docs: improve tool documentation and examples

- Update SerperDevTool documentation with accurate parameters and JSON response format
- Enhance XMLSearchTool and MDXSearchTool docs with RAG capabilities and required parameters
- Fix code block formatting across multiple tool documentation files
- Add clarification about environment variables and configuration
- Validate all examples against actual implementations
- Successfully tested with mkdocs build

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

README.md

@@ -85,6 +85,7 @@ 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
@@ -92,22 +93,6 @@ 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:

docs/concepts/knowledge.mdx

@@ -171,58 +171,6 @@ 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/memory.mdx

@@ -35,10 +35,41 @@ By default, the memory system is disabled, and you can ensure it is active by se
 The memory will use OpenAI embeddings by default, but you can change it by setting `embedder` to a different model. 
 It's also possible to initialize the memory instance with your own instance.
 
-The 'embedder' only applies to **Short-Term Memory** which uses Chroma for RAG.
-The **Long-Term Memory** uses SQLite3 to store task results. Currently, there is no way to override these storage implementations.
-The data storage files are saved into a platform-specific location found using the appdirs package,
-and the name of the project can be overridden using the **CREWAI_STORAGE_DIR** environment variable.
+Each memory type uses different storage implementations:
+
+- **Short-Term Memory**: Uses Chroma for RAG (Retrieval-Augmented Generation) with configurable embeddings
+- **Long-Term Memory**: Uses SQLite3 for persistent storage of task results and metadata
+- **Entity Memory**: Uses either RAG storage (default) or Mem0 for entity information
+- **User Memory**: Available through Mem0 integration for personalized experiences
+
+The data storage files are saved in a platform-specific location using the appdirs package.
+You can override the storage location using the **CREWAI_STORAGE_DIR** environment variable.
+
+### Storage Implementation Details
+
+#### Short-Term Memory
+- Default: ChromaDB with RAG
+- Configurable embeddings (OpenAI, Ollama, Google AI, etc.)
+- Supports custom embedding functions
+- Optional Mem0 integration for enhanced capabilities
+
+#### Long-Term Memory
+- SQLite3 storage with structured schema
+- Stores task descriptions, metadata, timestamps, and quality scores
+- Supports querying by task description with configurable limits
+- Includes error handling and reset capabilities
+
+#### Entity Memory
+- Default: RAG storage with ChromaDB
+- Optional Mem0 integration
+- Structured entity storage (name, type, description)
+- Supports metadata and relationship mapping
+
+#### User Memory
+- Requires Mem0 integration
+- Stores user preferences and interaction history
+- Supports personalized context building
+- Configurable through memory_config
 
 ### Example: Configuring Memory for a Crew
 
@@ -93,11 +124,41 @@ my_crew = Crew(
 )
 ```
 
-## Integrating Mem0 for Enhanced User Memory
+## Integrating Mem0 Provider
 
-[Mem0](https://mem0.ai/) is a self-improving memory layer for LLM applications, enabling personalized AI experiences. 
+[Mem0](https://mem0.ai/) is a self-improving memory layer for LLM applications that can enhance all memory types in CrewAI. It provides advanced features for storing and retrieving contextual information.
 
-To include user-specific memory you can get your API key [here](https://app.mem0.ai/dashboard/api-keys) and refer the [docs](https://docs.mem0.ai/platform/quickstart#4-1-create-memories) for adding user preferences.
+### Configuration
+
+To use Mem0, you'll need:
+1. An API key from [Mem0 Dashboard](https://app.mem0.ai/dashboard/api-keys)
+2. The `mem0ai` package installed: `pip install mem0ai`
+
+You can configure Mem0 in two ways:
+
+1. **Environment Variable**:
+```bash
+export MEM0_API_KEY="your-api-key"
+```
+
+2. **Memory Config**:
+```python
+memory_config = {
+    "provider": "mem0",
+    "config": {
+        "api_key": "your-api-key",
+        "user_id": "user123"  # Required for user memory
+    }
+}
+```
+
+### Memory Type Support
+
+Mem0 can be used with all memory types:
+- **Short-Term Memory**: Enhanced context retention
+- **Long-Term Memory**: Improved task history storage
+- **Entity Memory**: Better entity relationship tracking
+- **User Memory**: Personalized user preferences and history
 
 
 ```python Code
@@ -135,9 +196,118 @@ crew = Crew(
 ```
 
 
-## Additional Embedding Providers
+## Memory Interface Details
 
-### Using OpenAI embeddings (already default)
+When implementing custom memory storage, be aware of these interface requirements:
+
+### Base Memory Class
+```python
+class Memory:
+    def save(
+        self,
+        value: Any,
+        metadata: Optional[Dict[str, Any]] = None,
+        agent: Optional[str] = None,
+    ) -> None:
+        """Save data to memory with optional metadata and agent information."""
+        pass
+
+    def search(
+        self,
+        query: str,
+        limit: int = 3,
+        score_threshold: float = 0.35,
+    ) -> List[Any]:
+        """Search memory with configurable limit and relevance threshold."""
+        pass
+```
+
+### Memory Type Specifics
+
+1. **LongTermMemory**:
+   ```python
+   class LongTermMemoryItem:
+       task: str                      # Task description
+       expected_output: str           # Expected task output
+       metadata: Dict[str, Any]       # Additional metadata
+       agent: Optional[str] = None    # Associated agent
+       datetime: str                  # Timestamp
+       quality: float                 # Task quality score (0-1)
+   ```
+   - Saves task results with quality scores and timestamps
+   - Search returns historical task data ordered by date
+   - Note: Implementation has type hint differences from base Memory class
+
+2. **EntityMemory**:
+   ```python
+   class EntityMemoryItem:
+       name: str                      # Entity name
+       type: str                      # Entity type
+       description: str               # Entity description
+       metadata: Dict[str, Any]       # Additional metadata
+       agent: Optional[str] = None    # Associated agent
+   ```
+   - Saves entity information with type and description
+   - Search supports entity relationship queries
+   - Note: Implementation has type hint differences from base Memory class
+
+3. **ShortTermMemory**:
+   ```python
+   class ShortTermMemoryItem:
+       data: Any                      # Memory content
+       metadata: Dict[str, Any]       # Additional metadata
+       agent: Optional[str] = None    # Associated agent
+   ```
+   - Saves recent interactions with metadata
+   - Search supports semantic similarity
+   - Follows base Memory class interface exactly
+
+### Error Handling and Reset
+
+Each memory type includes error handling and reset capabilities:
+
+```python
+# Reset short-term memory
+try:
+    crew.short_term_memory.reset()
+except Exception as e:
+    print(f"Error resetting short-term memory: {e}")
+
+# Reset entity memory
+try:
+    crew.entity_memory.reset()
+except Exception as e:
+    print(f"Error resetting entity memory: {e}")
+
+# Reset long-term memory
+try:
+    crew.long_term_memory.reset()
+except Exception as e:
+    print(f"Error resetting long-term memory: {e}")
+```
+
+Common error scenarios:
+- Database connection issues
+- File permission errors
+- Storage initialization failures
+- Embedding generation errors
+
+### Implementation Notes
+
+1. **Type Hint Considerations**:
+   - LongTermMemory.save() expects LongTermMemoryItem
+   - EntityMemory.save() expects EntityMemoryItem
+   - ShortTermMemory.save() follows base Memory interface
+
+2. **Storage Reset Behavior**:
+   - Short-term: Clears ChromaDB collection
+   - Long-term: Truncates SQLite table
+   - Entity: Clears entity storage
+   - Mem0: Provider-specific reset
+
+## Embedding Providers
+
+CrewAI supports multiple embedding providers for RAG-based memory types:
 ```python Code
 from crewai import Crew, Agent, Task, Process
 

docs/how-to/mlflow-observability.mdx

@@ -0,0 +1,196 @@
+---
+title: Agent Monitoring with MLFlow
+description: How to monitor and track CrewAI Agents using MLFlow for experiment tracking and model registry.
+icon: chart-line
+---
+
+# Introduction
+
+MLFlow is an open-source platform for managing the end-to-end machine learning lifecycle. When integrated with CrewAI, it provides powerful capabilities for tracking agent performance, logging metrics, and managing experiments. This guide demonstrates how to implement precise monitoring and tracking of your CrewAI agents using MLFlow.
+
+## MLFlow Integration
+
+MLFlow offers comprehensive experiment tracking and model registry capabilities that complement CrewAI's agent-based workflows:
+
+- **Experiment Tracking**: Monitor agent performance metrics and execution patterns
+- **Metric Logging**: Track costs, latency, and success rates
+- **Artifact Management**: Store and version agent configurations and outputs
+- **Model Registry**: Maintain different versions of agent configurations
+
+### Features
+
+- **Real-time Monitoring**: Track agent performance as tasks are executed
+- **Metric Collection**: Gather detailed statistics on agent operations
+- **Experiment Organization**: Group related agent runs for comparison
+- **Resource Tracking**: Monitor computational and token usage
+- **Custom Metrics**: Define and track domain-specific performance indicators
+
+## Getting Started
+
+<Steps>
+   <Step title="Install Dependencies">
+      Install MLFlow alongside CrewAI:
+      ```bash
+      pip install mlflow crewai
+      ```
+   </Step>
+   <Step title="Configure MLFlow">
+      Set up MLFlow tracking in your environment:
+      ```python
+      import mlflow
+      from crewai import Agent, Task, Crew
+      
+      # Configure MLFlow tracking
+      mlflow.set_tracking_uri("http://localhost:5000")
+      mlflow.set_experiment("crewai-agents")
+      ```
+   </Step>
+   <Step title="Create Tracking Callbacks">
+      Implement MLFlow callbacks for monitoring:
+      ```python
+      class MLFlowCallback:
+          def __init__(self):
+              self.start_time = time.time()
+              
+          def on_step(self, agent, task, step_number, step_input, step_output):
+              mlflow.log_metrics({
+                  "step_number": step_number,
+                  "step_duration": time.time() - self.start_time,
+                  "output_length": len(step_output)
+              })
+              
+          def on_task(self, agent, task, output):
+              mlflow.log_metrics({
+                  "task_duration": time.time() - self.start_time,
+                  "final_output_length": len(output)
+              })
+              mlflow.log_param("task_description", task.description)
+      ```
+   </Step>
+   <Step title="Integrate with CrewAI">
+      Apply MLFlow tracking to your CrewAI agents:
+      ```python
+      # Create MLFlow callback
+      mlflow_callback = MLFlowCallback()
+      
+      # Create agent with tracking
+      researcher = Agent(
+          role='Researcher',
+          goal='Conduct market analysis',
+          backstory='Expert market researcher with deep analytical skills',
+          step_callback=mlflow_callback.on_step
+      )
+      
+      # Create crew with tracking
+      crew = Crew(
+          agents=[researcher],
+          tasks=[...],
+          task_callback=mlflow_callback.on_task
+      )
+      
+      # Execute with MLFlow tracking
+      with mlflow.start_run():
+          result = crew.kickoff()
+      ```
+   </Step>
+</Steps>
+
+## Advanced Usage
+
+### Custom Metric Tracking
+
+Track specific metrics relevant to your use case:
+
+```python
+class CustomMLFlowCallback:
+    def __init__(self):
+        self.metrics = {}
+        
+    def on_step(self, agent, task, step_number, step_input, step_output):
+        # Track custom metrics
+        self.metrics[f"agent_{agent.role}_steps"] = step_number
+        
+        # Log tool usage
+        if hasattr(task, 'tools'):
+            for tool in task.tools:
+                mlflow.log_param(f"tool_used_{step_number}", tool.name)
+        
+        # Track token usage
+        mlflow.log_metric(
+            f"step_{step_number}_tokens",
+            len(step_output)
+        )
+```
+
+### Experiment Organization
+
+Group related experiments for better analysis:
+
+```python
+def run_agent_experiment(agent_config, task_config):
+    with mlflow.start_run(
+        run_name=f"agent_experiment_{agent_config['role']}"
+    ) as run:
+        # Log configuration
+        mlflow.log_params(agent_config)
+        mlflow.log_params(task_config)
+        
+        # Create and run agent
+        agent = Agent(**agent_config)
+        task = Task(**task_config)
+        
+        # Execute and log results
+        result = agent.execute(task)
+        mlflow.log_metric("execution_time", task.execution_time)
+        
+        return result
+```
+
+## Best Practices
+
+1. **Structured Logging**
+   - Use consistent metric names across experiments
+   - Group related metrics using common prefixes
+   - Include timestamps for temporal analysis
+
+2. **Resource Monitoring**
+   - Track token usage per agent and task
+   - Monitor execution time for performance optimization
+   - Log tool usage patterns and success rates
+
+3. **Experiment Organization**
+   - Use meaningful experiment names
+   - Group related runs under the same experiment
+   - Tag runs with relevant metadata
+
+4. **Performance Optimization**
+   - Monitor agent efficiency metrics
+   - Track resource utilization
+   - Identify bottlenecks in task execution
+
+## Viewing Results
+
+Access your MLFlow dashboard to analyze agent performance:
+
+1. Start the MLFlow UI:
+   ```bash
+   mlflow ui --port 5000
+   ```
+
+2. Open your browser and navigate to `http://localhost:5000`
+
+3. View experiment results including:
+   - Agent performance metrics
+   - Task execution times
+   - Resource utilization
+   - Custom metrics and parameters
+
+## Security Considerations
+
+- Ensure sensitive data is properly sanitized before logging
+- Use appropriate access controls for MLFlow server
+- Monitor and audit logged information regularly
+
+## Conclusion
+
+MLFlow integration provides comprehensive monitoring and experimentation capabilities for CrewAI agents. By following these guidelines and best practices, you can effectively track, analyze, and optimize your agent-based workflows while maintaining security and efficiency.

docs/mint.json

@@ -100,7 +100,8 @@
         "how-to/conditional-tasks",
         "how-to/agentops-observability",
         "how-to/langtrace-observability",
-        "how-to/openlit-observability"
+        "how-to/openlit-observability",
+        "how-to/mlflow-observability"
       ]
     },
     {
@@ -163,4 +164,4 @@
     "linkedin": "https://www.linkedin.com/company/crewai-inc",
     "youtube": "https://youtube.com/@crewAIInc"
   }
-}
+}

docs/tools/codeinterpretertool.mdx

@@ -31,7 +31,7 @@ Remember that when using this tool, the code must be generated by the Agent itse
 The code must be a Python3 code. And it will take some time for the first time to run 
 because it needs to build the Docker image.
 
-```python Code
+```python
 from crewai import Agent
 from crewai_tools import CodeInterpreterTool
 
@@ -43,7 +43,7 @@ Agent(
 
 We also provide a simple way to use it directly from the Agent.
 
-```python Code
+```python
 from crewai import Agent
 
 agent = Agent(

docs/tools/composiotool.mdx

@@ -27,7 +27,7 @@ The following example demonstrates how to initialize the tool and execute a gith
 
 1. Initialize Composio tools
 
-```python Code
+```python
 from composio import App
 from crewai_tools import ComposioTool
 from crewai import Agent, Task
@@ -38,19 +38,19 @@ tools = [ComposioTool.from_action(action=Action.GITHUB_ACTIVITY_STAR_REPO_FOR_AU
 
 If you don't know what action you want to use, use `from_app` and `tags` filter to get relevant actions
 
-```python Code
+```python
 tools = ComposioTool.from_app(App.GITHUB, tags=["important"])
 ```
 
 or use `use_case` to search relevant actions
 
-```python Code
+```python
 tools = ComposioTool.from_app(App.GITHUB, use_case="Star a github repository")
 ```
 
 2. Define agent
 
-```python Code
+```python
 crewai_agent = Agent(
     role="Github Agent",
     goal="You take action on Github using Github APIs",
@@ -65,7 +65,7 @@ crewai_agent = Agent(
 
 3. Execute task
 
-```python Code
+```python
 task = Task(
     description="Star a repo ComposioHQ/composio on GitHub",
     agent=crewai_agent,
@@ -75,4 +75,4 @@ task = Task(
 task.execute()
 ```
 
-* More detailed list of tools can be found [here](https://app.composio.dev)
+* More detailed list of tools can be found [here](https://app.composio.dev)

docs/tools/dalletool.mdx

@@ -22,7 +22,7 @@ pip install 'crewai[tools]'
 
 Remember that when using this tool, the text must be generated by the Agent itself. The text must be a description of the image you want to generate.
 
-```python Code
+```python
 from crewai_tools import DallETool
 
 Agent(
@@ -31,9 +31,16 @@ Agent(
 )
 ```
 
-If needed you can also tweak the parameters of the DALL-E model by passing them as arguments to the `DallETool` class. For example:
+## Arguments
 
-```python Code
+- `model`: The DALL-E model to use (e.g., "dall-e-3")
+- `size`: Image size (e.g., "1024x1024")
+- `quality`: Image quality ("standard" or "hd")
+- `n`: Number of images to generate
+
+## Configuration Example
+
+```python
 from crewai_tools import DallETool
 
 dalle_tool = DallETool(model="dall-e-3",
@@ -48,4 +55,4 @@ Agent(
 ```
 
 The parameters are based on the `client.images.generate` method from the OpenAI API. For more information on the parameters, 
-please refer to the [OpenAI API documentation](https://platform.openai.com/docs/guides/images/introduction?lang=python).
+please refer to the [OpenAI API documentation](https://platform.openai.com/docs/guides/images/introduction?lang=python).

docs/tools/filewritetool.mdx

@@ -20,11 +20,11 @@ Install the crewai_tools package to use the `FileWriterTool` in your projects:
 pip install 'crewai[tools]'
 ```
 
-## Example
+## Usage
 
-To get started with the `FileWriterTool`:
+Here's how to use the `FileWriterTool`:
 
-```python Code
+```python
 from crewai_tools import FileWriterTool
 
 # Initialize the tool
@@ -45,4 +45,4 @@ print(result)
 
 By integrating the `FileWriterTool` into your crews, the agents can execute the process of writing content to files and creating directories. 
 This tool is essential for tasks that require saving output data, creating structured file systems, and more. By adhering to the setup and usage guidelines provided, 
-incorporating this tool into projects is straightforward and efficient.
+incorporating this tool into projects is straightforward and efficient.

docs/tools/jsonsearchtool.mdx

@@ -23,11 +23,11 @@ To install the JSONSearchTool, use the following pip command:
 pip install 'crewai[tools]'
 ```
 
-## Usage Examples
+## Example
 
 Here are updated examples on how to utilize the JSONSearchTool effectively for searching within JSON files. These examples take into account the current implementation and usage patterns identified in the codebase.
 
-```python Code
+```python
 from crewai.json_tools import JSONSearchTool  # Updated import path
 
 # General JSON content search
@@ -47,7 +47,7 @@ tool = JSONSearchTool(json_path='./path/to/your/file.json')
 
 The JSONSearchTool supports extensive customization through a configuration dictionary. This allows users to select different models for embeddings and summarization based on their requirements.
 
-```python Code
+```python
 tool = JSONSearchTool(
     config={
         "llm": {
@@ -70,4 +70,4 @@ tool = JSONSearchTool(
         },
     }
 )
-```
+```

docs/tools/mdxsearchtool.mdx

@@ -22,11 +22,13 @@ Before using the MDX Search Tool, ensure the `crewai_tools` package is installed
 pip install 'crewai[tools]'
 ```
 
-## Usage Example
+## Example
 
-To use the MDX Search Tool, you must first set up the necessary environment variables. Then, integrate the tool into your crewAI project to begin your market research. Below is a basic example of how to do this:
+To use the MDX Search Tool, you must first set up the necessary environment variables for your chosen LLM and embeddings providers (e.g., OpenAI API key if using the default configuration). Then, integrate the tool into your crewAI project as shown in the examples below.
 
-```python Code
+The tool will perform semantic search using RAG technology to find and extract relevant content from your MDX files based on the search query:
+
+```python
 from crewai_tools import MDXSearchTool
 
 # Initialize the tool to search any MDX content it learns about during execution
@@ -40,13 +42,16 @@ tool = MDXSearchTool(mdx='path/to/your/document.mdx')
 
 ## Parameters
 
-- mdx: **Optional**. Specifies the MDX file path for the search. It can be provided during initialization.
+- `mdx`: **Optional**. Specifies the MDX file path for the search. It can be provided during initialization or when running the search.
+- `search_query`: **Required**. The query string to search for within the MDX content.
+
+The tool inherits from `RagTool` which provides advanced RAG (Retrieval-Augmented Generation) capabilities for semantic search within MDX content.
 
 ## Customization of Model and Embeddings
 
 The tool defaults to using OpenAI for embeddings and summarization. For customization, utilize a configuration dictionary as shown below:
 
-```python Code
+```python
 tool = MDXSearchTool(
     config=dict(
         llm=dict(
@@ -70,4 +75,4 @@ tool = MDXSearchTool(
         ),
     )
 )
-```
+```

docs/tools/serperdevtool.mdx

@@ -27,7 +27,7 @@ pip install 'crewai[tools]'
 
 The following example demonstrates how to initialize the tool and execute a search with a given query:
 
-```python Code
+```python
 from crewai_tools import SerperDevTool
 
 # Initialize the tool for internet searching capabilities
@@ -44,22 +44,27 @@ To effectively use the `SerperDevTool`, follow these steps:
 
 ## Parameters
 
-The `SerperDevTool` comes with several parameters that will be passed to the API :
+The `SerperDevTool` comes with several parameters that can be configured:
 
-- **search_url**: The URL endpoint for the search API. (Default is `https://google.serper.dev/search`)
+- **base_url**: The base URL for the Serper API. Default is `https://google.serper.dev`.
+- **n_results**: Number of search results to return. Default is `10`.
+- **save_file**: Boolean flag to save search results to a file. Default is `False`.
+- **search_type**: Type of search to perform. Can be either `search` (default) or `news`.
 
+Additional parameters that can be passed during search:
 - **country**: Optional. Specify the country for the search results.
 - **location**: Optional. Specify the location for the search results.
 - **locale**: Optional. Specify the locale for the search results.
-- **n_results**: Number of search results to return. Default is `10`.
 
-The values for `country`, `location`, `locale` and `search_url` can be found on the [Serper Playground](https://serper.dev/playground).
+The values for `country`, `location`, and `locale` can be found on the [Serper Playground](https://serper.dev/playground).
+
+Note: The tool requires the `SERPER_API_KEY` environment variable to be set with your Serper API key.
 
 ## Example with Parameters
 
 Here is an example demonstrating how to use the tool with additional parameters:
 
-```python Code
+```python
 from crewai_tools import SerperDevTool
 
 tool = SerperDevTool(
@@ -71,18 +76,29 @@ print(tool.run(search_query="ChatGPT"))
 
 # Using Tool: Search the internet
 
-# Search results: Title: Role of chat gpt in public health
-# Link: https://link.springer.com/article/10.1007/s10439-023-03172-7
-# Snippet: … ChatGPT in public health. In this overview, we will examine the potential uses of ChatGPT in
-# ---
-# Title: Potential use of chat gpt in global warming
-# Link: https://link.springer.com/article/10.1007/s10439-023-03171-8
-# Snippet: … as ChatGPT, have the potential to play a critical role in advancing our understanding of climate
-# ---
+# Search results:
+{
+  "searchParameters": {
+    "q": "ChatGPT",
+    "type": "search"
+  },
+  "organic": [
+    {
+      "title": "Role of chat gpt in public health",
+      "link": "https://link.springer.com/article/10.1007/s10439-023-03172-7",
+      "snippet": "ChatGPT in public health. In this overview, we will examine the potential uses of ChatGPT in"
+    },
+    {
+      "title": "Potential use of chat gpt in global warming",
+      "link": "https://link.springer.com/article/10.1007/s10439-023-03171-8",
+      "snippet": "as ChatGPT, have the potential to play a critical role in advancing our understanding of climate"
+    }
+  ]
+}
 
 ```
 
-```python Code
+```python
 from crewai_tools import SerperDevTool
 
 tool = SerperDevTool(

docs/tools/spidertool.mdx

@@ -26,7 +26,7 @@ pip install spider-client 'crewai[tools]'
 This example shows you how you can use the `SpiderTool` to enable your agent to scrape and crawl websites. 
 The data returned from the Spider API is already LLM-ready, so no need to do any cleaning there.
 
-```python Code
+```python
 from crewai_tools import SpiderTool
 
 def main():
@@ -89,4 +89,4 @@ if __name__ == "__main__":
 | **query_selector**  | `string`   | CSS query selector for content extraction from markup.                                                                                                |
 | **full_resources**  | `bool`     | Downloads all resources linked to the website.                                                                                                        |
 | **request_timeout** | `int`      | Timeout in seconds for requests (5-60). Default is `30`.                                                                                              |
-| **run_in_background** | `bool`   | Runs the request in the background, useful for data storage and triggering dashboard crawls. No effect if `storageless` is set.                        |
+| **run_in_background** | `bool`   | Runs the request in the background, useful for data storage and triggering dashboard crawls. No effect if `storageless` is set.                        |

docs/tools/visiontool.mdx

@@ -19,11 +19,11 @@ Install the crewai_tools package
 pip install 'crewai[tools]'
 ```
 
-## Usage
+## Example
 
-In order to use the VisionTool, the OpenAI API key should be set in the environment variable `OPENAI_API_KEY`.
+To use the VisionTool, first ensure the OpenAI API key is set in the environment variable `OPENAI_API_KEY`. Here's an example:
 
-```python Code
+```python
 from crewai_tools import VisionTool
 
 vision_tool = VisionTool()

docs/tools/websitesearchtool.mdx

@@ -27,11 +27,11 @@ pip install 'crewai[tools]'
 
 This command installs the necessary dependencies to ensure that once the tool is fully integrated, users can start using it immediately.
 
-## Example Usage
+## Example
 
 Below are examples of how the WebsiteSearchTool could be utilized in different scenarios. Please note, these examples are illustrative and represent planned functionality:
 
-```python Code
+```python
 from crewai_tools import WebsiteSearchTool
 
 # Example of initiating tool that agents can use 
@@ -52,7 +52,7 @@ tool = WebsiteSearchTool(website='https://example.com')
 By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
 
 
-```python Code
+```python
 tool = WebsiteSearchTool(
     config=dict(
         llm=dict(
@@ -74,4 +74,4 @@ tool = WebsiteSearchTool(
         ),
     )
 )
-```
+```

docs/tools/xmlsearchtool.mdx

@@ -29,7 +29,9 @@ pip install 'crewai[tools]'
 Here are two examples demonstrating how to use the XMLSearchTool. 
 The first example shows searching within a specific XML file, while the second example illustrates initiating a search without predefining an XML path, providing flexibility in search scope.
 
-```python Code
+Note: The tool uses RAG (Retrieval-Augmented Generation) to perform semantic search within XML content, so results will include relevant context from the XML file based on the search query.
+
+```python
 from crewai_tools import XMLSearchTool
 
 # Allow agents to search within any XML file's content 
@@ -47,12 +49,15 @@ tool = XMLSearchTool(xml='path/to/your/xmlfile.xml')
 
 - `xml`: This is the path to the XML file you wish to search. 
 It is an optional parameter during the tool's initialization but must be provided either at initialization or as part of the `run` method's arguments to execute a search.
+- `search_query`: The query string to search for within the XML content. This is a required parameter when running the search.
+
+The tool inherits from `RagTool` which provides advanced RAG (Retrieval-Augmented Generation) capabilities for semantic search within XML content.
 
 ## Custom model and embeddings
 
 By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
 
-```python Code  
+```python
 tool = XMLSearchTool(
     config=dict(
         llm=dict(
@@ -74,4 +79,4 @@ tool = XMLSearchTool(
         ),
     )
 )
-```
+```

pyproject.toml

@@ -8,38 +8,27 @@ 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",
-    
-    # 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
+    "instructor>=1.3.3",
+    "regex>=2024.9.11",
     "click>=8.1.7",
+    "python-dotenv>=1.0.0",
     "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",
 ]
 
@@ -50,9 +39,6 @@ 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 = [

src/crewai/flow/flow.py

@@ -30,47 +30,7 @@ from crewai.telemetry import Telemetry
 T = TypeVar("T", bound=Union[BaseModel, Dict[str, Any]])
 
 
-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 start(condition=None):
     def decorator(func):
         func.__is_start_method__ = True
         if condition is not None:
@@ -95,42 +55,8 @@ def start(condition: Optional[Union[str, dict, Callable]] = None) -> Callable:
 
     return decorator
 
-def listen(condition: Union[str, dict, Callable]) -> Callable:
-    """
-    Creates a listener that executes when specified conditions are met.
 
-    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 listen(condition):
     def decorator(func):
         if isinstance(condition, str):
             func.__trigger_methods__ = [condition]
@@ -154,49 +80,10 @@ def listen(condition: Union[str, dict, Callable]) -> Callable:
     return decorator
 
 
-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 router(condition):
     def decorator(func):
         func.__is_router__ = True
+        # Handle conditions like listen/start
         if isinstance(condition, str):
             func.__trigger_methods__ = [condition]
             func.__condition_type__ = "OR"
@@ -218,39 +105,8 @@ def router(condition: Union[str, dict, Callable]) -> Callable:
 
     return decorator
 
-def or_(*conditions: Union[str, dict, Callable]) -> dict:
-    """
-    Combines multiple conditions with OR logic for flow control.
 
-    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
-    """
+def or_(*conditions):
     methods = []
     for condition in conditions:
         if isinstance(condition, dict) and "methods" in condition:
@@ -264,39 +120,7 @@ def or_(*conditions: Union[str, dict, Callable]) -> dict:
     return {"type": "OR", "methods": methods}
 
 
-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
-    """
+def and_(*conditions):
     methods = []
     for condition in conditions:
         if isinstance(condition, dict) and "methods" in condition:
@@ -462,23 +286,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
         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]
         )
@@ -499,28 +306,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
         return result
 
     async def _execute_listeners(self, trigger_method: str, result: Any) -> None:
-        """
-        Executes all listeners and routers triggered by a method completion.
-
-        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(
@@ -550,33 +335,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
     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
@@ -605,33 +363,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
         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]
 

src/crewai/flow/flow_visualizer.py

@@ -1,14 +1,12 @@
 # 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,
@@ -18,209 +16,89 @@ 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):
-        """
-        Generate and save an HTML visualization of the flow.
+        net = Network(
+            directed=True,
+            height="750px",
+            width="100%",
+            bgcolor=self.colors["bg"],
+            layout=None,
+        )
 
-        Parameters
-        ----------
-        filename : str
-            Name of the output file (without extension).
-
-        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,
-            )
-
-            # Set options to disable physics
-            net.set_options(
-                """
-                var options = {
-                    "nodes": {
-                        "font": {
-                            "multi": "html"
-                        }
-                    },
-                    "physics": {
-                        "enabled": false
-                    }
-                }
+        # Set options to disable physics
+        net.set_options(
             """
-            )
+            var options = {
+                "nodes": {
+                    "font": {
+                        "multi": "html"
+                    }
+                },
+                "physics": {
+                    "enabled": false
+                }
+            }
+        """
+        )
 
-            # 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)}")
+        # Calculate levels for nodes
+        node_levels = calculate_node_levels(self.flow)
 
-            # 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)}")
+        # Compute positions
+        node_positions = compute_positions(self.flow, node_levels)
 
-            # 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)}")
+        # Add nodes to the network
+        add_nodes_to_network(net, self.flow, node_positions, self.node_styles)
 
-            # 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)}")
+        # Add edges to the network
+        add_edges(net, self.flow, node_positions, self.colors)
 
-            # 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)}")
+        network_html = net.generate_html()
+        final_html_content = self._generate_final_html(network_html)
 
-            # 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)}")
+        # 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")
 
-        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()
+        self._cleanup_pyvis_lib()
 
     def _generate_final_html(self, network_html):
-        """
-        Generate the final HTML content with network visualization and legend.
+        # 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")
 
-        Parameters
-        ----------
-        network_html : str
-            HTML content generated by pyvis Network.
+        html_handler = HTMLTemplateHandler(template_path, logo_path)
+        network_body = html_handler.extract_body_content(network_html)
 
-        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)}")
+        # 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
 
     def _cleanup_pyvis_lib(self):
-        """
-        Clean up the generated lib folder from pyvis.
-
-        This method safely removes the temporary lib directory created by pyvis
-        during network visualization generation.
-        """
+        # Clean up the generated lib folder
+        lib_folder = os.path.join(os.getcwd(), "lib")
         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

@@ -1,53 +1,26 @@
 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):
-        """
-        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}")
+        self.template_path = template_path
+        self.logo_path = logo_path
 
     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:
@@ -75,7 +48,6 @@ 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

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

src/crewai/flow/path_utils.py

@@ -1,135 +0,0 @@
-"""
-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

@@ -1,25 +1,9 @@
-"""
-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: Any) -> Optional[List[str]]:
+def get_possible_return_constants(function):
     try:
         source = inspect.getsource(function)
     except OSError:
@@ -93,34 +77,11 @@ def get_possible_return_constants(function: Any) -> Optional[List[str]]:
     return list(return_values) if return_values else None
 
 
-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]] = {}
+def calculate_node_levels(flow):
+    levels = {}
+    queue = []
+    visited = set()
+    pending_and_listeners = {}
 
     # Make all start methods at level 0
     for method_name, method in flow._methods.items():
@@ -179,20 +140,7 @@ def calculate_node_levels(flow: Any) -> Dict[str, int]:
     return levels
 
 
-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.
-    """
+def count_outgoing_edges(flow):
     counts = {}
     for method_name in flow._methods:
         counts[method_name] = 0
@@ -204,53 +152,16 @@ def count_outgoing_edges(flow: Any) -> Dict[str, int]:
     return counts
 
 
-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()
+def build_ancestor_dict(flow):
+    ancestors = {node: set() for node in flow._methods}
+    visited = set()
     for node in flow._methods:
         if node not in visited:
             dfs_ancestors(node, ancestors, visited, flow)
     return ancestors
 
 
-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.
-    """
+def dfs_ancestors(node, ancestors, visited, flow):
     if node in visited:
         return
     visited.add(node)
@@ -274,48 +185,12 @@ def dfs_ancestors(
                     dfs_ancestors(listener_name, ancestors, visited, flow)
 
 
-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.
-    """
+def is_ancestor(node, ancestor_candidate, ancestors):
     return ancestor_candidate in ancestors.get(node, set())
 
 
-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]] = {}
+def build_parent_children_dict(flow):
+    parent_children = {}
 
     # Map listeners to their trigger methods
     for listener_name, (_, trigger_methods) in flow._listeners.items():
@@ -339,24 +214,7 @@ def build_parent_children_dict(flow: Any) -> Dict[str, List[str]]:
     return 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.
-    """
+def get_child_index(parent, child, parent_children):
     children = parent_children.get(parent, [])
     children.sort()
     return children.index(child)

src/crewai/flow/visualization_utils.py

@@ -1,23 +1,5 @@
-"""
-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,
@@ -27,25 +9,8 @@ from .utils import (
 )
 
 
-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'.
-    """
+def method_calls_crew(method):
+    """Check if the method calls `.crew()`."""
     try:
         source = inspect.getsource(method)
         source = inspect.cleandoc(source)
@@ -55,7 +20,6 @@ def method_calls_crew(method: Any) -> bool:
         return False
 
     class CrewCallVisitor(ast.NodeVisitor):
-        """AST visitor to detect .crew() method calls."""
         def __init__(self):
             self.found = False
 
@@ -70,34 +34,7 @@ def method_calls_crew(method: Any) -> bool:
     return visitor.found
 
 
-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 add_nodes_to_network(net, flow, node_positions, node_styles):
     def human_friendly_label(method_name):
         return method_name.replace("_", " ").title()
 
@@ -136,33 +73,9 @@ def add_nodes_to_network(
         )
 
 
-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]] = {}
+def compute_positions(flow, node_levels, y_spacing=150, x_spacing=150):
+    level_nodes = {}
+    node_positions = {}
 
     for method_name, level in node_levels.items():
         level_nodes.setdefault(level, []).append(method_name)
@@ -177,33 +90,7 @@ def compute_positions(
     return node_positions
 
 
-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)
-    """
+def add_edges(net, flow, node_positions, colors):
     ancestors = build_ancestor_dict(flow)
     parent_children = build_parent_children_dict(flow)
 
@@ -239,7 +126,7 @@ def add_edges(
                     else:
                         edge_smooth = {"type": "cubicBezier"}
                 else:
-                    edge_smooth.update({"type": "continuous"})
+                    edge_smooth = False
 
                 edge_style = {
                     "color": edge_color,
@@ -302,7 +189,7 @@ def add_edges(
                             else:
                                 edge_smooth = {"type": "cubicBezier"}
                         else:
-                            edge_smooth.update({"type": "continuous"})
+                            edge_smooth = False
 
                         edge_style = {
                             "color": colors["router_edge"],

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -26,10 +26,9 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
     safe_file_paths: List[Path] = Field(default_factory=list)
 
     @field_validator("file_path", "file_paths", mode="before")
-    def validate_file_path(cls, v, info):
+    def validate_file_path(cls, v, values):
         """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:
+        if v is None and ("file_path" not in values or values.get("file_path") is None):
             raise ValueError("Either file_path or file_paths must be provided")
         return v
 

src/crewai/task.py

@@ -179,7 +179,6 @@ class Task(BaseModel):
     _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)
 
@@ -214,46 +213,8 @@ class Task(BaseModel):
 
     @field_validator("output_file")
     @classmethod
-    def output_file_validation(cls, value: Optional[str]) -> Optional[str]:
-        """Validate the output file path.
-        
-        Args:
-            value: The output file path to validate. Can be None or a string.
-                  If the path contains template variables (e.g. {var}), leading slashes are preserved.
-                  For regular paths, leading slashes are stripped.
-        
-        Returns:
-            The validated and potentially modified path, or None if no path was provided.
-            
-        Raises:
-            ValueError: If the path contains invalid characters, path traversal attempts,
-                      or other security concerns.
-        """
-        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
+    def output_file_validation(cls, value: str) -> str:
+        """Validate the output file path by removing the / from the beginning of the path."""
         if value.startswith("/"):
             return value[1:]
         return value
@@ -432,89 +393,27 @@ class Task(BaseModel):
         tasks_slices = [self.description, output]
         return "\n".join(tasks_slices)
 
-    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.
-        """
+    def interpolate_inputs(self, inputs: Dict[str, Any]) -> None:
+        """Interpolate inputs into the task description and expected output."""
         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 not inputs:
-            return
-
-        try:
+        if inputs:
             self.description = self._original_description.format(**inputs)
-        except KeyError as e:
-            raise ValueError(f"Missing required template variable '{e.args[0]}' in description") from e
-        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: str, inputs: Dict[str, Any]) -> str:
+        """Interpolate placeholders (e.g., {key}) in a string while leaving JSON untouched."""
+        escaped_string = input_string.replace("{", "{{").replace("}", "}}")
 
-    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")
+        for key in inputs.keys():
+            escaped_string = escaped_string.replace(f"{{{{{key}}}}}", f"{{{key}}}")
 
-        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
+        return escaped_string.format(**inputs)
 
     def increment_tools_errors(self) -> None:
         """Increment the tools errors counter."""

src/crewai/tools/agent_tools/base_agent_tools.py

@@ -1,4 +1,3 @@
-import logging
 from typing import Optional, Union
 
 from pydantic import Field
@@ -8,8 +7,6 @@ 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"""
@@ -19,25 +16,6 @@ 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:
@@ -47,27 +25,11 @@ class BaseAgentTool(BaseTool):
         return coworker
 
     def _execute(
-        self,
-        agent_name: Optional[str],
-        task: str,
-        context: Optional[str] = None
+        self, agent_name: Union[str, None], task: str, context: Union[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
@@ -76,49 +38,31 @@ class BaseAgentTool(BaseTool):
             # {"task": "....", "coworker": "....
             # when it should look like this:
             # {"task": "....", "coworker": "...."}
-            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_name = agent_name.casefold().replace('"', "").replace("\n", "")
             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 self.sanitize_agent_name(available_agent.role) == sanitized_name
+                if available_agent.role.casefold().replace("\n", "") == agent_name
             ]
-            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
+        except Exception as _:
             return self.i18n.errors("agent_tool_unexisting_coworker").format(
                 coworkers="\n".join(
-                    [f"- {self.sanitize_agent_name(agent.role)}" for agent in self.agents]
-                ),
-                error=str(e)
+                    [f"- {agent.role.casefold()}" for agent in self.agents]
+                )
             )
 
         if not agent:
-            # No matching agent found after sanitization
             return self.i18n.errors("agent_tool_unexisting_coworker").format(
                 coworkers="\n".join(
-                    [f"- {self.sanitize_agent_name(agent.role)}" for agent in self.agents]
-                ),
-                error=f"No agent found with role '{sanitized_name}'"
+                    [f"- {agent.role.casefold()}" for agent in self.agents]
+                )
             )
 
         agent = agent[0]
-        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)
-            )
+        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)

src/crewai/translations/en.json

@@ -33,8 +33,7 @@
     "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}",
-    "agent_tool_execution_error": "Error executing task with agent '{agent_role}'. Error: {error}"
+    "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}"
   },
   "tools": {
     "delegate_work": "Delegate a specific task to one of the following coworkers: {coworkers}\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolute everything you know, don't reference things but instead explain them.",

src/crewai/utilities/planning_handler.py

@@ -1,5 +1,3 @@
-import json
-import logging
 from typing import Any, List, Optional
 
 from pydantic import BaseModel, Field
@@ -7,8 +5,6 @@ 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")
@@ -72,39 +68,19 @@ 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):
-            knowledge_list = self._get_agent_knowledge(task)
-            task_summary = f"""
+            tasks_summary.append(
+                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": %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)
+                "agent_tools": {task.agent.tools if task.agent else "None"}
+                """
+            )
         return " ".join(tasks_summary)

tests/cassettes/test_crew_output_file_end_to_end.yaml

@@ -1,243 +0,0 @@
-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/crew_test.py

@@ -391,71 +391,6 @@ 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 = [
@@ -2006,90 +1941,6 @@ def test_crew_log_file_output(tmp_path):
     assert test_file.exists()
 
 
-@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"
-
-
-@pytest.mark.vcr(filter_headers=["authorization"])
-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()
-
-
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_manager_agent():
     from unittest.mock import patch
@@ -3274,4 +3125,4 @@ def test_multimodal_agent_live_image_analysis():
     # 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
+    assert "error" not in result.raw.lower()  # No error messages in response

tests/knowledge/knowledge_test.py

@@ -584,28 +584,3 @@ def test_docling_source_with_local_file():
     docling_source = CrewDoclingSource(file_paths=[pdf_path])
     assert docling_source.file_paths == [pdf_path]
     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

@@ -719,24 +719,21 @@ 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", "date": "2024"})
+    task.interpolate_inputs(inputs={"topic": "AI"})
     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", "date": "2025"})
+    task.interpolate_inputs(inputs={"topic": "ML"})
     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():
@@ -875,61 +872,3 @@ 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

@@ -1,55 +0,0 @@
-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/utilities/test_knowledge_planning.py

@@ -1,84 +0,0 @@
-"""
-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

@@ -1,14 +1,10 @@
-from typing import Optional
-from unittest.mock import MagicMock, patch
+from unittest.mock import 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,
@@ -96,72 +92,7 @@ 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 '"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
+        assert tasks_summary.endswith('"agent_tools": []\n                ')
 
     def test_handle_crew_planning_different_llm(self, crew_planner_different_llm):
         with patch.object(Task, "execute_sync") as execute: