fix(mem0_storage): ensure memory_config is set correctly when config is provided

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

.github/workflows/tests.yml

@@ -12,6 +12,9 @@ jobs:
   tests:
     runs-on: ubuntu-latest
     timeout-minutes: 15
+    strategy:
+      matrix:
+        python-version: ['3.10', '3.11', '3.12']
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -21,9 +24,8 @@ jobs:
         with:
           enable-cache: true
 
-
-      - name: Set up Python
-        run: uv python install 3.12.8
+      - name: Set up Python ${{ matrix.python-version }}
+        run: uv python install ${{ matrix.python-version }}
 
       - name: Install the project
         run: uv sync --dev --all-extras

.gitignore

@@ -25,4 +25,5 @@ agentops.log
 test_flow.html
 crewairules.mdc
 plan.md
-conceptual_plan.md
+conceptual_plan.md
+build_image

README.md

@@ -257,10 +257,14 @@ reporting_task:
 from crewai import Agent, Crew, Process, Task
 from crewai.project import CrewBase, agent, crew, task
 from crewai_tools import SerperDevTool
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from typing import List
 
 @CrewBase
 class LatestAiDevelopmentCrew():
 	"""LatestAiDevelopment crew"""
+	agents: List[BaseAgent]
+	tasks: List[Task]
 
 	@agent
 	def researcher(self) -> Agent:

docs/concepts/agents.mdx

@@ -118,7 +118,7 @@ class LatestAiDevelopmentCrew():
   @agent
   def researcher(self) -> Agent:
     return Agent(
-      config=self.agents_config['researcher'],
+      config=self.agents_config['researcher'], # type: ignore[index]
       verbose=True,
       tools=[SerperDevTool()]
     )
@@ -126,7 +126,7 @@ class LatestAiDevelopmentCrew():
   @agent
   def reporting_analyst(self) -> Agent:
     return Agent(
-      config=self.agents_config['reporting_analyst'],
+      config=self.agents_config['reporting_analyst'], # type: ignore[index]
       verbose=True
     )
 ```

docs/concepts/collaboration.mdx

@@ -23,8 +23,7 @@ The `Crew` class has been enriched with several attributes to support advanced f
 | **Process Flow** (`process`)           | Defines execution logic (e.g., sequential, hierarchical) for task distribution.                                                                                                                                                |
 | **Verbose Logging** (`verbose`)        | Provides detailed logging for monitoring and debugging. Accepts integer and boolean values to control verbosity level.                                                                                                       |
 | **Rate Limiting** (`max_rpm`)          | Limits requests per minute to optimize resource usage. Setting guidelines depend on task complexity and load.                                                                                                                 |
-| **Internationalization / Customization** (`language`, `prompt_file`) | Supports prompt customization for global usability. [Example of file](https://github.com/joaomdmoura/crewAI/blob/main/src/crewai/translations/en.json)                                                                                      |
-| **Execution and Output Handling** (`full_output`) | Controls output granularity, distinguishing between full and final outputs.                                                                                                                                                  |
+| **Internationalization / Customization** (`prompt_file`) | Supports prompt customization for global usability. [Example of file](https://github.com/joaomdmoura/crewAI/blob/main/src/crewai/translations/en.json)                                                                                      |
 | **Callback and Telemetry** (`step_callback`, `task_callback`) | Enables step-wise and task-level execution monitoring and telemetry for performance analytics.                                                                                                                               |
 | **Crew Sharing** (`share_crew`)        | Allows sharing crew data with CrewAI for model improvement. Privacy implications and benefits should be considered.                                                                                                          |
 | **Usage Metrics** (`usage_metrics`)    | Logs all LLM usage metrics during task execution for performance insights.                                                                                                                           |
@@ -49,4 +48,4 @@ Consider a crew with a researcher agent tasked with data gathering and a writer
 
 ## Conclusion
 
-The integration of advanced attributes and functionalities into the CrewAI framework significantly enriches the agent collaboration ecosystem. These enhancements not only simplify interactions but also offer unprecedented flexibility and control, paving the way for sophisticated AI-driven solutions capable of tackling complex tasks through intelligent collaboration and delegation.
+The integration of advanced attributes and functionalities into the CrewAI framework significantly enriches the agent collaboration ecosystem. These enhancements not only simplify interactions but also offer unprecedented flexibility and control, paving the way for sophisticated AI-driven solutions capable of tackling complex tasks through intelligent collaboration and delegation.

docs/concepts/crews.mdx

@@ -20,13 +20,10 @@ A crew in crewAI represents a collaborative group of agents working together to
 | **Function Calling LLM** _(optional)_ | `function_calling_llm` | If passed, the crew will use this LLM to do function calling for tools for all agents in the crew. Each agent can have its own LLM, which overrides the crew's LLM for function calling.                                                                  |
 | **Config** _(optional)_               | `config`               | Optional configuration settings for the crew, in `Json` or `Dict[str, Any]` format.                                                                                                                                                                       |
 | **Max RPM** _(optional)_              | `max_rpm`              | Maximum requests per minute the crew adheres to during execution. Defaults to `None`.                                                                                                                                                                     |
-| **Language** _(optional)_             | `language`             | Language used for the crew, defaults to English.                                                                                                                                                                                                          |
-| **Language File** _(optional)_        | `language_file`        | Path to the language file to be used for the crew.                                                                                                                                                                                                        |
 | **Memory** _(optional)_               | `memory`               | Utilized for storing execution memories (short-term, long-term, entity memory).                                                                                                                                                                           |
 | **Memory Config** _(optional)_        | `memory_config`        | Configuration for the memory provider to be used by the crew.                                                                                                                                                                                             |
 | **Cache** _(optional)_                | `cache`                | Specifies whether to use a cache for storing the results of tools' execution. Defaults to `True`.                                                                                                                                                         |
 | **Embedder** _(optional)_             | `embedder`             | Configuration for the embedder to be used by the crew. Mostly used by memory for now. Default is `{"provider": "openai"}`.                                                                                                                                |
-| **Full Output** _(optional)_          | `full_output`          | Whether the crew should return the full output with all tasks outputs or just the final output. Defaults to `False`.                                                                                                                                      |
 | **Step Callback** _(optional)_        | `step_callback`        | A function that is called after each step of every agent. This can be used to log the agent's actions or to perform other operations; it won't override the agent-specific `step_callback`.                                                               |
 | **Task Callback** _(optional)_        | `task_callback`        | A function that is called after the completion of each task. Useful for monitoring or additional operations post-task execution.                                                                                                                          |
 | **Share Crew** _(optional)_           | `share_crew`           | Whether you want to share the complete crew information and execution with the crewAI team to make the library better, and allow us to train models.                                                                                                      |
@@ -55,12 +52,16 @@ After creating your CrewAI project as outlined in the [Installation](/installati
 ```python code
 from crewai import Agent, Crew, Task, Process
 from crewai.project import CrewBase, agent, task, crew, before_kickoff, after_kickoff
-
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from typing import List
 
 @CrewBase
 class YourCrewName:
     """Description of your crew"""
 
+    agents: List[BaseAgent]
+    tasks: List[Task]
+
     # Paths to your YAML configuration files
     # To see an example agent and task defined in YAML, checkout the following:
     # - Task: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
@@ -83,27 +84,27 @@ class YourCrewName:
     @agent
     def agent_one(self) -> Agent:
         return Agent(
-            config=self.agents_config['agent_one'],
+            config=self.agents_config['agent_one'], # type: ignore[index]
             verbose=True
         )
 
     @agent
     def agent_two(self) -> Agent:
         return Agent(
-            config=self.agents_config['agent_two'],
+            config=self.agents_config['agent_two'], # type: ignore[index]
             verbose=True
         )
 
     @task
     def task_one(self) -> Task:
         return Task(
-            config=self.tasks_config['task_one']
+            config=self.tasks_config['task_one'] # type: ignore[index]
         )
 
     @task
     def task_two(self) -> Task:
         return Task(
-            config=self.tasks_config['task_two']
+            config=self.tasks_config['task_two'] # type: ignore[index]
         )
 
     @crew

docs/concepts/flows.mdx

@@ -545,16 +545,20 @@ The `third_method` and `fourth_method` listen to the output of the `second_metho
 
 When you run this Flow, the output will change based on the random boolean value generated by the `start_method`.
 
-## Adding LiteAgent to Flows
+## Adding Agents to Flows
 
-LiteAgents can be seamlessly integrated into your flows, providing a lightweight alternative to full Crews when you need simpler, focused task execution. Here's an example of how to use a LiteAgent within a flow to perform market research:
+Agents can be seamlessly integrated into your flows, providing a lightweight alternative to full Crews when you need simpler, focused task execution. Here's an example of how to use an Agent within a flow to perform market research:
 
 ```python
-from typing import List, cast
-from crewai_tools.tools.website_search.website_search_tool import WebsiteSearchTool
+import asyncio
+from typing import Any, Dict, List
+
+from crewai_tools import SerperDevTool
 from pydantic import BaseModel, Field
+
+from crewai.agent import Agent
 from crewai.flow.flow import Flow, listen, start
-from crewai.lite_agent import LiteAgent
+
 
 # Define a structured output format
 class MarketAnalysis(BaseModel):
@@ -562,28 +566,30 @@ class MarketAnalysis(BaseModel):
     market_size: str = Field(description="Estimated market size")
     competitors: List[str] = Field(description="Major competitors in the space")
 
+
 # Define flow state
 class MarketResearchState(BaseModel):
     product: str = ""
     analysis: MarketAnalysis | None = None
 
+
+# Create a flow class
 class MarketResearchFlow(Flow[MarketResearchState]):
     @start()
-    def initialize_research(self):
+    def initialize_research(self) -> Dict[str, Any]:
         print(f"Starting market research for {self.state.product}")
+        return {"product": self.state.product}
 
     @listen(initialize_research)
-    def analyze_market(self):
-        # Create a LiteAgent for market research
-        analyst = LiteAgent(
+    async def analyze_market(self) -> Dict[str, Any]:
+        # Create an Agent for market research
+        analyst = Agent(
             role="Market Research Analyst",
             goal=f"Analyze the market for {self.state.product}",
             backstory="You are an experienced market analyst with expertise in "
             "identifying market trends and opportunities.",
-            llm="gpt-4o",
-            tools=[WebsiteSearchTool()],
+            tools=[SerperDevTool()],
             verbose=True,
-            response_format=MarketAnalysis,
         )
 
         # Define the research query
@@ -592,49 +598,65 @@ class MarketResearchFlow(Flow[MarketResearchState]):
         1. Key market trends
         2. Market size
         3. Major competitors
-        
+
         Format your response according to the specified structure.
         """
 
-        # Execute the analysis
-        result = analyst.kickoff(query)
-        self.state.analysis = cast(MarketAnalysis, result.pydantic)
-        return result.pydantic
+        # Execute the analysis with structured output format
+        result = await analyst.kickoff_async(query, response_format=MarketAnalysis)
+        if result.pydantic:
+            print("result", result.pydantic)
+        else:
+            print("result", result)
+
+        # Return the analysis to update the state
+        return {"analysis": result.pydantic}
 
     @listen(analyze_market)
-    def present_results(self):
-        analysis = self.state.analysis
-        if analysis is None:
-            print("No analysis results available")
-            return
-
+    def present_results(self, analysis) -> None:
         print("\nMarket Analysis Results")
         print("=====================")
 
-        print("\nKey Market Trends:")
-        for trend in analysis.key_trends:
-            print(f"- {trend}")
+        if isinstance(analysis, dict):
+            # If we got a dict with 'analysis' key, extract the actual analysis object
+            market_analysis = analysis.get("analysis")
+        else:
+            market_analysis = analysis
 
-        print(f"\nMarket Size: {analysis.market_size}")
+        if market_analysis and isinstance(market_analysis, MarketAnalysis):
+            print("\nKey Market Trends:")
+            for trend in market_analysis.key_trends:
+                print(f"- {trend}")
+
+            print(f"\nMarket Size: {market_analysis.market_size}")
+
+            print("\nMajor Competitors:")
+            for competitor in market_analysis.competitors:
+                print(f"- {competitor}")
+        else:
+            print("No structured analysis data available.")
+            print("Raw analysis:", analysis)
 
-        print("\nMajor Competitors:")
-        for competitor in analysis.competitors:
-            print(f"- {competitor}")
 
 # Usage example
-flow = MarketResearchFlow()
-result = flow.kickoff(inputs={"product": "AI-powered chatbots"})
+async def run_flow():
+    flow = MarketResearchFlow()
+    result = await flow.kickoff_async(inputs={"product": "AI-powered chatbots"})
+    return result
+
+
+# Run the flow
+if __name__ == "__main__":
+    asyncio.run(run_flow())
 ```
 
-This example demonstrates several key features of using LiteAgents in flows:
+This example demonstrates several key features of using Agents in flows:
 
 1. **Structured Output**: Using Pydantic models to define the expected output format (`MarketAnalysis`) ensures type safety and structured data throughout the flow.
 
 2. **State Management**: The flow state (`MarketResearchState`) maintains context between steps and stores both inputs and outputs.
 
-3. **Tool Integration**: LiteAgents can use tools (like `WebsiteSearchTool`) to enhance their capabilities.
-
-If you want to learn more about LiteAgents, check out the [LiteAgent](/concepts/lite-agent) page.
+3. **Tool Integration**: Agents can use tools (like `WebsiteSearchTool`) to enhance their capabilities.
 
 ## Adding Crews to Flows
 

docs/concepts/lite-agent.mdx

@@ -1,242 +0,0 @@
----
-title: LiteAgent
-description: A lightweight, single-purpose agent for simple autonomous tasks within the CrewAI framework.
-icon: feather
----
-
-## Overview
-
-A `LiteAgent` is a streamlined version of CrewAI's Agent, designed for simpler, standalone tasks that don't require the full complexity of a crew-based workflow. It's perfect for quick automations, single-purpose tasks, or when you need a lightweight solution.
-
-<Tip>
-  Think of a LiteAgent as a specialized worker that excels at individual tasks.
-  While regular Agents are team players in a crew, LiteAgents are solo
-  performers optimized for specific operations.
-</Tip>
-
-## LiteAgent Attributes
-
-| Attribute                        | Parameter         | Type                   | Description                                                     |
-| :------------------------------- | :---------------- | :--------------------- | :-------------------------------------------------------------- |
-| **Role**                         | `role`            | `str`                  | Defines the agent's function and expertise.                     |
-| **Goal**                         | `goal`            | `str`                  | The specific objective that guides the agent's actions.         |
-| **Backstory**                    | `backstory`       | `str`                  | Provides context and personality to the agent.                  |
-| **LLM** _(optional)_             | `llm`             | `Union[str, LLM, Any]` | Language model powering the agent. Defaults to "gpt-4".         |
-| **Tools** _(optional)_           | `tools`           | `List[BaseTool]`       | Capabilities available to the agent. Defaults to an empty list. |
-| **Verbose** _(optional)_         | `verbose`         | `bool`                 | Enable detailed execution logs. Default is False.               |
-| **Response Format** _(optional)_ | `response_format` | `Type[BaseModel]`      | Pydantic model for structured output. Optional.                 |
-
-## Creating a LiteAgent
-
-Here's a simple example of creating and using a standalone LiteAgent:
-
-```python
-from typing import List, cast
-
-from crewai_tools import SerperDevTool
-from pydantic import BaseModel, Field
-
-from crewai.lite_agent import LiteAgent
-
-
-# Define a structured output format
-class MovieReview(BaseModel):
-    title: str = Field(description="The title of the movie")
-    rating: float = Field(description="Rating out of 10")
-    pros: List[str] = Field(description="List of positive aspects")
-    cons: List[str] = Field(description="List of negative aspects")
-
-
-# Create a LiteAgent
-critic = LiteAgent(
-    role="Movie Critic",
-    goal="Provide insightful movie reviews",
-    backstory="You are an experienced film critic known for balanced, thoughtful reviews.",
-    tools=[SerperDevTool()],
-    verbose=True,
-    response_format=MovieReview,
-)
-
-# Use the agent
-query = """
-Review the movie 'Inception'. Include:
-1. Your rating out of 10
-2. Key positive aspects
-3. Areas that could be improved
-"""
-
-result = critic.kickoff(query)
-
-
-# Access the structured output
-review = cast(MovieReview, result.pydantic)
-print(f"\nMovie Review: {review.title}")
-print(f"Rating: {review.rating}/10")
-print("\nPros:")
-for pro in review.pros:
-    print(f"- {pro}")
-print("\nCons:")
-for con in review.cons:
-    print(f"- {con}")
-
-```
-
-This example demonstrates the core features of a LiteAgent:
-
-- Structured output using Pydantic models
-- Tool integration with WebSearchTool
-- Simple execution with `kickoff()`
-- Easy access to both raw and structured results
-
-## Using LiteAgent in a Flow
-
-For more complex scenarios, you can integrate LiteAgents into a Flow. Here's an example of a market research flow:
-
-````python
-from typing import List
-from pydantic import BaseModel, Field
-from crewai.flow.flow import Flow, start, listen
-from crewai.lite_agent import LiteAgent
-from crewai.tools import WebSearchTool
-
-# Define a structured output format
-class MarketAnalysis(BaseModel):
-    key_trends: List[str] = Field(description="List of identified market trends")
-    market_size: str = Field(description="Estimated market size")
-    competitors: List[str] = Field(description="Major competitors in the space")
-
-# Define flow state
-class MarketResearchState(BaseModel):
-    product: str = ""
-    analysis: MarketAnalysis = None
-
-# Create a flow class
-class MarketResearchFlow(Flow[MarketResearchState]):
-    @start()
-    def initialize_research(self, product: str):
-        print(f"Starting market research for {product}")
-        self.state.product = product
-
-    @listen(initialize_research)
-    async def analyze_market(self):
-        # Create a LiteAgent for market research
-        analyst = LiteAgent(
-            role="Market Research Analyst",
-            goal=f"Analyze the market for {self.state.product}",
-            backstory="You are an experienced market analyst with expertise in "
-                     "identifying market trends and opportunities.",
-            tools=[WebSearchTool()],
-            verbose=True,
-            response_format=MarketAnalysis
-        )
-
-        # Define the research query
-        query = f"""
-        Research the market for {self.state.product}. Include:
-        1. Key market trends
-        2. Market size
-        3. Major competitors
-
-        Format your response according to the specified structure.
-        """
-
-        # Execute the analysis
-        result = await analyst.kickoff_async(query)
-        self.state.analysis = result.pydantic
-        return result.pydantic
-
-    @listen(analyze_market)
-    def present_results(self):
-        analysis = self.state.analysis
-        print("\nMarket Analysis Results")
-        print("=====================")
-
-        print("\nKey Market Trends:")
-        for trend in analysis.key_trends:
-            print(f"- {trend}")
-
-        print(f"\nMarket Size: {analysis.market_size}")
-
-        print("\nMajor Competitors:")
-        for competitor in analysis.competitors:
-            print(f"- {competitor}")
-
-# Usage example
-import asyncio
-
-async def run_flow():
-    flow = MarketResearchFlow()
-    result = await flow.kickoff(inputs={"product": "AI-powered chatbots"})
-    return result
-
-# Run the flow
-if __name__ == "__main__":
-    asyncio.run(run_flow())
-
-## Key Features
-
-### 1. Simplified Setup
-Unlike regular Agents, LiteAgents are designed for quick setup and standalone operation. They don't require crew configuration or task management.
-
-### 2. Structured Output
-LiteAgents support Pydantic models for response formatting, making it easy to get structured, type-safe data from your agent's operations.
-
-### 3. Tool Integration
-Just like regular Agents, LiteAgents can use tools to enhance their capabilities:
-```python
-from crewai.tools import SerperDevTool, CalculatorTool
-
-agent = LiteAgent(
-    role="Research Assistant",
-    goal="Find and analyze information",
-    tools=[SerperDevTool(), CalculatorTool()],
-    verbose=True
-)
-````
-
-### 4. Async Support
-
-LiteAgents support asynchronous execution through the `kickoff_async` method, making them suitable for non-blocking operations in your application.
-
-## Response Formatting
-
-LiteAgents support structured output through Pydantic models using the `response_format` parameter. This feature ensures type safety and consistent output structure, making it easier to work with agent responses in your application.
-
-### Basic Usage
-
-```python
-from pydantic import BaseModel, Field
-
-class SearchResult(BaseModel):
-    title: str = Field(description="The title of the found content")
-    summary: str = Field(description="A brief summary of the content")
-    relevance_score: float = Field(description="Relevance score from 0 to 1")
-
-agent = LiteAgent(
-    role="Search Specialist",
-    goal="Find and summarize relevant information",
-    response_format=SearchResult
-)
-
-result = await agent.kickoff_async("Find information about quantum computing")
-print(f"Title: {result.pydantic.title}")
-print(f"Summary: {result.pydantic.summary}")
-print(f"Relevance: {result.pydantic.relevance_score}")
-```
-
-### Handling Responses
-
-When using `response_format`, the agent's response will be available in two forms:
-
-1. **Raw Response**: Access the unstructured string response
-
-   ```python
-   result = await agent.kickoff_async("Analyze the market")
-   print(result.raw)  # Original LLM response
-   ```
-
-2. **Structured Response**: Access the parsed Pydantic model
-   ```python
-   print(result.pydantic)  # Parsed response as Pydantic model
-   print(result.pydantic.dict())  # Convert to dictionary
-   ```

docs/concepts/llms.mdx

@@ -438,7 +438,7 @@ In this section, you'll find detailed examples that help you select, configure,
         @agent
         def researcher(self) -> Agent:
             return Agent(
-                config=self.agents_config['researcher'],
+                config=self.agents_config['researcher'], # type: ignore[index]
                 llm=local_nvidia_nim_llm
             )
         
@@ -535,14 +535,13 @@ In this section, you'll find detailed examples that help you select, configure,
   <Accordion title="Hugging Face">
     Set the following environment variables in your `.env` file:
     ```toml Code
-    HUGGINGFACE_API_KEY=<your-api-key>
+    HF_TOKEN=<your-api-key>
     ```
 
     Example usage in your CrewAI project:
     ```python Code
     llm = LLM(
-        model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct",
-        base_url="your_api_endpoint"
+        model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct"
     )
     ```
   </Accordion>

docs/concepts/memory.mdx

@@ -18,7 +18,8 @@ reason, and learn from past interactions.
 | **Long-Term Memory** | Preserves valuable insights and learnings from past executions, allowing agents to build and refine their knowledge over time. |
 | **Entity Memory**    | Captures and organizes information about entities (people, places, concepts) encountered during tasks, facilitating deeper understanding and relationship mapping. Uses `RAG` for storing entity information. |
 | **Contextual Memory**| Maintains the context of interactions by combining `ShortTermMemory`, `LongTermMemory`, and `EntityMemory`, aiding in the coherence and relevance of agent responses over a sequence of tasks or a conversation. |
-| **User Memory**      | Stores user-specific information and preferences, enhancing personalization and user experience. |
+| **External Memory**  | Enables integration with external memory systems and providers (like Mem0), allowing for specialized memory storage and retrieval across different applications. Supports custom storage implementations for flexible memory management. |
+| **User Memory**      | ⚠️ **DEPRECATED**: This component is deprecated and will be removed in a future version. Please use [External Memory](#using-external-memory) instead. |
 
 ## How Memory Systems Empower Agents
 
@@ -144,6 +145,7 @@ from crewai.memory import LongTermMemory
 # Simple memory configuration
 crew = Crew(memory=True)  # Uses default storage locations
 ```
+Note that External Memory won’t be defined when `memory=True` is set, as we can’t infer which external memory would be suitable for your case
 
 ### Custom Storage Configuration
 ```python
@@ -274,6 +276,104 @@ crew = Crew(
 )
 ```
 
+### Using External Memory
+
+External Memory is a powerful feature that allows you to integrate external memory systems with your CrewAI applications. This is particularly useful when you want to use specialized memory providers or maintain memory across different applications.
+Since it’s an external memory, we’re not able to add a default value to it - unlike with Long Term and Short Term memory. 
+
+#### Basic Usage with Mem0
+
+The most common way to use External Memory is with Mem0 as the provider:
+
+```python
+import os
+from crewai import Agent, Crew, Process, Task
+from crewai.memory.external.external_memory import ExternalMemory
+
+os.environ["MEM0_API_KEY"] = "YOUR-API-KEY"
+
+agent = Agent(
+    role="You are a helpful assistant",
+    goal="Plan a vacation for the user",
+    backstory="You are a helpful assistant that can plan a vacation for the user",
+    verbose=True,
+)
+task = Task(
+    description="Give things related to the user's vacation",
+    expected_output="A plan for the vacation",
+    agent=agent,
+)
+
+crew = Crew(
+    agents=[agent],
+    tasks=[task],
+    verbose=True,
+    process=Process.sequential,
+    external_memory=ExternalMemory(
+        embedder_config={"provider": "mem0", "config": {"user_id": "U-123"}} # you can provide an entire Mem0 configuration
+    ),
+)
+
+crew.kickoff(
+    inputs={"question": "which destination is better for a beach vacation?"}
+)
+```
+
+#### Using External Memory with Custom Storage
+
+You can also create custom storage implementations for External Memory. Here's an example of how to create a custom storage:
+
+```python
+from crewai import Agent, Crew, Process, Task
+from crewai.memory.external.external_memory import ExternalMemory
+from crewai.memory.storage.interface import Storage
+
+
+class CustomStorage(Storage):
+    def __init__(self):
+        self.memories = []
+
+    def save(self, value, metadata=None, agent=None):
+        self.memories.append({"value": value, "metadata": metadata, "agent": agent})
+
+    def search(self, query, limit=10, score_threshold=0.5):
+        # Implement your search logic here
+        return []
+
+    def reset(self):
+        self.memories = []
+
+
+# Create external memory with custom storage
+external_memory = ExternalMemory(
+    storage=CustomStorage(),
+    embedder_config={"provider": "mem0", "config": {"user_id": "U-123"}},
+)
+
+agent = Agent(
+    role="You are a helpful assistant",
+    goal="Plan a vacation for the user",
+    backstory="You are a helpful assistant that can plan a vacation for the user",
+    verbose=True,
+)
+task = Task(
+    description="Give things related to the user's vacation",
+    expected_output="A plan for the vacation",
+    agent=agent,
+)
+
+crew = Crew(
+    agents=[agent],
+    tasks=[task],
+    verbose=True,
+    process=Process.sequential,
+    external_memory=external_memory,
+)
+
+crew.kickoff(
+    inputs={"question": "which destination is better for a beach vacation?"}
+)
+```
 
 
 ## Additional Embedding Providers

docs/concepts/tasks.mdx

@@ -113,7 +113,7 @@ class LatestAiDevelopmentCrew():
   @agent
   def researcher(self) -> Agent:
     return Agent(
-      config=self.agents_config['researcher'],
+      config=self.agents_config['researcher'], # type: ignore[index]
       verbose=True,
       tools=[SerperDevTool()]
     )
@@ -121,20 +121,20 @@ class LatestAiDevelopmentCrew():
   @agent
   def reporting_analyst(self) -> Agent:
     return Agent(
-      config=self.agents_config['reporting_analyst'],
+      config=self.agents_config['reporting_analyst'], # type: ignore[index]
       verbose=True
     )
 
   @task
   def research_task(self) -> Task:
     return Task(
-      config=self.tasks_config['research_task']
+      config=self.tasks_config['research_task'] # type: ignore[index]
     )
 
   @task
   def reporting_task(self) -> Task:
     return Task(
-      config=self.tasks_config['reporting_task']
+      config=self.tasks_config['reporting_task'] # type: ignore[index]
     )
 
   @crew

docs/docs.json

@@ -66,7 +66,6 @@
               "concepts/tasks",
               "concepts/crews",
               "concepts/flows",
-              "concepts/lite-agent",
               "concepts/knowledge",
               "concepts/llms",
               "concepts/processes",
@@ -77,9 +76,7 @@
               "concepts/testing",
               "concepts/cli",
               "concepts/tools",
-              "concepts/event-listener",
-              "concepts/langchain-tools",
-              "concepts/llamaindex-tools"
+              "concepts/event-listener"
             ]
           },
           {
@@ -98,7 +95,9 @@
               "how-to/kickoff-async",
               "how-to/kickoff-for-each",
               "how-to/replay-tasks-from-latest-crew-kickoff",
-              "how-to/conditional-tasks"
+              "how-to/conditional-tasks",
+              "how-to/langchain-tools",
+              "how-to/llamaindex-tools"
             ]
           },
           {
@@ -197,6 +196,11 @@
           "anchor": "Community",
           "href": "https://community.crewai.com",
           "icon": "discourse"
+        },
+        {
+          "anchor": "Tutorials",
+          "href": "https://www.youtube.com/@crewAIInc",
+          "icon": "youtube"
         }
       ]
     }
@@ -231,4 +235,4 @@
       "reddit": "https://www.reddit.com/r/crewAIInc/"
     }
   }
-}
+}

docs/guides/crews/first-crew.mdx

@@ -185,15 +185,20 @@ Let's modify the `crew.py` file:
 from crewai import Agent, Crew, Process, Task
 from crewai.project import CrewBase, agent, crew, task
 from crewai_tools import SerperDevTool
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from typing import List
 
 @CrewBase
 class ResearchCrew():
     """Research crew for comprehensive topic analysis and reporting"""
 
+    agents: List[BaseAgent]
+    tasks: List[Task]
+
     @agent
     def researcher(self) -> Agent:
         return Agent(
-            config=self.agents_config['researcher'],
+            config=self.agents_config['researcher'], # type: ignore[index]
             verbose=True,
             tools=[SerperDevTool()]
         )
@@ -201,20 +206,20 @@ class ResearchCrew():
     @agent
     def analyst(self) -> Agent:
         return Agent(
-            config=self.agents_config['analyst'],
+            config=self.agents_config['analyst'], # type: ignore[index]
             verbose=True
         )
 
     @task
     def research_task(self) -> Task:
         return Task(
-            config=self.tasks_config['research_task']
+            config=self.tasks_config['research_task'] # type: ignore[index]
         )
 
     @task
     def analysis_task(self) -> Task:
         return Task(
-            config=self.tasks_config['analysis_task'],
+            config=self.tasks_config['analysis_task'], # type: ignore[index]
             output_file='output/report.md'
         )
 
@@ -387,4 +392,4 @@ Now that you've built your first crew, you can:
 
 <Check>
 Congratulations! You've successfully built your first CrewAI crew that can research and analyze any topic you provide. This foundational experience has equipped you with the skills to create increasingly sophisticated AI systems that can tackle complex, multi-stage problems through collaborative intelligence.
-</Check>
+</Check>

docs/guides/flows/first-flow.mdx

@@ -203,35 +203,40 @@ These task definitions provide detailed instructions to our agents, ensuring the
 # src/guide_creator_flow/crews/content_crew/content_crew.py
 from crewai import Agent, Crew, Process, Task
 from crewai.project import CrewBase, agent, crew, task
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from typing import List
 
 @CrewBase
 class ContentCrew():
     """Content writing crew"""
 
+    agents: List[BaseAgent]
+    tasks: List[Task]
+
     @agent
     def content_writer(self) -> Agent:
         return Agent(
-            config=self.agents_config['content_writer'],
+            config=self.agents_config['content_writer'], # type: ignore[index]
             verbose=True
         )
 
     @agent
     def content_reviewer(self) -> Agent:
         return Agent(
-            config=self.agents_config['content_reviewer'],
+            config=self.agents_config['content_reviewer'], # type: ignore[index]
             verbose=True
         )
 
     @task
     def write_section_task(self) -> Task:
         return Task(
-            config=self.tasks_config['write_section_task']
+            config=self.tasks_config['write_section_task'] # type: ignore[index]
         )
 
     @task
     def review_section_task(self) -> Task:
         return Task(
-            config=self.tasks_config['review_section_task'],
+            config=self.tasks_config['review_section_task'], # type: ignore[index]
             context=[self.write_section_task()]
         )
 
@@ -263,6 +268,7 @@ Let's create our flow in the `main.py` file:
 ```python
 #!/usr/bin/env python
 import json
+import os
 from typing import List, Dict
 from pydantic import BaseModel, Field
 from crewai import LLM
@@ -341,6 +347,9 @@ class GuideCreatorFlow(Flow[GuideCreatorState]):
         outline_dict = json.loads(response)
         self.state.guide_outline = GuideOutline(**outline_dict)
 
+        # Ensure output directory exists before saving
+        os.makedirs("output", exist_ok=True)
+
         # Save the outline to a file
         with open("output/guide_outline.json", "w") as f:
             json.dump(outline_dict, f, indent=2)

docs/installation.mdx

@@ -4,6 +4,21 @@ description: Get started with CrewAI - Install, configure, and build your first
 icon: wrench
 ---
 
+## Video Tutorial
+Watch this video tutorial for a step-by-step demonstration of the installation process:
+
+<iframe
+  width="100%"
+  height="400"
+  src="https://www.youtube.com/embed/-kSOTtYzgEw"
+  title="CrewAI Installation Guide"
+  frameborder="0"
+  style={{ borderRadius: '10px' }}
+  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
+  allowfullscreen
+></iframe>
+
+## Text Tutorial
 <Note>
   **Python Version Requirements**
 

docs/quickstart.mdx

@@ -87,15 +87,20 @@ Follow the steps below to get Crewing! 🚣‍♂️
     from crewai import Agent, Crew, Process, Task
     from crewai.project import CrewBase, agent, crew, task
     from crewai_tools import SerperDevTool
+    from crewai.agents.agent_builder.base_agent import BaseAgent
+    from typing import List
 
     @CrewBase
     class LatestAiDevelopmentCrew():
       """LatestAiDevelopment crew"""
 
+      agents: List[BaseAgent]
+      tasks: List[Task]
+
       @agent
       def researcher(self) -> Agent:
         return Agent(
-          config=self.agents_config['researcher'],
+          config=self.agents_config['researcher'], # type: ignore[index]
           verbose=True,
           tools=[SerperDevTool()]
         )
@@ -103,20 +108,20 @@ Follow the steps below to get Crewing! 🚣‍♂️
       @agent
       def reporting_analyst(self) -> Agent:
         return Agent(
-          config=self.agents_config['reporting_analyst'],
+          config=self.agents_config['reporting_analyst'], # type: ignore[index]
           verbose=True
         )
 
       @task
       def research_task(self) -> Task:
         return Task(
-          config=self.tasks_config['research_task'],
+          config=self.tasks_config['research_task'], # type: ignore[index]
         )
 
       @task
       def reporting_task(self) -> Task:
         return Task(
-          config=self.tasks_config['reporting_task'],
+          config=self.tasks_config['reporting_task'], # type: ignore[index]
           output_file='output/report.md' # This is the file that will be contain the final report.
         )
 

docs/telemetry.mdx

@@ -22,7 +22,16 @@ usage of tools, API calls, responses, any data processed by the agents, or secre
 When the `share_crew` feature is enabled, detailed data including task descriptions, agents' backstories or goals, and other specific attributes are collected 
 to provide deeper insights. This expanded data collection may include personal information if users have incorporated it into their crews or tasks. 
 Users should carefully consider the content of their crews and tasks before enabling `share_crew`. 
-Users can disable telemetry by setting the environment variable `OTEL_SDK_DISABLED` to `true`.
+Users can disable telemetry by setting the environment variable `CREWAI_DISABLE_TELEMETRY` to `true` or by setting `OTEL_SDK_DISABLED` to `true` (note that the latter disables all OpenTelemetry instrumentation globally).
+
+### Examples:
+```python
+# Disable CrewAI telemetry only
+os.environ['CREWAI_DISABLE_TELEMETRY'] = 'true'
+
+# Disable all OpenTelemetry (including CrewAI)
+os.environ['OTEL_SDK_DISABLED'] = 'true'
+```
 
 ### Data Explanation:
 | Defaulted | Data                                      | Reason and Specifics                                                                                                       |
@@ -55,4 +64,4 @@ This enables a deeper insight into usage patterns.
 <Warning>
     If you enable `share_crew`, the collected data may include personal information if it has been incorporated into crew configurations, task descriptions, or outputs. 
     Users should carefully review their data and ensure compliance with GDPR and other applicable privacy regulations before enabling this feature.
-</Warning>
+</Warning>

docs/tools/weaviatevectorsearchtool.mdx

@@ -25,7 +25,7 @@ uv add weaviate-client
 To effectively use the `WeaviateVectorSearchTool`, follow these steps:
 
 1. **Package Installation**: Confirm that the `crewai[tools]` and `weaviate-client` packages are installed in your Python environment.
-2. **Weaviate Setup**: Set up a Weaviate cluster. You can follow the [Weaviate documentation](https://weaviate.io/developers/wcs/connect) for instructions.
+2. **Weaviate Setup**: Set up a Weaviate cluster. You can follow the [Weaviate documentation](https://weaviate.io/developers/wcs/manage-clusters/connect) for instructions.
 3. **API Keys**: Obtain your Weaviate cluster URL and API key.
 4. **OpenAI API Key**: Ensure you have an OpenAI API key set in your environment variables as `OPENAI_API_KEY`.
 
@@ -161,4 +161,4 @@ rag_agent = Agent(
 
 ## Conclusion
 
-The `WeaviateVectorSearchTool` provides a powerful way to search for semantically similar documents in a Weaviate vector database. By leveraging vector embeddings, it enables more accurate and contextually relevant search results compared to traditional keyword-based searches. This tool is particularly useful for applications that require finding information based on meaning rather than exact matches. 
+The `WeaviateVectorSearchTool` provides a powerful way to search for semantically similar documents in a Weaviate vector database. By leveraging vector embeddings, it enables more accurate and contextually relevant search results compared to traditional keyword-based searches. This tool is particularly useful for applications that require finding information based on meaning rather than exact matches. 

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.108.0"
+version = "0.114.0"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
@@ -45,7 +45,7 @@ Documentation = "https://docs.crewai.com"
 Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
-tools = ["crewai-tools~=0.38.0"]
+tools = ["crewai-tools~=0.40.1"]
 embeddings = [
     "tiktoken~=0.7.0"
 ]

src/crewai/__init__.py

@@ -2,12 +2,14 @@ import warnings
 
 from crewai.agent import Agent
 from crewai.crew import Crew
+from crewai.crews.crew_output import CrewOutput
 from crewai.flow.flow import Flow
 from crewai.knowledge.knowledge import Knowledge
 from crewai.llm import LLM
 from crewai.llms.base_llm import BaseLLM
 from crewai.process import Process
 from crewai.task import Task
+from crewai.tasks.task_output import TaskOutput
 
 warnings.filterwarnings(
     "ignore",
@@ -15,14 +17,16 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.108.0"
+__version__ = "0.114.0"
 __all__ = [
     "Agent",
     "Crew",
+    "CrewOutput",
     "Process",
     "Task",
     "LLM",
     "BaseLLM",
     "Flow",
     "Knowledge",
+    "TaskOutput",
 ]

src/crewai/agent.py

@@ -1,7 +1,6 @@
-import re
 import shutil
 import subprocess
-from typing import Any, Dict, List, Literal, Optional, Sequence, Union
+from typing import Any, Dict, List, Literal, Optional, Sequence, Type, Union
 
 from pydantic import Field, InstanceOf, PrivateAttr, model_validator
 
@@ -11,6 +10,7 @@ from crewai.agents.crew_agent_executor import CrewAgentExecutor
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.utils.knowledge_utils import extract_knowledge_context
+from crewai.lite_agent import LiteAgent, LiteAgentOutput
 from crewai.llm import BaseLLM
 from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.security import Fingerprint
@@ -156,6 +156,23 @@ class Agent(BaseAgent):
         except (TypeError, ValueError) as e:
             raise ValueError(f"Invalid Knowledge Configuration: {str(e)}")
 
+    def _is_any_available_memory(self) -> bool:
+        """Check if any memory is available."""
+        if not self.crew:
+            return False
+
+        memory_attributes = [
+            "memory",
+            "memory_config",
+            "_short_term_memory",
+            "_long_term_memory",
+            "_entity_memory",
+            "_user_memory",
+            "_external_memory",
+        ]
+
+        return any(getattr(self.crew, attr) for attr in memory_attributes)
+
     def execute_task(
         self,
         task: Task,
@@ -200,13 +217,14 @@ class Agent(BaseAgent):
                 task=task_prompt, context=context
             )
 
-        if self.crew and self.crew.memory:
+        if self._is_any_available_memory():
             contextual_memory = ContextualMemory(
                 self.crew.memory_config,
                 self.crew._short_term_memory,
                 self.crew._long_term_memory,
                 self.crew._entity_memory,
                 self.crew._user_memory,
+                self.crew._external_memory,
             )
             memory = contextual_memory.build_context_for_task(task, context)
             if memory.strip() != "":
@@ -448,3 +466,75 @@ class Agent(BaseAgent):
 
     def set_fingerprint(self, fingerprint: Fingerprint):
         self.security_config.fingerprint = fingerprint
+
+    def kickoff(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        response_format: Optional[Type[Any]] = None,
+    ) -> LiteAgentOutput:
+        """
+        Execute the agent with the given messages using a LiteAgent instance.
+
+        This method is useful when you want to use the Agent configuration but
+        with the simpler and more direct execution flow of LiteAgent.
+
+        Args:
+            messages: Either a string query or a list of message dictionaries.
+                     If a string is provided, it will be converted to a user message.
+                     If a list is provided, each dict should have 'role' and 'content' keys.
+            response_format: Optional Pydantic model for structured output.
+
+        Returns:
+            LiteAgentOutput: The result of the agent execution.
+        """
+        lite_agent = LiteAgent(
+            role=self.role,
+            goal=self.goal,
+            backstory=self.backstory,
+            llm=self.llm,
+            tools=self.tools or [],
+            max_iterations=self.max_iter,
+            max_execution_time=self.max_execution_time,
+            respect_context_window=self.respect_context_window,
+            verbose=self.verbose,
+            response_format=response_format,
+            i18n=self.i18n,
+            original_agent=self,
+        )
+
+        return lite_agent.kickoff(messages)
+
+    async def kickoff_async(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        response_format: Optional[Type[Any]] = None,
+    ) -> LiteAgentOutput:
+        """
+        Execute the agent asynchronously with the given messages using a LiteAgent instance.
+
+        This is the async version of the kickoff method.
+
+        Args:
+            messages: Either a string query or a list of message dictionaries.
+                     If a string is provided, it will be converted to a user message.
+                     If a list is provided, each dict should have 'role' and 'content' keys.
+            response_format: Optional Pydantic model for structured output.
+
+        Returns:
+            LiteAgentOutput: The result of the agent execution.
+        """
+        lite_agent = LiteAgent(
+            role=self.role,
+            goal=self.goal,
+            backstory=self.backstory,
+            llm=self.llm,
+            tools=self.tools or [],
+            max_iterations=self.max_iter,
+            max_execution_time=self.max_execution_time,
+            respect_context_window=self.respect_context_window,
+            verbose=self.verbose,
+            response_format=response_format,
+            i18n=self.i18n,
+        )
+
+        return await lite_agent.kickoff_async(messages)

src/crewai/agents/agent_builder/base_agent_executor_mixin.py

@@ -47,11 +47,31 @@ class CrewAgentExecutorMixin:
                 print(f"Failed to add to short term memory: {e}")
                 pass
 
+    def _create_external_memory(self, output) -> None:
+        """Create and save a external-term memory item if conditions are met."""
+        if (
+            self.crew
+            and self.agent
+            and self.task
+            and hasattr(self.crew, "_external_memory")
+            and self.crew._external_memory
+        ):
+            try:
+                self.crew._external_memory.save(
+                    value=output.text,
+                    metadata={
+                        "description": self.task.description,
+                    },
+                    agent=self.agent.role,
+                )
+            except Exception as e:
+                print(f"Failed to add to external memory: {e}")
+                pass
+
     def _create_long_term_memory(self, output) -> None:
         """Create and save long-term and entity memory items based on evaluation."""
         if (
             self.crew
-            and self.crew.memory
             and self.crew._long_term_memory
             and self.crew._entity_memory
             and self.task
@@ -93,6 +113,15 @@ class CrewAgentExecutorMixin:
             except Exception as e:
                 print(f"Failed to add to long term memory: {e}")
                 pass
+        elif (
+            self.crew
+            and self.crew._long_term_memory
+            and self.crew._entity_memory is None
+        ):
+            self._printer.print(
+                content="Long term memory is enabled, but entity memory is not enabled. Please configure entity memory or set memory=True to automatically enable it.",
+                color="bold_yellow",
+            )
 
     def _ask_human_input(self, final_answer: str) -> str:
         """Prompt human input with mode-appropriate messaging."""

src/crewai/agents/crew_agent_executor.py

@@ -129,6 +129,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
 
         self._create_short_term_memory(formatted_answer)
         self._create_long_term_memory(formatted_answer)
+        self._create_external_memory(formatted_answer)
         return {"output": formatted_answer.output}
 
     def _invoke_loop(self) -> AgentFinish:

src/crewai/cli/constants.py

@@ -91,6 +91,12 @@ ENV_VARS = {
             "key_name": "CEREBRAS_API_KEY",
         },
     ],
+    "huggingface": [
+        {
+            "prompt": "Enter your Huggingface API key (HF_TOKEN) (press Enter to skip)",
+            "key_name": "HF_TOKEN",
+        },
+    ],
     "sambanova": [
         {
             "prompt": "Enter your SambaNovaCloud API key (press Enter to skip)",
@@ -106,6 +112,7 @@ PROVIDERS = [
     "gemini",
     "nvidia_nim",
     "groq",
+    "huggingface",
     "ollama",
     "watson",
     "bedrock",
@@ -270,6 +277,12 @@ MODELS = {
         "bedrock/mistral.mistral-7b-instruct-v0:2",
         "bedrock/mistral.mixtral-8x7b-instruct-v0:1",
     ],
+    "huggingface": [
+        "huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct",
+        "huggingface/mistralai/Mixtral-8x7B-Instruct-v0.1",
+        "huggingface/tiiuae/falcon-180B-chat",
+        "huggingface/google/gemma-7b-it",
+    ],
     "sambanova": [
         "sambanova/Meta-Llama-3.3-70B-Instruct",
         "sambanova/QwQ-32B-Preview",

src/crewai/cli/install_crew.py

@@ -3,6 +3,10 @@ import subprocess
 import click
 
 
+# Be mindful about changing this.
+# on some enviorments we don't use this command but instead uv sync directly
+# so if you expect this to support more things you will need to replicate it there
+# ask @joaomdmoura if you are unsure
 def install_crew(proxy_options: list[str]) -> None:
     """
     Install the crew by running the UV command to lock and install.

src/crewai/cli/templates/crew/crew.py

@@ -1,6 +1,7 @@
 from crewai import Agent, Crew, Process, Task
 from crewai.project import CrewBase, agent, crew, task
-
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from typing import List
 # If you want to run a snippet of code before or after the crew starts,
 # you can use the @before_kickoff and @after_kickoff decorators
 # https://docs.crewai.com/concepts/crews#example-crew-class-with-decorators
@@ -9,25 +10,26 @@ from crewai.project import CrewBase, agent, crew, task
 class {{crew_name}}():
     """{{crew_name}} crew"""
 
+    agents: List[BaseAgent]
+    tasks: List[Task]
+
     # Learn more about YAML configuration files here:
     # Agents: https://docs.crewai.com/concepts/agents#yaml-configuration-recommended
     # Tasks: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
-    agents_config = 'config/agents.yaml'
-    tasks_config = 'config/tasks.yaml'
-
+    
     # If you would like to add tools to your agents, you can learn more about it here:
     # https://docs.crewai.com/concepts/agents#agent-tools
     @agent
     def researcher(self) -> Agent:
         return Agent(
-            config=self.agents_config['researcher'],
+            config=self.agents_config['researcher'], # type: ignore[index]
             verbose=True
         )
 
     @agent
     def reporting_analyst(self) -> Agent:
         return Agent(
-            config=self.agents_config['reporting_analyst'],
+            config=self.agents_config['reporting_analyst'], # type: ignore[index]
             verbose=True
         )
 
@@ -37,13 +39,13 @@ class {{crew_name}}():
     @task
     def research_task(self) -> Task:
         return Task(
-            config=self.tasks_config['research_task'],
+            config=self.tasks_config['research_task'], # type: ignore[index]
         )
 
     @task
     def reporting_task(self) -> Task:
         return Task(
-            config=self.tasks_config['reporting_task'],
+            config=self.tasks_config['reporting_task'], # type: ignore[index]
             output_file='report.md'
         )
 

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

@@ -33,7 +33,8 @@ def train():
     Train the crew for a given number of iterations.
     """
     inputs = {
-        "topic": "AI LLMs"
+        "topic": "AI LLMs",
+        'current_year': str(datetime.now().year)
     }
     try:
         {{crew_name}}().crew().train(n_iterations=int(sys.argv[1]), filename=sys.argv[2], inputs=inputs)
@@ -59,8 +60,9 @@ def test():
         "topic": "AI LLMs",
         "current_year": str(datetime.now().year)
     }
+    
     try:
-        {{crew_name}}().crew().test(n_iterations=int(sys.argv[1]), openai_model_name=sys.argv[2], inputs=inputs)
+        {{crew_name}}().crew().test(n_iterations=int(sys.argv[1]), eval_llm=sys.argv[2], inputs=inputs)
 
     except Exception as e:
         raise Exception(f"An error occurred while testing the crew: {e}")

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

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.108.0,<1.0.0"
+    "crewai[tools]>=0.114.0,<1.0.0"
 ]
 
 [project.scripts]

src/crewai/cli/templates/flow/crews/poem_crew/poem_crew.py

@@ -1,5 +1,7 @@
 from crewai import Agent, Crew, Process, Task
 from crewai.project import CrewBase, agent, crew, task
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from typing import List
 
 # If you want to run a snippet of code before or after the crew starts,
 # you can use the @before_kickoff and @after_kickoff decorators
@@ -10,6 +12,9 @@ from crewai.project import CrewBase, agent, crew, task
 class PoemCrew:
     """Poem Crew"""
 
+    agents: List[BaseAgent]
+    tasks: List[Task]
+
     # Learn more about YAML configuration files here:
     # Agents: https://docs.crewai.com/concepts/agents#yaml-configuration-recommended
     # Tasks: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
@@ -21,7 +26,7 @@ class PoemCrew:
     @agent
     def poem_writer(self) -> Agent:
         return Agent(
-            config=self.agents_config["poem_writer"],
+            config=self.agents_config["poem_writer"],  # type: ignore[index]
         )
 
     # To learn more about structured task outputs,
@@ -30,7 +35,7 @@ class PoemCrew:
     @task
     def write_poem(self) -> Task:
         return Task(
-            config=self.tasks_config["write_poem"],
+            config=self.tasks_config["write_poem"],  # type: ignore[index]
         )
 
     @crew

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

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.108.0,<1.0.0",
+    "crewai[tools]>=0.114.0,<1.0.0",
 ]
 
 [project.scripts]

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

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.108.0"
+    "crewai[tools]>=0.114.0"
 ]
 
 [tool.crewai]

src/crewai/crew.py

@@ -28,6 +28,7 @@ from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.llm import LLM, BaseLLM
 from crewai.memory.entity.entity_memory import EntityMemory
+from crewai.memory.external.external_memory import ExternalMemory
 from crewai.memory.long_term.long_term_memory import LongTermMemory
 from crewai.memory.short_term.short_term_memory import ShortTermMemory
 from crewai.memory.user.user_memory import UserMemory
@@ -105,6 +106,7 @@ class Crew(BaseModel):
     _long_term_memory: Optional[InstanceOf[LongTermMemory]] = PrivateAttr()
     _entity_memory: Optional[InstanceOf[EntityMemory]] = PrivateAttr()
     _user_memory: Optional[InstanceOf[UserMemory]] = PrivateAttr()
+    _external_memory: Optional[InstanceOf[ExternalMemory]] = PrivateAttr()
     _train: Optional[bool] = PrivateAttr(default=False)
     _train_iteration: Optional[int] = PrivateAttr()
     _inputs: Optional[Dict[str, Any]] = PrivateAttr(default=None)
@@ -145,6 +147,10 @@ class Crew(BaseModel):
         default=None,
         description="An instance of the UserMemory to be used by the Crew to store/fetch memories of a specific user.",
     )
+    external_memory: Optional[InstanceOf[ExternalMemory]] = Field(
+        default=None,
+        description="An Instance of the ExternalMemory to be used by the Crew",
+    )
     embedder: Optional[dict] = Field(
         default=None,
         description="Configuration for the embedder to be used for the crew.",
@@ -269,40 +275,51 @@ class Crew(BaseModel):
 
         return self
 
+    def _initialize_user_memory(self):
+        if (
+            self.memory_config
+            and "user_memory" in self.memory_config
+            and self.memory_config.get("provider") == "mem0"
+        ):  # Check for user_memory in config
+            user_memory_config = self.memory_config["user_memory"]
+            if isinstance(
+                user_memory_config, dict
+            ):  # Check if it's a configuration dict
+                self._user_memory = UserMemory(crew=self)
+            else:
+                raise TypeError("user_memory must be a configuration dictionary")
+
+    def _initialize_default_memories(self):
+        self._long_term_memory = self._long_term_memory or LongTermMemory()
+        self._short_term_memory = self._short_term_memory or ShortTermMemory(
+            crew=self,
+            embedder_config=self.embedder,
+        )
+        self._entity_memory = self.entity_memory or EntityMemory(
+            crew=self, embedder_config=self.embedder
+        )
+
     @model_validator(mode="after")
     def create_crew_memory(self) -> "Crew":
-        """Set private attributes."""
+        """Initialize private memory attributes."""
+        self._external_memory = (
+            # External memory doesn’t support a default value since it was designed to be managed entirely externally
+            self.external_memory.set_crew(self)
+            if self.external_memory
+            else None
+        )
+
+        self._long_term_memory = self.long_term_memory
+        self._short_term_memory = self.short_term_memory
+        self._entity_memory = self.entity_memory
+
+        # UserMemory is gonna to be deprecated in the future, but we have to initialize a default value for now
+        self._user_memory = None
+
         if self.memory:
-            self._long_term_memory = (
-                self.long_term_memory if self.long_term_memory else LongTermMemory()
-            )
-            self._short_term_memory = (
-                self.short_term_memory
-                if self.short_term_memory
-                else ShortTermMemory(
-                    crew=self,
-                    embedder_config=self.embedder,
-                )
-            )
-            self._entity_memory = (
-                self.entity_memory
-                if self.entity_memory
-                else EntityMemory(crew=self, embedder_config=self.embedder)
-            )
-            if (
-                self.memory_config
-                and "user_memory" in self.memory_config
-                and self.memory_config.get("provider") == "mem0"
-            ):  # Check for user_memory in config
-                user_memory_config = self.memory_config["user_memory"]
-                if isinstance(
-                    user_memory_config, dict
-                ):  # Check if it's a configuration dict
-                    self._user_memory = UserMemory(crew=self)
-                else:
-                    raise TypeError("user_memory must be a configuration dictionary")
-            else:
-                self._user_memory = None  # No user memory if not in config
+            self._initialize_default_memories()
+            self._initialize_user_memory()
+
         return self
 
     @model_validator(mode="after")
@@ -1167,6 +1184,7 @@ class Crew(BaseModel):
             "_short_term_memory",
             "_long_term_memory",
             "_entity_memory",
+            "_external_memory",
             "_telemetry",
             "agents",
             "tasks",
@@ -1201,6 +1219,17 @@ class Crew(BaseModel):
 
         copied_data = self.model_dump(exclude=exclude)
         copied_data = {k: v for k, v in copied_data.items() if v is not None}
+        if self.short_term_memory:
+            copied_data["short_term_memory"] = self.short_term_memory.model_copy(deep=True)
+        if self.long_term_memory:
+            copied_data["long_term_memory"] = self.long_term_memory.model_copy(deep=True)
+        if self.entity_memory:
+            copied_data["entity_memory"] = self.entity_memory.model_copy(deep=True)
+        if self.external_memory:
+            copied_data["external_memory"] = self.external_memory.model_copy(deep=True)
+        if self.user_memory:
+            copied_data["user_memory"] = self.user_memory.model_copy(deep=True)
+
 
         copied_data.pop("agents", None)
         copied_data.pop("tasks", None)
@@ -1313,7 +1342,15 @@ class Crew(BaseModel):
             RuntimeError: If memory reset operation fails.
         """
         VALID_TYPES = frozenset(
-            ["long", "short", "entity", "knowledge", "kickoff_outputs", "all"]
+            [
+                "long",
+                "short",
+                "entity",
+                "knowledge",
+                "kickoff_outputs",
+                "all",
+                "external",
+            ]
         )
 
         if command_type not in VALID_TYPES:
@@ -1339,6 +1376,7 @@ class Crew(BaseModel):
         memory_systems = [
             ("short term", getattr(self, "_short_term_memory", None)),
             ("entity", getattr(self, "_entity_memory", None)),
+            ("external", getattr(self, "_external_memory", None)),
             ("long term", getattr(self, "_long_term_memory", None)),
             ("task output", getattr(self, "_task_output_handler", None)),
             ("knowledge", getattr(self, "knowledge", None)),
@@ -1366,6 +1404,7 @@ class Crew(BaseModel):
             "entity": (self._entity_memory, "entity"),
             "knowledge": (self.knowledge, "knowledge"),
             "kickoff_outputs": (self._task_output_handler, "task output"),
+            "external": (self._external_memory, "external"),
         }
 
         memory_system, name = reset_functions[memory_type]

src/crewai/flow/flow.py

@@ -1043,6 +1043,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
             import traceback
 
             traceback.print_exc()
+            raise
 
     def _log_flow_event(
         self, message: str, color: str = "yellow", level: str = "info"

src/crewai/lite_agent.py

@@ -1,6 +1,4 @@
 import asyncio
-import json
-import re
 import uuid
 from datetime import datetime
 from typing import Any, Callable, Dict, List, Optional, Type, Union, cast
@@ -49,11 +47,6 @@ from crewai.utilities.events.llm_events import (
     LLMCallStartedEvent,
     LLMCallType,
 )
-from crewai.utilities.events.tool_usage_events import (
-    ToolUsageErrorEvent,
-    ToolUsageFinishedEvent,
-    ToolUsageStartedEvent,
-)
 from crewai.utilities.llm_utils import create_llm
 from crewai.utilities.printer import Printer
 from crewai.utilities.token_counter_callback import TokenCalcHandler
@@ -157,6 +150,10 @@ class LiteAgent(BaseModel):
         default=[], description="Results of the tools used by the agent."
     )
 
+    # Reference of Agent
+    original_agent: Optional[BaseAgent] = Field(
+        default=None, description="Reference to the agent that created this LiteAgent"
+    )
     # Private Attributes
     _parsed_tools: List[CrewStructuredTool] = PrivateAttr(default_factory=list)
     _token_process: TokenProcess = PrivateAttr(default_factory=TokenProcess)
@@ -165,7 +162,7 @@ class LiteAgent(BaseModel):
     _messages: List[Dict[str, str]] = PrivateAttr(default_factory=list)
     _iterations: int = PrivateAttr(default=0)
     _printer: Printer = PrivateAttr(default_factory=Printer)
-
+    
     @model_validator(mode="after")
     def setup_llm(self):
         """Set up the LLM and other components after initialization."""
@@ -414,18 +411,6 @@ class LiteAgent(BaseModel):
                 formatted_answer = process_llm_response(answer, self.use_stop_words)
 
                 if isinstance(formatted_answer, AgentAction):
-                    # Emit tool usage started event
-                    crewai_event_bus.emit(
-                        self,
-                        event=ToolUsageStartedEvent(
-                            agent_key=self.key,
-                            agent_role=self.role,
-                            tool_name=formatted_answer.tool,
-                            tool_args=formatted_answer.tool_input,
-                            tool_class=formatted_answer.tool,
-                        ),
-                    )
-
                     try:
                         tool_result = execute_tool_and_check_finality(
                             agent_action=formatted_answer,
@@ -433,34 +418,9 @@ class LiteAgent(BaseModel):
                             i18n=self.i18n,
                             agent_key=self.key,
                             agent_role=self.role,
-                        )
-                        # Emit tool usage finished event
-                        crewai_event_bus.emit(
-                            self,
-                            event=ToolUsageFinishedEvent(
-                                agent_key=self.key,
-                                agent_role=self.role,
-                                tool_name=formatted_answer.tool,
-                                tool_args=formatted_answer.tool_input,
-                                tool_class=formatted_answer.tool,
-                                started_at=datetime.now(),
-                                finished_at=datetime.now(),
-                                output=tool_result.result,
-                            ),
+                            agent=self.original_agent,
                         )
                     except Exception as e:
-                        # Emit tool usage error event
-                        crewai_event_bus.emit(
-                            self,
-                            event=ToolUsageErrorEvent(
-                                agent_key=self.key,
-                                agent_role=self.role,
-                                tool_name=formatted_answer.tool,
-                                tool_args=formatted_answer.tool_input,
-                                tool_class=formatted_answer.tool,
-                                error=str(e),
-                            ),
-                        )
                         raise e
 
                     formatted_answer = handle_agent_action_core(

src/crewai/llm.py

@@ -707,15 +707,6 @@ class LLM(BaseLLM):
                     function_name, lambda: None
                 )  # Ensure fn is always a callable
                 logging.error(f"Error executing function '{function_name}': {e}")
-                crewai_event_bus.emit(
-                    self,
-                    event=ToolExecutionErrorEvent(
-                        tool_name=function_name,
-                        tool_args=function_args,
-                        tool_class=fn,
-                        error=str(e),
-                    ),
-                )
                 crewai_event_bus.emit(
                     self,
                     event=LLMCallFailedEvent(error=f"Tool execution error: {str(e)}"),

src/crewai/memory/__init__.py

@@ -2,5 +2,12 @@ from .entity.entity_memory import EntityMemory
 from .long_term.long_term_memory import LongTermMemory
 from .short_term.short_term_memory import ShortTermMemory
 from .user.user_memory import UserMemory
+from .external.external_memory import ExternalMemory
 
-__all__ = ["UserMemory", "EntityMemory", "LongTermMemory", "ShortTermMemory"]
+__all__ = [
+    "UserMemory",
+    "EntityMemory",
+    "LongTermMemory",
+    "ShortTermMemory",
+    "ExternalMemory",
+]

src/crewai/memory/contextual/contextual_memory.py

@@ -1,6 +1,12 @@
 from typing import Any, Dict, Optional
 
-from crewai.memory import EntityMemory, LongTermMemory, ShortTermMemory, UserMemory
+from crewai.memory import (
+    EntityMemory,
+    ExternalMemory,
+    LongTermMemory,
+    ShortTermMemory,
+    UserMemory,
+)
 
 
 class ContextualMemory:
@@ -11,6 +17,7 @@ class ContextualMemory:
         ltm: LongTermMemory,
         em: EntityMemory,
         um: UserMemory,
+        exm: ExternalMemory,
     ):
         if memory_config is not None:
             self.memory_provider = memory_config.get("provider")
@@ -20,6 +27,7 @@ class ContextualMemory:
         self.ltm = ltm
         self.em = em
         self.um = um
+        self.exm = exm
 
     def build_context_for_task(self, task, context) -> str:
         """
@@ -35,6 +43,7 @@ class ContextualMemory:
         context.append(self._fetch_ltm_context(task.description))
         context.append(self._fetch_stm_context(query))
         context.append(self._fetch_entity_context(query))
+        context.append(self._fetch_external_context(query))
         if self.memory_provider == "mem0":
             context.append(self._fetch_user_context(query))
         return "\n".join(filter(None, context))
@@ -44,6 +53,10 @@ class ContextualMemory:
         Fetches recent relevant insights from STM related to the task's description and expected_output,
         formatted as bullet points.
         """
+
+        if self.stm is None:
+            return ""
+
         stm_results = self.stm.search(query)
         formatted_results = "\n".join(
             [
@@ -58,6 +71,10 @@ class ContextualMemory:
         Fetches historical data or insights from LTM that are relevant to the task's description and expected_output,
         formatted as bullet points.
         """
+
+        if self.ltm is None:
+            return ""
+
         ltm_results = self.ltm.search(task, latest_n=2)
         if not ltm_results:
             return None
@@ -77,6 +94,9 @@ class ContextualMemory:
         Fetches relevant entity information from Entity Memory related to the task's description and expected_output,
         formatted as bullet points.
         """
+        if self.em is None:
+            return ""
+
         em_results = self.em.search(query)
         formatted_results = "\n".join(
             [
@@ -106,3 +126,24 @@ class ContextualMemory:
             f"- {result['memory']}" for result in user_memories
         )
         return f"User memories/preferences:\n{formatted_memories}"
+
+    def _fetch_external_context(self, query: str) -> str:
+        """
+        Fetches and formats relevant information from External Memory.
+        Args:
+            query (str): The search query to find relevant information.
+        Returns:
+            str: Formatted information as bullet points, or an empty string if none found.
+        """
+        if self.exm is None:
+            return ""
+
+        external_memories = self.exm.search(query)
+
+        if not external_memories:
+            return ""
+
+        formatted_memories = "\n".join(
+            f"- {result['memory']}" for result in external_memories
+        )
+        return f"External memories:\n{formatted_memories}"

src/crewai/memory/external/external_memory.py

@@ -0,0 +1,61 @@
+from typing import TYPE_CHECKING, Any, Dict, Optional
+
+from crewai.memory.external.external_memory_item import ExternalMemoryItem
+from crewai.memory.memory import Memory
+from crewai.memory.storage.interface import Storage
+
+if TYPE_CHECKING:
+    from crewai.memory.storage.mem0_storage import Mem0Storage
+
+
+class ExternalMemory(Memory):
+    def __init__(self, storage: Optional[Storage] = None, **data: Any):
+        super().__init__(storage=storage, **data)
+
+    @staticmethod
+    def _configure_mem0(crew: Any, config: Dict[str, Any]) -> "Mem0Storage":
+        from crewai.memory.storage.mem0_storage import Mem0Storage
+
+        return Mem0Storage(type="external", crew=crew, config=config)
+
+    @staticmethod
+    def external_supported_storages() -> Dict[str, Any]:
+        return {
+            "mem0": ExternalMemory._configure_mem0,
+        }
+
+    @staticmethod
+    def create_storage(crew: Any, embedder_config: Optional[Dict[str, Any]]) -> Storage:
+        if not embedder_config:
+            raise ValueError("embedder_config is required")
+
+        if "provider" not in embedder_config:
+            raise ValueError("embedder_config must include a 'provider' key")
+
+        provider = embedder_config["provider"]
+        supported_storages = ExternalMemory.external_supported_storages()
+        if provider not in supported_storages:
+            raise ValueError(f"Provider {provider} not supported")
+
+        return supported_storages[provider](crew, embedder_config.get("config", {}))
+
+    def save(
+        self,
+        value: Any,
+        metadata: Optional[Dict[str, Any]] = None,
+        agent: Optional[str] = None,
+    ) -> None:
+        """Saves a value into the external storage."""
+        item = ExternalMemoryItem(value=value, metadata=metadata, agent=agent)
+        super().save(value=item.value, metadata=item.metadata, agent=item.agent)
+
+    def reset(self) -> None:
+        self.storage.reset()
+
+    def set_crew(self, crew: Any) -> "ExternalMemory":
+        super().set_crew(crew)
+
+        if not self.storage:
+            self.storage = self.create_storage(crew, self.embedder_config)
+
+        return self

src/crewai/memory/external/external_memory_item.py

@@ -0,0 +1,13 @@
+from typing import Any, Dict, Optional
+
+
+class ExternalMemoryItem:
+    def __init__(
+        self,
+        value: Any,
+        metadata: Optional[Dict[str, Any]] = None,
+        agent: Optional[str] = None,
+    ):
+        self.value = value
+        self.metadata = metadata
+        self.agent = agent

src/crewai/memory/memory.py

@@ -9,6 +9,7 @@ class Memory(BaseModel):
     """
 
     embedder_config: Optional[Dict[str, Any]] = None
+    crew: Optional[Any] = None
 
     storage: Any
 
@@ -36,3 +37,7 @@ class Memory(BaseModel):
         return self.storage.search(
             query=query, limit=limit, score_threshold=score_threshold
         )
+
+    def set_crew(self, crew: Any) -> "Memory":
+        self.crew = crew
+        return self

src/crewai/memory/storage/mem0_storage.py

@@ -11,15 +11,20 @@ class Mem0Storage(Storage):
     Extends Storage to handle embedding and searching across entities using Mem0.
     """
 
-    def __init__(self, type, crew=None):
+    def __init__(self, type, crew=None, config=None):
         super().__init__()
-
-        if type not in ["user", "short_term", "long_term", "entities"]:
-            raise ValueError("Invalid type for Mem0Storage. Must be 'user' or 'agent'.")
+        supported_types = ["user", "short_term", "long_term", "entities", "external"]
+        if type not in supported_types:
+            raise ValueError(
+                f"Invalid type '{type}' for Mem0Storage. Must be one of: "
+                + ", ".join(supported_types)
+            )
 
         self.memory_type = type
         self.crew = crew
-        self.memory_config = crew.memory_config
+        self.config = config or {}
+        # TODO: Memory config will be removed in the future the config will be passed as a parameter
+        self.memory_config = self.config if config is not None else getattr(crew, "memory_config", {}) or {}
 
         # User ID is required for user memory type "user" since it's used as a unique identifier for the user.
         user_id = self._get_user_id()
@@ -27,7 +32,7 @@ class Mem0Storage(Storage):
             raise ValueError("User ID is required for user memory type")
 
         # API key in memory config overrides the environment variable
-        config = self.memory_config.get("config", {})
+        config = self._get_config()
         mem0_api_key = config.get("api_key") or os.getenv("MEM0_API_KEY")
         mem0_org_id = config.get("org_id")
         mem0_project_id = config.get("project_id")
@@ -43,7 +48,7 @@ class Mem0Storage(Storage):
                 self.memory = MemoryClient(api_key=mem0_api_key)
         else:
             if mem0_local_config and len(mem0_local_config):
-                self.memory = Memory.from_config(config)
+                self.memory = Memory.from_config(mem0_local_config)
             else:
                 self.memory = Memory()
 
@@ -56,26 +61,34 @@ class Mem0Storage(Storage):
     def save(self, value: Any, metadata: Dict[str, Any]) -> None:
         user_id = self._get_user_id()
         agent_name = self._get_agent_name()
-        if self.memory_type == "user":
-            self.memory.add(value, user_id=user_id, metadata={**metadata})
-        elif self.memory_type == "short_term":
-            agent_name = self._get_agent_name()
-            self.memory.add(
-                value, agent_id=agent_name, metadata={"type": "short_term", **metadata}
-            )
+        params = None
+        if self.memory_type == "short_term":
+            params = {
+                "agent_id": agent_name,
+                "infer": False,
+                "metadata": {"type": "short_term", **metadata},
+            }
         elif self.memory_type == "long_term":
-            agent_name = self._get_agent_name()
-            self.memory.add(
-                value,
-                agent_id=agent_name,
-                infer=False,
-                metadata={"type": "long_term", **metadata},
-            )
+            params = {
+                "agent_id": agent_name,
+                "infer": False,
+                "metadata": {"type": "long_term", **metadata},
+            }
         elif self.memory_type == "entities":
-            entity_name = self._get_agent_name()
-            self.memory.add(
-                value, user_id=entity_name, metadata={"type": "entity", **metadata}
-            )
+            params = {
+                "agent_id": agent_name,
+                "infer": False,
+                "metadata": {"type": "entity", **metadata},
+            }
+        elif self.memory_type == "external":
+            params = {
+                "user_id": user_id,
+                "agent_id": agent_name,
+                "metadata": {"type": "external", **metadata},
+            }
+
+        if params:
+            self.memory.add(value, **params | {"output_format": "v1.1"})
 
     def search(
         self,
@@ -84,41 +97,43 @@ class Mem0Storage(Storage):
         score_threshold: float = 0.35,
     ) -> List[Any]:
         params = {"query": query, "limit": limit}
-        if self.memory_type == "user":
-            user_id = self._get_user_id()
+        if user_id := self._get_user_id():
             params["user_id"] = user_id
-        elif self.memory_type == "short_term":
-            agent_name = self._get_agent_name()
+
+        agent_name = self._get_agent_name()
+        if self.memory_type == "short_term":
             params["agent_id"] = agent_name
             params["metadata"] = {"type": "short_term"}
         elif self.memory_type == "long_term":
-            agent_name = self._get_agent_name()
             params["agent_id"] = agent_name
             params["metadata"] = {"type": "long_term"}
         elif self.memory_type == "entities":
-            agent_name = self._get_agent_name()
             params["agent_id"] = agent_name
             params["metadata"] = {"type": "entity"}
+        elif self.memory_type == "external":
+            params["agent_id"] = agent_name
+            params["metadata"] = {"type": "external"}
 
         # Discard the filters for now since we create the filters
         # automatically when the crew is created.
         results = self.memory.search(**params)
         return [r for r in results if r["score"] >= score_threshold]
 
-    def _get_user_id(self):
-        if self.memory_type == "user":
-            if hasattr(self, "memory_config") and self.memory_config is not None:
-                return self.memory_config.get("config", {}).get("user_id")
-            else:
-                return None
-        return None
+    def _get_user_id(self) -> str:
+        return self._get_config().get("user_id", "")
 
-    def _get_agent_name(self):
-        agents = self.crew.agents if self.crew else []
+    def _get_agent_name(self) -> str:
+        if not self.crew:
+            return ""
+
+        agents = self.crew.agents
         agents = [self._sanitize_role(agent.role) for agent in agents]
         agents = "_".join(agents)
         return agents
 
+    def _get_config(self) -> Dict[str, Any]:
+        return self.config or getattr(self, "memory_config", {}).get("config", {}) or {}
+
     def reset(self):
         if self.memory:
             self.memory.reset()

src/crewai/memory/user/user_memory.py

@@ -1,3 +1,4 @@
+import warnings
 from typing import Any, Dict, Optional
 
 from crewai.memory.memory import Memory
@@ -12,6 +13,12 @@ class UserMemory(Memory):
     """
 
     def __init__(self, crew=None):
+        warnings.warn(
+            "UserMemory is deprecated and will be removed in a future version. "
+            "Please use ExternalMemory instead.",
+            DeprecationWarning,
+            stacklevel=2,
+        )
         try:
             from crewai.memory.storage.mem0_storage import Mem0Storage
         except ImportError:
@@ -48,6 +55,4 @@ class UserMemory(Memory):
         try:
             self.storage.reset()
         except Exception as e:
-            raise Exception(
-                f"An error occurred while resetting the user memory: {e}"
-            )
+            raise Exception(f"An error occurred while resetting the user memory: {e}")

src/crewai/project/crew_base.py

@@ -137,13 +137,11 @@ def CrewBase(cls: T) -> T:
                 all_functions, "is_cache_handler"
             )
             callbacks = self._filter_functions(all_functions, "is_callback")
-            agents = self._filter_functions(all_functions, "is_agent")
 
             for agent_name, agent_info in self.agents_config.items():
                 self._map_agent_variables(
                     agent_name,
                     agent_info,
-                    agents,
                     llms,
                     tool_functions,
                     cache_handler_functions,
@@ -154,7 +152,6 @@ def CrewBase(cls: T) -> T:
             self,
             agent_name: str,
             agent_info: Dict[str, Any],
-            agents: Dict[str, Callable],
             llms: Dict[str, Callable],
             tool_functions: Dict[str, Callable],
             cache_handler_functions: Dict[str, Callable],
@@ -172,9 +169,10 @@ def CrewBase(cls: T) -> T:
                 ]
 
             if function_calling_llm := agent_info.get("function_calling_llm"):
-                self.agents_config[agent_name]["function_calling_llm"] = agents[
-                    function_calling_llm
-                ]()
+                try:
+                    self.agents_config[agent_name]["function_calling_llm"] = llms[function_calling_llm]()
+                except KeyError:
+                    self.agents_config[agent_name]["function_calling_llm"] = function_calling_llm
 
             if step_callback := agent_info.get("step_callback"):
                 self.agents_config[agent_name]["step_callback"] = callbacks[

src/crewai/telemetry/telemetry.py

@@ -45,10 +45,10 @@ class Telemetry:
     """
 
     def __init__(self):
-        self.ready = False
-        self.trace_set = False
+        self.ready: bool = False
+        self.trace_set: bool = False
 
-        if os.getenv("OTEL_SDK_DISABLED", "false").lower() == "true":
+        if self._is_telemetry_disabled():
             return
 
         try:
@@ -75,6 +75,13 @@ class Telemetry:
             ):
                 raise  # Re-raise the exception to not interfere with system signals
             self.ready = False
+            
+    def _is_telemetry_disabled(self) -> bool:
+        """Check if telemetry should be disabled based on environment variables."""
+        return (
+            os.getenv("OTEL_SDK_DISABLED", "false").lower() == "true" or
+            os.getenv("CREWAI_DISABLE_TELEMETRY", "false").lower() == "true"
+        )
 
     def set_tracer(self):
         if self.ready and not self.trace_set:

src/crewai/tools/base_tool.py

@@ -1,3 +1,4 @@
+import asyncio
 import warnings
 from abc import ABC, abstractmethod
 from inspect import signature
@@ -65,7 +66,13 @@ class BaseTool(BaseModel, ABC):
         **kwargs: Any,
     ) -> Any:
         print(f"Using Tool: {self.name}")
-        return self._run(*args, **kwargs)
+        result = self._run(*args, **kwargs)
+
+        # If _run is async, we safely run it
+        if asyncio.iscoroutine(result):
+            return asyncio.run(result)
+
+        return result
 
     @abstractmethod
     def _run(
@@ -244,9 +251,13 @@ def to_langchain(
     return [t.to_structured_tool() if isinstance(t, BaseTool) else t for t in tools]
 
 
-def tool(*args):
+def tool(*args, result_as_answer=False):
     """
     Decorator to create a tool from a function.
+    
+    Args:
+        *args: Positional arguments, either the function to decorate or the tool name.
+        result_as_answer: Flag to indicate if the tool result should be used as the final agent answer.
     """
 
     def _make_with_name(tool_name: str) -> Callable:
@@ -272,6 +283,7 @@ def tool(*args):
                 description=f.__doc__,
                 func=f,
                 args_schema=args_schema,
+                result_as_answer=result_as_answer,
             )
 
         return _make_tool

src/crewai/tools/tool_usage.py

@@ -2,7 +2,6 @@ import ast
 import datetime
 import json
 import time
-from dataclasses import dataclass
 from difflib import SequenceMatcher
 from json import JSONDecodeError
 from textwrap import dedent
@@ -26,6 +25,7 @@ from crewai.utilities.events.tool_usage_events import (
     ToolSelectionErrorEvent,
     ToolUsageErrorEvent,
     ToolUsageFinishedEvent,
+    ToolUsageStartedEvent,
     ToolValidateInputErrorEvent,
 )
 
@@ -166,6 +166,21 @@ class ToolUsage:
                 if self.task:
                     self.task.increment_tools_errors()
 
+        if self.agent:
+            event_data = {
+                "agent_key": self.agent.key,
+                "agent_role": self.agent.role,
+                "tool_name": self.action.tool,
+                "tool_args": self.action.tool_input,
+                "tool_class": self.action.tool,
+                "agent": self.agent,
+            }
+
+            if self.agent.fingerprint:
+                event_data.update(self.agent.fingerprint)
+
+            crewai_event_bus.emit(self,ToolUsageStartedEvent(**event_data))
+            
         started_at = time.time()
         from_cache = False
         result = None  # type: ignore

src/crewai/utilities/agent_utils.py

@@ -16,7 +16,6 @@ from crewai.tools.base_tool import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.tools.tool_types import ToolResult
 from crewai.utilities import I18N, Printer
-from crewai.utilities.events.tool_usage_events import ToolUsageStartedEvent
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
 )

src/crewai/utilities/tool_utils.py

@@ -5,11 +5,6 @@ from crewai.security import Fingerprint
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.tools.tool_types import ToolResult
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
-from crewai.utilities.events import crewai_event_bus
-from crewai.utilities.events.tool_usage_events import (
-    ToolUsageErrorEvent,
-    ToolUsageStartedEvent,
-)
 from crewai.utilities.i18n import I18N
 
 
@@ -42,10 +37,8 @@ def execute_tool_and_check_finality(
         ToolResult containing the execution result and whether it should be treated as a final answer
     """
     try:
-        # Create tool name to tool map
         tool_name_to_tool_map = {tool.name: tool for tool in tools}
 
-        # Emit tool usage event if agent info is available
         if agent_key and agent_role and agent:
             fingerprint_context = fingerprint_context or {}
             if agent:
@@ -59,22 +52,6 @@ def execute_tool_and_check_finality(
                         except Exception as e:
                             raise ValueError(f"Failed to set fingerprint: {e}")
 
-            event_data = {
-                "agent_key": agent_key,
-                "agent_role": agent_role,
-                "tool_name": agent_action.tool,
-                "tool_args": agent_action.tool_input,
-                "tool_class": agent_action.tool,
-                "agent": agent,
-            }
-            event_data.update(fingerprint_context)
-            crewai_event_bus.emit(
-                agent,
-                event=ToolUsageStartedEvent(
-                    **event_data,
-                ),
-            )
-
         # Create tool usage instance
         tool_usage = ToolUsage(
             tools_handler=tools_handler,
@@ -110,17 +87,4 @@ def execute_tool_and_check_finality(
         return ToolResult(tool_result, False)
 
     except Exception as e:
-        # Emit error event if agent info is available
-        if agent_key and agent_role and agent:
-            crewai_event_bus.emit(
-                agent,
-                event=ToolUsageErrorEvent(
-                    agent_key=agent_key,
-                    agent_role=agent_role,
-                    tool_name=agent_action.tool,
-                    tool_args=agent_action.tool_input,
-                    tool_class=agent_action.tool,
-                    error=str(e),
-                ),
-            )
         raise e

tests/cassettes/test_lite_agent_created_with_correct_parameters[False].yaml

@@ -0,0 +1,486 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour
+      personal goal is: Test Goal\n\nYou ONLY have access to the following tools,
+      and should NEVER make up tools that are not listed here:\n\nTool Name: search_web\nTool
+      Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Search the web for information about a topic.\nTool Name: calculate\nTool Arguments:
+      {''expression'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Calculate the result of a mathematical expression.\n\nIMPORTANT: Use the following
+      format in your response:\n\n```\nThought: you should always think about what
+      to do\nAction: the action to take, only one name of [search_web, calculate],
+      just the name, exactly as it''s written.\nAction Input: the input to the action,
+      just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
+      values.\nObservation: the result of the action\n```\n\nOnce all necessary information
+      is gathered, return the following format:\n\n```\nThought: I now know the final
+      answer\nFinal Answer: the final answer to the original input question\n```"},
+      {"role": "user", "content": "Test query"}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1220'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=skEg5DBE_nQ5gLAsfGzhjTetiNUJ_Y2bXWLMsvjIi7s-1744222695-1.0.1.1-qyjwnTgJKwF54pRhf0YHxW_BUw6p7SC60kwFsF9XTq4i2u2mnFKVq4WbsgvQDeuDEIxyaNb.ngWUVOU1GIX1O2Hcxcdn6TSaJ8NXTQw28F8;
+        _cfuvid=Hwvd7n4RVfOZLGiOKPaHmYJC7h8rCQmlmnBgBsKqy4Y-1744222695443-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BKUIMCbxAr4MO0Ku8tDYBgJ30LGXi\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744222714,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"```\\nThought: I need more information
+      to understand what specific query to search for.\\nAction: search_web\\nAction
+      Input: {\\\"query\\\":\\\"Test query\\\"}\",\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 242,\n    \"completion_tokens\":
+      31,\n    \"total_tokens\": 273,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92dc01f9bd96cf41-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 09 Apr 2025 18:18:34 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '749'
+      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:
+      - '149999732'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_99e3ad4ee98371cc1c55a2f5c6ae3962
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour
+      personal goal is: Test Goal\n\nYou ONLY have access to the following tools,
+      and should NEVER make up tools that are not listed here:\n\nTool Name: search_web\nTool
+      Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Search the web for information about a topic.\nTool Name: calculate\nTool Arguments:
+      {''expression'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Calculate the result of a mathematical expression.\n\nIMPORTANT: Use the following
+      format in your response:\n\n```\nThought: you should always think about what
+      to do\nAction: the action to take, only one name of [search_web, calculate],
+      just the name, exactly as it''s written.\nAction Input: the input to the action,
+      just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
+      values.\nObservation: the result of the action\n```\n\nOnce all necessary information
+      is gathered, return the following format:\n\n```\nThought: I now know the final
+      answer\nFinal Answer: the final answer to the original input question\n```"},
+      {"role": "user", "content": "Test query"}, {"role": "assistant", "content":
+      "```\nThought: I need more information to understand what specific query to
+      search for.\nAction: search_web\nAction Input: {\"query\":\"Test query\"}\nObservation:
+      Found information about Test query: This is a simulated search result for demonstration
+      purposes."}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1518'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=skEg5DBE_nQ5gLAsfGzhjTetiNUJ_Y2bXWLMsvjIi7s-1744222695-1.0.1.1-qyjwnTgJKwF54pRhf0YHxW_BUw6p7SC60kwFsF9XTq4i2u2mnFKVq4WbsgvQDeuDEIxyaNb.ngWUVOU1GIX1O2Hcxcdn6TSaJ8NXTQw28F8;
+        _cfuvid=Hwvd7n4RVfOZLGiOKPaHmYJC7h8rCQmlmnBgBsKqy4Y-1744222695443-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BKUINDYiGwrVyJU7wUoXCw3hft7yF\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744222715,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"```\\nThought: I now know the final answer\\nFinal
+      Answer: This is a simulated search result for demonstration purposes.\\n```\",\n
+      \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      295,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 321,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92dc02003c9ecf41-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 09 Apr 2025 18:18:35 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '531'
+      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:
+      - '149999667'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_dd9052c40d5d61ecc5eb141f49df3abe
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour
+      personal goal is: Test Goal\n\nYou ONLY have access to the following tools,
+      and should NEVER make up tools that are not listed here:\n\nTool Name: search_web\nTool
+      Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Search the web for information about a topic.\nTool Name: calculate\nTool Arguments:
+      {''expression'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Calculate the result of a mathematical expression.\n\nIMPORTANT: Use the following
+      format in your response:\n\n```\nThought: you should always think about what
+      to do\nAction: the action to take, only one name of [search_web, calculate],
+      just the name, exactly as it''s written.\nAction Input: the input to the action,
+      just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
+      values.\nObservation: the result of the action\n```\n\nOnce all necessary information
+      is gathered, return the following format:\n\n```\nThought: I now know the final
+      answer\nFinal Answer: the final answer to the original input question\n```\nIMPORTANT:
+      Your final answer MUST contain all the information requested in the following
+      format: {\n  \"test_field\": str\n}\n\nIMPORTANT: Ensure the final output does
+      not include any code block markers like ```json or ```python."}, {"role": "user",
+      "content": "Test query"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1451'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=skEg5DBE_nQ5gLAsfGzhjTetiNUJ_Y2bXWLMsvjIi7s-1744222695-1.0.1.1-qyjwnTgJKwF54pRhf0YHxW_BUw6p7SC60kwFsF9XTq4i2u2mnFKVq4WbsgvQDeuDEIxyaNb.ngWUVOU1GIX1O2Hcxcdn6TSaJ8NXTQw28F8;
+        _cfuvid=Hwvd7n4RVfOZLGiOKPaHmYJC7h8rCQmlmnBgBsKqy4Y-1744222695443-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BKUIN3xeM6JBgLjV5HQA8MTI2Uuem\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744222715,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"```\\nThought: I need to clarify what
+      specific information or topic the test query is targeting.\\nAction: search_web\\nAction
+      Input: {\\\"query\\\":\\\"What is the purpose of a test query in data retrieval?\\\"}\",\n
+      \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      288,\n    \"completion_tokens\": 43,\n    \"total_tokens\": 331,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92dc0204d91ccf41-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 09 Apr 2025 18:18:36 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '728'
+      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:
+      - '149999675'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_e792e993009ddfe84cfbb503560d88cf
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour
+      personal goal is: Test Goal\n\nYou ONLY have access to the following tools,
+      and should NEVER make up tools that are not listed here:\n\nTool Name: search_web\nTool
+      Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Search the web for information about a topic.\nTool Name: calculate\nTool Arguments:
+      {''expression'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Calculate the result of a mathematical expression.\n\nIMPORTANT: Use the following
+      format in your response:\n\n```\nThought: you should always think about what
+      to do\nAction: the action to take, only one name of [search_web, calculate],
+      just the name, exactly as it''s written.\nAction Input: the input to the action,
+      just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
+      values.\nObservation: the result of the action\n```\n\nOnce all necessary information
+      is gathered, return the following format:\n\n```\nThought: I now know the final
+      answer\nFinal Answer: the final answer to the original input question\n```\nIMPORTANT:
+      Your final answer MUST contain all the information requested in the following
+      format: {\n  \"test_field\": str\n}\n\nIMPORTANT: Ensure the final output does
+      not include any code block markers like ```json or ```python."}, {"role": "user",
+      "content": "Test query"}, {"role": "assistant", "content": "```\nThought: I
+      need to clarify what specific information or topic the test query is targeting.\nAction:
+      search_web\nAction Input: {\"query\":\"What is the purpose of a test query in
+      data retrieval?\"}\nObservation: Found information about What is the purpose
+      of a test query in data retrieval?: This is a simulated search result for demonstration
+      purposes."}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1846'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=skEg5DBE_nQ5gLAsfGzhjTetiNUJ_Y2bXWLMsvjIi7s-1744222695-1.0.1.1-qyjwnTgJKwF54pRhf0YHxW_BUw6p7SC60kwFsF9XTq4i2u2mnFKVq4WbsgvQDeuDEIxyaNb.ngWUVOU1GIX1O2Hcxcdn6TSaJ8NXTQw28F8;
+        _cfuvid=Hwvd7n4RVfOZLGiOKPaHmYJC7h8rCQmlmnBgBsKqy4Y-1744222695443-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BKUIOqyLDCIZv6YIz1hlaW479SIzg\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744222716,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"```\\nThought: I now know the final answer\\nFinal
+      Answer: {\\n  \\\"test_field\\\": \\\"A test query is utilized to evaluate the
+      functionality, performance, and accuracy of data retrieval systems, ensuring
+      they return expected results.\\\"\\n}\\n```\",\n        \"refusal\": null,\n
+      \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 362,\n    \"completion_tokens\":
+      49,\n    \"total_tokens\": 411,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92dc020a3defcf41-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 09 Apr 2025 18:18:37 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '805'
+      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:
+      - '149999588'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_3b6c80fd3066b9e0054d0d2280bc4c98
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_lite_agent_returns_usage_metrics_async.yaml

@@ -0,0 +1,249 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Research Assistant.
+      You are a helpful research assistant who can search for information about the
+      population of Tokyo.\nYour personal goal is: Find information about the population
+      of Tokyo\n\nYou ONLY have access to the following tools, and should NEVER make
+      up tools that are not listed here:\n\nTool Name: search_web\nTool Arguments:
+      {''query'': {''description'': None, ''type'': ''str''}}\nTool Description: Search
+      the web for information about a topic.\n\nIMPORTANT: Use the following format
+      in your response:\n\n```\nThought: you should always think about what to do\nAction:
+      the action to take, only one name of [search_web], just the name, exactly as
+      it''s written.\nAction Input: the input to the action, just a simple JSON object,
+      enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
+      result of the action\n```\n\nOnce all necessary information is gathered, return
+      the following format:\n\n```\nThought: I now know the final answer\nFinal Answer:
+      the final answer to the original input question\n```"}, {"role": "user", "content":
+      "What is the population of Tokyo? Return your strucutred output in JSON format
+      with the following fields: summary, confidence"}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1290'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=u769MG.poap6iEjFpbByMFUC0FygMEqYSurr5DfLbas-1743447969501-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BKUM5MZbz4TG6qmUtTrgKo8gI48FO\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744222945,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"```\\nThought: I need to find the current
+      population of Tokyo.\\nAction: search_web\\nAction Input: {\\\"query\\\":\\\"current
+      population of Tokyo 2023\\\"}\",\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 248,\n    \"completion_tokens\":
+      33,\n    \"total_tokens\": 281,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92dc079f8e5a7ab0-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 09 Apr 2025 18:22:26 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=1F.UUVSjZyp8QMRT0dTQXUJc5WlGpC3xAx4FY7KCQbs-1744222946-1.0.1.1-vcXIZcokSjfxyFeoTTUAWmBGmJpv0ss9iFqt5EJVZGE1PvSV2ov0erCS.KIo0xItBMuX_MtCgDSaYMPI3L9QDsLatWqfUFieHiFh0CrX4h8;
+        path=/; expires=Wed, 09-Apr-25 18:52:26 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=RbJuVW8hReYElyyghEbAFletdnJZ2mk5rn9D8EGuyNk-1744222946580-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1282'
+      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:
+      - '149999713'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_845ed875afd48dee3d88f33cbab88cc2
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Research Assistant.
+      You are a helpful research assistant who can search for information about the
+      population of Tokyo.\nYour personal goal is: Find information about the population
+      of Tokyo\n\nYou ONLY have access to the following tools, and should NEVER make
+      up tools that are not listed here:\n\nTool Name: search_web\nTool Arguments:
+      {''query'': {''description'': None, ''type'': ''str''}}\nTool Description: Search
+      the web for information about a topic.\n\nIMPORTANT: Use the following format
+      in your response:\n\n```\nThought: you should always think about what to do\nAction:
+      the action to take, only one name of [search_web], just the name, exactly as
+      it''s written.\nAction Input: the input to the action, just a simple JSON object,
+      enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
+      result of the action\n```\n\nOnce all necessary information is gathered, return
+      the following format:\n\n```\nThought: I now know the final answer\nFinal Answer:
+      the final answer to the original input question\n```"}, {"role": "user", "content":
+      "What is the population of Tokyo? Return your strucutred output in JSON format
+      with the following fields: summary, confidence"}, {"role": "assistant", "content":
+      "```\nThought: I need to find the current population of Tokyo.\nAction: search_web\nAction
+      Input: {\"query\":\"current population of Tokyo 2023\"}\nObservation: Tokyo''s
+      population in 2023 was approximately 21 million people in the city proper, and
+      37 million in the greater metropolitan area."}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1619'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=RbJuVW8hReYElyyghEbAFletdnJZ2mk5rn9D8EGuyNk-1744222946580-0.0.1.1-604800000;
+        __cf_bm=1F.UUVSjZyp8QMRT0dTQXUJc5WlGpC3xAx4FY7KCQbs-1744222946-1.0.1.1-vcXIZcokSjfxyFeoTTUAWmBGmJpv0ss9iFqt5EJVZGE1PvSV2ov0erCS.KIo0xItBMuX_MtCgDSaYMPI3L9QDsLatWqfUFieHiFh0CrX4h8
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BKUM69pnk6VLn5rpDjGdg21mOxFke\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744222946,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"```\\nThought: I now know the final answer\\nFinal
+      Answer: {\\\"summary\\\":\\\"The population of Tokyo is approximately 21 million
+      in the city proper and 37 million in the greater metropolitan area as of 2023.\\\",\\\"confidence\\\":\\\"high\\\"}\\n```\",\n
+      \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      315,\n    \"completion_tokens\": 51,\n    \"total_tokens\": 366,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92dc07a8ac9f7ab0-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 09 Apr 2025 18:22:27 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1024'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999642'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_d72860d8629025988b1170e939bc1f20
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_tool_execution_error_event.yaml

@@ -1,112 +0,0 @@
-interactions:
-- request:
-    body: '{"messages": [{"role": "user", "content": "Use the failing tool"}], "model":
-      "gpt-4o-mini", "stop": [], "tools": [{"type": "function", "function": {"name":
-      "failing_tool", "description": "This tool always fails.", "parameters": {"type":
-      "object", "properties": {"param": {"type": "string", "description": "A test
-      parameter"}}, "required": ["param"]}}}]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '353'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.8
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-B2P4zoJZuES7Aom8ugEq1modz5Vsl\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1739912761,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
-      \           \"id\": \"call_F6fJxISpMKUBIGV6dd2vjRNG\",\n            \"type\":
-      \"function\",\n            \"function\": {\n              \"name\": \"failing_tool\",\n
-      \             \"arguments\": \"{\\\"param\\\":\\\"test\\\"}\"\n            }\n
-      \         }\n        ],\n        \"refusal\": null\n      },\n      \"logprobs\":
-      null,\n      \"finish_reason\": \"tool_calls\"\n    }\n  ],\n  \"usage\": {\n
-      \   \"prompt_tokens\": 51,\n    \"completion_tokens\": 15,\n    \"total_tokens\":
-      66,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\":
-      0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
-      0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\":
-      0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\":
-      \"fp_00428b782a\"\n}\n"
-    headers:
-      CF-RAY:
-      - 9140fa827f38eb1e-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 18 Feb 2025 21:06:02 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=xbuu3IQpCMh.43ZrqL1TRMECOc6QldgHV0hzOX1GrWI-1739912762-1.0.1.1-t7iyq5xMioPrwfeaHLvPT9rwRPp7Q9A9uIm69icH9dPxRD4xMA3cWqb1aXj1_e2IyAEQQWFe1UWjlmJ22aHh3Q;
-        path=/; expires=Tue, 18-Feb-25 21:36:02 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=x9l.Rhja8_wXDN.j8qcEU1PvvEqAwZp4Fd3s_aj4qwM-1739912762161-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '861'
-      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:
-      - '149999978'
-      x-ratelimit-reset-requests:
-      - 2ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_8666ec3aa6677cb346ba00993556051d
-    http_version: HTTP/1.1
-    status_code: 200
-version: 1

tests/cassettes/test_using_contextual_memory_with_long_term_memory.yaml

@@ -0,0 +1,209 @@
+interactions:
+- request:
+    body: !!binary |
+      CuAMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkStwwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKdCAoQe1SuF2c2xWX4juAv74oXphII/LGj/b5w49QqDENyZXcgQ3JlYXRlZDABOcCZ
+      B6F1rTUYQRhzEqF1rTUYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIGM5N2I1ZmViNWQxYjY2YmI1OTAwNmFhYTAx
+      YTI5Y2Q2SjEKB2NyZXdfaWQSJgokMDU1YWZhNGQtNWU5MS00YWU1LTg4ZTQtMGQ3N2I2OTZiODJl
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
+      X2ZpbmdlcnByaW50EiYKJGI3NzY4MjJlLTU4YzItNDg5Ni05NmVhLTlmNDQzNjc4NThjNko7Chtj
+      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xMlQxNzo1MjozMS4zOTkzMTdK
+      0QIKC2NyZXdfYWdlbnRzEsECCr4CW3sia2V5IjogIjA3ZDk5YjYzMDQxMWQzNWZkOTA0N2E1MzJk
+      NTNkZGE3IiwgImlkIjogIjI5MmZlMjI4LTNlYzEtNDE4Zi05NzQzLTFkNTI3ZGY5M2QwYyIsICJy
+      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJt
+      YXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRv
+      LW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRp
+      b24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSv8B
+      CgpjcmV3X3Rhc2tzEvABCu0BW3sia2V5IjogIjYzOTk2NTE3ZjNmM2YxYzk0ZDZiYjYxN2FhMGIx
+      YzRmIiwgImlkIjogIjhlY2E1NTQzLTc3MDEtNDhjMy1hODM1LWI4YWE2YmE3YTMzZSIsICJhc3lu
+      Y19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUi
+      OiAiUmVzZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiMDdkOTliNjMwNDExZDM1ZmQ5MDQ3YTUzMmQ1
+      M2RkYTciLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQmqGVrPp33uFfE2WlsNm/
+      phIIx0mZ95NGSyIqDFRhc2sgQ3JlYXRlZDABObBlHqF1rTUYQbi3HqF1rTUYSi4KCGNyZXdfa2V5
+      EiIKIGM5N2I1ZmViNWQxYjY2YmI1OTAwNmFhYTAxYTI5Y2Q2SjEKB2NyZXdfaWQSJgokMDU1YWZh
+      NGQtNWU5MS00YWU1LTg4ZTQtMGQ3N2I2OTZiODJlSi4KCHRhc2tfa2V5EiIKIDYzOTk2NTE3ZjNm
+      M2YxYzk0ZDZiYjYxN2FhMGIxYzRmSjEKB3Rhc2tfaWQSJgokOGVjYTU1NDMtNzcwMS00OGMzLWE4
+      MzUtYjhhYTZiYTdhMzNlSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokYjc3NjgyMmUtNThjMi00ODk2
+      LTk2ZWEtOWY0NDM2Nzg1OGM2SjoKEHRhc2tfZmluZ2VycHJpbnQSJgokYTk5NjE4ZTYtODFhZC00
+      N2YyLWE4ZGEtOTc1NjkzN2YxYmIwSjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoy
+      MDI1LTA0LTEyVDE3OjUyOjMxLjM5ODIxNEo7ChFhZ2VudF9maW5nZXJwcmludBImCiRlZjkxZGYx
+      NS0zNmNiLTQ0MDQtOWFkMi05MmM1OTQ1NGU2ZTZ6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1635'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.31.1
+    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:
+      - Sat, 12 Apr 2025 20:52:35 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
+      an expert in research and you love to learn new things.\nYour personal goal
+      is: You research about math.\nTo give my best complete final answer to the task
+      respond using the exact following format:\n\nThought: I now can give a great
+      answer\nFinal Answer: Your final answer must be the great and the most complete
+      as possible, it must be outcome described.\n\nI MUST use these formats, my job
+      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Research a topic
+      to teach a kid aged 6 about math.\n\nThis is the expected criteria for your
+      final answer: A topic, explanation, angle, and examples.\nyou MUST return the
+      actual complete content as the final answer, not a summary.\n\n# Useful context:
+      \n<MagicMock name=''build_context_for_task()'' id=''13586043616''>\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:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1031'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BLc7zvaXoFAArOIDK9TrMtdq8kKY0\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744491151,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer.  \\nFinal
+      Answer: \\n\\n**Topic: Introduction to Addition with Fun Objects**\\n\\n**Explanation:**
+      \ \\nAt its core, addition is all about combining two or more groups of things
+      to find out how many there are in total. We can think of addition as a way to
+      bring friends together! Imagine if you have some apples and your friend brings
+      some more apples; together, you want to find out how many apples there are altogether.
+      This is the foundation of addition, and it can be made fun and engaging for
+      a 6-year-old.\\n\\n**Angle:**  \\nTo make this relatable and enjoyable, we can
+      use everyday objects that kids love, such as toys, fruits, or even drawings.
+      We can create little stories or scenarios that involve addition, turning it
+      into a game where they get to count and add things together. By using real items,
+      children can see and feel what addition means, making it easier to grasp the
+      concept.\\n\\n**Examples:**  \\n1. **Using Fruits:**  \\n   Let's say you have
+      3 oranges. You can say, \\\"I have 3 oranges.\\\" Then, if your friend brings
+      you 2 more oranges, you can introduce the addition by saying, \\\"Now, how many
+      do we have all together?\\\"  \\n   - So you would show it as: 3 (oranges you
+      have) + 2 (oranges your friend brought) = ?  \\n   To find the answer, you can
+      count all the oranges together: 1, 2, 3 (your oranges) and 4, 5 (your friend's
+      oranges).  \\n   - The answer is 5 oranges in total!\\n\\n2. **Using Toys:**
+      \ \\n   If a child has 4 toy cars and finds 3 more under the couch, we can ask,
+      \\\"How many cars do you have now?\\\"  \\n   - Write it down: 4 (toy cars)
+      + 3 (found cars) = ?  \\n   Then, count the toy cars together: 1, 2, 3, 4 (original
+      cars), 5, 6, 7.  \\n   - The answer is 7 toy cars!\\n\\n3. **Story Scenario:**
+      \ \\n   Create an engaging story: \\\"Once upon a time, there were 2 friendly
+      puppies. One day, 3 more puppies came to play. How many puppies are playing
+      now?\\\"  \\n   - Present it as: 2 (original puppies) + 3 (new puppies) = ?
+      \ \\n   Count the puppies: 1, 2 (the first two) and then 3, 4, 5 (the new ones).
+      \ \\n   - The answer is 5 puppies playing!\\n\\nBy presenting addition through
+      fun scenarios and interactive counting, a 6-year-old can learn and understand
+      addition while enjoying the process. They can even use crayons to draw the items
+      or fruit to count in a playful, hands-on approach. This makes math not just
+      a subject, but also a delightful adventure!\",\n        \"refusal\": null,\n
+      \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 206,\n    \"completion_tokens\":
+      609,\n    \"total_tokens\": 815,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_44added55e\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92f59ba1fa19572a-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 12 Apr 2025 20:52:44 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=C7ejNhC7vNTBO9VtBqzN_ce__mP2Dz8noDo2lIcNBn0-1744491164-1.0.1.1-kQgWk4d54JIGxg_yCJ.7uV9HkU8JXrhpfIth0WHDdqf9ESzAsQyDu0xKVLYnga.xswBnm5kePpuFCcnIqGKgyag31cEyuiFFf6JHTvQcvWI;
+        path=/; expires=Sat, 12-Apr-25 21:22:44 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=QuvcyYK0MZfY9dNclglrzesXcplWfoZN.rd4J57.xtY-1744491164641-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '12806'
+      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:
+      - '149999777'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_49f3c203229149ce08c0813ac4071355
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_warning_long_term_memory_without_entity_memory.yaml

@@ -0,0 +1,205 @@
+interactions:
+- request:
+    body: !!binary |
+      CuAMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkStwwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKdCAoQE1JYPHUcNy20EEB8E7lQKRIIeom6mAik9I0qDENyZXcgQ3JlYXRlZDABOdhP
+      ANFPrzUYQWCwCNFPrzUYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIGM5N2I1ZmViNWQxYjY2YmI1OTAwNmFhYTAx
+      YTI5Y2Q2SjEKB2NyZXdfaWQSJgokMjNmZDllZTktMWRiZC00M2FjLTlhZGYtNTQ5YWFhZTNkMTNj
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
+      X2ZpbmdlcnByaW50EiYKJDk2M2UyNDA4LTI3MzktNGU3ZS04ZTAzLTIxOGUzZjhmMTFhZEo7Chtj
+      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xMlQxODoyNjoyOC4wMTg1MzVK
+      0QIKC2NyZXdfYWdlbnRzEsECCr4CW3sia2V5IjogIjA3ZDk5YjYzMDQxMWQzNWZkOTA0N2E1MzJk
+      NTNkZGE3IiwgImlkIjogIjA3ZWIyOWYzLWE2OWQtNGQ1MC1iZGJiLTAwNjEzN2UzYjU4MiIsICJy
+      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJt
+      YXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRv
+      LW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRp
+      b24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSv8B
+      CgpjcmV3X3Rhc2tzEvABCu0BW3sia2V5IjogIjYzOTk2NTE3ZjNmM2YxYzk0ZDZiYjYxN2FhMGIx
+      YzRmIiwgImlkIjogImUwOWIzMzg1LThmNTAtNDIxYy1hYzE0LTdhZDU5NTU4YmY4NiIsICJhc3lu
+      Y19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUi
+      OiAiUmVzZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiMDdkOTliNjMwNDExZDM1ZmQ5MDQ3YTUzMmQ1
+      M2RkYTciLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQ/KSXqXcsLoGmHCaEWYIa
+      9xII/Ucae2PMp18qDFRhc2sgQ3JlYXRlZDABObAfF9FPrzUYQeCUF9FPrzUYSi4KCGNyZXdfa2V5
+      EiIKIGM5N2I1ZmViNWQxYjY2YmI1OTAwNmFhYTAxYTI5Y2Q2SjEKB2NyZXdfaWQSJgokMjNmZDll
+      ZTktMWRiZC00M2FjLTlhZGYtNTQ5YWFhZTNkMTNjSi4KCHRhc2tfa2V5EiIKIDYzOTk2NTE3ZjNm
+      M2YxYzk0ZDZiYjYxN2FhMGIxYzRmSjEKB3Rhc2tfaWQSJgokZTA5YjMzODUtOGY1MC00MjFjLWFj
+      MTQtN2FkNTk1NThiZjg2SjoKEGNyZXdfZmluZ2VycHJpbnQSJgokOTYzZTI0MDgtMjczOS00ZTdl
+      LThlMDMtMjE4ZTNmOGYxMWFkSjoKEHRhc2tfZmluZ2VycHJpbnQSJgokN2FhMTE0NDAtYjNkYi00
+      Y2VmLTgzYjUtNTk3ZTMwMTIxZGZhSjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoy
+      MDI1LTA0LTEyVDE4OjI2OjI4LjAxNzMyNEo7ChFhZ2VudF9maW5nZXJwcmludBImCiQ0MDczMjdk
+      NC1hMzRjLTQyNTUtYWIxYy1iM2I1OTNiMmM4MTJ6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1635'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.31.1
+    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:
+      - Sat, 12 Apr 2025 21:26:32 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
+      an expert in research and you love to learn new things.\nYour personal goal
+      is: You research about math.\nTo give my best complete final answer to the task
+      respond using the exact following format:\n\nThought: I now can give a great
+      answer\nFinal Answer: Your final answer must be the great and the most complete
+      as possible, it must be outcome described.\n\nI MUST use these formats, my job
+      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Research a topic
+      to teach a kid aged 6 about math.\n\nThis is the expected criteria for your
+      final answer: A topic, explanation, angle, and examples.\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:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '947'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BLceqFO97kLaTEPUSKGHkGlckpxLe\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744493188,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: \\n\\n**Topic:** Introduction to Addition\\n\\n**Explanation:**  \\nAddition
+      is a fundamental concept in math that means putting together two or more numbers
+      to find out how many there are in total. When we add, we combine quantities
+      to see the total amount we have. The symbol for addition is \\\"+\\\". \\n\\nLet's
+      break it down so it's easy to understand. If you have a small group of apples
+      and then you get more apples, to find out how many apples you have altogether,
+      you add them up! \\n\\n**Angle:**  \\nTo teach this concept to a 6-year-old,
+      we can use tangible objects they can relate to, such as fruits, toys, or stickers.
+      Kids learn best through play and visual representation, so using real-life examples
+      will make the concept of addition exciting and engaging!\\n\\n**Examples:**
+      \ \\n1. **Using Fruits:** \\n   - Start with 2 apples. \\n\\n     \U0001F34F\U0001F34F
+      (2 apples)\\n\\n   - Then, you receive 3 more apples. \\n\\n     \U0001F34F\U0001F34F\U0001F34F
+      (3 apples)\\n\\n   - To find out how many apples you have now, we add them together:
+      \\n\\n     2 + 3 = 5 \\n\\n   - Show them the total by counting all the apples
+      together: \\n\\n     \U0001F34F\U0001F34F\U0001F34F\U0001F34F\U0001F34F (5 apples)\\n\\n2.
+      **Using Toys:** \\n   - Let\u2019s say there are 4 toy cars. \\n\\n     \U0001F697\U0001F697\U0001F697\U0001F697
+      (4 toy cars)\\n\\n   - If you get 2 more toy cars. \\n\\n     \U0001F697\U0001F697
+      (2 toy cars)\\n\\n   - How many do we have in total? \\n\\n     4 + 2 = 6 \\n\\n
+      \  - Count them all together: \\n\\n     \U0001F697\U0001F697\U0001F697\U0001F697\U0001F697\U0001F697
+      (6 toy cars)\\n\\n3. **Using Stickers:**  \\n   - You have 5 stickers. \\n\\n
+      \    \U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F (5 stickers)\\n\\n   -
+      Your friend gives you 4 more stickers. \\n\\n     \U0001F31F\U0001F31F\U0001F31F\U0001F31F
+      (4 stickers)\\n\\n   - Now, let\u2019s see how many stickers you have in total:
+      \\n\\n     5 + 4 = 9 \\n\\n   - Count them together: \\n\\n     \U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F
+      (9 stickers)\\n\\n**Conclusion:**  \\nTry to make addition fun! Use snacks or
+      play time to practice addition. Ask questions during snack time, such as \u201CIf
+      you eat one of your 5 cookies, how many will you have left?\u201D This approach
+      makes learning relatable and enjoyable, enhancing their understanding of math
+      in everyday situations. Happy adding!\",\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 182,\n    \"completion_tokens\":
+      561,\n    \"total_tokens\": 743,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_44added55e\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92f5cd5a19257e0f-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 12 Apr 2025 21:26:36 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=RJADJOyAKqFS8232yM1dbM71E3ODRyiAty_s9rGvM0Y-1744493196-1.0.1.1-f4yxtdxM2DD78r7TOvv1J75SF6jkKDecDiDNH3cGysXRR3R.QycZfAzjKzWFkncqaQY4jeqGFYZlVR06qIdq2Gw178QxYpOC6MrJT1eqduw;
+        path=/; expires=Sat, 12-Apr-25 21:56:36 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=l0OvqELD24_KHHDhiAwih_bsqFrop1327mHak9Y_Ovk-1744493196966-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '8640'
+      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:
+      - '149999797'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_dda2c2217b856a9012403aeb7378a9e2
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cli/test_constants.py

@@ -0,0 +1,23 @@
+import pytest
+
+from crewai.cli.constants import ENV_VARS, MODELS, PROVIDERS
+
+
+def test_huggingface_in_providers():
+    """Test that Huggingface is in the PROVIDERS list."""
+    assert "huggingface" in PROVIDERS
+
+
+def test_huggingface_env_vars():
+    """Test that Huggingface environment variables are properly configured."""
+    assert "huggingface" in ENV_VARS
+    assert any(
+        detail.get("key_name") == "HF_TOKEN"
+        for detail in ENV_VARS["huggingface"]
+    )
+
+
+def test_huggingface_models():
+    """Test that Huggingface models are properly configured."""
+    assert "huggingface" in MODELS
+    assert len(MODELS["huggingface"]) > 0

tests/config/agents.yaml

@@ -8,6 +8,7 @@ researcher:
     developments in {topic}. Known for your ability to find the most relevant
     information and present it in a clear and concise manner.
   verbose: true
+  function_calling_llm: "local_llm"
 
 reporting_analyst:
   role: >
@@ -18,4 +19,5 @@ reporting_analyst:
     You're a meticulous analyst with a keen eye for detail. You're known for
     your ability to turn complex data into clear and concise reports, making
     it easy for others to understand and act on the information you provide.
-  verbose: true
+  verbose: true
+  function_calling_llm: "online_llm"

tests/crew_test.py

@@ -3,6 +3,7 @@
 import hashlib
 import json
 import os
+import tempfile
 from concurrent.futures import Future
 from unittest import mock
 from unittest.mock import MagicMock, patch
@@ -19,6 +20,8 @@ from crewai.crews.crew_output import CrewOutput
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.llm import LLM
 from crewai.memory.contextual.contextual_memory import ContextualMemory
+from crewai.memory.long_term.long_term_memory import LongTermMemory
+from crewai.memory.short_term.short_term_memory import ShortTermMemory
 from crewai.process import Process
 from crewai.task import Task
 from crewai.tasks.conditional_task import ConditionalTask
@@ -2405,6 +2408,136 @@ def test_using_contextual_memory():
         contextual_mem.assert_called_once()
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_using_contextual_memory_with_long_term_memory():
+    from unittest.mock import patch
+
+    math_researcher = Agent(
+        role="Researcher",
+        goal="You research about math.",
+        backstory="You're an expert in research and you love to learn new things.",
+        allow_delegation=False,
+    )
+
+    task1 = Task(
+        description="Research a topic to teach a kid aged 6 about math.",
+        expected_output="A topic, explanation, angle, and examples.",
+        agent=math_researcher,
+    )
+
+    crew = Crew(
+        agents=[math_researcher],
+        tasks=[task1],
+        long_term_memory=LongTermMemory(),
+    )
+
+    with patch.object(ContextualMemory, "build_context_for_task") as contextual_mem:
+        crew.kickoff()
+        contextual_mem.assert_called_once()
+        assert crew.memory is False
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_warning_long_term_memory_without_entity_memory():
+    from unittest.mock import patch
+
+    math_researcher = Agent(
+        role="Researcher",
+        goal="You research about math.",
+        backstory="You're an expert in research and you love to learn new things.",
+        allow_delegation=False,
+    )
+
+    task1 = Task(
+        description="Research a topic to teach a kid aged 6 about math.",
+        expected_output="A topic, explanation, angle, and examples.",
+        agent=math_researcher,
+    )
+
+    crew = Crew(
+        agents=[math_researcher],
+        tasks=[task1],
+        long_term_memory=LongTermMemory(),
+    )
+
+    with (
+        patch("crewai.utilities.printer.Printer.print") as mock_print,
+        patch(
+            "crewai.memory.long_term.long_term_memory.LongTermMemory.save"
+        ) as save_memory,
+    ):
+        crew.kickoff()
+        mock_print.assert_called_with(
+            content="Long term memory is enabled, but entity memory is not enabled. Please configure entity memory or set memory=True to automatically enable it.",
+            color="bold_yellow",
+        )
+        save_memory.assert_not_called()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_long_term_memory_with_memory_flag():
+    from unittest.mock import patch
+
+    math_researcher = Agent(
+        role="Researcher",
+        goal="You research about math.",
+        backstory="You're an expert in research and you love to learn new things.",
+        allow_delegation=False,
+    )
+
+    task1 = Task(
+        description="Research a topic to teach a kid aged 6 about math.",
+        expected_output="A topic, explanation, angle, and examples.",
+        agent=math_researcher,
+    )
+
+    crew = Crew(
+        agents=[math_researcher],
+        tasks=[task1],
+        memory=True,
+        long_term_memory=LongTermMemory(),
+    )
+
+    with (
+        patch("crewai.utilities.printer.Printer.print") as mock_print,
+        patch(
+            "crewai.memory.long_term.long_term_memory.LongTermMemory.save"
+        ) as save_memory,
+    ):
+        crew.kickoff()
+        mock_print.assert_not_called()
+        save_memory.assert_called_once()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_using_contextual_memory_with_short_term_memory():
+    from unittest.mock import patch
+
+    math_researcher = Agent(
+        role="Researcher",
+        goal="You research about math.",
+        backstory="You're an expert in research and you love to learn new things.",
+        allow_delegation=False,
+    )
+
+    task1 = Task(
+        description="Research a topic to teach a kid aged 6 about math.",
+        expected_output="A topic, explanation, angle, and examples.",
+        agent=math_researcher,
+    )
+
+    crew = Crew(
+        agents=[math_researcher],
+        tasks=[task1],
+        short_term_memory=ShortTermMemory(),
+    )
+
+    with patch.object(ContextualMemory, "build_context_for_task") as contextual_mem:
+        crew.kickoff()
+        contextual_mem.assert_called_once()
+        assert crew.memory is False
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_disabled_memory_using_contextual_memory():
     from unittest.mock import patch
@@ -3936,11 +4069,17 @@ def test_crew_guardrail_feedback_in_context():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_before_kickoff_callback():
-    from crewai.project import CrewBase, agent, before_kickoff, task
+    from crewai.project import CrewBase
 
     @CrewBase
     class TestCrewClass:
-        from crewai.project import crew
+        from typing import List
+
+        from crewai.agents.agent_builder.base_agent import BaseAgent
+        from crewai.project import CrewBase, agent, before_kickoff, crew, task
+
+        agents: List[BaseAgent]
+        tasks: List[Task]
 
         agents_config = None
         tasks_config = None
@@ -4116,6 +4255,54 @@ def test_crew_kickoff_for_each_works_with_manager_agent_copy():
     assert crew_copy.manager_agent.id != crew.manager_agent.id
     assert crew_copy.manager_agent.role == crew.manager_agent.role
     assert crew_copy.manager_agent.goal == crew.manager_agent.goal
-    assert crew_copy.manager_agent.backstory == crew.manager_agent.backstory
-    assert isinstance(crew_copy.manager_agent.agent_executor, CrewAgentExecutor)
-    assert isinstance(crew_copy.manager_agent.cache_handler, CacheHandler)
+
+def test_crew_copy_with_memory():
+    """Test that copying a crew with memory enabled does not raise validation errors and copies memory correctly."""
+    agent = Agent(role="Test Agent", goal="Test Goal", backstory="Test Backstory")
+    task = Task(description="Test Task", expected_output="Test Output", agent=agent)
+    crew = Crew(agents=[agent], tasks=[task], memory=True)
+
+    original_short_term_id = id(crew._short_term_memory) if crew._short_term_memory else None
+    original_long_term_id = id(crew._long_term_memory) if crew._long_term_memory else None
+    original_entity_id = id(crew._entity_memory) if crew._entity_memory else None
+    original_external_id = id(crew._external_memory) if crew._external_memory else None
+    original_user_id = id(crew._user_memory) if crew._user_memory else None
+
+
+    try:
+        crew_copy = crew.copy()
+
+        assert hasattr(crew_copy, "_short_term_memory"), "Copied crew should have _short_term_memory"
+        assert crew_copy._short_term_memory is not None, "Copied _short_term_memory should not be None"
+        assert id(crew_copy._short_term_memory) != original_short_term_id, "Copied _short_term_memory should be a new object"
+
+        assert hasattr(crew_copy, "_long_term_memory"), "Copied crew should have _long_term_memory"
+        assert crew_copy._long_term_memory is not None, "Copied _long_term_memory should not be None"
+        assert id(crew_copy._long_term_memory) != original_long_term_id, "Copied _long_term_memory should be a new object"
+
+        assert hasattr(crew_copy, "_entity_memory"), "Copied crew should have _entity_memory"
+        assert crew_copy._entity_memory is not None, "Copied _entity_memory should not be None"
+        assert id(crew_copy._entity_memory) != original_entity_id, "Copied _entity_memory should be a new object"
+
+        if original_external_id:
+             assert hasattr(crew_copy, "_external_memory"), "Copied crew should have _external_memory"
+             assert crew_copy._external_memory is not None, "Copied _external_memory should not be None"
+             assert id(crew_copy._external_memory) != original_external_id, "Copied _external_memory should be a new object"
+        else:
+             assert not hasattr(crew_copy, "_external_memory") or crew_copy._external_memory is None, "Copied _external_memory should be None if not originally present"
+
+        if original_user_id:
+             assert hasattr(crew_copy, "_user_memory"), "Copied crew should have _user_memory"
+             assert crew_copy._user_memory is not None, "Copied _user_memory should not be None"
+             assert id(crew_copy._user_memory) != original_user_id, "Copied _user_memory should be a new object"
+        else:
+             assert not hasattr(crew_copy, "_user_memory") or crew_copy._user_memory is None, "Copied _user_memory should be None if not originally present"
+
+
+    except pydantic_core.ValidationError as e:
+         if "Input should be an instance of" in str(e) and ("Memory" in str(e)):
+              pytest.fail(f"Copying with memory raised Pydantic ValidationError, likely due to incorrect memory copy: {e}")
+         else:
+              raise e # Re-raise other validation errors
+    except Exception as e:
+        pytest.fail(f"Copying crew raised an unexpected exception: {e}")

tests/imports_test.py

@@ -0,0 +1,15 @@
+"""Test that all public API classes are properly importable."""
+
+
+def test_task_output_import():
+    """Test that TaskOutput can be imported from crewai."""
+    from crewai import TaskOutput
+    
+    assert TaskOutput is not None
+    
+    
+def test_crew_output_import():
+    """Test that CrewOutput can be imported from crewai."""
+    from crewai import CrewOutput
+    
+    assert CrewOutput is not None

tests/llm_test.py

@@ -395,51 +395,3 @@ def test_deepseek_r1_with_open_router():
     result = llm.call("What is the capital of France?")
     assert isinstance(result, str)
     assert "Paris" in result
-
-
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_tool_execution_error_event():
-    llm = LLM(model="gpt-4o-mini")
-
-    def failing_tool(param: str) -> str:
-        """This tool always fails."""
-        raise Exception("Tool execution failed!")
-
-    tool_schema = {
-        "type": "function",
-        "function": {
-            "name": "failing_tool",
-            "description": "This tool always fails.",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "param": {"type": "string", "description": "A test parameter"}
-                },
-                "required": ["param"],
-            },
-        },
-    }
-
-    received_events = []
-
-    @crewai_event_bus.on(ToolExecutionErrorEvent)
-    def event_handler(source, event):
-        received_events.append(event)
-
-    available_functions = {"failing_tool": failing_tool}
-
-    messages = [{"role": "user", "content": "Use the failing tool"}]
-
-    llm.call(
-        messages,
-        tools=[tool_schema],
-        available_functions=available_functions,
-    )
-
-    assert len(received_events) == 1
-    event = received_events[0]
-    assert isinstance(event, ToolExecutionErrorEvent)
-    assert event.tool_name == "failing_tool"
-    assert event.tool_args == {"param": "test"}
-    assert event.tool_class == failing_tool
-    assert "Tool execution failed!" in event.error

tests/memory/external/cassettes/test_crew_external_memory_save_using_crew_without_memory_flag[save].yaml

@@ -0,0 +1,182 @@
+interactions:
+- request:
+    body: !!binary |
+      Ct8MCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkStgwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKcCAoQfm0pqVSMD2d8x7Z0oecKIRIIgWppMg8y3GoqDENyZXcgQ3JlYXRlZDABORAN
+      KtAWrDUYQagXMtAWrDUYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIDA3YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhk
+      MjgzMmM2SjEKB2NyZXdfaWQSJgokNGY1NjNkN2MtYmYyOC00ZWM2LTgzNzQtMDZlMjZiYzA1NWU0
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
+      X2ZpbmdlcnByaW50EiYKJGU4MGY4MDFmLWViZmQtNDlkOS1iNTEwLTM0NmVjN2VlNzAzZko7Chtj
+      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xMlQxNzoyNzoyNC42NTU4NzhK
+      0AIKC2NyZXdfYWdlbnRzEsACCr0CW3sia2V5IjogIjAyZGYxM2UzNjcxMmFiZjUxZDIzOGZlZWJh
+      YjFjYTI2IiwgImlkIjogIjg5MjdlNzQ1LWNkNWQtNDJkMy1hMjA2LTEyYTUxOWRlMDY1OCIsICJy
+      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAyNSwgIm1h
+      eF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8t
+      bWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlv
+      bj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/wEK
+      CmNyZXdfdGFza3MS8AEK7QFbeyJrZXkiOiAiN2I0MmRmM2MzYzc0YzIxYzg5NDgwZTBjMDcwNTM4
+      NWYiLCAiaWQiOiAiNDM0MDgzNDYtMjA5OC00M2I1LWE0NWUtMmU2MWY4ZmYxZTliIiwgImFzeW5j
+      X2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6
+      ICJSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6ICIwMmRmMTNlMzY3MTJhYmY1MWQyMzhmZWViYWIx
+      Y2EyNiIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChDv1iM8ejIY7tezTF4KBssA
+      Eghn2bJnw2f60SoMVGFzayBDcmVhdGVkMAE58LFA0BasNRhB4AdB0BasNRhKLgoIY3Jld19rZXkS
+      IgogMDdhNzE3NjhjYzRjOTNlYWIzYjMxZTNjOGQyODMyYzZKMQoHY3Jld19pZBImCiQ0ZjU2M2Q3
+      Yy1iZjI4LTRlYzYtODM3NC0wNmUyNmJjMDU1ZTRKLgoIdGFza19rZXkSIgogN2I0MmRmM2MzYzc0
+      YzIxYzg5NDgwZTBjMDcwNTM4NWZKMQoHdGFza19pZBImCiQ0MzQwODM0Ni0yMDk4LTQzYjUtYTQ1
+      ZS0yZTYxZjhmZjFlOWJKOgoQY3Jld19maW5nZXJwcmludBImCiRlODBmODAxZi1lYmZkLTQ5ZDkt
+      YjUxMC0zNDZlYzdlZTcwM2ZKOgoQdGFza19maW5nZXJwcmludBImCiQ2YjgzODVkYS0yYWJjLTRm
+      NWEtOTk3NC0xNjhiMzVhNDBlOTlKOwobdGFza19maW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIw
+      MjUtMDQtMTJUMTc6Mjc6MjQuNjU1ODQ4SjsKEWFnZW50X2ZpbmdlcnByaW50EiYKJDIyNTI4NDRl
+      LWNlMTYtNDYyZi04NDI4LTYwYzZmMWYyNGE3N3oCGAGFAQABAAA=
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1634'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.31.1
+    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:
+      - Sat, 12 Apr 2025 20:27:26 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You are
+      a researcher at a leading tech think tank.\nYour personal goal is: Search relevant
+      data and provide results\nTo give my best complete final answer to the task
+      respond using the exact following format:\n\nThought: I now can give a great
+      answer\nFinal Answer: Your final answer must be the great and the most complete
+      as possible, it must be outcome described.\n\nI MUST use these formats, my job
+      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Perform a search
+      on specific topics.\n\nThis is the expected criteria for your final answer:
+      A list of relevant URLs based on the search query.\nyou MUST return the actual
+      complete content as the final answer, not a summary.\n\n# Useful context: \nExternal
+      memories:\n\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:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '989'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=nSje5Zn_Lk69BDG85XIauC2hrZjGl0pR2sel9__KWGw-1744489610-1.0.1.1-CPlAgcgTAE30uWrbi_2wiCWrbRDRWiaa.YuQMgST42DLDVg_wdNlJMDQT3Lsqk.g.BO68A66TTirWA0blQaQw.9xdBbPwKO609_ftjdwi5U;
+        _cfuvid=XLC52GLAWCOeWn2vI379CnSGKjPa7f.qr2vSAQ_R66M-1744489610542-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BLbjg0OfADWdrLsZxrjKHEeVVbWle\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744489644,\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: Here is a list of relevant URLs based on the specified search query:
+      \ \\n\\n1. https://www.forbes.com/technology/  \\n2. https://www.sciencedirect.com/
+      \ \\n3. https://www.techcrunch.com/  \\n4. https://www.wired.com/  \\n5. https://www.researchgate.net/
+      \ \\n6. https://www.springer.com/  \\n7. https://www.jstor.org/  \\n8. https://www.statista.com/
+      \ \\n9. https://www.pwc.com/gx/en/services/consulting/technology.html  \\n10.
+      https://www.gartner.com/en/information-technology  \\n\\nThese URLs provide
+      access to a wealth of information on various technology-related topics, including
+      articles, research papers, and analytics.\",\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 185,\n    \"completion_tokens\":
+      169,\n    \"total_tokens\": 354,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_80cf447eee\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92f576d83a447e05-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 12 Apr 2025 20:27:27 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '2273'
+      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:
+      - '149999788'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_38f6879956c29e6c61c844d1906fa2e8
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/memory/external/cassettes/test_crew_external_memory_save_using_crew_without_memory_flag[search].yaml

@@ -0,0 +1,190 @@
+interactions:
+- request:
+    body: !!binary |
+      Ct8MCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkStgwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKcCAoQjin/Su47zAwLq3Hv6yv8GhIImRMfAPs+FOMqDENyZXcgQ3JlYXRlZDABOYCY
+      xbgUrDUYQVie07gUrDUYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIDA3YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhk
+      MjgzMmM2SjEKB2NyZXdfaWQSJgokY2UyMGFlNWYtZmMyNy00YWJhLWExYWMtNzUwY2ZhZmMwMTE4
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
+      X2ZpbmdlcnByaW50EiYKJDQ4NGFmZDhjLTczMmEtNGM1Ni1hZjk2LTU2MzkwMjNmYjhjOUo7Chtj
+      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xMlQxNzoyNzoxNS42NzMyMjNK
+      0AIKC2NyZXdfYWdlbnRzEsACCr0CW3sia2V5IjogIjAyZGYxM2UzNjcxMmFiZjUxZDIzOGZlZWJh
+      YjFjYTI2IiwgImlkIjogImYyYjZkYTU1LTNiMGItNDZiNy05Mzk5LWE5NDJmYjQ4YzU2OSIsICJy
+      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAyNSwgIm1h
+      eF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8t
+      bWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlv
+      bj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/wEK
+      CmNyZXdfdGFza3MS8AEK7QFbeyJrZXkiOiAiN2I0MmRmM2MzYzc0YzIxYzg5NDgwZTBjMDcwNTM4
+      NWYiLCAiaWQiOiAiYmE1MjFjNDgtYzcwNS00MDRlLWE5MDktMjkwZGM0NTlkOThkIiwgImFzeW5j
+      X2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6
+      ICJSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6ICIwMmRmMTNlMzY3MTJhYmY1MWQyMzhmZWViYWIx
+      Y2EyNiIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChAmCOpHN6fX3l0shQvTLjrB
+      EgjLTyt4A1p7wyoMVGFzayBDcmVhdGVkMAE5gN7juBSsNRhBmFfkuBSsNRhKLgoIY3Jld19rZXkS
+      IgogMDdhNzE3NjhjYzRjOTNlYWIzYjMxZTNjOGQyODMyYzZKMQoHY3Jld19pZBImCiRjZTIwYWU1
+      Zi1mYzI3LTRhYmEtYTFhYy03NTBjZmFmYzAxMThKLgoIdGFza19rZXkSIgogN2I0MmRmM2MzYzc0
+      YzIxYzg5NDgwZTBjMDcwNTM4NWZKMQoHdGFza19pZBImCiRiYTUyMWM0OC1jNzA1LTQwNGUtYTkw
+      OS0yOTBkYzQ1OWQ5OGRKOgoQY3Jld19maW5nZXJwcmludBImCiQ0ODRhZmQ4Yy03MzJhLTRjNTYt
+      YWY5Ni01NjM5MDIzZmI4YzlKOgoQdGFza19maW5nZXJwcmludBImCiRhMDcyNjgwNC05ZjIwLTQw
+      ODgtYWFmOC1iNzhkYTUyNmM3NjlKOwobdGFza19maW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIw
+      MjUtMDQtMTJUMTc6Mjc6MTUuNjczMTgxSjsKEWFnZW50X2ZpbmdlcnByaW50EiYKJDNiZDE2MmNm
+      LWNmMWQtNGUwZi04ZmIzLTk3MDljMDkyNmM4ZHoCGAGFAQABAAA=
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1634'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.31.1
+    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:
+      - Sat, 12 Apr 2025 20:27:16 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You are
+      a researcher at a leading tech think tank.\nYour personal goal is: Search relevant
+      data and provide results\nTo give my best complete final answer to the task
+      respond using the exact following format:\n\nThought: I now can give a great
+      answer\nFinal Answer: Your final answer must be the great and the most complete
+      as possible, it must be outcome described.\n\nI MUST use these formats, my job
+      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Perform a search
+      on specific topics.\n\nThis is the expected criteria for your final answer:
+      A list of relevant URLs based on the search query.\nyou MUST return the actual
+      complete content as the final answer, not a summary.\n\n# Useful context: \nExternal
+      memories:\n\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:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '989'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=nSje5Zn_Lk69BDG85XIauC2hrZjGl0pR2sel9__KWGw-1744489610-1.0.1.1-CPlAgcgTAE30uWrbi_2wiCWrbRDRWiaa.YuQMgST42DLDVg_wdNlJMDQT3Lsqk.g.BO68A66TTirWA0blQaQw.9xdBbPwKO609_ftjdwi5U;
+        _cfuvid=XLC52GLAWCOeWn2vI379CnSGKjPa7f.qr2vSAQ_R66M-1744489610542-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BLbjXyMvmR8ctf0sqhp7F1ePskveM\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744489635,\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: Here is a list of relevant URLs based on the search query:\\n\\n1. **Artificial
+      Intelligence in Healthcare**\\n   - https://www.healthit.gov/topic/scientific-initiatives/ai-healthcare\\n
+      \  - https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7317789/\\n   - https://www.forbes.com/sites/bernardmarr/2021/10/18/the-top-5-ways-ai-is-being-used-in-healthcare/?sh=3edf5df51c9c\\n\\n2.
+      **Blockchain Technology in Supply Chain Management**\\n   - https://www.ibm.com/blockchain/supply-chain\\n
+      \  - https://www.gartner.com/en/newsroom/press-releases/2021-06-23-gartner-says-three-use-cases-for-blockchain-in-supply-chain-are-scaling\\n
+      \  - https://www2.deloitte.com/us/en/insights/industry/retail-distribution/blockchain-in-supply-chain.html\\n\\n3.
+      **Renewable Energy Innovations**\\n   - https://www.irena.org/publications/2020/Sep/Renewable-Power-Generation-Costs-in-2020\\n
+      \  - https://www.nrel.gov/docs/fy20osti/77021.pdf\\n   - https://www.cnbc.com/2021/11/03/renewable-energy-could-get-its-first-taste-of-markets-in-2021.html\\n\\n4.
+      **7G Technology Developments**\\n   - https://www.sciencedirect.com/science/article/pii/S1389128619308189\\n
+      \  - https://www.forbes.com/sites/bernardmarr/2021/11/01/what-is-7g-technology-a-beginners-guide-to-the-future-of-mobile-communications/?sh=51b8a7e1464a\\n
+      \  - https://www.ericsson.com/en/reports-and-research/reports/7g-networks-a-powerful-future-for-connected-society\\n\\n5.
+      **Impact of Quantum Computing on Cybersecurity**\\n   - https://www.ibm.com/blogs/research/2021/09/quantum-computing-cybersecurity/\\n
+      \  - https://www.sciencedirect.com/science/article/pii/S0167739X21000072\\n
+      \  - https://www.techrepublic.com/article/how-quantum-computing-will-change-cybersecurity/\\n\\nThese
+      URLs should provide comprehensive information on the topics searched, providing
+      valuable insights and data for your research needs.\",\n        \"refusal\":
+      null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 185,\n    \"completion_tokens\":
+      534,\n    \"total_tokens\": 719,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_80cf447eee\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92f576a01d3b7e05-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 12 Apr 2025 20:27:24 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '8805'
+      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:
+      - '149999788'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_7c2d313d0b5997e903553a782b2afa25
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/memory/external/external_memory_test.py

@@ -0,0 +1,223 @@
+from unittest.mock import MagicMock, patch
+
+import pytest
+from mem0.memory.main import Memory
+
+from crewai.agent import Agent
+from crewai.crew import Crew, Process
+from crewai.memory.external.external_memory import ExternalMemory
+from crewai.memory.external.external_memory_item import ExternalMemoryItem
+from crewai.memory.storage.interface import Storage
+from crewai.task import Task
+
+
+@pytest.fixture
+def mock_mem0_memory():
+    mock_memory = MagicMock(spec=Memory)
+    return mock_memory
+
+
+@pytest.fixture
+def patch_configure_mem0(mock_mem0_memory):
+    with patch(
+        "crewai.memory.external.external_memory.ExternalMemory._configure_mem0",
+        return_value=mock_mem0_memory,
+    ) as mocked:
+        yield mocked
+
+
+@pytest.fixture
+def external_memory_with_mocked_config(patch_configure_mem0):
+    embedder_config = {"provider": "mem0"}
+    external_memory = ExternalMemory(embedder_config=embedder_config)
+    return external_memory
+
+
+@pytest.fixture
+def crew_with_external_memory(external_memory_with_mocked_config, patch_configure_mem0):
+    agent = Agent(
+        role="Researcher",
+        goal="Search relevant data and provide results",
+        backstory="You are a researcher at a leading tech think tank.",
+        tools=[],
+        verbose=True,
+    )
+
+    task = Task(
+        description="Perform a search on specific topics.",
+        expected_output="A list of relevant URLs based on the search query.",
+        agent=agent,
+    )
+
+    crew = Crew(
+        agents=[agent],
+        tasks=[task],
+        verbose=True,
+        process=Process.sequential,
+        memory=True,
+        external_memory=external_memory_with_mocked_config,
+    )
+
+    return crew
+
+
+@pytest.fixture
+def crew_with_external_memory_without_memory_flag(
+    external_memory_with_mocked_config, patch_configure_mem0
+):
+    agent = Agent(
+        role="Researcher",
+        goal="Search relevant data and provide results",
+        backstory="You are a researcher at a leading tech think tank.",
+        tools=[],
+        verbose=True,
+    )
+
+    task = Task(
+        description="Perform a search on specific topics.",
+        expected_output="A list of relevant URLs based on the search query.",
+        agent=agent,
+    )
+
+    crew = Crew(
+        agents=[agent],
+        tasks=[task],
+        verbose=True,
+        process=Process.sequential,
+        external_memory=external_memory_with_mocked_config,
+    )
+
+    return crew
+
+
+def test_external_memory_initialization(external_memory_with_mocked_config):
+    assert external_memory_with_mocked_config is not None
+    assert isinstance(external_memory_with_mocked_config, ExternalMemory)
+
+
+def test_external_memory_save(external_memory_with_mocked_config):
+    memory_item = ExternalMemoryItem(
+        value="test value", metadata={"task": "test_task"}, agent="test_agent"
+    )
+
+    with patch.object(ExternalMemory, "save") as mock_save:
+        external_memory_with_mocked_config.save(
+            value=memory_item.value,
+            metadata=memory_item.metadata,
+            agent=memory_item.agent,
+        )
+
+        mock_save.assert_called_once_with(
+            value=memory_item.value,
+            metadata=memory_item.metadata,
+            agent=memory_item.agent,
+        )
+
+
+def test_external_memory_reset(external_memory_with_mocked_config):
+    with patch(
+        "crewai.memory.external.external_memory.ExternalMemory.reset"
+    ) as mock_reset:
+        external_memory_with_mocked_config.reset()
+        mock_reset.assert_called_once()
+
+
+def test_external_memory_supported_storages():
+    supported_storages = ExternalMemory.external_supported_storages()
+    assert "mem0" in supported_storages
+    assert callable(supported_storages["mem0"])
+
+
+def test_external_memory_create_storage_invalid_provider():
+    embedder_config = {"provider": "invalid_provider", "config": {}}
+
+    with pytest.raises(ValueError, match="Provider invalid_provider not supported"):
+        ExternalMemory.create_storage(None, embedder_config)
+
+
+def test_external_memory_create_storage_missing_provider():
+    embedder_config = {"config": {}}
+
+    with pytest.raises(
+        ValueError, match="embedder_config must include a 'provider' key"
+    ):
+        ExternalMemory.create_storage(None, embedder_config)
+
+
+def test_external_memory_create_storage_missing_config():
+    with pytest.raises(ValueError, match="embedder_config is required"):
+        ExternalMemory.create_storage(None, None)
+
+
+def test_crew_with_external_memory_initialization(crew_with_external_memory):
+    assert crew_with_external_memory._external_memory is not None
+    assert isinstance(crew_with_external_memory._external_memory, ExternalMemory)
+    assert crew_with_external_memory._external_memory.crew == crew_with_external_memory
+
+
+@pytest.mark.parametrize("mem_type", ["external", "all"])
+def test_crew_external_memory_reset(mem_type, crew_with_external_memory):
+    with patch(
+        "crewai.memory.external.external_memory.ExternalMemory.reset"
+    ) as mock_reset:
+        crew_with_external_memory.reset_memories(mem_type)
+        mock_reset.assert_called_once()
+
+
+@pytest.mark.parametrize("mem_method", ["search", "save"])
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_external_memory_save_with_memory_flag(
+    mem_method, crew_with_external_memory
+):
+    with patch(
+        f"crewai.memory.external.external_memory.ExternalMemory.{mem_method}"
+    ) as mock_method:
+        crew_with_external_memory.kickoff()
+        assert mock_method.call_count > 0
+
+
+@pytest.mark.parametrize("mem_method", ["search", "save"])
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_external_memory_save_using_crew_without_memory_flag(
+    mem_method, crew_with_external_memory_without_memory_flag
+):
+    with patch(
+        f"crewai.memory.external.external_memory.ExternalMemory.{mem_method}"
+    ) as mock_method:
+        crew_with_external_memory_without_memory_flag.kickoff()
+        assert mock_method.call_count > 0
+
+
+def test_external_memory_custom_storage(crew_with_external_memory):
+    class CustomStorage(Storage):
+        def __init__(self):
+            self.memories = []
+
+        def save(self, value, metadata=None, agent=None):
+            self.memories.append({"value": value, "metadata": metadata, "agent": agent})
+
+        def search(self, query, limit=10, score_threshold=0.5):
+            return self.memories
+
+        def reset(self):
+            self.memories = []
+
+    custom_storage = CustomStorage()
+    external_memory = ExternalMemory(storage=custom_storage)
+
+    # by ensuring the crew is set, we can test that the storage is used
+    external_memory.set_crew(crew_with_external_memory)
+
+    test_value = "test value"
+    test_metadata = {"source": "test"}
+    test_agent = "test_agent"
+    external_memory.save(value=test_value, metadata=test_metadata, agent=test_agent)
+
+    results = external_memory.search("test")
+    assert len(results) == 1
+    assert results[0]["value"] == test_value
+    assert results[0]["metadata"] == test_metadata | {"agent": test_agent}
+
+    external_memory.reset()
+    results = external_memory.search("test")
+    assert len(results) == 0

tests/project_test.py

@@ -1,8 +1,20 @@
+from typing import List
+
 import pytest
 
 from crewai.agent import Agent
+from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.crew import Crew
-from crewai.project import CrewBase, after_kickoff, agent, before_kickoff, crew, task
+from crewai.llm import LLM
+from crewai.project import (
+    CrewBase,
+    after_kickoff,
+    agent,
+    before_kickoff,
+    crew,
+    llm,
+    task,
+)
 from crewai.task import Task
 
 
@@ -31,21 +43,32 @@ class InternalCrew:
     agents_config = "config/agents.yaml"
     tasks_config = "config/tasks.yaml"
 
+    agents: List[BaseAgent]
+    tasks: List[Task]
+
+    @llm
+    def local_llm(self):
+        return LLM(
+            model="openai/model_name",
+            api_key="None",
+            base_url="http://xxx.xxx.xxx.xxx:8000/v1",
+        )
+
     @agent
     def researcher(self):
-        return Agent(config=self.agents_config["researcher"])
+        return Agent(config=self.agents_config["researcher"])  # type: ignore[index]
 
     @agent
     def reporting_analyst(self):
-        return Agent(config=self.agents_config["reporting_analyst"])
+        return Agent(config=self.agents_config["reporting_analyst"])  # type: ignore[index]
 
     @task
     def research_task(self):
-        return Task(config=self.tasks_config["research_task"])
+        return Task(config=self.tasks_config["research_task"])  # type: ignore[index]
 
     @task
     def reporting_task(self):
-        return Task(config=self.tasks_config["reporting_task"])
+        return Task(config=self.tasks_config["reporting_task"])  # type: ignore[index]
 
     @before_kickoff
     def modify_inputs(self, inputs):
@@ -105,6 +128,20 @@ def test_task_name():
     ), "Custom task name is not being set as expected"
 
 
+def test_agent_function_calling_llm():
+    crew = InternalCrew()
+    llm = crew.local_llm()
+    obj_llm_agent = crew.researcher()
+    assert (
+        obj_llm_agent.function_calling_llm is llm
+    ), "agent's function_calling_llm is incorrect"
+
+    str_llm_agent = crew.reporting_analyst()
+    assert (
+        str_llm_agent.function_calling_llm.model == "online_llm"
+    ), "agent's function_calling_llm is incorrect"
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_before_kickoff_modification():
     crew = InternalCrew()
@@ -135,24 +172,27 @@ def test_before_kickoff_with_none_input():
 def test_multiple_before_after_kickoff():
     @CrewBase
     class MultipleHooksCrew:
+        agents: List[BaseAgent]
+        tasks: List[Task]
+
         agents_config = "config/agents.yaml"
         tasks_config = "config/tasks.yaml"
 
         @agent
         def researcher(self):
-            return Agent(config=self.agents_config["researcher"])
+            return Agent(config=self.agents_config["researcher"])  # type: ignore[index]
 
         @agent
         def reporting_analyst(self):
-            return Agent(config=self.agents_config["reporting_analyst"])
+            return Agent(config=self.agents_config["reporting_analyst"])  # type: ignore[index]
 
         @task
         def research_task(self):
-            return Task(config=self.tasks_config["research_task"])
+            return Task(config=self.tasks_config["research_task"])  # type: ignore[index]
 
         @task
         def reporting_task(self):
-            return Task(config=self.tasks_config["reporting_task"])
+            return Task(config=self.tasks_config["reporting_task"])  # type: ignore[index]
 
         @before_kickoff
         def first_before(self, inputs):

tests/storage/test_mem0_storage.py

@@ -29,41 +29,32 @@ def mem0_storage_with_mocked_config(mock_mem0_memory):
     """Fixture to create a Mem0Storage instance with mocked dependencies"""
 
     # Patch the Memory class to return our mock
-    with patch('mem0.memory.main.Memory.from_config', return_value=mock_mem0_memory):
+    with patch("mem0.memory.main.Memory.from_config", return_value=mock_mem0_memory) as mock_from_config:
         config = {
             "vector_store": {
                 "provider": "mock_vector_store",
-                "config": {
-                    "host": "localhost",
-                    "port": 6333
-                }
+                "config": {"host": "localhost", "port": 6333},
             },
             "llm": {
                 "provider": "mock_llm",
-                "config": {
-                    "api_key": "mock-api-key",
-                    "model": "mock-model"
-                }
+                "config": {"api_key": "mock-api-key", "model": "mock-model"},
             },
             "embedder": {
                 "provider": "mock_embedder",
-                "config": {
-                    "api_key": "mock-api-key",
-                    "model": "mock-model"
-                }
+                "config": {"api_key": "mock-api-key", "model": "mock-model"},
             },
             "graph_store": {
                 "provider": "mock_graph_store",
                 "config": {
                     "url": "mock-url",
                     "username": "mock-user",
-                    "password": "mock-password"
-                }
+                    "password": "mock-password",
+                },
             },
             "history_db_path": "/mock/path",
             "version": "test-version",
             "custom_fact_extraction_prompt": "mock prompt 1",
-            "custom_update_memory_prompt": "mock prompt 2"
+            "custom_update_memory_prompt": "mock prompt 2",
         }
 
         # Instantiate the class with memory_config
@@ -75,13 +66,15 @@ def mem0_storage_with_mocked_config(mock_mem0_memory):
         )
 
         mem0_storage = Mem0Storage(type="short_term", crew=crew)
-        return mem0_storage
+        return mem0_storage, mock_from_config, config
 
 
 def test_mem0_storage_initialization(mem0_storage_with_mocked_config, mock_mem0_memory):
     """Test that Mem0Storage initializes correctly with the mocked config"""
-    assert mem0_storage_with_mocked_config.memory_type == "short_term"
-    assert mem0_storage_with_mocked_config.memory is mock_mem0_memory
+    mem0_storage, mock_from_config, config = mem0_storage_with_mocked_config
+    assert mem0_storage.memory_type == "short_term"
+    assert mem0_storage.memory is mock_mem0_memory
+    mock_from_config.assert_called_once_with(config)
 
 
 @pytest.fixture
@@ -92,23 +85,73 @@ def mock_mem0_memory_client():
 
 
 @pytest.fixture
-def mem0_storage_with_memory_client(mock_mem0_memory_client):
+def mem0_storage_with_memory_client_using_config_from_crew(mock_mem0_memory_client):
     """Fixture to create a Mem0Storage instance with mocked dependencies"""
 
     # We need to patch the MemoryClient before it's instantiated
-    with patch.object(MemoryClient, '__new__', return_value=mock_mem0_memory_client):
-            crew = MockCrew(
-                memory_config={
-                    "provider": "mem0",
-                    "config": {"user_id": "test_user", "api_key": "ABCDEFGH", "org_id": "my_org_id", "project_id": "my_project_id"},
-                }
-            )
+    with patch.object(MemoryClient, "__new__", return_value=mock_mem0_memory_client):
+        crew = MockCrew(
+            memory_config={
+                "provider": "mem0",
+                "config": {
+                    "user_id": "test_user",
+                    "api_key": "ABCDEFGH",
+                    "org_id": "my_org_id",
+                    "project_id": "my_project_id",
+                },
+            }
+        )
 
-            mem0_storage = Mem0Storage(type="short_term", crew=crew)
-            return mem0_storage
+        mem0_storage = Mem0Storage(type="short_term", crew=crew)
+        return mem0_storage
 
 
-def test_mem0_storage_with_memory_client_initialization(mem0_storage_with_memory_client, mock_mem0_memory_client):
+@pytest.fixture
+def mem0_storage_with_memory_client_using_explictly_config(mock_mem0_memory_client):
+    """Fixture to create a Mem0Storage instance with mocked dependencies"""
+
+    # We need to patch the MemoryClient before it's instantiated
+    with patch.object(MemoryClient, "__new__", return_value=mock_mem0_memory_client):
+        crew = MockCrew(
+            memory_config={
+                "provider": "mem0",
+                "config": {
+                    "user_id": "test_user",
+                    "api_key": "ABCDEFGH",
+                    "org_id": "my_org_id",
+                    "project_id": "my_project_id",
+                },
+            }
+        )
+
+        new_config = {"provider": "mem0", "config": {"api_key": "new-api-key"}}
+
+        mem0_storage = Mem0Storage(type="short_term", crew=crew, config=new_config)
+        return mem0_storage
+
+
+def test_mem0_storage_with_memory_client_initialization(
+    mem0_storage_with_memory_client_using_config_from_crew, mock_mem0_memory_client
+):
     """Test Mem0Storage initialization with MemoryClient"""
-    assert mem0_storage_with_memory_client.memory_type == "short_term"
-    assert mem0_storage_with_memory_client.memory is mock_mem0_memory_client
+    assert (
+        mem0_storage_with_memory_client_using_config_from_crew.memory_type
+        == "short_term"
+    )
+    assert (
+        mem0_storage_with_memory_client_using_config_from_crew.memory
+        is mock_mem0_memory_client
+    )
+
+
+def test_mem0_storage_with_explict_config(
+    mem0_storage_with_memory_client_using_explictly_config,
+):
+    expected_config = {"provider": "mem0", "config": {"api_key": "new-api-key"}}
+    assert (
+        mem0_storage_with_memory_client_using_explictly_config.config == expected_config
+    )
+    assert (
+        mem0_storage_with_memory_client_using_explictly_config.memory_config
+        == expected_config
+    )

tests/telemetry/test_telemetry_disable.py

@@ -0,0 +1,30 @@
+import os
+from unittest.mock import patch
+
+import pytest
+
+from crewai.telemetry import Telemetry
+
+
+@pytest.mark.parametrize("env_var,value,expected_ready", [
+    ("OTEL_SDK_DISABLED", "true", False),
+    ("OTEL_SDK_DISABLED", "TRUE", False),
+    ("CREWAI_DISABLE_TELEMETRY", "true", False),
+    ("CREWAI_DISABLE_TELEMETRY", "TRUE", False),
+    ("OTEL_SDK_DISABLED", "false", True),
+    ("CREWAI_DISABLE_TELEMETRY", "false", True),
+])
+def test_telemetry_environment_variables(env_var, value, expected_ready):
+    """Test telemetry state with different environment variable configurations."""
+    with patch.dict(os.environ, {env_var: value}):
+        with patch("crewai.telemetry.telemetry.TracerProvider"):
+            telemetry = Telemetry()
+            assert telemetry.ready is expected_ready
+
+
+def test_telemetry_enabled_by_default():
+    """Test that telemetry is enabled by default."""
+    with patch.dict(os.environ, {}, clear=True):
+        with patch("crewai.telemetry.telemetry.TracerProvider"):
+            telemetry = Telemetry()
+            assert telemetry.ready is True

tests/test_lite_agent.py

@@ -4,8 +4,8 @@ from typing import cast
 import pytest
 from pydantic import BaseModel, Field
 
-from crewai import LLM
-from crewai.lite_agent import LiteAgent
+from crewai import LLM, Agent
+from crewai.lite_agent import LiteAgent, LiteAgentOutput
 from crewai.tools import BaseTool
 from crewai.utilities.events import crewai_event_bus
 from crewai.utilities.events.tool_usage_events import ToolUsageStartedEvent
@@ -63,12 +63,74 @@ class ResearchResult(BaseModel):
     sources: list[str] = Field(description="List of sources used")
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.parametrize("verbose", [True, False])
+def test_lite_agent_created_with_correct_parameters(monkeypatch, verbose):
+    """Test that LiteAgent is created with the correct parameters when Agent.kickoff() is called."""
+    # Create a test agent with specific parameters
+    llm = LLM(model="gpt-4o-mini")
+    custom_tools = [WebSearchTool(), CalculatorTool()]
+    max_iter = 10
+    max_execution_time = 300
+
+    agent = Agent(
+        role="Test Agent",
+        goal="Test Goal",
+        backstory="Test Backstory",
+        llm=llm,
+        tools=custom_tools,
+        max_iter=max_iter,
+        max_execution_time=max_execution_time,
+        verbose=verbose,
+    )
+
+    # Create a mock to capture the created LiteAgent
+    created_lite_agent = None
+    original_lite_agent = LiteAgent
+
+    # Define a mock LiteAgent class that captures its arguments
+    class MockLiteAgent(original_lite_agent):
+        def __init__(self, **kwargs):
+            nonlocal created_lite_agent
+            created_lite_agent = kwargs
+            super().__init__(**kwargs)
+
+    # Patch the LiteAgent class
+    monkeypatch.setattr("crewai.agent.LiteAgent", MockLiteAgent)
+
+    # Call kickoff to create the LiteAgent
+    agent.kickoff("Test query")
+
+    # Verify all parameters were passed correctly
+    assert created_lite_agent is not None
+    assert created_lite_agent["role"] == "Test Agent"
+    assert created_lite_agent["goal"] == "Test Goal"
+    assert created_lite_agent["backstory"] == "Test Backstory"
+    assert created_lite_agent["llm"] == llm
+    assert len(created_lite_agent["tools"]) == 2
+    assert isinstance(created_lite_agent["tools"][0], WebSearchTool)
+    assert isinstance(created_lite_agent["tools"][1], CalculatorTool)
+    assert created_lite_agent["max_iterations"] == max_iter
+    assert created_lite_agent["max_execution_time"] == max_execution_time
+    assert created_lite_agent["verbose"] == verbose
+    assert created_lite_agent["response_format"] is None
+
+    # Test with a response_format
+    monkeypatch.setattr("crewai.agent.LiteAgent", MockLiteAgent)
+
+    class TestResponse(BaseModel):
+        test_field: str
+
+    agent.kickoff("Test query", response_format=TestResponse)
+    assert created_lite_agent["response_format"] == TestResponse
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_lite_agent_with_tools():
-    """Test that LiteAgent can use tools."""
+    """Test that Agent can use tools."""
     # Create a LiteAgent with tools
     llm = LLM(model="gpt-4o-mini")
-    agent = LiteAgent(
+    agent = Agent(
         role="Research Assistant",
         goal="Find information about the population of Tokyo",
         backstory="You are a helpful research assistant who can search for information about the population of Tokyo.",
@@ -106,7 +168,7 @@ def test_lite_agent_with_tools():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_lite_agent_structured_output():
-    """Test that LiteAgent can return a simple structured output."""
+    """Test that Agent can return a simple structured output."""
 
     class SimpleOutput(BaseModel):
         """Simple structure for agent outputs."""
@@ -117,18 +179,18 @@ def test_lite_agent_structured_output():
     web_search_tool = WebSearchTool()
 
     llm = LLM(model="gpt-4o-mini")
-    agent = LiteAgent(
+    agent = Agent(
         role="Info Gatherer",
         goal="Provide brief information",
         backstory="You gather and summarize information quickly.",
         llm=llm,
         tools=[web_search_tool],
         verbose=True,
-        response_format=SimpleOutput,
     )
 
     result = agent.kickoff(
-        "What is the population of Tokyo? Return your strucutred output in JSON format with the following fields: summary, confidence"
+        "What is the population of Tokyo? Return your strucutred output in JSON format with the following fields: summary, confidence",
+        response_format=SimpleOutput,
     )
 
     print(f"\n=== Agent Result Type: {type(result)}")
@@ -155,7 +217,7 @@ def test_lite_agent_structured_output():
 def test_lite_agent_returns_usage_metrics():
     """Test that LiteAgent returns usage metrics."""
     llm = LLM(model="gpt-4o-mini")
-    agent = LiteAgent(
+    agent = Agent(
         role="Research Assistant",
         goal="Find information about the population of Tokyo",
         backstory="You are a helpful research assistant who can search for information about the population of Tokyo.",
@@ -170,3 +232,26 @@ def test_lite_agent_returns_usage_metrics():
 
     assert result.usage_metrics is not None
     assert result.usage_metrics["total_tokens"] > 0
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.asyncio
+async def test_lite_agent_returns_usage_metrics_async():
+    """Test that LiteAgent returns usage metrics when run asynchronously."""
+    llm = LLM(model="gpt-4o-mini")
+    agent = Agent(
+        role="Research Assistant",
+        goal="Find information about the population of Tokyo",
+        backstory="You are a helpful research assistant who can search for information about the population of Tokyo.",
+        llm=llm,
+        tools=[WebSearchTool()],
+        verbose=True,
+    )
+
+    result = await agent.kickoff_async(
+        "What is the population of Tokyo? Return your strucutred output in JSON format with the following fields: summary, confidence"
+    )
+    assert isinstance(result, LiteAgentOutput)
+    assert "21 million" in result.raw or "37 million" in result.raw
+    assert result.usage_metrics is not None
+    assert result.usage_metrics["total_tokens"] > 0

tests/tools/test_base_tool.py

@@ -1,4 +1,8 @@
-from typing import Callable
+import asyncio
+import inspect
+import unittest
+from typing import Any, Callable, Dict, List
+from unittest.mock import patch
 
 from crewai.tools import BaseTool, tool
 
@@ -100,3 +104,91 @@ def test_default_cache_function_is_true():
     my_tool = MyCustomTool()
     # Assert all the right attributes were defined
     assert my_tool.cache_function()
+
+
+def test_result_as_answer_in_tool_decorator():
+    @tool("Tool with result as answer", result_as_answer=True)
+    def my_tool_with_result_as_answer(question: str) -> str:
+        """This tool will return its result as the final answer."""
+        return question
+    
+    assert my_tool_with_result_as_answer.result_as_answer is True
+    
+    converted_tool = my_tool_with_result_as_answer.to_structured_tool()
+    assert converted_tool.result_as_answer is True
+    
+    @tool("Tool with default result_as_answer")
+    def my_tool_with_default(question: str) -> str:
+        """This tool uses the default result_as_answer value."""
+        return question
+    
+    assert my_tool_with_default.result_as_answer is False
+    
+    converted_tool = my_tool_with_default.to_structured_tool()
+    assert converted_tool.result_as_answer is False
+
+
+class SyncTool(BaseTool):
+    """Test implementation with a synchronous _run method"""
+    name: str = "sync_tool"
+    description: str = "A synchronous tool for testing"
+
+    def _run(self, input_text: str) -> str:
+        """Process input text synchronously."""
+        return f"Processed {input_text} synchronously"
+
+
+class AsyncTool(BaseTool):
+    """Test implementation with an asynchronous _run method"""
+    name: str = "async_tool"
+    description: str = "An asynchronous tool for testing"
+
+    async def _run(self, input_text: str) -> str:
+        """Process input text asynchronously."""
+        await asyncio.sleep(0.1)  # Simulate async operation
+        return f"Processed {input_text} asynchronously"
+
+
+def test_sync_run_returns_direct_result():
+    """Test that _run in a synchronous tool returns a direct result, not a coroutine."""
+    tool = SyncTool()
+    result = tool._run(input_text="hello")
+
+    assert not asyncio.iscoroutine(result)
+    assert result == "Processed hello synchronously"
+
+    run_result = tool.run(input_text="hello")
+    assert run_result == "Processed hello synchronously"
+
+
+def test_async_run_returns_coroutine():
+    """Test that _run in an asynchronous tool returns a coroutine object."""
+    tool = AsyncTool()
+    result = tool._run(input_text="hello")
+
+    assert asyncio.iscoroutine(result)
+    result.close()  # Clean up the coroutine
+
+
+def test_run_calls_asyncio_run_for_async_tools():
+    """Test that asyncio.run is called when using async tools."""
+    async_tool = AsyncTool()
+
+    with patch('asyncio.run') as mock_run:
+        mock_run.return_value = "Processed test asynchronously"
+        async_result = async_tool.run(input_text="test")
+
+        mock_run.assert_called_once()
+        assert async_result == "Processed test asynchronously"
+
+
+def test_run_does_not_call_asyncio_run_for_sync_tools():
+    """Test that asyncio.run is NOT called when using sync tools."""
+    sync_tool = SyncTool()
+
+    with patch('asyncio.run') as mock_run:
+        sync_result = sync_tool.run(input_text="test")
+
+        mock_run.assert_not_called()
+        assert sync_result == "Processed test synchronously"
+

uv.lock

@@ -1,19 +1,42 @@
 version = 1
-revision = 1
 requires-python = ">=3.10, <3.13"
 resolution-markers = [
-    "python_full_version < '3.11' and sys_platform == 'darwin'",
-    "python_full_version < '3.11' and platform_machine == 'aarch64' and sys_platform == 'linux'",
-    "(python_full_version < '3.11' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.11' and sys_platform != 'darwin' and sys_platform != 'linux')",
-    "python_full_version == '3.11.*' and sys_platform == 'darwin'",
-    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and sys_platform == 'linux'",
-    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform != 'darwin' and sys_platform != 'linux')",
-    "python_full_version >= '3.12' and python_full_version < '3.12.4' and sys_platform == 'darwin'",
-    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and sys_platform == 'linux'",
-    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and sys_platform != 'darwin' and sys_platform != 'linux')",
-    "python_full_version >= '3.12.4' and sys_platform == 'darwin'",
-    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and sys_platform == 'linux'",
-    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12.4' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version < '3.11' and platform_system == 'Darwin' and sys_platform == 'darwin'",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'darwin'",
+    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform == 'darwin') or (python_full_version < '3.11' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'darwin')",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Darwin' and sys_platform == 'linux'",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'linux'",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'linux'",
+    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_system == 'Darwin' and sys_platform != 'darwin') or (python_full_version < '3.11' and platform_system == 'Darwin' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux'",
+    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform != 'darwin') or (python_full_version < '3.11' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version == '3.11.*' and platform_system == 'Darwin' and sys_platform == 'darwin'",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'darwin'",
+    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform == 'darwin') or (python_full_version == '3.11.*' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'darwin')",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Darwin' and sys_platform == 'linux'",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'linux'",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'linux'",
+    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_system == 'Darwin' and sys_platform != 'darwin') or (python_full_version == '3.11.*' and platform_system == 'Darwin' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux'",
+    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform != 'darwin') or (python_full_version == '3.11.*' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system == 'Darwin' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'darwin'",
+    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform == 'darwin') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'darwin')",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Darwin' and sys_platform == 'linux'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'linux'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'linux'",
+    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_system == 'Darwin' and sys_platform != 'darwin') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system == 'Darwin' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux'",
+    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform != 'darwin') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12.4' and platform_system == 'Darwin' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'darwin'",
+    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform == 'darwin') or (python_full_version >= '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'darwin')",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Darwin' and sys_platform == 'linux'",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'linux'",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'linux'",
+    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_system == 'Darwin' and sys_platform != 'darwin') or (python_full_version >= '3.12.4' and platform_system == 'Darwin' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux'",
+    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform != 'darwin') or (python_full_version >= '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux')",
 ]
 
 [[package]]
@@ -321,7 +344,7 @@ name = "build"
 version = "1.2.2.post1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "(os_name == 'nt' and platform_machine != 'aarch64' and sys_platform == 'linux') or (os_name == 'nt' and sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "colorama", marker = "os_name == 'nt'" },
     { name = "importlib-metadata", marker = "python_full_version < '3.10.2'" },
     { name = "packaging" },
     { name = "pyproject-hooks" },
@@ -556,7 +579,7 @@ name = "click"
 version = "8.1.8"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "colorama", marker = "platform_system == 'Windows'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/b9/2e/0090cbf739cee7d23781ad4b89a9894a41538e4fcf4c31dcdd705b78eb8b/click-8.1.8.tar.gz", hash = "sha256:ed53c9d8990d83c2a27deae68e4ee337473f6330c040a31d4225c9574d16096a", size = 226593 }
 wheels = [
@@ -607,7 +630,7 @@ wheels = [
 
 [[package]]
 name = "crewai"
-version = "0.108.0"
+version = "0.114.0"
 source = { editable = "." }
 dependencies = [
     { name = "appdirs" },
@@ -695,7 +718,7 @@ requires-dist = [
     { name = "blinker", specifier = ">=1.9.0" },
     { name = "chromadb", specifier = ">=0.5.23" },
     { name = "click", specifier = ">=8.1.7" },
-    { name = "crewai-tools", marker = "extra == 'tools'", specifier = "~=0.38.0" },
+    { name = "crewai-tools", marker = "extra == 'tools'", specifier = "~=0.40.1" },
     { name = "docling", marker = "extra == 'docling'", specifier = ">=2.12.0" },
     { name = "fastembed", marker = "extra == 'fastembed'", specifier = ">=0.4.1" },
     { name = "instructor", specifier = ">=1.3.3" },
@@ -722,7 +745,6 @@ requires-dist = [
     { name = "tomli-w", specifier = ">=1.1.0" },
     { name = "uv", specifier = ">=0.4.25" },
 ]
-provides-extras = ["tools", "embeddings", "agentops", "fastembed", "pdfplumber", "pandas", "openpyxl", "mem0", "docling", "aisuite"]
 
 [package.metadata.requires-dev]
 dev = [
@@ -745,7 +767,7 @@ dev = [
 
 [[package]]
 name = "crewai-tools"
-version = "0.38.1"
+version = "0.40.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "chromadb" },
@@ -760,9 +782,9 @@ dependencies = [
     { name = "pytube" },
     { name = "requests" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/85/3f/d3b5697b4c6756cec65316c9ea9ccd9054f7b73670d1580befd3632ba031/crewai_tools-0.38.1.tar.gz", hash = "sha256:6abe75b3b339d53a9cf4e2d80124d863ff62a82b36753c30bec64318881876b2", size = 737620 }
+sdist = { url = "https://files.pythonhosted.org/packages/16/ff/0c16c9943ec1501b12fc72aca7815f191ffe94d5f1fe4e9c353ee8c4ad1d/crewai_tools-0.40.1.tar.gz", hash = "sha256:6af5040b2277df8fd592238a17bf584f95dcc9ef7766236534999c8a9e9d0b52", size = 744094 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/2b/2b/a6c9007647ffbb6a3c204b3ef26806030d6b041e3e012d4cec43c21335d6/crewai_tools-0.38.1-py3-none-any.whl", hash = "sha256:d9d3a88060f1f30c8f4ea044f6dd564a50d0a22b8a018a6fcec202b36246b9d8", size = 561414 },
+    { url = "https://files.pythonhosted.org/packages/35/05/619c00bae2dda038f0d218dd5197120c938e9c9ccef1b9e50cfb037486f6/crewai_tools-0.40.1-py3-none-any.whl", hash = "sha256:8f459f74dee64364bfdbc524c815c4afcfb9ed532b51e6b8b4f616398d46cf1e", size = 573286 },
 ]
 
 [[package]]
@@ -2496,7 +2518,7 @@ version = "1.6.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "click" },
-    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "colorama", marker = "platform_system == 'Windows'" },
     { name = "ghp-import" },
     { name = "jinja2" },
     { name = "markdown" },
@@ -2677,7 +2699,7 @@ version = "2.10.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "pygments" },
-    { name = "pywin32", marker = "sys_platform == 'win32'" },
+    { name = "pywin32", marker = "platform_system == 'Windows'" },
     { name = "tqdm" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/3a/93/80ac75c20ce54c785648b4ed363c88f148bf22637e10c9863db4fbe73e74/mpire-2.10.2.tar.gz", hash = "sha256:f66a321e93fadff34585a4bfa05e95bd946cf714b442f51c529038eb45773d97", size = 271270 }
@@ -2924,7 +2946,7 @@ name = "nvidia-cudnn-cu12"
 version = "9.1.0.70"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/9f/fd/713452cd72343f682b1c7b9321e23829f00b842ceaedcda96e742ea0b0b3/nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl", hash = "sha256:165764f44ef8c61fcdfdfdbe769d687e06374059fbb388b6c89ecb0e28793a6f", size = 664752741 },
@@ -2951,9 +2973,9 @@ name = "nvidia-cusolver-cu12"
 version = "11.4.5.107"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
-    { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
-    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/bc/1d/8de1e5c67099015c834315e333911273a8c6aaba78923dd1d1e25fc5f217/nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd", size = 124161928 },
@@ -2964,7 +2986,7 @@ name = "nvidia-cusparse-cu12"
 version = "12.1.0.106"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/65/5b/cfaeebf25cd9fdec14338ccb16f6b2c4c7fa9163aefcf057d86b9cc248bb/nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c", size = 195958278 },
@@ -2975,6 +2997,7 @@ name = "nvidia-nccl-cu12"
 version = "2.20.5"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/c1/bb/d09dda47c881f9ff504afd6f9ca4f502ded6d8fc2f572cacc5e39da91c28/nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1fc150d5c3250b170b29410ba682384b14581db722b2531b0d8d33c595f33d01", size = 176238458 },
     { url = "https://files.pythonhosted.org/packages/4b/2a/0a131f572aa09f741c30ccd45a8e56316e8be8dfc7bc19bf0ab7cfef7b19/nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:057f6bf9685f75215d0c53bf3ac4a10b3e6578351de307abad9e18a99182af56", size = 176249402 },
 ]
 
@@ -2984,6 +3007,7 @@ version = "12.6.85"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/9d/d7/c5383e47c7e9bf1c99d5bd2a8c935af2b6d705ad831a7ec5c97db4d82f4f/nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:eedc36df9e88b682efe4309aa16b5b4e78c2407eac59e8c10a6a47535164369a", size = 19744971 },
+    { url = "https://files.pythonhosted.org/packages/31/db/dc71113d441f208cdfe7ae10d4983884e13f464a6252450693365e166dcf/nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cf4eaa7d4b6b543ffd69d6abfb11efdeb2db48270d94dfd3a452c24150829e41", size = 19270338 },
 ]
 
 [[package]]
@@ -3501,7 +3525,7 @@ name = "portalocker"
 version = "2.10.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "pywin32", marker = "sys_platform == 'win32'" },
+    { name = "pywin32", marker = "platform_system == 'Windows'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/ed/d3/c6c64067759e87af98cc668c1cc75171347d0f1577fab7ca3749134e3cd4/portalocker-2.10.1.tar.gz", hash = "sha256:ef1bf844e878ab08aee7e40184156e1151f228f103aa5c6bd0724cc330960f8f", size = 40891 }
 wheels = [
@@ -5008,19 +5032,19 @@ dependencies = [
     { name = "fsspec" },
     { name = "jinja2" },
     { name = "networkx" },
-    { name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cuda-cupti-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cuda-nvrtc-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cusolver-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-nccl-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-nvtx-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cuda-cupti-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cuda-nvrtc-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cusolver-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-nccl-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-nvtx-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
     { name = "sympy" },
-    { name = "triton", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "triton", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
     { name = "typing-extensions" },
 ]
 wheels = [
@@ -5067,7 +5091,7 @@ name = "tqdm"
 version = "4.66.5"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "colorama", marker = "platform_system == 'Windows'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/58/83/6ba9844a41128c62e810fddddd72473201f3eacde02046066142a2d96cc5/tqdm-4.66.5.tar.gz", hash = "sha256:e1020aef2e5096702d8a025ac7d16b1577279c9d63f8375b63083e9a5f0fcbad", size = 169504 }
 wheels = [
@@ -5109,7 +5133,7 @@ name = "triton"
 version = "3.0.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "filelock", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "filelock", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/45/27/14cc3101409b9b4b9241d2ba7deaa93535a217a211c86c4cc7151fb12181/triton-3.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e1efef76935b2febc365bfadf74bcb65a6f959a9872e5bddf44cc9e0adce1e1a", size = 209376304 },