22 Dec 2024 19:26:01 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
+      time CEO of a content creation agency with a Senior Writer on the team. You''re
+      now working on a new project and want to make sure the content produced is amazing.\nYour
+      personal goal is: Make sure the writers in your company produce amazing content.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
+      ''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
+      just returns the input\n\nUse the following format:\n\nThought: you should always
+      think about what to do\nAction: the action to take, only one name of [Test Tool],
+      just the name, exactly as it''s written.\nAction Input: the input to the action,
+      just a simple python dictionary, enclosed in curly braces, using \" to wrap
+      keys and values.\nObservation: the result of the action\n\nOnce all necessary
+      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
+      the final answer to the original input question"}, {"role": "user", "content":
+      "\nCurrent Task: Produce and amazing 1 paragraph draft of an article about AI
+      Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
+      article about AI.\nyou MUST return the actual complete content as the final
+      answer, not a summary.\n\nBegin! This is VERY important to you, use the tools
+      available and give your best Final Answer, your job depends on it!\n\nThought:"},
+      {"role": "assistant", "content": "I need to gather information to create an
+      amazing paragraph draft about AI Agents that aligns with the expected criteria
+      of a 4-paragraph article about AI. \n\nAction: Test Tool  \nAction Input: {\"query\":
+      \"Write a captivating and informative paragraph about AI Agents, focusing on
+      their capabilities, applications, and significance in modern technology.\"}  \nObservation:
+      Processed: Write a captivating and informative paragraph about AI Agents, focusing
+      on their capabilities, applications, and significance in modern technology."},
+      {"role": "assistant", "content": "Thought: I have received the content related
+      to AI Agents, which I need to now use as a foundation for creating a complete
+      4-paragraph article about AI. \n\nAction: Test Tool  \nAction Input: {\"query\":
+      \"Based on the previous paragraph about AI Agents, write a 4-paragraph article
+      about AI, including an introduction, discussion of AI Agents, their applications,
+      and a conclusion on the future of AI.\"}  \nObservation: Processed: Based on
+      the previous paragraph about AI Agents, write a 4-paragraph article about AI,
+      including an introduction, discussion of AI Agents, their applications, and
+      a conclusion on the future of AI."}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2820'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=vwBNilrHRgMLd8ALWzYrBO5Lm8ieJzbQ3WCVOgmuJ.s-1734895557-1.0.1.1-z.QnDsynL_Ndu.JkWrh_wGMo57vvpK88nWDBTA8P.6prlSRmA91GQLpP62yRUbCW6yoKFbDxroSaYO6qrzZPRg;
+        _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhLsNJa6GxRIHF8l8eViU7D6CyBHP\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734895559,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I have gathered the complete
+      article on AI, which aligns with the expected criteria. Now I will present the
+      final answer as required. \\n\\nFinal Answer: \\n\\nArtificial Intelligence
+      (AI) has rapidly evolved to become an integral part of our modern world, driving
+      significant advancements across various industries. AI refers to the simulation
+      of human intelligence in machines programmed to think and learn like humans.
+      This technology enables machines to analyze data, recognize patterns, and make
+      decisions with minimal human intervention, paving the way for innovation in
+      fields like healthcare, finance, and transportation.\\n\\nAI Agents, in particular,
+      embody the future of artificial intelligence by acting autonomously to perform
+      complex tasks. These agents leverage machine learning and natural language processing
+      to interact with users and understand their needs. They're deployed in customer
+      service applications, virtual assistants, and personal scheduling tools, showcasing
+      their capability to streamline processes and enhance user experience. By mimicking
+      human reasoning, AI Agents can adapt to changing situations and provide personalized
+      solutions.\\n\\nThe applications of AI Agents extend beyond mere task completion;
+      they are transforming the way businesses operate. In the realm of customer engagement,
+      AI Agents analyze customer behavior to provide insights that help companies
+      tailor their offerings. In healthcare, they assist in diagnosing illnesses by
+      analyzing patient data and suggesting treatments. The versatility of AI Agents
+      makes them invaluable assets in our increasingly automated world.\\n\\nAs we
+      look to the future, the potential of AI continues to expand. With ongoing advancements
+      in technology, AI Agents are set to become even more sophisticated, further
+      bridging the gap between humans and machines. The prospects of AI promise not
+      only to improve efficiency and productivity but also to change the way we live
+      and work, promising a future where intelligent, autonomous agents support us
+      in our daily lives.\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      546,\n    \"completion_tokens\": 343,\n    \"total_tokens\": 889,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f62803eed8100d5-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 22 Dec 2024 19:26:04 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:
+      - '4897'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999342'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_65fdf94aa8bbc10f64f2a27ccdcc5cc8
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_crew_with_delegating_agents_should_not_override_task_tools.yaml

@@ -0,0 +1,623 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
+      time CEO of a content creation agency with a Senior Writer on the team. You''re
+      now working on a new project and want to make sure the content produced is amazing.\nYour
+      personal goal is: Make sure the writers in your company produce amazing content.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
+      ''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
+      just returns the input\nTool Name: Delegate work to coworker\nTool Arguments:
+      {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
+      {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
+      {''description'': ''The role/name of the coworker to delegate to'', ''type'':
+      ''str''}}\nTool Description: Delegate a specific task to one of the following
+      coworkers: Senior Writer\nThe input to this tool should be the coworker, the
+      task you want them to do, and ALL necessary context to execute the task, they
+      know nothing about the task, so share absolute everything you know, don''t reference
+      things but instead explain them.\nTool Name: Ask question to coworker\nTool
+      Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
+      ''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
+      ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
+      ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
+      of the following coworkers: Senior Writer\nThe input to this tool should be
+      the coworker, the question you have for them, and ALL necessary context to ask
+      the question properly, they know nothing about the question, so share absolute
+      everything you know, don''t reference things but instead explain them.\n\nUse
+      the following format:\n\nThought: you should always think about what to do\nAction:
+      the action to take, only one name of [Test Tool, Delegate work to coworker,
+      Ask question to coworker], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple python dictionary, enclosed in
+      curly braces, using \" to wrap keys and values.\nObservation: the result of
+      the action\n\nOnce all necessary information is gathered:\n\nThought: I now
+      know the final answer\nFinal Answer: the final answer to the original input
+      question"}, {"role": "user", "content": "\nCurrent Task: Produce and amazing
+      1 paragraph draft of an article about AI Agents.\n\nThis is the expect criteria
+      for your final answer: A 4 paragraph article about AI.\nyou MUST return the
+      actual complete content as the final answer, not a summary.\n\nBegin! This is
+      VERY important to you, use the tools available and give your best Final Answer,
+      your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2892'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhLQELAjJpn76wiLmWBinm3sqf32l\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734893814,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I need to gather information and insights
+      to ensure the Senior Writer produces a high-quality draft about AI Agents, which
+      will then serve as a foundation for the complete article.\\n\\nAction: Ask question
+      to coworker  \\nAction Input: {\\\"question\\\":\\\"Can you provide a detailed
+      overview of what AI Agents are, their functionalities, and their applications
+      in real-world scenarios? Please include examples of how they are being used
+      in various industries, and discuss their potential impact on the future of technology
+      and society.\\\",\\\"context\\\":\\\"We are looking to create a comprehensive
+      understanding of AI Agents as part of a four-paragraph article. This will help
+      generate a high-quality draft for the article.\\\",\\\"coworker\\\":\\\"Senior
+      Writer\\\"}  \",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      604,\n    \"completion_tokens\": 138,\n    \"total_tokens\": 742,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f6255a1bf08a519-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 22 Dec 2024 18:56:56 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=rVquIlcnYXc7wMkbKG5Ii90HxfQ_ukNJjDgSHhsWb1k-1734893816-1.0.1.1-33qDl8KNWcxLAGBuPhT8FrZ6QUnEy9oOYh2Fp2hIjDnF.cQlyrgxiWcuHljTTxG_mH7eQrf1AHJ6p8sxZJZ30A;
+        path=/; expires=Sun, 22-Dec-24 19:26:56 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=xqgLJsf3h5lBKZFTADRNNUqizeChNBBFoLvWiR2WPnw-1734893816555-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '2340'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999305'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_53956b48bd1188451efc104e8a234ef4
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CrEMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSiAwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRLgCQoQg/HA64g3phKbzz/hvUtbahIIpu+Csq+uWc0qDENyZXcgQ3JlYXRlZDABOSDm
+      Uli7lBMYQcgRXFi7lBMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogZTY0OTU3M2EyNmU1ODc5MGNhYzIxYTM3Y2Q0
+      NDQzN2FKMQoHY3Jld19pZBImCiRhMWFjMTc0Ny0xMTA0LTRlZjItODZkNi02ZGRhNTFmMDlmMTdK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSooFCgtjcmV3
+      X2FnZW50cxL6BAr3BFt7ImtleSI6ICIzMjgyMTdiNmMyOTU5YmRmYzQ3Y2FkMDBlODQ4OTBkMCIs
+      ICJpZCI6ICI4YWUwNGY0Yy0wMjNiLTRkNWQtODAwZC02ZjlkMWFmMWExOTkiLCAicm9sZSI6ICJD
+      RU8iLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjAsICJtYXhfcnBtIjogbnVsbCwg
+      ImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdh
+      dGlvbl9lbmFibGVkPyI6IHRydWUsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1h
+      eF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiOWE1MDE1ZWY0
+      ODk1ZGM2Mjc4ZDU0ODE4YmE0NDZhZjciLCAiaWQiOiAiNDg2MWQ4YTMtMjMxYS00Mzc5LTk2ZmEt
+      MWQwZmQyZDI1MGYxIiwgInJvbGUiOiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJib3NlPyI6IGZhbHNl
+      LCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0i
+      OiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2Us
+      ICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0
+      b29sc19uYW1lcyI6IFtdfV1KgwIKCmNyZXdfdGFza3MS9AEK8QFbeyJrZXkiOiAiMGI5ZDY1ZGI2
+      YjdhZWRmYjM5OGM1OWUyYTlmNzFlYzUiLCAiaWQiOiAiY2IyMmIxMzctZTA3ZC00NDA5LWI5NmMt
+      ZWQ2ZDU3MjFhNDNiIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6
+      IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJDRU8iLCAiYWdlbnRfa2V5IjogIjMyODIxN2I2YzI5NTli
+      ZGZjNDdjYWQwMGU4NDg5MGQwIiwgInRvb2xzX25hbWVzIjogWyJ0ZXN0IHRvb2wiXX1degIYAYUB
+      AAEAABKOAgoQB7Z9AEDI9OTStHqguBSbLxIIj9dttVFJs9cqDFRhc2sgQ3JlYXRlZDABOYDae1i7
+      lBMYQeBHfFi7lBMYSi4KCGNyZXdfa2V5EiIKIGU2NDk1NzNhMjZlNTg3OTBjYWMyMWEzN2NkNDQ0
+      MzdhSjEKB2NyZXdfaWQSJgokYTFhYzE3NDctMTEwNC00ZWYyLTg2ZDYtNmRkYTUxZjA5ZjE3Si4K
+      CHRhc2tfa2V5EiIKIDBiOWQ2NWRiNmI3YWVkZmIzOThjNTllMmE5ZjcxZWM1SjEKB3Rhc2tfaWQS
+      JgokY2IyMmIxMzctZTA3ZC00NDA5LWI5NmMtZWQ2ZDU3MjFhNDNiegIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1588'
+      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, 22 Dec 2024 18:56:59 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Senior Writer. You''re
+      a senior writer, specialized in technology, software engineering, AI and startups.
+      You work as a freelancer and are now working on writing content for a new customer.\nYour
+      personal goal is: Write the best content about AI and AI agents.\nTo give my
+      best complete final answer to the task use the exact following format:\n\nThought:
+      I now can give a great answer\nFinal Answer: Your final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent
+      Task: Can you provide a detailed overview of what AI Agents are, their functionalities,
+      and their applications in real-world scenarios? Please include examples of how
+      they are being used in various industries, and discuss their potential impact
+      on the future of technology and society.\n\nThis is the expect criteria for
+      your final answer: Your best answer to your coworker asking you this, accounting
+      for the context shared.\nyou MUST return the actual complete content as the
+      final answer, not a summary.\n\nThis is the context you''re working with:\nWe
+      are looking to create a comprehensive understanding of AI Agents as part of
+      a four-paragraph article. This will help generate a high-quality draft for the
+      article.\n\nBegin! This is VERY important to you, use the tools available and
+      give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1572'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rVquIlcnYXc7wMkbKG5Ii90HxfQ_ukNJjDgSHhsWb1k-1734893816-1.0.1.1-33qDl8KNWcxLAGBuPhT8FrZ6QUnEy9oOYh2Fp2hIjDnF.cQlyrgxiWcuHljTTxG_mH7eQrf1AHJ6p8sxZJZ30A;
+        _cfuvid=xqgLJsf3h5lBKZFTADRNNUqizeChNBBFoLvWiR2WPnw-1734893816555-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhLQG5ubl99yeBYm6TTV0sodagMND\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734893816,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: \\n\\n**Overview of AI Agents**  \\nAI agents are advanced software
+      systems designed to autonomously perform tasks, make decisions, and learn from
+      their environments without needing constant human intervention. They leverage
+      machine learning, natural language processing, and various AI techniques to
+      simulate human-like understanding and autonomy. These agents can be categorized
+      into three types: reactive agents (which operate purely based on their environment),
+      deliberative agents (which can make decisions based on reasoning), and hybrid
+      agents that incorporate aspects of both types. Their ability to adapt and learn
+      over time makes them instrumental in automating processes across various domains.\\n\\n**Functionalities
+      of AI Agents**  \\nThe core functionalities of AI agents include perception,
+      action, learning, and interaction. They perceive data through sensors or data
+      feeds, process information through algorithms, and take actions based on this
+      data. Machine learning allows them to refine their performance over time by
+      analyzing outcomes and adjusting their strategies accordingly. Interaction capabilities
+      enable them to communicate with users, providing insights, answering queries,
+      or even negotiating in some cases. These functionalities make AI agents invaluable
+      for tasks such as predictive analytics, personal assistance, and real-time decision-making
+      in complex systems.\\n\\n**Applications in Various Industries**  \\nAI agents
+      are already being utilized across multiple industries, demonstrating their versatility
+      and efficiency. In healthcare, AI agents assist in diagnostics by analyzing
+      medical records and suggesting treatment plans tailored to individual patients.
+      In finance, they power robo-advisors that manage investment portfolios, automate
+      trading strategies, and provide financial advice based on real-time market analysis.
+      Furthermore, in customer service, AI chatbots serve as virtual assistants, enhancing
+      user experience by providing instant support and resolving queries without human
+      intervention. The logistics and supply chain industries have also seen AI agents
+      optimize inventory management and route planning, significantly improving operational
+      efficiency.\\n\\n**Future Impact on Technology and Society**  \\nThe ongoing
+      development of AI agents is poised to have a profound impact on technology and
+      society. As these agents become more sophisticated, we can anticipate a shift
+      towards increased automation in both professional and personal spheres, leading
+      to enhanced productivity and new business models. However, this automation introduces
+      challenges such as job displacement and ethical considerations regarding decision-making
+      by AI. It is essential to foster an ongoing dialogue on the implications of
+      AI agents to ensure responsible development and integration into our daily lives.
+      As AI agents continue to evolve, they will undoubtedly play a pivotal role in
+      shaping the future of technology and its intersection with societal dynamics,
+      making it critical for us to engage thoughtfully with this emerging paradigm.\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 289,\n    \"completion_tokens\":
+      506,\n    \"total_tokens\": 795,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f6255b1f832a519-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 22 Dec 2024 18:57:04 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:
+      - '7836'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999630'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_c14268346d6ce72ceea4b1472f73c5ae
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CtsBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSsgEKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKbAQoQ7U/1ZgBSTkCXtesUNPA2URIIrnRWFVT58Z8qClRvb2wgVXNhZ2UwATl4lN3i
+      vZQTGEGgevzivZQTGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKJwoJdG9vbF9uYW1lEhoK
+      GEFzayBxdWVzdGlvbiB0byBjb3dvcmtlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '222'
+      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, 22 Dec 2024 18:57:09 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
+      time CEO of a content creation agency with a Senior Writer on the team. You''re
+      now working on a new project and want to make sure the content produced is amazing.\nYour
+      personal goal is: Make sure the writers in your company produce amazing content.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
+      ''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
+      just returns the input\nTool Name: Delegate work to coworker\nTool Arguments:
+      {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
+      {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
+      {''description'': ''The role/name of the coworker to delegate to'', ''type'':
+      ''str''}}\nTool Description: Delegate a specific task to one of the following
+      coworkers: Senior Writer\nThe input to this tool should be the coworker, the
+      task you want them to do, and ALL necessary context to execute the task, they
+      know nothing about the task, so share absolute everything you know, don''t reference
+      things but instead explain them.\nTool Name: Ask question to coworker\nTool
+      Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
+      ''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
+      ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
+      ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
+      of the following coworkers: Senior Writer\nThe input to this tool should be
+      the coworker, the question you have for them, and ALL necessary context to ask
+      the question properly, they know nothing about the question, so share absolute
+      everything you know, don''t reference things but instead explain them.\n\nUse
+      the following format:\n\nThought: you should always think about what to do\nAction:
+      the action to take, only one name of [Test Tool, Delegate work to coworker,
+      Ask question to coworker], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple python dictionary, enclosed in
+      curly braces, using \" to wrap keys and values.\nObservation: the result of
+      the action\n\nOnce all necessary information is gathered:\n\nThought: I now
+      know the final answer\nFinal Answer: the final answer to the original input
+      question"}, {"role": "user", "content": "\nCurrent Task: Produce and amazing
+      1 paragraph draft of an article about AI Agents.\n\nThis is the expect criteria
+      for your final answer: A 4 paragraph article about AI.\nyou MUST return the
+      actual complete content as the final answer, not a summary.\n\nBegin! This is
+      VERY important to you, use the tools available and give your best Final Answer,
+      your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I need
+      to gather information and insights to ensure the Senior Writer produces a high-quality
+      draft about AI Agents, which will then serve as a foundation for the complete
+      article.\n\nAction: Ask question to coworker  \nAction Input: {\"question\":\"Can
+      you provide a detailed overview of what AI Agents are, their functionalities,
+      and their applications in real-world scenarios? Please include examples of how
+      they are being used in various industries, and discuss their potential impact
+      on the future of technology and society.\",\"context\":\"We are looking to create
+      a comprehensive understanding of AI Agents as part of a four-paragraph article.
+      This will help generate a high-quality draft for the article.\",\"coworker\":\"Senior
+      Writer\"}  \nObservation: **Overview of AI Agents**  \nAI agents are advanced
+      software systems designed to autonomously perform tasks, make decisions, and
+      learn from their environments without needing constant human intervention. They
+      leverage machine learning, natural language processing, and various AI techniques
+      to simulate human-like understanding and autonomy. These agents can be categorized
+      into three types: reactive agents (which operate purely based on their environment),
+      deliberative agents (which can make decisions based on reasoning), and hybrid
+      agents that incorporate aspects of both types. Their ability to adapt and learn
+      over time makes them instrumental in automating processes across various domains.\n\n**Functionalities
+      of AI Agents**  \nThe core functionalities of AI agents include perception,
+      action, learning, and interaction. They perceive data through sensors or data
+      feeds, process information through algorithms, and take actions based on this
+      data. Machine learning allows them to refine their performance over time by
+      analyzing outcomes and adjusting their strategies accordingly. Interaction capabilities
+      enable them to communicate with users, providing insights, answering queries,
+      or even negotiating in some cases. These functionalities make AI agents invaluable
+      for tasks such as predictive analytics, personal assistance, and real-time decision-making
+      in complex systems.\n\n**Applications in Various Industries**  \nAI agents are
+      already being utilized across multiple industries, demonstrating their versatility
+      and efficiency. In healthcare, AI agents assist in diagnostics by analyzing
+      medical records and suggesting treatment plans tailored to individual patients.
+      In finance, they power robo-advisors that manage investment portfolios, automate
+      trading strategies, and provide financial advice based on real-time market analysis.
+      Furthermore, in customer service, AI chatbots serve as virtual assistants, enhancing
+      user experience by providing instant support and resolving queries without human
+      intervention. The logistics and supply chain industries have also seen AI agents
+      optimize inventory management and route planning, significantly improving operational
+      efficiency.\n\n**Future Impact on Technology and Society**  \nThe ongoing development
+      of AI agents is poised to have a profound impact on technology and society.
+      As these agents become more sophisticated, we can anticipate a shift towards
+      increased automation in both professional and personal spheres, leading to enhanced
+      productivity and new business models. However, this automation introduces challenges
+      such as job displacement and ethical considerations regarding decision-making
+      by AI. It is essential to foster an ongoing dialogue on the implications of
+      AI agents to ensure responsible development and integration into our daily lives.
+      As AI agents continue to evolve, they will undoubtedly play a pivotal role in
+      shaping the future of technology and its intersection with societal dynamics,
+      making it critical for us to engage thoughtfully with this emerging paradigm."}],
+      "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '6755'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rVquIlcnYXc7wMkbKG5Ii90HxfQ_ukNJjDgSHhsWb1k-1734893816-1.0.1.1-33qDl8KNWcxLAGBuPhT8FrZ6QUnEy9oOYh2Fp2hIjDnF.cQlyrgxiWcuHljTTxG_mH7eQrf1AHJ6p8sxZJZ30A;
+        _cfuvid=xqgLJsf3h5lBKZFTADRNNUqizeChNBBFoLvWiR2WPnw-1734893816555-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhLQOmLKuevpaWtRyyhHjHVYqvNVk\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734893824,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I have received a comprehensive
+      overview from the Senior Writer that includes the necessary information about
+      AI Agents, their functionalities, applications, and future implications. Now,
+      I can compile this into a final answer following the specified format: a complete
+      four-paragraph article.\\n\\nFinal Answer: \\n\\n**Overview of AI Agents**  \\nAI
+      agents are advanced software systems designed to autonomously perform tasks,
+      make decisions, and learn from their environments without needing constant human
+      intervention. They leverage machine learning, natural language processing, and
+      various AI techniques to simulate human-like understanding and autonomy. These
+      agents can be categorized into three types: reactive agents (which operate purely
+      based on their environment), deliberative agents (which can make decisions based
+      on reasoning), and hybrid agents that incorporate aspects of both types. Their
+      ability to adapt and learn over time makes them instrumental in automating processes
+      across various domains.\\n\\n**Functionalities of AI Agents**  \\nThe core functionalities
+      of AI agents include perception, action, learning, and interaction. They perceive
+      data through sensors or data feeds, process information through algorithms,
+      and take actions based on this data. Machine learning allows them to refine
+      their performance over time by analyzing outcomes and adjusting their strategies
+      accordingly. Interaction capabilities enable them to communicate with users,
+      providing insights, answering queries, or even negotiating in some cases. These
+      functionalities make AI agents invaluable for tasks such as predictive analytics,
+      personal assistance, and real-time decision-making in complex systems.\\n\\n**Applications
+      in Various Industries**  \\nAI agents are already being utilized across multiple
+      industries, demonstrating their versatility and efficiency. In healthcare, AI
+      agents assist in diagnostics by analyzing medical records and suggesting treatment
+      plans tailored to individual patients. In finance, they power robo-advisors
+      that manage investment portfolios, automate trading strategies, and provide
+      financial advice based on real-time market analysis. Furthermore, in customer
+      service, AI chatbots serve as virtual assistants, enhancing user experience
+      by providing instant support and resolving queries without human intervention.
+      The logistics and supply chain industries have also seen AI agents optimize
+      inventory management and route planning, significantly improving operational
+      efficiency.\\n\\n**Future Impact on Technology and Society**  \\nThe ongoing
+      development of AI agents is poised to have a profound impact on technology and
+      society. As these agents become more sophisticated, we can anticipate a shift
+      towards increased automation in both professional and personal spheres, leading
+      to enhanced productivity and new business models. However, this automation introduces
+      challenges such as job displacement and ethical considerations regarding decision-making
+      by AI. It is essential to foster an ongoing dialogue on the implications of
+      AI agents to ensure responsible development and integration into our daily lives.
+      As AI agents continue to evolve, they will undoubtedly play a pivotal role in
+      shaping the future of technology and its intersection with societal dynamics,
+      making it critical for us to engage thoughtfully with this emerging paradigm.\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 1242,\n    \"completion_tokens\":
+      550,\n    \"total_tokens\": 1792,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f6255e49b37a519-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 22 Dec 2024 18:57:12 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:
+      - '7562'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149998353'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_a812bbb85b3d785660c4662212614ab9
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_llm_call_with_ollama_gemma.yaml

@@ -1,35 +0,0 @@
-interactions:
-- request:
-    body: '{"model": "gemma2:latest", "prompt": "### User:\nRespond in 20 words. Who
-      are you?\n\n", "options": {"num_predict": 30, "temperature": 0.7}, "stream":
-      false}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '157'
-      Content-Type:
-      - application/json
-      User-Agent:
-      - python-requests/2.31.0
-    method: POST
-    uri: http://localhost:8080/api/generate
-  response:
-    body:
-      string: '{"model":"gemma2:latest","created_at":"2024-09-24T21:57:52.329049Z","response":"I
-        am Gemma, an open-weights AI assistant trained by Google DeepMind.  \n","done":true,"done_reason":"stop","context":[106,1645,108,6176,4926,235292,108,54657,575,235248,235284,235276,3907,235265,7702,708,692,235336,109,107,108,106,2516,108,235285,1144,137061,235269,671,2174,235290,30316,16481,20409,17363,731,6238,20555,35777,235265,139,108],"total_duration":991843667,"load_duration":31664750,"prompt_eval_count":25,"prompt_eval_duration":51409000,"eval_count":19,"eval_duration":908132000}'
-    headers:
-      Content-Length:
-      - '572'
-      Content-Type:
-      - application/json; charset=utf-8
-      Date:
-      - Tue, 24 Sep 2024 21:57:52 GMT
-    status:
-      code: 200
-      message: OK
-version: 1

tests/cassettes/test_llm_call_with_ollama_llama3.yaml

@@ -0,0 +1,36 @@
+interactions:
+- request:
+    body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Which
+      model are you??\n\n", "options": {"num_predict": 30, "temperature": 0.7}, "stream":
+      false}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '164'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - python-requests/2.32.3
+    method: POST
+    uri: http://localhost:11434/api/generate
+  response:
+    body:
+      string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:24:24.812595Z","response":"I''m
+        an AI, specifically a large language model, designed to understand and respond
+        to user queries with accuracy.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,16299,1646,527,499,71291,128009,128006,78191,128007,271,40,2846,459,15592,11,11951,264,3544,4221,1646,11,6319,311,3619,323,6013,311,1217,20126,449,13708,13],"total_duration":827817584,"load_duration":41560542,"prompt_eval_count":39,"prompt_eval_duration":384000000,"eval_count":23,"eval_duration":400000000}'
+    headers:
+      Content-Length:
+      - '683'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Thu, 02 Jan 2025 20:24:24 GMT
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_multimodal_agent_live_image_analysis.yaml

@@ -0,0 +1,481 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Image Analyst. You''re
+      an expert at visual analysis, trained to notice and describe details in images.\nYour
+      personal goal is: Analyze images with high attention to detail\nYou ONLY have
+      access to the following tools, and should NEVER make up tools that are not listed
+      here:\n\nTool Name: Add image to content\nTool Arguments: {''image_url'': {''description'':
+      ''The URL or path of the image to add'', ''type'': ''str''}, ''action'': {''description'':
+      ''Optional context or question about the image'', ''type'': ''str''}}\nTool
+      Description: See image to understand it''s content, you can optionally ask a
+      question about the image\n\nUse the following format:\n\nThought: you should
+      always think about what to do\nAction: the action to take, only one name of
+      [Add image to content], just the name, exactly as it''s written.\nAction Input:
+      the input to the action, just a simple python dictionary, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce
+      all necessary information is gathered:\n\nThought: I now know the final answer\nFinal
+      Answer: the final answer to the original input question"}, {"role": "user",
+      "content": "\nCurrent Task: \n        Analyze the provided image and describe
+      what you see in detail.\n        Focus on main elements, colors, composition,
+      and any notable details.\n        Image: https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=\n        \n\nThis
+      is the expect criteria for your final answer: A comprehensive description of
+      the image contents.\nyou MUST return the actual complete content as the final
+      answer, not a summary.\n\nBegin! This is VERY important to you, use the tools
+      available and give your best Final Answer, your job depends on it!\n\nThought:"}],
+      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1948'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AiuIfzzcje5KdvKIG5CkFeORroiKk\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735266213,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Action: Add image to content\\nAction
+      Input: {\\\"image_url\\\": \\\"https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=\\\",
+      \\\"action\\\": \\\"Analyze the provided image and describe what you see in
+      detail.\\\"}\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      417,\n    \"completion_tokens\": 103,\n    \"total_tokens\": 520,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_5f20662549\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f85d96b280df217-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 02:23:35 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=kJ1pw1xjCMSxjHSS8iJC5z_j2PZxl.i387KCpj9xNZU-1735266215-1.0.1.1-Ybg0wVTsrBlpVZmtQyA1ullY8m3v2Ix0N_SYlhr9z7zKfbLeqGZEVL37YSY.dvIiLVY3XPZzMtG8Xwo6UucW6A;
+        path=/; expires=Fri, 27-Dec-24 02:53:35 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=v_wJZ5m7qCjrnRfks0gT2GAk9yR14BdIDAQiQR7xxI8-1735266215000-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1212'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999539'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_663a2b18099a18361d6b02befc175289
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      Co4LCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS5QoKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKjBwoQHmzzumMNXHOgpJ4zCIxJSxII72WnLlLfRyYqDENyZXcgQ3JlYXRlZDABOQjB
+      gFxt5xQYQYhMiVxt5xQYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogZTM5NTY3YjUwNTI5MDljYTMzNDA5ODRiODM4
+      OTgwZWFKMQoHY3Jld19pZBImCiQ4MDA0YTA1NC0zYjNkLTQ4OGEtYTlkNC1kZWQzMDVhMDIxY2FK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSs4CCgtjcmV3
+      X2FnZW50cxK+Agq7Alt7ImtleSI6ICI5ZGM4Y2NlMDMwNDY4MTk2MDQxYjRjMzgwYjYxN2NiMCIs
+      ICJpZCI6ICJjNTZhZGI2Mi1lMGIwLTQzYzAtYmQ4OC0xYzEwYTNhNmU5NDQiLCAicm9sZSI6ICJJ
+      bWFnZSBBbmFseXN0IiwgInZlcmJvc2U/IjogdHJ1ZSwgIm1heF9pdGVyIjogMjAsICJtYXhfcnBt
+      IjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvIiwgImRl
+      bGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNl
+      LCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUqCAgoKY3Jld190YXNr
+      cxLzAQrwAVt7ImtleSI6ICJhOWE3NmNhNjk1N2QwYmZmYTY5ZWFiMjBiNjY0ODIyYiIsICJpZCI6
+      ICJhNzFiZDllNC0wNzdkLTRmMTQtODg0MS03MGMwZWM4MGZkMmMiLCAiYXN5bmNfZXhlY3V0aW9u
+      PyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIkltYWdlIEFu
+      YWx5c3QiLCAiYWdlbnRfa2V5IjogIjlkYzhjY2UwMzA0NjgxOTYwNDFiNGMzODBiNjE3Y2IwIiwg
+      InRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEOZ5pMdq9ep85DrP1Vv8Y8MSCE7ahOkm
+      2IDHKgxUYXNrIENyZWF0ZWQwATlIg85cbecUGEGQ9M5cbecUGEouCghjcmV3X2tleRIiCiBlMzk1
+      NjdiNTA1MjkwOWNhMzM0MDk4NGI4Mzg5ODBlYUoxCgdjcmV3X2lkEiYKJDgwMDRhMDU0LTNiM2Qt
+      NDg4YS1hOWQ0LWRlZDMwNWEwMjFjYUouCgh0YXNrX2tleRIiCiBhOWE3NmNhNjk1N2QwYmZmYTY5
+      ZWFiMjBiNjY0ODIyYkoxCgd0YXNrX2lkEiYKJGE3MWJkOWU0LTA3N2QtNGYxNC04ODQxLTcwYzBl
+      YzgwZmQyY3oCGAGFAQABAAASlwEKECyaQQK8JkKLh6S2mWHTeDgSCPWCpr7v9CQZKgpUb29sIFVz
+      YWdlMAE5MLyst23nFBhBOJy/t23nFBhKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC44Ni4wSiMKCXRv
+      b2xfbmFtZRIWChRBZGQgaW1hZ2UgdG8gY29udGVudEoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1425'
+      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:
+      - Fri, 27 Dec 2024 02:23:39 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Image Analyst. You''re
+      an expert at visual analysis, trained to notice and describe details in images.\nYour
+      personal goal is: Analyze images with high attention to detail\nYou ONLY have
+      access to the following tools, and should NEVER make up tools that are not listed
+      here:\n\nTool Name: Add image to content\nTool Arguments: {''image_url'': {''description'':
+      ''The URL or path of the image to add'', ''type'': ''str''}, ''action'': {''description'':
+      ''Optional context or question about the image'', ''type'': ''str''}}\nTool
+      Description: See image to understand it''s content, you can optionally ask a
+      question about the image\n\nUse the following format:\n\nThought: you should
+      always think about what to do\nAction: the action to take, only one name of
+      [Add image to content], just the name, exactly as it''s written.\nAction Input:
+      the input to the action, just a simple python dictionary, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce
+      all necessary information is gathered:\n\nThought: I now know the final answer\nFinal
+      Answer: the final answer to the original input question"}, {"role": "user",
+      "content": "\nCurrent Task: \n        Analyze the provided image and describe
+      what you see in detail.\n        Focus on main elements, colors, composition,
+      and any notable details.\n        Image: https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=\n        \n\nThis
+      is the expect criteria for your final answer: A comprehensive description of
+      the image contents.\nyou MUST return the actual complete content as the final
+      answer, not a summary.\n\nBegin! This is VERY important to you, use the tools
+      available and give your best Final Answer, your job depends on it!\n\nThought:"},
+      {"role": "user", "content": [{"type": "text", "text": "Analyze the provided
+      image and describe what you see in detail."}, {"type": "image_url", "image_url":
+      {"url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k="}}]}],
+      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2279'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=kJ1pw1xjCMSxjHSS8iJC5z_j2PZxl.i387KCpj9xNZU-1735266215-1.0.1.1-Ybg0wVTsrBlpVZmtQyA1ullY8m3v2Ix0N_SYlhr9z7zKfbLeqGZEVL37YSY.dvIiLVY3XPZzMtG8Xwo6UucW6A;
+        _cfuvid=v_wJZ5m7qCjrnRfks0gT2GAk9yR14BdIDAQiQR7xxI8-1735266215000-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AiuIiqT33ROFMdw1gNmqH9jiw6PfF\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735266216,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The image is an aerial view of Lower
+      Manhattan in New York City. \\n\\nMain Elements:\\n- The One World Trade Center
+      tower stands prominently, distinguishable by its sleek, tapering structure reaching
+      into the sky, surrounded by other skyscrapers.\\n- Skyscrapers in varying heights
+      and architectural styles, fill the densely packed urban landscape.\\n- A waterfront
+      is visible at the edges, with docks and piers extending into the water.\\n\\nColors:\\n-
+      The buildings exhibit a mix of colors, predominantly grays, whites, and browns,
+      against the blues of the sky and water.\\n- There's a section of greenery visible,
+      likely a park or recreational space, offering a contrast with its vibrant green
+      hues.\\n\\nComposition:\\n- The angle of the photograph showcases the expanse
+      of the city, highlighting the density and scale of the buildings.\\n- Water
+      borders the city on two prominent sides, creating a natural boundary and enhancing
+      the island's urban island feel.\\n\\nNotable Details:\\n- The image captures
+      the iconic layout of Manhattan, with the surrounding Hudson River and New York
+      Harbor visible in the background.\\n- Beyond Lower Manhattan, more of the cityscape
+      stretches into the distance, illustrating the vastness of New York City.\\n-
+      The day appears clear and sunny, with shadows casting from the buildings, indicating
+      time in the morning or late afternoon.\\n\\nOverall, the image is a striking
+      depiction of the dynamic and bustling environment of New York's Lower Manhattan,
+      encapsulating its urban character and proximity to the water.\",\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 858,\n    \"completion_tokens\":
+      295,\n    \"total_tokens\": 1153,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_5f20662549\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f85d9741d0cf217-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 02:23:40 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '5136'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-input-images:
+      - '50000'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-input-images:
+      - '49999'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29998756'
+      x-ratelimit-reset-input-images:
+      - 1ms
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 2ms
+      x-request-id:
+      - req_57a7430712d4ff4a81f600ffb94d3b6e
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Image Analyst. You''re
+      an expert at visual analysis, trained to notice and describe details in images.\nYour
+      personal goal is: Analyze images with high attention to detail\nYou ONLY have
+      access to the following tools, and should NEVER make up tools that are not listed
+      here:\n\nTool Name: Add image to content\nTool Arguments: {''image_url'': {''description'':
+      ''The URL or path of the image to add'', ''type'': ''str''}, ''action'': {''description'':
+      ''Optional context or question about the image'', ''type'': ''str''}}\nTool
+      Description: See image to understand it''s content, you can optionally ask a
+      question about the image\n\nUse the following format:\n\nThought: you should
+      always think about what to do\nAction: the action to take, only one name of
+      [Add image to content], just the name, exactly as it''s written.\nAction Input:
+      the input to the action, just a simple python dictionary, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce
+      all necessary information is gathered:\n\nThought: I now know the final answer\nFinal
+      Answer: the final answer to the original input question"}, {"role": "user",
+      "content": "\nCurrent Task: \n        Analyze the provided image and describe
+      what you see in detail.\n        Focus on main elements, colors, composition,
+      and any notable details.\n        Image: https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=\n        \n\nThis
+      is the expect criteria for your final answer: A comprehensive description of
+      the image contents.\nyou MUST return the actual complete content as the final
+      answer, not a summary.\n\nBegin! This is VERY important to you, use the tools
+      available and give your best Final Answer, your job depends on it!\n\nThought:"},
+      {"role": "user", "content": [{"type": "text", "text": "Analyze the provided
+      image and describe what you see in detail."}, {"type": "image_url", "image_url":
+      {"url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k="}}]},
+      {"role": "user", "content": "I did it wrong. Invalid Format: I missed the ''Action:''
+      after ''Thought:''. I will do right next, and don''t use a tool I have already
+      used.\n\nIf you don''t need to use any more tools, you must give your best complete
+      final answer, make sure it satisfies the expected criteria, use the EXACT format
+      below:\n\nThought: I now can give a great answer\nFinal Answer: my best complete
+      final answer to the task.\n\n"}], "model": "gpt-4o", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2717'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=kJ1pw1xjCMSxjHSS8iJC5z_j2PZxl.i387KCpj9xNZU-1735266215-1.0.1.1-Ybg0wVTsrBlpVZmtQyA1ullY8m3v2Ix0N_SYlhr9z7zKfbLeqGZEVL37YSY.dvIiLVY3XPZzMtG8Xwo6UucW6A;
+        _cfuvid=v_wJZ5m7qCjrnRfks0gT2GAk9yR14BdIDAQiQR7xxI8-1735266215000-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AiuInuYNldaQVo6B1EsEquT1VFMN7\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735266221,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+      Answer: The image is an aerial view of Lower Manhattan in New York City. The
+      photograph prominently features the cluster of skyscrapers that characterizes
+      the area, with One World Trade Center standing out as a particularly tall and
+      iconic structure. The buildings vary in color, with shades of glassy blue, grey,
+      and natural stone dominating the skyline. In the bottom part of the image, there
+      is a green space, likely Battery Park, providing a stark contrast to the dense
+      urban environment, with trees and pathways visible. The water surrounding Manhattan
+      is a deep blue, and several piers jut into the harbor. The Hudson River is visible
+      on the left, and the East River can be seen on the right, framing the island.
+      The overall composition captures the bustling and vibrant nature of New York\u2019s
+      financial hub, with bright sunlight illuminating the buildings, casting sharp
+      shadows and enhancing the depth of the cityscape. The sky is clear, suggesting
+      a sunny day with good visibility.\",\n        \"refusal\": null\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 952,\n    \"completion_tokens\": 203,\n
+      \   \"total_tokens\": 1155,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_5f20662549\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f85d995ad1ef217-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 02:23:43 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '3108'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-input-images:
+      - '50000'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-input-images:
+      - '49999'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29998656'
+      x-ratelimit-reset-input-images:
+      - 1ms
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 2ms
+      x-request-id:
+      - req_45f0e3d457a18f973a59074d16f137b6
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_task_tools_override_agent_tools.yaml

@@ -0,0 +1,569 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
+      an expert researcher, specialized in technology, software engineering, AI and
+      startups. You work as a freelancer and is now working on doing research and
+      analysis for a new customer.\nYour personal goal is: Make the best research
+      and analysis on content about AI and AI agents\nYou ONLY have access to the
+      following tools, and should NEVER make up tools that are not listed here:\n\nTool
+      Name: Test Tool\nTool Arguments: {''query'': {''description'': ''Query to process'',
+      ''type'': ''str''}}\nTool Description: A test tool that just returns the input\n\nUse
+      the following format:\n\nThought: you should always think about what to do\nAction:
+      the action to take, only one name of [Test Tool], just the name, exactly as
+      it''s written.\nAction Input: the input to the action, just a simple python
+      dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
+      the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question"}, {"role": "user", "content": "\nCurrent Task: Write a test
+      task\n\nThis is the expect 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-4o-mini", "stop":
+      ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1536'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhQfznhDMtsr58XvTuRDZoB1kxwfK\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734914011,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I need to come up with a suitable test
+      task that meets the criteria provided. I will focus on outlining a clear and
+      effective test task related to AI and AI agents.\\n\\nAction: Test Tool\\nAction
+      Input: {\\\"query\\\": \\\"Create a test task that involves evaluating the performance
+      of an AI agent in a given scenario, including criteria for success, tools required,
+      and process for assessment.\\\"}\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      298,\n    \"completion_tokens\": 78,\n    \"total_tokens\": 376,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_d02d531b47\"\n}\n"
+    headers:
+      CF-RAY:
+      - 8f6442b868fda486-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 23 Dec 2024 00:33:32 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=i6jvNjhsDne300GPAeEmyiJJKYqy7OPuamFG_kht3KE-1734914012-1.0.1.1-tCeVANAF521vkXpBdgYw.ov.fYUr6t5QC4LG_DugWyzu4C60Pi2CruTVniUgfCvkcu6rdHA5DwnaEZf2jFaRCQ;
+        path=/; expires=Mon, 23-Dec-24 01:03:32 GMT; 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:
+      - '1400'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999642'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_c3e50e9ca9dc22de5572692e1a9c0f16
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CrBzCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSh3MKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRLUCwoQEr8cFisEEEEUtXBvovq6lhIIYdkQ+ekBh3wqDENyZXcgQ3JlYXRlZDABOThc
+      YLAZpxMYQfCuabAZpxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogZGUxMDFkODU1M2VhMDI0NTM3YTA4ZjgxMmVl
+      NmI3NGFKMQoHY3Jld19pZBImCiRmNTc2MjViZC1jZmY3LTRlNGMtYWM1Zi0xZWFiNjQyMzJjMmRK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAkobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSpIFCgtjcmV3
+      X2FnZW50cxKCBQr/BFt7ImtleSI6ICI4YmQyMTM5YjU5NzUxODE1MDZlNDFmZDljNDU2M2Q3NSIs
+      ICJpZCI6ICI1Y2Y0OWVjNy05NWYzLTRkZDctODU3Mi1mODAwNDA4NjBiMjgiLCAicm9sZSI6ICJS
+      ZXNlYXJjaGVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6
+      IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwg
+      ImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZh
+      bHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICI5
+      YTUwMTVlZjQ4OTVkYzYyNzhkNTQ4MThiYTQ0NmFmNyIsICJpZCI6ICI0MTEyM2QzZC01NmEwLTRh
+      NTgtYTljNi1mZjUwNjRmZjNmNTEiLCAicm9sZSI6ICJTZW5pb3IgV3JpdGVyIiwgInZlcmJvc2U/
+      IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxs
+      aW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8i
+      OiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0
+      IjogMiwgInRvb2xzX25hbWVzIjogW119XUrvAwoKY3Jld190YXNrcxLgAwrdA1t7ImtleSI6ICI5
+      NDRhZWYwYmFjODQwZjFjMjdiZDgzYTkzN2JjMzYxYiIsICJpZCI6ICI3ZDM2NDFhNi1hZmM4LTRj
+      NmMtYjkzMy0wNGZlZjY2NjUxN2MiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5f
+      aW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIlJlc2VhcmNoZXIiLCAiYWdlbnRfa2V5Ijog
+      IjhiZDIxMzliNTk3NTE4MTUwNmU0MWZkOWM0NTYzZDc1IiwgInRvb2xzX25hbWVzIjogW119LCB7
+      ImtleSI6ICI5ZjJkNGU5M2FiNTkwYzcyNTg4NzAyNzUwOGFmOTI3OCIsICJpZCI6ICIzNTVjZjFh
+      OS1lOTkzLTQxMTQtOWM0NC0yZDM5MDlhMDljNWYiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNl
+      LCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIlNlbmlvciBXcml0ZXIiLCAi
+      YWdlbnRfa2V5IjogIjlhNTAxNWVmNDg5NWRjNjI3OGQ1NDgxOGJhNDQ2YWY3IiwgInRvb2xzX25h
+      bWVzIjogW119XXoCGAGFAQABAAASjgIKEHbV3nDt+ndNQNix1f+5+cASCL+l6KV3+FEpKgxUYXNr
+      IENyZWF0ZWQwATmgfo+wGacTGEEQE5CwGacTGEouCghjcmV3X2tleRIiCiBkZTEwMWQ4NTUzZWEw
+      MjQ1MzdhMDhmODEyZWU2Yjc0YUoxCgdjcmV3X2lkEiYKJGY1NzYyNWJkLWNmZjctNGU0Yy1hYzVm
+      LTFlYWI2NDIzMmMyZEouCgh0YXNrX2tleRIiCiA5NDRhZWYwYmFjODQwZjFjMjdiZDgzYTkzN2Jj
+      MzYxYkoxCgd0YXNrX2lkEiYKJDdkMzY0MWE2LWFmYzgtNGM2Yy1iOTMzLTA0ZmVmNjY2NTE3Y3oC
+      GAGFAQABAAASjgIKECqDENVoAz+3ybVKR/wz7dMSCKI9ILLFYx8SKgxUYXNrIENyZWF0ZWQwATng
+      63CzGacTGEE4AXKzGacTGEouCghjcmV3X2tleRIiCiBkZTEwMWQ4NTUzZWEwMjQ1MzdhMDhmODEy
+      ZWU2Yjc0YUoxCgdjcmV3X2lkEiYKJGY1NzYyNWJkLWNmZjctNGU0Yy1hYzVmLTFlYWI2NDIzMmMy
+      ZEouCgh0YXNrX2tleRIiCiA5ZjJkNGU5M2FiNTkwYzcyNTg4NzAyNzUwOGFmOTI3OEoxCgd0YXNr
+      X2lkEiYKJDM1NWNmMWE5LWU5OTMtNDExNC05YzQ0LTJkMzkwOWEwOWM1ZnoCGAGFAQABAAAS1AsK
+      EOofSLF1HDmhYMt7eIAeFo8SCCaKUQMuWNdnKgxDcmV3IENyZWF0ZWQwATkYKA62GacTGEFwlhW2
+      GacTGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4x
+      MS43Si4KCGNyZXdfa2V5EiIKIDRlOGU0MmNmMWVhN2U2NjhhMGU5MzJhNzAyMDY1NzQ5SjEKB2Ny
+      ZXdfaWQSJgokMmIzNTVjZDMtY2MwNi00Y2QxLTk0YjgtZTU5YjM5OGI3MjEzShwKDGNyZXdfcHJv
+      Y2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90
+      YXNrcxICGAJKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAkqSBQoLY3Jld19hZ2VudHMSggUK
+      /wRbeyJrZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNkNzUiLCAiaWQiOiAiNWNm
+      NDllYzctOTVmMy00ZGQ3LTg1NzItZjgwMDQwODYwYjI4IiwgInJvbGUiOiAiUmVzZWFyY2hlciIs
+      ICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVu
+      Y3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9u
+      X2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9y
+      ZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiOWE1MDE1ZWY0ODk1
+      ZGM2Mjc4ZDU0ODE4YmE0NDZhZjciLCAiaWQiOiAiNDExMjNkM2QtNTZhMC00YTU4LWE5YzYtZmY1
+      MDY0ZmYzZjUxIiwgInJvbGUiOiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAi
+      bWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAi
+      IiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJh
+      bGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29s
+      c19uYW1lcyI6IFtdfV1K7wMKCmNyZXdfdGFza3MS4AMK3QNbeyJrZXkiOiAiNjc4NDlmZjcxN2Ri
+      YWRhYmExYjk1ZDVmMmRmY2VlYTEiLCAiaWQiOiAiOGE5OTgxMDYtZjg5Zi00YTQ5LThjZjEtYjk4
+      MzQ5ZDE1NDRmIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZh
+      bHNlLCAiYWdlbnRfcm9sZSI6ICJSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6ICI4YmQyMTM5YjU5
+      NzUxODE1MDZlNDFmZDljNDU2M2Q3NSIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiODRh
+      ZjlmYzFjZDMzMTk5Y2ViYjlkNDE0MjE4NWY4MDIiLCAiaWQiOiAiYTViMTg0MDgtYjA1OC00ZDE1
+      LTkyMmUtNDJkN2M5Y2ViYjFhIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lu
+      cHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJTZW5pb3IgV3JpdGVyIiwgImFnZW50X2tleSI6
+      ICI5YTUwMTVlZjQ4OTVkYzYyNzhkNTQ4MThiYTQ0NmFmNyIsICJ0b29sc19uYW1lcyI6IFtdfV16
+      AhgBhQEAAQAAEsIJChDCLrcWQ+nu3SxOgnq50XhSEghjozRtuCFA0SoMQ3JldyBDcmVhdGVkMAE5
+      CDeCthmnExhBmHiIthmnExhKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC44Ni4wShoKDnB5dGhvbl92
+      ZXJzaW9uEggKBjMuMTEuN0ouCghjcmV3X2tleRIiCiBlM2ZkYTBmMzExMGZlODBiMTg5NDdjMDE0
+      NzE0MzBhNEoxCgdjcmV3X2lkEiYKJGM1ZDQ0YjY5LTRhNzMtNDA3Zi1iY2RhLTUzZmUxZTQ3YTU3
+      M0oeCgxjcmV3X3Byb2Nlc3MSDgoMaGllcmFyY2hpY2FsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRj
+      cmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAkqSBQoL
+      Y3Jld19hZ2VudHMSggUK/wRbeyJrZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNk
+      NzUiLCAiaWQiOiAiNWNmNDllYzctOTVmMy00ZGQ3LTg1NzItZjgwMDQwODYwYjI4IiwgInJvbGUi
+      OiAiUmVzZWFyY2hlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9y
+      cG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWlu
+      aSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8i
+      OiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXki
+      OiAiOWE1MDE1ZWY0ODk1ZGM2Mjc4ZDU0ODE4YmE0NDZhZjciLCAiaWQiOiAiNDExMjNkM2QtNTZh
+      MC00YTU4LWE5YzYtZmY1MDY0ZmYzZjUxIiwgInJvbGUiOiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJi
+      b3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25f
+      Y2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJs
+      ZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9s
+      aW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K2wEKCmNyZXdfdGFza3MSzAEKyQFbeyJrZXki
+      OiAiNWZhNjVjMDZhOWUzMWYyYzY5NTQzMjY2OGFjZDYyZGQiLCAiaWQiOiAiNjNhYTVlOTYtYTM4
+      Yy00YjcyLWJiZDQtYjM2NmU5NTlhOWZhIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1
+      bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJOb25lIiwgImFnZW50X2tleSI6IG51
+      bGwsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEuYJChA8kiyQ+AFdDSYkp0+TUWKvEgjW
+      0grLw8r5KioMQ3JldyBDcmVhdGVkMAE5iLivvhmnExhBeG21vhmnExhKGgoOY3Jld2FpX3ZlcnNp
+      b24SCAoGMC44Ni4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTEuN0ouCghjcmV3X2tleRIiCiBl
+      M2ZkYTBmMzExMGZlODBiMTg5NDdjMDE0NzE0MzBhNEoxCgdjcmV3X2lkEiYKJGIzZGQ1MGYxLTI0
+      YWQtNDE5OC04ZGFhLTMwZTU0OTQ3MTlhMEoeCgxjcmV3X3Byb2Nlc3MSDgoMaGllcmFyY2hpY2Fs
+      ShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19u
+      dW1iZXJfb2ZfYWdlbnRzEgIYAkqSBQoLY3Jld19hZ2VudHMSggUK/wRbeyJrZXkiOiAiOGJkMjEz
+      OWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNkNzUiLCAiaWQiOiAiNWNmNDllYzctOTVmMy00ZGQ3LTg1
+      NzItZjgwMDQwODYwYjI4IiwgInJvbGUiOiAiUmVzZWFyY2hlciIsICJ2ZXJib3NlPyI6IGZhbHNl
+      LCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0i
+      OiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2Us
+      ICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0
+      b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiOWE1MDE1ZWY0ODk1ZGM2Mjc4ZDU0ODE4YmE0NDZh
+      ZjciLCAiaWQiOiAiNDExMjNkM2QtNTZhMC00YTU4LWE5YzYtZmY1MDY0ZmYzZjUxIiwgInJvbGUi
+      OiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1h
+      eF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8t
+      bWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlv
+      bj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/wEK
+      CmNyZXdfdGFza3MS8AEK7QFbeyJrZXkiOiAiNWZhNjVjMDZhOWUzMWYyYzY5NTQzMjY2OGFjZDYy
+      ZGQiLCAiaWQiOiAiNzEyODlkZTAtODQ4My00NDM2LWI2OGMtNDc1MWIzNTU0ZmUzIiwgImFzeW5j
+      X2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6
+      ICJSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6ICI4YmQyMTM5YjU5NzUxODE1MDZlNDFmZDljNDU2
+      M2Q3NSIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChCTiJL+KK5ff9xnie6eZbEc
+      EghbtQixNaG5DioMVGFzayBDcmVhdGVkMAE5cIXNvhmnExhBuPbNvhmnExhKLgoIY3Jld19rZXkS
+      IgogZTNmZGEwZjMxMTBmZTgwYjE4OTQ3YzAxNDcxNDMwYTRKMQoHY3Jld19pZBImCiRiM2RkNTBm
+      MS0yNGFkLTQxOTgtOGRhYS0zMGU1NDk0NzE5YTBKLgoIdGFza19rZXkSIgogNWZhNjVjMDZhOWUz
+      MWYyYzY5NTQzMjY2OGFjZDYyZGRKMQoHdGFza19pZBImCiQ3MTI4OWRlMC04NDgzLTQ0MzYtYjY4
+      Yy00NzUxYjM1NTRmZTN6AhgBhQEAAQAAEpwBChBCdDi/i+SH0kHHlJKQjmYgEgiemV9jVU5fQSoK
+      VG9vbCBVc2FnZTABOVj/YL8ZpxMYQWCwZr8ZpxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYu
+      MEooCgl0b29sX25hbWUSGwoZRGVsZWdhdGUgd29yayB0byBjb3dvcmtlckoOCghhdHRlbXB0cxIC
+      GAF6AhgBhQEAAQAAEqUBChBRuZ6Z/nNag4ubLeZ8L/8pEghCX4biKNFb6SoTVG9vbCBSZXBlYXRl
+      ZCBVc2FnZTABOUj9wr8ZpxMYQdg+yb8ZpxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoo
+      Cgl0b29sX25hbWUSGwoZRGVsZWdhdGUgd29yayB0byBjb3dvcmtlckoOCghhdHRlbXB0cxICGAF6
+      AhgBhQEAAQAAEpwBChDnt1bxQsOb0LVscG9GDYVtEgjf62keNMl5ZyoKVG9vbCBVc2FnZTABOdha
+      6MAZpxMYQWii7cAZpxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEooCgl0b29sX25hbWUS
+      GwoZRGVsZWdhdGUgd29yayB0byBjb3dvcmtlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpsB
+      ChDFqFA9b42EIwUxeNLTeScxEgiGFk7FwiNxVioKVG9vbCBVc2FnZTABObDAY8EZpxMYQdhIaMEZ
+      pxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEonCgl0b29sX25hbWUSGgoYQXNrIHF1ZXN0
+      aW9uIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASwgkKEHpB0rbuWbSXijzV
+      QdTa3oQSCNSPnbmqe2PfKgxDcmV3IENyZWF0ZWQwATmIXxTCGacTGEF4GhnCGacTGEoaCg5jcmV3
+      YWlfdmVyc2lvbhIICgYwLjg2LjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMS43Si4KCGNyZXdf
+      a2V5EiIKIGUzZmRhMGYzMTEwZmU4MGIxODk0N2MwMTQ3MTQzMGE0SjEKB2NyZXdfaWQSJgokZGJm
+      YzNjMjctMmRjZS00MjIyLThiYmQtYmMxMjU3OTVlNWI1Sh4KDGNyZXdfcHJvY2VzcxIOCgxoaWVy
+      YXJjaGljYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUob
+      ChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSpIFCgtjcmV3X2FnZW50cxKCBQr/BFt7ImtleSI6
+      ICI4YmQyMTM5YjU5NzUxODE1MDZlNDFmZDljNDU2M2Q3NSIsICJpZCI6ICI1Y2Y0OWVjNy05NWYz
+      LTRkZDctODU3Mi1mODAwNDA4NjBiMjgiLCAicm9sZSI6ICJSZXNlYXJjaGVyIiwgInZlcmJvc2U/
+      IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxs
+      aW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8i
+      OiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0
+      IjogMiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICI5YTUwMTVlZjQ4OTVkYzYyNzhkNTQ4
+      MThiYTQ0NmFmNyIsICJpZCI6ICI0MTEyM2QzZC01NmEwLTRhNTgtYTljNi1mZjUwNjRmZjNmNTEi
+      LCAicm9sZSI6ICJTZW5pb3IgV3JpdGVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6
+      IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjog
+      ImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVf
+      ZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjog
+      W119XUrbAQoKY3Jld190YXNrcxLMAQrJAVt7ImtleSI6ICI1ZmE2NWMwNmE5ZTMxZjJjNjk1NDMy
+      NjY4YWNkNjJkZCIsICJpZCI6ICIyYWFjOTllMC0yNWVmLTQzN2MtYTJmZi1jZGFlMjg2ZWU2MzQi
+      LCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2Vu
+      dF9yb2xlIjogIk5vbmUiLCAiYWdlbnRfa2V5IjogbnVsbCwgInRvb2xzX25hbWVzIjogW119XXoC
+      GAGFAQABAAAS1QkKEM6Xt0BvAHy+TI7iLC6ovN0SCEfHP30NZESSKgxDcmV3IENyZWF0ZWQwATkg
+      PdnDGacTGEFIPN/DGacTGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMS43Si4KCGNyZXdfa2V5EiIKIGU2NDk1NzNhMjZlNTg3OTBjYWMyMWEzN2Nk
+      NDQ0MzdhSjEKB2NyZXdfaWQSJgokNjE3MDA3NGMtYzU5OS00ODkyLTkwYzYtMTcxYjhkM2Y1OTRh
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAkqKBQoLY3Jl
+      d19hZ2VudHMS+gQK9wRbeyJrZXkiOiAiMzI4MjE3YjZjMjk1OWJkZmM0N2NhZDAwZTg0ODkwZDAi
+      LCAiaWQiOiAiYjNmMTczZTktNjY3NS00OTFkLTgyYjctODM4NmRkMjExMDM1IiwgInJvbGUiOiAi
+      Q0VPIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGws
+      ICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVn
+      YXRpb25fZW5hYmxlZD8iOiB0cnVlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJt
+      YXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX0sIHsia2V5IjogIjlhNTAxNWVm
+      NDg5NWRjNjI3OGQ1NDgxOGJhNDQ2YWY3IiwgImlkIjogIjQxMTIzZDNkLTU2YTAtNGE1OC1hOWM2
+      LWZmNTA2NGZmM2Y1MSIsICJyb2xlIjogIlNlbmlvciBXcml0ZXIiLCAidmVyYm9zZT8iOiBmYWxz
+      ZSwgIm1heF9pdGVyIjogMjAsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxt
+      IjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNl
+      LCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAi
+      dG9vbHNfbmFtZXMiOiBbXX1dSvgBCgpjcmV3X3Rhc2tzEukBCuYBW3sia2V5IjogIjBiOWQ2NWRi
+      NmI3YWVkZmIzOThjNTllMmE5ZjcxZWM1IiwgImlkIjogImJiNmI1Njg3LTg5NGMtNDAyNS05M2My
+      LTMyYjdkZmEwZTUxMyIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8i
+      OiBmYWxzZSwgImFnZW50X3JvbGUiOiAiQ0VPIiwgImFnZW50X2tleSI6ICIzMjgyMTdiNmMyOTU5
+      YmRmYzQ3Y2FkMDBlODQ4OTBkMCIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChCK
+      KIL9w7sqoMzG3JItjK8eEgiR4RSmJw+SMSoMVGFzayBDcmVhdGVkMAE5CCjywxmnExhByIXywxmn
+      ExhKLgoIY3Jld19rZXkSIgogZTY0OTU3M2EyNmU1ODc5MGNhYzIxYTM3Y2Q0NDQzN2FKMQoHY3Jl
+      d19pZBImCiQ2MTcwMDc0Yy1jNTk5LTQ4OTItOTBjNi0xNzFiOGQzZjU5NGFKLgoIdGFza19rZXkS
+      IgogMGI5ZDY1ZGI2YjdhZWRmYjM5OGM1OWUyYTlmNzFlYzVKMQoHdGFza19pZBImCiRiYjZiNTY4
+      Ny04OTRjLTQwMjUtOTNjMi0zMmI3ZGZhMGU1MTN6AhgBhQEAAQAAEpwBChD+/zv5udkceIEyIb7d
+      ne5vEgj1My75q1O7UCoKVG9vbCBVc2FnZTABOThPfMQZpxMYQcA4g8QZpxMYShoKDmNyZXdhaV92
+      ZXJzaW9uEggKBjAuODYuMEooCgl0b29sX25hbWUSGwoZRGVsZWdhdGUgd29yayB0byBjb3dvcmtl
+      ckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEuAJChBIzM1Xa9IhegFDHxt6rj3eEgj9z56V1hXk
+      aCoMQ3JldyBDcmVhdGVkMAE5mEoMxRmnExhBoPsRxRmnExhKGgoOY3Jld2FpX3ZlcnNpb24SCAoG
+      MC44Ni4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTEuN0ouCghjcmV3X2tleRIiCiBlNjQ5NTcz
+      YTI2ZTU4NzkwY2FjMjFhMzdjZDQ0NDM3YUoxCgdjcmV3X2lkEiYKJGQ4MjhhZWM2LTg2N2MtNDdh
+      YS04ODY4LWQwMWYwNGM0MGE0MUocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3
+      X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29m
+      X2FnZW50cxICGAJKigUKC2NyZXdfYWdlbnRzEvoECvcEW3sia2V5IjogIjMyODIxN2I2YzI5NTli
+      ZGZjNDdjYWQwMGU4NDg5MGQwIiwgImlkIjogImIzZjE3M2U5LTY2NzUtNDkxZC04MmI3LTgzODZk
+      ZDIxMTAzNSIsICJyb2xlIjogIkNFTyIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAy
+      MCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJn
+      cHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogdHJ1ZSwgImFsbG93X2NvZGVfZXhl
+      Y3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119
+      LCB7ImtleSI6ICI5YTUwMTVlZjQ4OTVkYzYyNzhkNTQ4MThiYTQ0NmFmNyIsICJpZCI6ICI0MTEy
+      M2QzZC01NmEwLTRhNTgtYTljNi1mZjUwNjRmZjNmNTEiLCAicm9sZSI6ICJTZW5pb3IgV3JpdGVy
+      IiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJm
+      dW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRp
+      b25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4
+      X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUqDAgoKY3Jld190YXNrcxL0AQrx
+      AVt7ImtleSI6ICIwYjlkNjVkYjZiN2FlZGZiMzk4YzU5ZTJhOWY3MWVjNSIsICJpZCI6ICI5YTBj
+      ODZhZi0wYTE0LTQ4MzgtOTJmZC02NDhhZGM1NzJlMDMiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZh
+      bHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIkNFTyIsICJhZ2VudF9r
+      ZXkiOiAiMzI4MjE3YjZjMjk1OWJkZmM0N2NhZDAwZTg0ODkwZDAiLCAidG9vbHNfbmFtZXMiOiBb
+      InRlc3QgdG9vbCJdfV16AhgBhQEAAQAAEo4CChDl0EBv/8sdeV8eJ45EUBpxEgj+C7UlokySqSoM
+      VGFzayBDcmVhdGVkMAE5oI8jxRmnExhBYO0jxRmnExhKLgoIY3Jld19rZXkSIgogZTY0OTU3M2Ey
+      NmU1ODc5MGNhYzIxYTM3Y2Q0NDQzN2FKMQoHY3Jld19pZBImCiRkODI4YWVjNi04NjdjLTQ3YWEt
+      ODg2OC1kMDFmMDRjNDBhNDFKLgoIdGFza19rZXkSIgogMGI5ZDY1ZGI2YjdhZWRmYjM5OGM1OWUy
+      YTlmNzFlYzVKMQoHdGFza19pZBImCiQ5YTBjODZhZi0wYTE0LTQ4MzgtOTJmZC02NDhhZGM1NzJl
+      MDN6AhgBhQEAAQAAEpsBChArkcRTKJCaWLUYbx8DLyvTEgikYuS5tmbKNioKVG9vbCBVc2FnZTAB
+      OSh+MscZpxMYQdgTOMcZpxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEonCgl0b29sX25h
+      bWUSGgoYQXNrIHF1ZXN0aW9uIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAAS
+      6wkKEHxFJsjiUgQromzfQHpYYMISCBkGairjk9kkKgxDcmV3IENyZWF0ZWQwATk4/rXHGacTGEGY
+      yrvHGacTGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoG
+      My4xMS43Si4KCGNyZXdfa2V5EiIKIGU2NDk1NzNhMjZlNTg3OTBjYWMyMWEzN2NkNDQ0MzdhSjEK
+      B2NyZXdfaWQSJgokMjY3NzEyNzItOTRlZC00NDVkLTg1MGEtYTkyYTZjOWI5YmJkShwKDGNyZXdf
+      cHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9v
+      Zl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAkqVBQoLY3Jld19hZ2VudHMS
+      hQUKggVbeyJrZXkiOiAiMzI4MjE3YjZjMjk1OWJkZmM0N2NhZDAwZTg0ODkwZDAiLCAiaWQiOiAi
+      YjNmMTczZTktNjY3NS00OTFkLTgyYjctODM4NmRkMjExMDM1IiwgInJvbGUiOiAiQ0VPIiwgInZl
+      cmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlv
+      bl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5h
+      YmxlZD8iOiB0cnVlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlf
+      bGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbInRlc3QgdG9vbCJdfSwgeyJrZXkiOiAiOWE1MDE1
+      ZWY0ODk1ZGM2Mjc4ZDU0ODE4YmE0NDZhZjciLCAiaWQiOiAiNDExMjNkM2QtNTZhMC00YTU4LWE5
+      YzYtZmY1MDY0ZmYzZjUxIiwgInJvbGUiOiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJib3NlPyI6IGZh
+      bHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19s
+      bG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFs
+      c2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIs
+      ICJ0b29sc19uYW1lcyI6IFtdfV1KgwIKCmNyZXdfdGFza3MS9AEK8QFbeyJrZXkiOiAiMGI5ZDY1
+      ZGI2YjdhZWRmYjM5OGM1OWUyYTlmNzFlYzUiLCAiaWQiOiAiNjYzOTEwZjYtNTlkYS00NjE3LTli
+      ZTMtNTBmMDdhNmQ5N2U3IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0
+      PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJDRU8iLCAiYWdlbnRfa2V5IjogIjMyODIxN2I2YzI5
+      NTliZGZjNDdjYWQwMGU4NDg5MGQwIiwgInRvb2xzX25hbWVzIjogWyJ0ZXN0IHRvb2wiXX1degIY
+      AYUBAAEAABKOAgoQ1qBlNY8Yu1muyMaMnchyJBII0vE2y9FMwz0qDFRhc2sgQ3JlYXRlZDABObDR
+      zscZpxMYQah5z8cZpxMYSi4KCGNyZXdfa2V5EiIKIGU2NDk1NzNhMjZlNTg3OTBjYWMyMWEzN2Nk
+      NDQ0MzdhSjEKB2NyZXdfaWQSJgokMjY3NzEyNzItOTRlZC00NDVkLTg1MGEtYTkyYTZjOWI5YmJk
+      Si4KCHRhc2tfa2V5EiIKIDBiOWQ2NWRiNmI3YWVkZmIzOThjNTllMmE5ZjcxZWM1SjEKB3Rhc2tf
+      aWQSJgokNjYzOTEwZjYtNTlkYS00NjE3LTliZTMtNTBmMDdhNmQ5N2U3egIYAYUBAAEAABKMAQoQ
+      a8ZDV3ZaBmcOZE5dJ87f1hII7iBRAQfEmdAqClRvb2wgVXNhZ2UwATmYcwjIGacTGEE4RxLIGacT
+      GEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKGAoJdG9vbF9uYW1lEgsKCVRlc3QgVG9vbEoO
+      CghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEowBChBqK4036ypaH1gZ3OIOE/0HEgiF8wTQDQGRlSoK
+      VG9vbCBVc2FnZTABOYBiSsgZpxMYQRCYUsgZpxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYu
+      MEoYCgl0b29sX25hbWUSCwoJVGVzdCBUb29sSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASwQcK
+      EIWSiNjtKgeNQ6oIv8gjJ+MSCG8YnypCXfw1KgxDcmV3IENyZWF0ZWQwATnYUW/KGacTGEEoenTK
+      GacTGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4x
+      MS43Si4KCGNyZXdfa2V5EiIKIDk4MjQ2MGVlMmRkMmNmMTJhNzEzOGI3MDg1OWZlODE3SjEKB2Ny
+      ZXdfaWQSJgokZDNkODZjNmEtNWNmMi00MGI0LWExZGQtMzA5NTYyODdjNWE3ShwKDGNyZXdfcHJv
+      Y2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90
+      YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrcAgoLY3Jld19hZ2VudHMSzAIK
+      yQJbeyJrZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNkNzUiLCAiaWQiOiAiNWNm
+      NDllYzctOTVmMy00ZGQ3LTg1NzItZjgwMDQwODYwYjI4IiwgInJvbGUiOiAiUmVzZWFyY2hlciIs
+      ICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVu
+      Y3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9u
+      X2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9y
+      ZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFsidGVzdCB0b29sIl19XUqSAgoKY3Jld190
+      YXNrcxKDAgqAAlt7ImtleSI6ICJmODM5Yzg3YzNkNzU3Yzg4N2Y0Y2U3NGQxODY0YjAyYSIsICJp
+      ZCI6ICJjM2Y2NjY2MS00YWNjLTQ5OWQtYjJkNC1kZjI0Nzg1MTJhZGYiLCAiYXN5bmNfZXhlY3V0
+      aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIlJlc2Vh
+      cmNoZXIiLCAiYWdlbnRfa2V5IjogIjhiZDIxMzliNTk3NTE4MTUwNmU0MWZkOWM0NTYzZDc1Iiwg
+      InRvb2xzX25hbWVzIjogWyJhbm90aGVyIHRlc3QgdG9vbCJdfV16AhgBhQEAAQAAEo4CChD8dNvp
+      UItERukk59GnvESYEghtjirHyG3B3SoMVGFzayBDcmVhdGVkMAE5MAGByhmnExhBIFeByhmnExhK
+      LgoIY3Jld19rZXkSIgogOTgyNDYwZWUyZGQyY2YxMmE3MTM4YjcwODU5ZmU4MTdKMQoHY3Jld19p
+      ZBImCiRkM2Q4NmM2YS01Y2YyLTQwYjQtYTFkZC0zMDk1NjI4N2M1YTdKLgoIdGFza19rZXkSIgog
+      ZjgzOWM4N2MzZDc1N2M4ODdmNGNlNzRkMTg2NGIwMmFKMQoHdGFza19pZBImCiRjM2Y2NjY2MS00
+      YWNjLTQ5OWQtYjJkNC1kZjI0Nzg1MTJhZGZ6AhgBhQEAAQAAEowBChDdoNfQMW/Om7LQU9gZGDrl
+      Egjw71DM3bnOWCoKVG9vbCBVc2FnZTABOUgPFC8apxMYQdhtKi8apxMYShoKDmNyZXdhaV92ZXJz
+      aW9uEggKBjAuODYuMEoYCgl0b29sX25hbWUSCwoJVGVzdCBUb29sSg4KCGF0dGVtcHRzEgIYAXoC
+      GAGFAQABAAA=
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '14771'
+      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:
+      - Mon, 23 Dec 2024 00:33:37 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
+      an expert researcher, specialized in technology, software engineering, AI and
+      startups. You work as a freelancer and is now working on doing research and
+      analysis for a new customer.\nYour personal goal is: Make the best research
+      and analysis on content about AI and AI agents\nYou ONLY have access to the
+      following tools, and should NEVER make up tools that are not listed here:\n\nTool
+      Name: Test Tool\nTool Arguments: {''query'': {''description'': ''Query to process'',
+      ''type'': ''str''}}\nTool Description: A test tool that just returns the input\n\nUse
+      the following format:\n\nThought: you should always think about what to do\nAction:
+      the action to take, only one name of [Test Tool], just the name, exactly as
+      it''s written.\nAction Input: the input to the action, just a simple python
+      dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
+      the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question"}, {"role": "user", "content": "\nCurrent Task: Write a test
+      task\n\nThis is the expect 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:"}, {"role": "assistant", "content":
+      "I need to come up with a suitable test task that meets the criteria provided.
+      I will focus on outlining a clear and effective test task related to AI and
+      AI agents.\n\nAction: Test Tool\nAction Input: {\"query\": \"Create a test task
+      that involves evaluating the performance of an AI agent in a given scenario,
+      including criteria for success, tools required, and process for assessment.\"}\nObservation:
+      Processed: Create a test task that involves evaluating the performance of an
+      AI agent in a given scenario, including criteria for success, tools required,
+      and process for assessment."}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2160'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000;
+        __cf_bm=i6jvNjhsDne300GPAeEmyiJJKYqy7OPuamFG_kht3KE-1734914012-1.0.1.1-tCeVANAF521vkXpBdgYw.ov.fYUr6t5QC4LG_DugWyzu4C60Pi2CruTVniUgfCvkcu6rdHA5DwnaEZf2jFaRCQ
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhQg0Cx1FED7gOwMpJUD5cQxVzQBK\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734914012,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I need to compile a complete
+      and detailed test task based on the processed input, ensuring it includes all
+      necessary components as per the expect criteria.\\n\\nFinal Answer: \\n### Test
+      Task: Evaluating the Performance of an AI Agent\\n\\n**Objective:** \\nTo evaluate
+      the performance of an AI agent in simulating conversation with users in a customer
+      service context.\\n\\n**Scenario:**\\nAn AI agent is tasked with handling customer
+      inquiries on an e-commerce platform. The agent must respond to questions about
+      product availability, order tracking, returns, and other common queries.\\n\\n**Criteria
+      for Success:**\\n1. **Accuracy:** The AI should provide correct information
+      in at least 90% of the interactions.\\n2. **Response Time:** The average response
+      time should be under 2 seconds.\\n3. **User Satisfaction:** Aim for a user satisfaction
+      score of 85% or higher based on follow-up surveys after interactions.\\n4. **Fallback
+      Rate:** The AI should not default to a human agent more than 10% of the time.\\n\\n**Tools
+      Required:**\\n- Chatbot development platform (e.g., Dialogflow, Rasa)\\n- Metrics
+      tracking software (to measure accuracy, response times, and user satisfaction)\\n-
+      Survey tool (e.g., Google Forms, SurveyMonkey) for feedback collection\\n\\n**Process
+      for Assessment:**\\n1. **Setup:** Deploy the AI agent on a testing environment
+      simulating real customer inquiries.\\n2. **Data Collection:** Run the test for
+      a predetermined period (e.g., one week) or until a set number of interactions
+      (e.g., 1000).\\n3. **Measurement:**\\n   - Record the interactions and analyze
+      the accuracy of the AI's responses.\\n   - Measure the average response time
+      for each interaction.\\n   - Collect user satisfaction scores via surveys sent
+      after the interaction.\\n4. **Analysis:** Compile the data to see if the AI
+      met the success criteria. Identify strengths and weaknesses in the responses.\\n5.
+      **Review:** Share findings with the development team to strategize improvements.\\n\\nThis
+      detailed task will help assess the AI agent\u2019s capabilities and provide
+      insights for further enhancements.\",\n        \"refusal\": null\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 416,\n    \"completion_tokens\": 422,\n
+      \   \"total_tokens\": 838,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_d02d531b47\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f6442c2ba15a486-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 23 Dec 2024 00:33:39 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:
+      - '6734'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999497'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_7d8df8b840e279bd64280d161d854161
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cli/tools/test_main.py

@@ -28,9 +28,10 @@ def test_create_success(mock_subprocess):
     with in_temp_dir():
         tool_command = ToolCommand()
 
-        with patch.object(tool_command, "login") as mock_login, patch(
-            "sys.stdout", new=StringIO()
-        ) as fake_out:
+        with (
+            patch.object(tool_command, "login") as mock_login,
+            patch("sys.stdout", new=StringIO()) as fake_out,
+        ):
             tool_command.create("test-tool")
             output = fake_out.getvalue()
 
@@ -82,7 +83,7 @@ def test_install_success(mock_get, mock_subprocess_run):
         capture_output=False,
         text=True,
         check=True,
-        env=unittest.mock.ANY
+        env=unittest.mock.ANY,
     )
 
     assert "Successfully installed sample-tool" in output

tests/crew_test.py

@@ -332,22 +332,39 @@ def test_manager_agent_delegating_to_assigned_task_agent():
         tasks=[task],
     )
 
-    crew.kickoff()
-
-    # Check if the manager agent has the correct tools
-    assert crew.manager_agent is not None
-    assert crew.manager_agent.tools is not None
-
-    assert len(crew.manager_agent.tools) == 2
-    assert (
-        "Delegate a specific task to one of the following coworkers: Researcher\n"
-        in crew.manager_agent.tools[0].description
-    )
-    assert (
-        "Ask a specific question to one of the following coworkers: Researcher\n"
-        in crew.manager_agent.tools[1].description
+    mock_task_output = TaskOutput(
+        description="Mock description", raw="mocked output", agent="mocked agent"
     )
 
+    # Because we are mocking execute_sync, we never hit the underlying _execute_core
+    # which sets the output attribute of the task
+    task.output = mock_task_output
+
+    with patch.object(
+        Task, "execute_sync", return_value=mock_task_output
+    ) as mock_execute_sync:
+        crew.kickoff()
+
+        # Verify execute_sync was called once
+        mock_execute_sync.assert_called_once()
+
+        # Get the tools argument from the call
+        _, kwargs = mock_execute_sync.call_args
+        tools = kwargs["tools"]
+
+        # Verify the delegation tools were passed correctly
+        assert len(tools) == 2
+        assert any(
+            "Delegate a specific task to one of the following coworkers: Researcher"
+            in tool.description
+            for tool in tools
+        )
+        assert any(
+            "Ask a specific question to one of the following coworkers: Researcher"
+            in tool.description
+            for tool in tools
+        )
+
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_manager_agent_delegating_to_all_agents():
@@ -382,6 +399,83 @@ def test_manager_agent_delegating_to_all_agents():
     )
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_manager_agent_delegates_with_varied_role_cases():
+    """
+    Test that the manager agent can delegate to agents regardless of case or whitespace variations in role names.
+    This test verifies the fix for issue #1503 where role matching was too strict.
+    """
+    # Create agents with varied case and whitespace in roles
+    researcher_spaced = Agent(
+        role=" Researcher ",  # Extra spaces
+        goal="Research with spaces in role",
+        backstory="A researcher with spaces in role name",
+        allow_delegation=False,
+    )
+
+    writer_caps = Agent(
+        role="SENIOR WRITER",  # All caps
+        goal="Write with caps in role",
+        backstory="A writer with caps in role name",
+        allow_delegation=False,
+    )
+
+    task = Task(
+        description="Research and write about AI. The researcher should do the research, and the writer should write it up.",
+        expected_output="A well-researched article about AI.",
+        agent=researcher_spaced,  # Assign to researcher with spaces
+    )
+
+    crew = Crew(
+        agents=[researcher_spaced, writer_caps],
+        process=Process.hierarchical,
+        manager_llm="gpt-4o",
+        tasks=[task],
+    )
+
+    mock_task_output = TaskOutput(
+        description="Mock description", raw="mocked output", agent="mocked agent"
+    )
+    task.output = mock_task_output
+
+    with patch.object(
+        Task, "execute_sync", return_value=mock_task_output
+    ) as mock_execute_sync:
+        crew.kickoff()
+
+        # Verify execute_sync was called once
+        mock_execute_sync.assert_called_once()
+
+        # Get the tools argument from the call
+        _, kwargs = mock_execute_sync.call_args
+        tools = kwargs["tools"]
+
+        # Verify the delegation tools were passed correctly and can handle case/whitespace variations
+        assert len(tools) == 2
+
+        # Check delegation tool descriptions (should work despite case/whitespace differences)
+        delegation_tool = tools[0]
+        question_tool = tools[1]
+
+        assert (
+            "Delegate a specific task to one of the following coworkers:"
+            in delegation_tool.description
+        )
+        assert (
+            " Researcher " in delegation_tool.description
+            or "SENIOR WRITER" in delegation_tool.description
+        )
+
+        assert (
+            "Ask a specific question to one of the following coworkers:"
+            in question_tool.description
+        )
+        assert (
+            " Researcher " in question_tool.description
+            or "SENIOR WRITER" in question_tool.description
+        )
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_with_delegating_agents():
     tasks = [
@@ -402,10 +496,274 @@ def test_crew_with_delegating_agents():
 
     assert (
         result.raw
-        == "This is the complete content as specified:\nArtificial Intelligence (AI) Agents are sophisticated computer programs designed to perform tasks that typically require human intelligence, such as decision making, problem-solving, and learning. These agents operate autonomously, utilizing vast amounts of data, advanced algorithms, and machine learning techniques to analyze their environment, adapt to new information, and improve their performance over time.\n\nThe significance of AI Agents lies in their transformative potential across various industries. In healthcare, for example, they assist in diagnosing diseases with greater accuracy and speed than human practitioners, offering personalized treatment plans by analyzing patient data. In finance, AI Agents predict market trends, manage risks, and even execute trades, contributing to more stable and profitable financial systems. Customer service sectors benefit significantly from AI Agents, as they provide personalized and efficient responses, often resolving issues faster than traditional methods.\n\nMoreover, AI Agents are also making substantial contributions in fields like education and manufacturing. In education, they offer tailored learning experiences by assessing individual student needs and adjusting teaching methods accordingly. They help educators identify students who might need additional support and provide resources to enhance learning outcomes. In manufacturing, AI Agents optimize production lines, predict equipment failures, and improve supply chain management, thus boosting productivity and reducing downtime.\n\nAs these AI-powered entities continue to evolve, they are not only enhancing operational efficiencies but also driving innovation and creating new opportunities for growth and development in every sector they penetrate. The future of AI Agents looks promising, with the potential to revolutionize the way we live and work, making processes more efficient, decisions more data-driven, and solutions more innovative than ever before."
+        == "In the rapidly evolving landscape of technology, AI agents have emerged as formidable tools, revolutionizing how we interact with data and automate tasks. These sophisticated systems leverage machine learning and natural language processing to perform a myriad of functions, from virtual personal assistants to complex decision-making companions in industries such as finance, healthcare, and education. By mimicking human intelligence, AI agents can analyze massive data sets at unparalleled speeds, enabling businesses to uncover valuable insights, enhance productivity, and elevate user experiences to unprecedented levels.\n\nOne of the most striking aspects of AI agents is their adaptability; they learn from their interactions and continuously improve their performance over time. This feature is particularly valuable in customer service where AI agents can address inquiries, resolve issues, and provide personalized recommendations without the limitations of human fatigue. Moreover, with intuitive interfaces, AI agents enhance user interactions, making technology more accessible and user-friendly, thereby breaking down barriers that have historically hindered digital engagement.\n\nDespite their immense potential, the deployment of AI agents raises important ethical and practical considerations. Issues related to privacy, data security, and the potential for job displacement necessitate thoughtful dialogue and proactive measures. Striking a balance between technological innovation and societal impact will be crucial as organizations integrate these agents into their operations. Additionally, ensuring transparency in AI decision-making processes is vital to maintain public trust as AI agents become an integral part of daily life.\n\nLooking ahead, the future of AI agents appears bright, with ongoing advancements promising even greater capabilities. As we continue to harness the power of AI, we can expect these agents to play a transformative role in shaping various sectors—streamlining workflows, enabling smarter decision-making, and fostering more personalized experiences. Embracing this technology responsibly can lead to a future where AI agents not only augment human effort but also inspire creativity and efficiency across the board, ultimately redefining our interaction with the digital world."
     )
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_with_delegating_agents_should_not_override_task_tools():
+    from typing import Type
+
+    from pydantic import BaseModel, Field
+
+    from crewai.tools import BaseTool
+
+    class TestToolInput(BaseModel):
+        """Input schema for TestTool."""
+
+        query: str = Field(..., description="Query to process")
+
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool that just returns the input"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Processed: {query}"
+
+    # Create a task with the test tool
+    tasks = [
+        Task(
+            description="Produce and amazing 1 paragraph draft of an article about AI Agents.",
+            expected_output="A 4 paragraph article about AI.",
+            agent=ceo,
+            tools=[TestTool()],
+        )
+    ]
+
+    crew = Crew(
+        agents=[ceo, writer],
+        process=Process.sequential,
+        tasks=tasks,
+    )
+
+    mock_task_output = TaskOutput(
+        description="Mock description", raw="mocked output", agent="mocked agent"
+    )
+
+    # Because we are mocking execute_sync, we never hit the underlying _execute_core
+    # which sets the output attribute of the task
+    tasks[0].output = mock_task_output
+
+    with patch.object(
+        Task, "execute_sync", return_value=mock_task_output
+    ) as mock_execute_sync:
+        crew.kickoff()
+
+        # Execute the task and verify both tools are present
+        _, 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"
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_with_delegating_agents_should_not_override_agent_tools():
+    from typing import Type
+
+    from pydantic import BaseModel, Field
+
+    from crewai.tools import BaseTool
+
+    class TestToolInput(BaseModel):
+        """Input schema for TestTool."""
+
+        query: str = Field(..., description="Query to process")
+
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool that just returns the input"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Processed: {query}"
+
+    new_ceo = ceo.model_copy()
+    new_ceo.tools = [TestTool()]
+
+    # Create a task with the test tool
+    tasks = [
+        Task(
+            description="Produce and amazing 1 paragraph draft of an article about AI Agents.",
+            expected_output="A 4 paragraph article about AI.",
+            agent=new_ceo,
+        )
+    ]
+
+    crew = Crew(
+        agents=[new_ceo, writer],
+        process=Process.sequential,
+        tasks=tasks,
+    )
+
+    mock_task_output = TaskOutput(
+        description="Mock description", raw="mocked output", agent="mocked agent"
+    )
+
+    # Because we are mocking execute_sync, we never hit the underlying _execute_core
+    # which sets the output attribute of the task
+    tasks[0].output = mock_task_output
+
+    with patch.object(
+        Task, "execute_sync", return_value=mock_task_output
+    ) as mock_execute_sync:
+        crew.kickoff()
+
+        # Execute the task and verify both tools are present
+        _, 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"
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_task_tools_override_agent_tools():
+    from typing import Type
+
+    from pydantic import BaseModel, Field
+
+    from crewai.tools import BaseTool
+
+    class TestToolInput(BaseModel):
+        """Input schema for TestTool."""
+
+        query: str = Field(..., description="Query to process")
+
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool that just returns the input"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Processed: {query}"
+
+    class AnotherTestTool(BaseTool):
+        name: str = "Another Test Tool"
+        description: str = "Another test tool"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Another processed: {query}"
+
+    # Set agent tools
+    new_researcher = researcher.model_copy()
+    new_researcher.tools = [TestTool()]
+
+    # Create task with different tools
+    task = Task(
+        description="Write a test task",
+        expected_output="Test output",
+        agent=new_researcher,
+        tools=[AnotherTestTool()],
+    )
+
+    crew = Crew(agents=[new_researcher], tasks=[task], process=Process.sequential)
+
+    crew.kickoff()
+
+    # Verify task tools override agent tools
+    assert len(task.tools) == 1  # AnotherTestTool
+    assert any(isinstance(tool, AnotherTestTool) for tool in task.tools)
+    assert not any(isinstance(tool, TestTool) for tool in task.tools)
+
+    # Verify agent tools remain unchanged
+    assert len(new_researcher.tools) == 1
+    assert isinstance(new_researcher.tools[0], TestTool)
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_task_tools_override_agent_tools_with_allow_delegation():
+    """
+    Test that task tools override agent tools while preserving delegation tools when allow_delegation=True
+    """
+    from typing import Type
+
+    from pydantic import BaseModel, Field
+
+    from crewai.tools import BaseTool
+
+    class TestToolInput(BaseModel):
+        query: str = Field(..., description="Query to process")
+
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool that just returns the input"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Processed: {query}"
+
+    class AnotherTestTool(BaseTool):
+        name: str = "Another Test Tool"
+        description: str = "Another test tool"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Another processed: {query}"
+
+    # Set up agents with tools and allow_delegation
+    researcher_with_delegation = researcher.model_copy()
+    researcher_with_delegation.allow_delegation = True
+    researcher_with_delegation.tools = [TestTool()]
+
+    writer_for_delegation = writer.model_copy()
+
+    # Create a task with different tools
+    task = Task(
+        description="Write a test task",
+        expected_output="Test output",
+        agent=researcher_with_delegation,
+        tools=[AnotherTestTool()],
+    )
+
+    crew = Crew(
+        agents=[researcher_with_delegation, writer_for_delegation],
+        tasks=[task],
+        process=Process.sequential,
+    )
+
+    mock_task_output = TaskOutput(
+        description="Mock description", raw="mocked output", agent="mocked agent"
+    )
+
+    # We mock execute_sync to verify which tools get used at runtime
+    with patch.object(
+        Task, "execute_sync", return_value=mock_task_output
+    ) as mock_execute_sync:
+        crew.kickoff()
+
+        # Inspect the call kwargs to verify the actual tools passed to execution
+        _, kwargs = mock_execute_sync.call_args
+        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"
+
+        # Confirm delegation tool(s) are 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
+    assert isinstance(researcher_with_delegation.tools[0], TestTool)
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_verbose_output(capsys):
     tasks = [
@@ -692,8 +1050,8 @@ def test_three_task_with_async_execution():
     )
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
 @pytest.mark.asyncio
+@pytest.mark.vcr(filter_headers=["authorization"])
 async def test_crew_async_kickoff():
     inputs = [
         {"topic": "dog"},
@@ -740,8 +1098,9 @@ async def test_crew_async_kickoff():
             assert result[0].token_usage.successful_requests > 0  # type: ignore
 
 
+@pytest.mark.asyncio
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_async_task_execution_call_count():
+async def test_async_task_execution_call_count():
     from unittest.mock import MagicMock, patch
 
     list_ideas = Task(
@@ -868,7 +1227,6 @@ def test_kickoff_for_each_empty_input():
     assert results == []
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
 def test_kickoff_for_each_invalid_input():
     """Tests if kickoff_for_each raises TypeError for invalid input types."""
 
@@ -891,7 +1249,6 @@ def test_kickoff_for_each_invalid_input():
         crew.kickoff_for_each("invalid input")
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
 def test_kickoff_for_each_error_handling():
     """Tests error handling in kickoff_for_each when kickoff raises an error."""
     from unittest.mock import patch
@@ -928,7 +1285,6 @@ def test_kickoff_for_each_error_handling():
             crew.kickoff_for_each(inputs=inputs)
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
 @pytest.mark.asyncio
 async def test_kickoff_async_basic_functionality_and_output():
     """Tests the basic functionality and output of kickoff_async."""
@@ -963,7 +1319,6 @@ async def test_kickoff_async_basic_functionality_and_output():
         mock_kickoff.assert_called_once_with(inputs)
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
 @pytest.mark.asyncio
 async def test_async_kickoff_for_each_async_basic_functionality_and_output():
     """Tests the basic functionality and output of kickoff_for_each_async."""
@@ -1010,7 +1365,6 @@ async def test_async_kickoff_for_each_async_basic_functionality_and_output():
             mock_kickoff_async.assert_any_call(inputs=input_data)
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
 @pytest.mark.asyncio
 async def test_async_kickoff_for_each_async_empty_input():
     """Tests if akickoff_for_each_async handles an empty input list."""
@@ -1193,11 +1547,24 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
 
     crew = Crew(agents=[programmer], tasks=[task])
 
-    with patch.object(Agent, "execute_task") as executor:
-        executor.return_value = "ok"
+    mock_task_output = TaskOutput(
+        description="Mock description", raw="mocked output", agent="mocked agent"
+    )
+
+    with patch.object(
+        Task, "execute_sync", return_value=mock_task_output
+    ) as mock_execute_sync:
         crew.kickoff()
-        assert len(programmer.tools) == 1
-        assert programmer.tools[0].__class__ == CodeInterpreterTool
+
+        # Get the tools that were actually used in execution
+        _, kwargs = mock_execute_sync.call_args
+        used_tools = kwargs["tools"]
+
+        # 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"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -1307,21 +1674,45 @@ def test_hierarchical_crew_creation_tasks_with_agents():
         process=Process.hierarchical,
         manager_llm="gpt-4o",
     )
-    crew.kickoff()
 
-    assert crew.manager_agent is not None
-    assert crew.manager_agent.tools is not None
-    assert (
-        "Delegate a specific task to one of the following coworkers: Senior Writer\n"
-        in crew.manager_agent.tools[0].description
+    mock_task_output = TaskOutput(
+        description="Mock description", raw="mocked output", agent="mocked agent"
     )
 
+    # Because we are mocking execute_sync, we never hit the underlying _execute_core
+    # which sets the output attribute of the task
+    task.output = mock_task_output
+
+    with patch.object(
+        Task, "execute_sync", return_value=mock_task_output
+    ) as mock_execute_sync:
+        crew.kickoff()
+
+        # Verify execute_sync was called once
+        mock_execute_sync.assert_called_once()
+
+        # Get the tools argument from the call
+        _, kwargs = mock_execute_sync.call_args
+        tools = kwargs["tools"]
+
+        # Verify the delegation tools were passed correctly
+        assert len(tools) == 2
+        assert any(
+            "Delegate a specific task to one of the following coworkers: Senior Writer"
+            in tool.description
+            for tool in tools
+        )
+        assert any(
+            "Ask a specific question to one of the following coworkers: Senior Writer"
+            in tool.description
+            for tool in tools
+        )
+
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_hierarchical_crew_creation_tasks_with_async_execution():
     """
-    Agents are not required for tasks in a hierarchical process but sometimes they are still added
-    This test makes sure that the manager still delegates the task to the agent even if the agent is passed in the task
+    Tests that async tasks in hierarchical crews are handled correctly with proper delegation tools
     """
     task = Task(
         description="Write one amazing paragraph about AI.",
@@ -1337,14 +1728,43 @@ def test_hierarchical_crew_creation_tasks_with_async_execution():
         manager_llm="gpt-4o",
     )
 
-    crew.kickoff()
-    assert crew.manager_agent is not None
-    assert crew.manager_agent.tools is not None
-    assert (
-        "Delegate a specific task to one of the following coworkers: Senior Writer\n"
-        in crew.manager_agent.tools[0].description
+    mock_task_output = TaskOutput(
+        description="Mock description", raw="mocked output", agent="mocked agent"
     )
 
+    # Create a mock Future that returns our TaskOutput
+    mock_future = MagicMock(spec=Future)
+    mock_future.result.return_value = mock_task_output
+
+    # Because we are mocking execute_async, we never hit the underlying _execute_core
+    # which sets the output attribute of the task
+    task.output = mock_task_output
+
+    with patch.object(
+        Task, "execute_async", return_value=mock_future
+    ) as mock_execute_async:
+        crew.kickoff()
+
+        # Verify execute_async was called once
+        mock_execute_async.assert_called_once()
+
+        # Get the tools argument from the call
+        _, kwargs = mock_execute_async.call_args
+        tools = kwargs["tools"]
+
+        # Verify the delegation tools were passed correctly
+        assert len(tools) == 2
+        assert any(
+            "Delegate a specific task to one of the following coworkers: Senior Writer\n"
+            in tool.description
+            for tool in tools
+        )
+        assert any(
+            "Ask a specific question to one of the following coworkers: Senior Writer\n"
+            in tool.description
+            for tool in tools
+        )
+
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_hierarchical_crew_creation_tasks_with_sync_last():
@@ -1640,6 +2060,88 @@ def test_crew_log_file_output(tmp_path):
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_output_file_end_to_end(tmp_path):
+    """Test output file functionality in a full crew context."""
+    # Create an agent
+    agent = Agent(
+        role="Researcher",
+        goal="Analyze AI topics",
+        backstory="You have extensive AI research experience.",
+        allow_delegation=False,
+    )
+
+    # Create a task with dynamic output file path
+    dynamic_path = tmp_path / "output_{topic}.txt"
+    task = Task(
+        description="Explain the advantages of {topic}.",
+        expected_output="A summary of the main advantages, bullet points recommended.",
+        agent=agent,
+        output_file=str(dynamic_path),
+    )
+
+    # Create and run the crew
+    crew = Crew(
+        agents=[agent],
+        tasks=[task],
+        process=Process.sequential,
+    )
+    crew.kickoff(inputs={"topic": "AI"})
+
+    # Verify file creation and cleanup
+    expected_file = tmp_path / "output_AI.txt"
+    assert expected_file.exists(), f"Output file {expected_file} was not created"
+
+
+def test_crew_output_file_validation_failures():
+    """Test output file validation failures in a crew context."""
+    agent = Agent(
+        role="Researcher",
+        goal="Analyze data",
+        backstory="You analyze data files.",
+        allow_delegation=False,
+    )
+
+    # Test path traversal
+    with pytest.raises(ValueError, match="Path traversal"):
+        task = Task(
+            description="Analyze data",
+            expected_output="Analysis results",
+            agent=agent,
+            output_file="../output.txt",
+        )
+        Crew(agents=[agent], tasks=[task]).kickoff()
+
+    # Test shell special characters
+    with pytest.raises(ValueError, match="Shell special characters"):
+        task = Task(
+            description="Analyze data",
+            expected_output="Analysis results",
+            agent=agent,
+            output_file="output.txt | rm -rf /",
+        )
+        Crew(agents=[agent], tasks=[task]).kickoff()
+
+    # Test shell expansion
+    with pytest.raises(ValueError, match="Shell expansion"):
+        task = Task(
+            description="Analyze data",
+            expected_output="Analysis results",
+            agent=agent,
+            output_file="~/output.txt",
+        )
+        Crew(agents=[agent], tasks=[task]).kickoff()
+
+    # Test invalid template variable
+    with pytest.raises(ValueError, match="Invalid template variable"):
+        task = Task(
+            description="Analyze data",
+            expected_output="Analysis results",
+            agent=agent,
+            output_file="{invalid-name}/output.txt",
+        )
+        Crew(agents=[agent], tasks=[task]).kickoff()
+
+
 def test_manager_agent():
     from unittest.mock import patch
 
@@ -2583,3 +3085,255 @@ def test_hierarchical_verbose_false_manager_agent():
 
     assert crew.manager_agent is not None
     assert not crew.manager_agent.verbose
+
+
+def test_task_tools_preserve_code_execution_tools():
+    """
+    Test that task tools don't override code execution tools when allow_code_execution=True
+    """
+    from typing import Type
+
+    from crewai_tools import CodeInterpreterTool
+    from pydantic import BaseModel, Field
+
+    from crewai.tools import BaseTool
+
+    class TestToolInput(BaseModel):
+        """Input schema for TestTool."""
+
+        query: str = Field(..., description="Query to process")
+
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool that just returns the input"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Processed: {query}"
+
+    # Create a programmer agent with code execution enabled
+    programmer = Agent(
+        role="Programmer",
+        goal="Write code to solve problems.",
+        backstory="You're a programmer who loves to solve problems with code.",
+        allow_delegation=True,
+        allow_code_execution=True,
+    )
+
+    # Create a code reviewer agent
+    reviewer = Agent(
+        role="Code Reviewer",
+        goal="Review code for bugs and improvements",
+        backstory="You're an experienced code reviewer who ensures code quality and best practices.",
+        allow_delegation=True,
+        allow_code_execution=True,
+    )
+
+    # Create a task with its own tools
+    task = Task(
+        description="Write a program to calculate fibonacci numbers.",
+        expected_output="A working fibonacci calculator.",
+        agent=programmer,
+        tools=[TestTool()],
+    )
+
+    crew = Crew(
+        agents=[programmer, reviewer],
+        tasks=[task],
+        process=Process.sequential,
+    )
+
+    mock_task_output = TaskOutput(
+        description="Mock description", raw="mocked output", agent="mocked agent"
+    )
+
+    with patch.object(
+        Task, "execute_sync", return_value=mock_task_output
+    ) as mock_execute_sync:
+        crew.kickoff()
+
+        # Get the tools that were actually used in execution
+        _, kwargs = mock_execute_sync.call_args
+        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"
+
+        # Verify the total number of tools (TestTool + CodeInterpreter + 2 delegation tools)
+        assert (
+            len(used_tools) == 4
+        ), "Should have TestTool, CodeInterpreter, and 2 delegation tools"
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_multimodal_flag_adds_multimodal_tools():
+    """
+    Test that an agent with multimodal=True automatically has multimodal tools added to the task execution.
+    """
+    from crewai.tools.agent_tools.add_image_tool import AddImageTool
+
+    # Create an agent that supports multimodal
+    multimodal_agent = Agent(
+        role="Multimodal Analyst",
+        goal="Handle multiple media types (text, images, etc.).",
+        backstory="You're an agent specialized in analyzing text, images, and other media.",
+        allow_delegation=False,
+        multimodal=True,  # crucial for adding the multimodal tool
+    )
+
+    # Create a dummy task
+    task = Task(
+        description="Describe what's in this image and generate relevant metadata.",
+        expected_output="An image description plus any relevant metadata.",
+        agent=multimodal_agent,
+    )
+
+    # Define a crew with the multimodal agent
+    crew = Crew(agents=[multimodal_agent], tasks=[task], process=Process.sequential)
+
+    mock_task_output = TaskOutput(
+        description="Mock description", raw="mocked output", agent="mocked agent"
+    )
+
+    # Mock execute_sync to verify the tools passed at runtime
+    with patch.object(
+        Task, "execute_sync", return_value=mock_task_output
+    ) as mock_execute_sync:
+        crew.kickoff()
+
+        # Get the tools that were actually used in execution
+        _, kwargs = mock_execute_sync.call_args
+        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"
+
+        # Verify we have exactly one tool (just the AddImageTool)
+        assert len(used_tools) == 1, "Should only have the AddImageTool"
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_multimodal_agent_image_tool_handling():
+    """
+    Test that multimodal agents properly handle image tools in the CrewAgentExecutor
+    """
+    # Create a multimodal agent
+    multimodal_agent = Agent(
+        role="Image Analyst",
+        goal="Analyze images and provide descriptions",
+        backstory="You're an expert at analyzing and describing images.",
+        allow_delegation=False,
+        multimodal=True,
+    )
+
+    # Create a task that involves image analysis
+    task = Task(
+        description="Analyze this image and describe what you see.",
+        expected_output="A detailed description of the image.",
+        agent=multimodal_agent,
+    )
+
+    crew = Crew(agents=[multimodal_agent], tasks=[task])
+
+    # Mock the image tool response
+    mock_image_tool_result = {
+        "role": "user",
+        "content": [
+            {"type": "text", "text": "Please analyze this image"},
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": "https://example.com/test-image.jpg",
+                },
+            },
+        ],
+    }
+
+    # Create a mock task output for the final result
+    mock_task_output = TaskOutput(
+        description="Mock description",
+        raw="A detailed analysis of the image",
+        agent="Image Analyst",
+    )
+
+    with patch.object(Task, "execute_sync") as mock_execute_sync:
+        # Set up the mock to return our task output
+        mock_execute_sync.return_value = mock_task_output
+
+        # Execute the crew
+        crew.kickoff()
+
+        # Get the tools that were passed to execute_sync
+        _, kwargs = mock_execute_sync.call_args
+        tools = kwargs["tools"]
+
+        # Verify the AddImageTool is present and properly configured
+        image_tools = [tool for tool in tools if tool.name == "Add image to content"]
+        assert len(image_tools) == 1, "Should have exactly one AddImageTool"
+
+        # Test the tool's execution
+        image_tool = image_tools[0]
+        result = image_tool._run(
+            image_url="https://example.com/test-image.jpg",
+            action="Please analyze this image",
+        )
+
+        # Verify the tool returns the expected format
+        assert result == mock_image_tool_result
+        assert result["role"] == "user"
+        assert len(result["content"]) == 2
+        assert result["content"][0]["type"] == "text"
+        assert result["content"][1]["type"] == "image_url"
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_multimodal_agent_live_image_analysis():
+    """
+    Test that multimodal agents can analyze images through a real API call
+    """
+    # Create a multimodal agent
+    image_analyst = Agent(
+        role="Image Analyst",
+        goal="Analyze images with high attention to detail",
+        backstory="You're an expert at visual analysis, trained to notice and describe details in images.",
+        allow_delegation=False,
+        multimodal=True,
+        verbose=True,
+        llm="gpt-4o",
+    )
+
+    # Create a task for image analysis
+    analyze_image = Task(
+        description="""
+        Analyze the provided image and describe what you see in detail.
+        Focus on main elements, colors, composition, and any notable details.
+        Image: {image_url}
+        """,
+        expected_output="A comprehensive description of the image contents.",
+        agent=image_analyst,
+    )
+
+    # Create and run the crew
+    crew = Crew(agents=[image_analyst], tasks=[analyze_image])
+
+    # Execute with an image URL
+    result = crew.kickoff(
+        inputs={
+            "image_url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k="
+        }
+    )
+
+    # Verify we got a meaningful response
+    assert isinstance(result.raw, str)
+    assert len(result.raw) > 100  # Expecting a detailed analysis
+    assert "error" not in result.raw.lower()  # No error messages in response

tests/flow_test.py

@@ -263,3 +263,62 @@ def test_flow_with_custom_state():
     flow = StateFlow()
     flow.kickoff()
     assert flow.counter == 2
+
+
+def test_router_with_multiple_conditions():
+    """Test a router that triggers when any of multiple steps complete (OR condition),
+    and another router that triggers only after all specified steps complete (AND condition).
+    """
+
+    execution_order = []
+
+    class ComplexRouterFlow(Flow):
+        @start()
+        def step_a(self):
+            execution_order.append("step_a")
+
+        @start()
+        def step_b(self):
+            execution_order.append("step_b")
+
+        @router(or_("step_a", "step_b"))
+        def router_or(self):
+            execution_order.append("router_or")
+            return "next_step_or"
+
+        @listen("next_step_or")
+        def handle_next_step_or_event(self):
+            execution_order.append("handle_next_step_or_event")
+
+        @listen(handle_next_step_or_event)
+        def branch_2_step(self):
+            execution_order.append("branch_2_step")
+
+        @router(and_(handle_next_step_or_event, branch_2_step))
+        def router_and(self):
+            execution_order.append("router_and")
+            return "final_step"
+
+        @listen("final_step")
+        def log_final_step(self):
+            execution_order.append("log_final_step")
+
+    flow = ComplexRouterFlow()
+    flow.kickoff()
+
+    assert "step_a" in execution_order
+    assert "step_b" in execution_order
+    assert "router_or" in execution_order
+    assert "handle_next_step_or_event" in execution_order
+    assert "branch_2_step" in execution_order
+    assert "router_and" in execution_order
+    assert "log_final_step" in execution_order
+
+    # Check that the AND router triggered after both relevant steps:
+    assert execution_order.index("router_and") > execution_order.index(
+        "handle_next_step_or_event"
+    )
+    assert execution_order.index("router_and") > execution_order.index("branch_2_step")
+
+    # final_step should run after router_and
+    assert execution_order.index("log_final_step") > execution_order.index("router_and")

tests/knowledge/knowledge_test.py

@@ -1,10 +1,12 @@
 """Test Knowledge creation and querying functionality."""
 
 from pathlib import Path
+from typing import List, Union
 from unittest.mock import patch
 
 import pytest
 
+from crewai.knowledge.source.crew_docling_source import CrewDoclingSource
 from crewai.knowledge.source.csv_knowledge_source import CSVKnowledgeSource
 from crewai.knowledge.source.excel_knowledge_source import ExcelKnowledgeSource
 from crewai.knowledge.source.json_knowledge_source import JSONKnowledgeSource
@@ -200,7 +202,7 @@ def test_single_short_file(mock_vector_db, tmpdir):
         f.write(content)
 
     file_source = TextFileKnowledgeSource(
-        file_path=file_path, metadata={"preference": "personal"}
+        file_paths=[file_path], metadata={"preference": "personal"}
     )
     mock_vector_db.sources = [file_source]
     mock_vector_db.query.return_value = [{"context": content, "score": 0.9}]
@@ -242,7 +244,7 @@ def test_single_2k_character_file(mock_vector_db, tmpdir):
         f.write(content)
 
     file_source = TextFileKnowledgeSource(
-        file_path=file_path, metadata={"preference": "personal"}
+        file_paths=[file_path], metadata={"preference": "personal"}
     )
     mock_vector_db.sources = [file_source]
     mock_vector_db.query.return_value = [{"context": content, "score": 0.9}]
@@ -279,7 +281,7 @@ def test_multiple_short_files(mock_vector_db, tmpdir):
         file_paths.append((file_path, item["metadata"]))
 
     file_sources = [
-        TextFileKnowledgeSource(file_path=path, metadata=metadata)
+        TextFileKnowledgeSource(file_paths=[path], metadata=metadata)
         for path, metadata in file_paths
     ]
     mock_vector_db.sources = file_sources
@@ -352,7 +354,7 @@ def test_multiple_2k_character_files(mock_vector_db, tmpdir):
         file_paths.append(file_path)
 
     file_sources = [
-        TextFileKnowledgeSource(file_path=path, metadata={"preference": "personal"})
+        TextFileKnowledgeSource(file_paths=[path], metadata={"preference": "personal"})
         for path in file_paths
     ]
     mock_vector_db.sources = file_sources
@@ -399,7 +401,7 @@ def test_hybrid_string_and_files(mock_vector_db, tmpdir):
         file_paths.append(file_path)
 
     file_sources = [
-        TextFileKnowledgeSource(file_path=path, metadata={"preference": "personal"})
+        TextFileKnowledgeSource(file_paths=[path], metadata={"preference": "personal"})
         for path in file_paths
     ]
 
@@ -424,7 +426,7 @@ def test_pdf_knowledge_source(mock_vector_db):
 
     # Create a PDFKnowledgeSource
     pdf_source = PDFKnowledgeSource(
-        file_path=pdf_path, metadata={"preference": "personal"}
+        file_paths=[pdf_path], metadata={"preference": "personal"}
     )
     mock_vector_db.sources = [pdf_source]
     mock_vector_db.query.return_value = [
@@ -461,7 +463,7 @@ def test_csv_knowledge_source(mock_vector_db, tmpdir):
 
     # Create a CSVKnowledgeSource
     csv_source = CSVKnowledgeSource(
-        file_path=csv_path, metadata={"preference": "personal"}
+        file_paths=[csv_path], metadata={"preference": "personal"}
     )
     mock_vector_db.sources = [csv_source]
     mock_vector_db.query.return_value = [
@@ -496,7 +498,7 @@ def test_json_knowledge_source(mock_vector_db, tmpdir):
 
     # Create a JSONKnowledgeSource
     json_source = JSONKnowledgeSource(
-        file_path=json_path, metadata={"preference": "personal"}
+        file_paths=[json_path], metadata={"preference": "personal"}
     )
     mock_vector_db.sources = [json_source]
     mock_vector_db.query.return_value = [
@@ -529,7 +531,7 @@ def test_excel_knowledge_source(mock_vector_db, tmpdir):
 
     # Create an ExcelKnowledgeSource
     excel_source = ExcelKnowledgeSource(
-        file_path=excel_path, metadata={"preference": "personal"}
+        file_paths=[excel_path], metadata={"preference": "personal"}
     )
     mock_vector_db.sources = [excel_source]
     mock_vector_db.query.return_value = [
@@ -543,3 +545,59 @@ def test_excel_knowledge_source(mock_vector_db, tmpdir):
     # Assert that the correct information is retrieved
     assert any("30" in result["context"] for result in results)
     mock_vector_db.query.assert_called_once()
+
+
+def test_docling_source(mock_vector_db):
+    docling_source = CrewDoclingSource(
+        file_paths=[
+            "https://lilianweng.github.io/posts/2024-11-28-reward-hacking/",
+        ],
+    )
+    mock_vector_db.sources = [docling_source]
+    mock_vector_db.query.return_value = [
+        {
+            "context": "Reward hacking is a technique used to improve the performance of reinforcement learning agents.",
+            "score": 0.9,
+        }
+    ]
+    # Perform a query
+    query = "What is reward hacking?"
+    results = mock_vector_db.query(query)
+    assert any("reward hacking" in result["context"].lower() for result in results)
+    mock_vector_db.query.assert_called_once()
+
+
+def test_multiple_docling_sources():
+    urls: List[Union[Path, str]] = [
+        "https://lilianweng.github.io/posts/2024-11-28-reward-hacking/",
+        "https://lilianweng.github.io/posts/2024-07-07-hallucination/",
+    ]
+    docling_source = CrewDoclingSource(file_paths=urls)
+
+    assert docling_source.file_paths == urls
+    assert docling_source.content is not None
+
+
+def test_file_path_validation():
+    """Test file path validation for knowledge sources."""
+    current_dir = Path(__file__).parent
+    pdf_path = current_dir / "crewai_quickstart.pdf"
+
+    # Test valid single file_path
+    source = PDFKnowledgeSource(file_path=pdf_path)
+    assert source.safe_file_paths == [pdf_path]
+
+    # Test valid file_paths list
+    source = PDFKnowledgeSource(file_paths=[pdf_path])
+    assert source.safe_file_paths == [pdf_path]
+
+    # Test both file_path and file_paths provided (should use file_paths)
+    source = PDFKnowledgeSource(file_path=pdf_path, file_paths=[pdf_path])
+    assert source.safe_file_paths == [pdf_path]
+
+    # Test neither file_path nor file_paths provided
+    with pytest.raises(
+        ValueError,
+        match="file_path/file_paths must be a Path, str, or a list of these types",
+    ):
+        PDFKnowledgeSource()

tests/task_test.py

@@ -719,21 +719,60 @@ def test_interpolate_inputs():
     task = Task(
         description="Give me a list of 5 interesting ideas about {topic} to explore for an article, what makes them unique and interesting.",
         expected_output="Bullet point list of 5 interesting ideas about {topic}.",
+        output_file="/tmp/{topic}/output_{date}.txt",
     )
 
-    task.interpolate_inputs(inputs={"topic": "AI"})
+    task.interpolate_inputs(inputs={"topic": "AI", "date": "2024"})
     assert (
         task.description
         == "Give me a list of 5 interesting ideas about AI to explore for an article, what makes them unique and interesting."
     )
     assert task.expected_output == "Bullet point list of 5 interesting ideas about AI."
+    assert task.output_file == "/tmp/AI/output_2024.txt"
 
-    task.interpolate_inputs(inputs={"topic": "ML"})
+    task.interpolate_inputs(inputs={"topic": "ML", "date": "2025"})
     assert (
         task.description
         == "Give me a list of 5 interesting ideas about ML to explore for an article, what makes them unique and interesting."
     )
     assert task.expected_output == "Bullet point list of 5 interesting ideas about ML."
+    assert task.output_file == "/tmp/ML/output_2025.txt"
+
+
+def test_interpolate_only():
+    """Test the interpolate_only method for various scenarios including JSON structure preservation."""
+    task = Task(
+        description="Unused in this test", expected_output="Unused in this test"
+    )
+
+    # Test JSON structure preservation
+    json_string = '{"info": "Look at {placeholder}", "nested": {"val": "{nestedVal}"}}'
+    result = task.interpolate_only(
+        input_string=json_string,
+        inputs={"placeholder": "the data", "nestedVal": "something else"},
+    )
+    assert '"info": "Look at the data"' in result
+    assert '"val": "something else"' in result
+    assert "{placeholder}" not in result
+    assert "{nestedVal}" not in result
+
+    # Test normal string interpolation
+    normal_string = "Hello {name}, welcome to {place}!"
+    result = task.interpolate_only(
+        input_string=normal_string, inputs={"name": "John", "place": "CrewAI"}
+    )
+    assert result == "Hello John, welcome to CrewAI!"
+
+    # Test empty string
+    result = task.interpolate_only(input_string="", inputs={"unused": "value"})
+    assert result == ""
+
+    # Test string with no placeholders
+    no_placeholders = "Hello, this is a test"
+    result = task.interpolate_only(
+        input_string=no_placeholders, inputs={"unused": "value"}
+    )
+    assert result == no_placeholders
 
 
 def test_task_output_str_with_pydantic():
@@ -830,3 +869,70 @@ def test_key():
     assert (
         task.key == hash
     ), "The key should be the hash of the non-interpolated description."
+
+
+def test_output_file_validation():
+    """Test output file path validation."""
+    # Valid paths
+    assert (
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="output.txt",
+        ).output_file
+        == "output.txt"
+    )
+    assert (
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="/tmp/output.txt",
+        ).output_file
+        == "tmp/output.txt"
+    )
+    assert (
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="{dir}/output_{date}.txt",
+        ).output_file
+        == "{dir}/output_{date}.txt"
+    )
+
+    # Invalid paths
+    with pytest.raises(ValueError, match="Path traversal"):
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="../output.txt",
+        )
+    with pytest.raises(ValueError, match="Path traversal"):
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="folder/../output.txt",
+        )
+    with pytest.raises(ValueError, match="Shell special characters"):
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="output.txt | rm -rf /",
+        )
+    with pytest.raises(ValueError, match="Shell expansion"):
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="~/output.txt",
+        )
+    with pytest.raises(ValueError, match="Shell expansion"):
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="$HOME/output.txt",
+        )
+    with pytest.raises(ValueError, match="Invalid template variable"):
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="{invalid-name}/output.txt",
+        )

tests/test_manager_llm_delegation.py

@@ -0,0 +1,56 @@
+from unittest.mock import MagicMock
+
+import pytest
+
+from crewai import Agent, Task
+from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
+
+
+class TestAgentTool(BaseAgentTool):
+    """Concrete implementation of BaseAgentTool for testing."""
+
+    def _run(self, *args, **kwargs):
+        """Implement required _run method."""
+        return "Test response"
+
+
+@pytest.mark.parametrize(
+    "role_name,should_match",
+    [
+        ("Futel Official Infopoint", True),  # exact match
+        ('  "Futel Official Infopoint"  ', True),  # extra quotes and spaces
+        ("Futel Official Infopoint\n", True),  # trailing newline
+        ('"Futel Official Infopoint"', True),  # embedded quotes
+        (" FUTEL\nOFFICIAL   INFOPOINT ", True),  # multiple whitespace and newline
+        ("futel official infopoint", True),  # lowercase
+        ("FUTEL OFFICIAL INFOPOINT", True),  # uppercase
+        ("Non Existent Agent", False),  # non-existent agent
+        (None, False),  # None agent name
+    ],
+)
+def test_agent_tool_role_matching(role_name, should_match):
+    """Test that agent tools can match roles regardless of case, whitespace, and special characters."""
+    # Create test agent
+    test_agent = Agent(
+        role="Futel Official Infopoint",
+        goal="Answer questions about Futel",
+        backstory="Futel Football Club info",
+        allow_delegation=False,
+    )
+
+    # Create test agent tool
+    agent_tool = TestAgentTool(
+        name="test_tool", description="Test tool", agents=[test_agent]
+    )
+
+    # Test role matching
+    result = agent_tool._execute(agent_name=role_name, task="Test task", context=None)
+
+    if should_match:
+        assert (
+            "coworker mentioned not found" not in result.lower()
+        ), f"Should find agent with role name: {role_name}"
+    else:
+        assert (
+            "coworker mentioned not found" in result.lower()
+        ), f"Should not find agent with role name: {role_name}"

tests/test_task_guardrails.py

@@ -0,0 +1,129 @@
+"""Tests for task guardrails functionality."""
+
+from unittest.mock import Mock
+
+import pytest
+
+from crewai.task import Task
+from crewai.tasks.task_output import TaskOutput
+
+
+def test_task_without_guardrail():
+    """Test that tasks work normally without guardrails (backward compatibility)."""
+    agent = Mock()
+    agent.role = "test_agent"
+    agent.execute_task.return_value = "test result"
+    agent.crew = None
+
+    task = Task(description="Test task", expected_output="Output")
+
+    result = task.execute_sync(agent=agent)
+    assert isinstance(result, TaskOutput)
+    assert result.raw == "test result"
+
+
+def test_task_with_successful_guardrail():
+    """Test that successful guardrail validation passes transformed result."""
+
+    def guardrail(result: TaskOutput):
+        return (True, result.raw.upper())
+
+    agent = Mock()
+    agent.role = "test_agent"
+    agent.execute_task.return_value = "test result"
+    agent.crew = None
+
+    task = Task(description="Test task", expected_output="Output", guardrail=guardrail)
+
+    result = task.execute_sync(agent=agent)
+    assert isinstance(result, TaskOutput)
+    assert result.raw == "TEST RESULT"
+
+
+def test_task_with_failing_guardrail():
+    """Test that failing guardrail triggers retry with error context."""
+
+    def guardrail(result: TaskOutput):
+        return (False, "Invalid format")
+
+    agent = Mock()
+    agent.role = "test_agent"
+    agent.execute_task.side_effect = ["bad result", "good result"]
+    agent.crew = None
+
+    task = Task(
+        description="Test task",
+        expected_output="Output",
+        guardrail=guardrail,
+        max_retries=1,
+    )
+
+    # First execution fails guardrail, second succeeds
+    agent.execute_task.side_effect = ["bad result", "good result"]
+    with pytest.raises(Exception) as exc_info:
+        task.execute_sync(agent=agent)
+
+    assert "Task failed guardrail validation" in str(exc_info.value)
+    assert task.retry_count == 1
+
+
+def test_task_with_guardrail_retries():
+    """Test that guardrail respects max_retries configuration."""
+
+    def guardrail(result: TaskOutput):
+        return (False, "Invalid format")
+
+    agent = Mock()
+    agent.role = "test_agent"
+    agent.execute_task.return_value = "bad result"
+    agent.crew = None
+
+    task = Task(
+        description="Test task",
+        expected_output="Output",
+        guardrail=guardrail,
+        max_retries=2,
+    )
+
+    with pytest.raises(Exception) as exc_info:
+        task.execute_sync(agent=agent)
+
+    assert task.retry_count == 2
+    assert "Task failed guardrail validation after 2 retries" in str(exc_info.value)
+    assert "Invalid format" in str(exc_info.value)
+
+
+def test_guardrail_error_in_context():
+    """Test that guardrail error is passed in context for retry."""
+
+    def guardrail(result: TaskOutput):
+        return (False, "Expected JSON, got string")
+
+    agent = Mock()
+    agent.role = "test_agent"
+    agent.crew = None
+
+    task = Task(
+        description="Test task",
+        expected_output="Output",
+        guardrail=guardrail,
+        max_retries=1,
+    )
+
+    # Mock execute_task to succeed on second attempt
+    first_call = True
+
+    def execute_task(task, context, tools):
+        nonlocal first_call
+        if first_call:
+            first_call = False
+            return "invalid"
+        return '{"valid": "json"}'
+
+    agent.execute_task.side_effect = execute_task
+
+    with pytest.raises(Exception) as exc_info:
+        task.execute_sync(agent=agent)
+
+    assert "Task failed guardrail validation" in str(exc_info.value)
+    assert "Expected JSON, got string" in str(exc_info.value)

tests/utilities/test_knowledge_planning.py

@@ -0,0 +1,84 @@
+"""
+Tests for verifying the integration of knowledge sources in the planning process.
+This module ensures that agent knowledge is properly included during task planning.
+"""
+
+from unittest.mock import patch
+
+import pytest
+
+from crewai.agent import Agent
+from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
+from crewai.task import Task
+from crewai.utilities.planning_handler import CrewPlanner
+
+
+@pytest.fixture
+def mock_knowledge_source():
+    """
+    Create a mock knowledge source with test content.
+    Returns:
+        StringKnowledgeSource:
+            A knowledge source containing AI-related test content
+    """
+    content = """
+    Important context about AI:
+    1. AI systems use machine learning algorithms
+    2. Neural networks are a key component
+    3. Training data is essential for good performance
+    """
+    return StringKnowledgeSource(content=content)
+
+@patch('crewai.knowledge.storage.knowledge_storage.chromadb')
+def test_knowledge_included_in_planning(mock_chroma):
+    """Test that verifies knowledge sources are properly included in planning."""
+    # Mock ChromaDB collection
+    mock_collection = mock_chroma.return_value.get_or_create_collection.return_value
+    mock_collection.add.return_value = None
+    
+    # Create an agent with knowledge
+    agent = Agent(
+        role="AI Researcher",
+        goal="Research and explain AI concepts",
+        backstory="Expert in artificial intelligence",
+        knowledge_sources=[
+            StringKnowledgeSource(
+                content="AI systems require careful training and validation."
+            )
+        ]
+    )
+
+    # Create a task for the agent
+    task = Task(
+        description="Explain the basics of AI systems",
+        expected_output="A clear explanation of AI fundamentals",
+        agent=agent
+    )
+
+    # Create a crew planner
+    planner = CrewPlanner([task], None)
+
+    # Get the task summary
+    task_summary = planner._create_tasks_summary()
+
+    # Verify that knowledge is included in planning when present
+    assert "AI systems require careful training" in task_summary, \
+        "Knowledge content should be present in task summary when knowledge exists"
+    assert '"agent_knowledge"' in task_summary, \
+        "agent_knowledge field should be present in task summary when knowledge exists"
+
+    # Verify that knowledge is properly formatted
+    assert isinstance(task.agent.knowledge_sources, list), \
+        "Knowledge sources should be stored in a list"
+    assert len(task.agent.knowledge_sources) > 0, \
+        "At least one knowledge source should be present"
+    assert task.agent.knowledge_sources[0].content in task_summary, \
+        "Knowledge source content should be included in task summary"
+
+    # Verify that other expected components are still present
+    assert task.description in task_summary, \
+        "Task description should be present in task summary"
+    assert task.expected_output in task_summary, \
+        "Expected output should be present in task summary"
+    assert agent.role in task_summary, \
+        "Agent role should be present in task summary"

tests/utilities/test_planning_handler.py

@@ -1,10 +1,14 @@
-from unittest.mock import patch
+from typing import Optional
+from unittest.mock import MagicMock, patch
 
 import pytest
+from pydantic import BaseModel
 
 from crewai.agent import Agent
+from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.task import Task
 from crewai.tasks.task_output import TaskOutput
+from crewai.tools.base_tool import BaseTool
 from crewai.utilities.planning_handler import (
     CrewPlanner,
     PlannerTaskPydanticOutput,
@@ -92,7 +96,72 @@ class TestCrewPlanner:
         tasks_summary = crew_planner._create_tasks_summary()
         assert isinstance(tasks_summary, str)
         assert tasks_summary.startswith("\n                Task Number 1 - Task 1")
-        assert tasks_summary.endswith('"agent_tools": []\n                ')
+        assert '"agent_tools": "agent has no tools"' in tasks_summary
+        # Knowledge field should not be present when empty
+        assert '"agent_knowledge"' not in tasks_summary
+
+    @patch('crewai.knowledge.storage.knowledge_storage.chromadb')
+    def test_create_tasks_summary_with_knowledge_and_tools(self, mock_chroma):
+        """Test task summary generation with both knowledge and tools present."""
+        # Mock ChromaDB collection
+        mock_collection = mock_chroma.return_value.get_or_create_collection.return_value
+        mock_collection.add.return_value = None
+
+        # Create mock tools with proper string descriptions and structured tool support
+        class MockTool(BaseTool):
+            name: str
+            description: str
+
+            def __init__(self, name: str, description: str):
+                tool_data = {"name": name, "description": description}
+                super().__init__(**tool_data)
+            
+            def __str__(self):
+                return self.name
+            
+            def __repr__(self):
+                return self.name
+            
+            def to_structured_tool(self):
+                return self
+
+            def _run(self, *args, **kwargs):
+                pass
+
+            def _generate_description(self) -> str:
+                """Override _generate_description to avoid args_schema handling."""
+                return self.description
+
+        tool1 = MockTool("tool1", "Tool 1 description")
+        tool2 = MockTool("tool2", "Tool 2 description")
+
+        # Create a task with knowledge and tools
+        task = Task(
+            description="Task with knowledge and tools",
+            expected_output="Expected output",
+            agent=Agent(
+                role="Test Agent",
+                goal="Test Goal",
+                backstory="Test Backstory",
+                tools=[tool1, tool2],
+                knowledge_sources=[
+                    StringKnowledgeSource(content="Test knowledge content")
+                ]
+            )
+        )
+        
+        # Create planner with the new task
+        planner = CrewPlanner([task], None)
+        tasks_summary = planner._create_tasks_summary()
+        
+        # Verify task summary content
+        assert isinstance(tasks_summary, str)
+        assert task.description in tasks_summary
+        assert task.expected_output in tasks_summary
+        assert '"agent_tools": [tool1, tool2]' in tasks_summary
+        assert '"agent_knowledge": "[\\"Test knowledge content\\"]"' in tasks_summary
+        assert task.agent.role in tasks_summary
+        assert task.agent.goal in tasks_summary
 
     def test_handle_crew_planning_different_llm(self, crew_planner_different_llm):
         with patch.object(Task, "execute_sync") as execute: