dropped for clarity

* Fix #2536: Add CREWAI_DISABLE_TELEMETRY environment variable

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

* Fix import order in telemetry test file

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

* Fix telemetry implementation based on PR feedback

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

* Revert telemetry implementation changes while keeping CREWAI_DISABLE_TELEMETRY functionality

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

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>

.gitignore

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

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.                                                                                                      |

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/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
 
@@ -274,6 +275,102 @@ 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.
+
+#### Basic Usage with Mem0
+
+The most common way to use External Memory is with Mem0 as the provider:
+
+```python
+from crewai import Agent, Crew, Process, Task
+from crewai.memory.external.external_memory import ExternalMemory
+
+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,
+    memory=True,
+    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,
+    memory=True,
+    external_memory=external_memory,
+)
+
+crew.kickoff(
+    inputs={"question": "which destination is better for a beach vacation?"}
+)
+```
 
 
 ## Additional Embedding Providers

docs/docs.json

@@ -66,7 +66,6 @@
               "concepts/tasks",
               "concepts/crews",
               "concepts/flows",
-              "concepts/lite-agent",
               "concepts/knowledge",
               "concepts/llms",
               "concepts/processes",
@@ -231,4 +230,4 @@
       "reddit": "https://www.reddit.com/r/crewAIInc/"
     }
   }
-}
+}

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>

pyproject.toml

@@ -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",
@@ -19,10 +21,12 @@ __version__ = "0.108.0"
 __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
@@ -207,6 +207,7 @@ class Agent(BaseAgent):
                 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 +449,74 @@ 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,
+        )
+
+        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

@@ -47,6 +47,27 @@ 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 (

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/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/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.",
@@ -191,14 +197,6 @@ class Crew(BaseModel):
         default=None,
         description="Path to the prompt json file to be used for the crew.",
     )
-    language: Optional[str] = Field(
-        default="en",
-        description="Language used for the crew, defaults to English.",
-    )
-    language_file: Optional[str] = Field(
-        default=None,
-        description="Path to the language file to be used for the crew.",
-    )
     output_log_file: Optional[Union[bool, str]] = Field(
         default=None,
         description="Path to the log file to be saved",
@@ -297,6 +295,12 @@ class Crew(BaseModel):
                 if self.entity_memory
                 else EntityMemory(crew=self, embedder_config=self.embedder)
             )
+            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
+            )
             if (
                 self.memory_config
                 and "user_memory" in self.memory_config
@@ -617,7 +621,7 @@ class Crew(BaseModel):
                 self._interpolate_inputs(inputs)
             self._set_tasks_callbacks()
 
-            i18n = self._create_i18n()
+            i18n = I18N(prompt_file=self.prompt_file)
 
             for agent in self.agents:
                 agent.i18n = i18n
@@ -758,17 +762,8 @@ class Crew(BaseModel):
         self._create_manager_agent()
         return self._execute_tasks(self.tasks)
 
-    def _create_i18n(self) -> I18N:
-        """
-        Create an I18N instance with the crew's configuration.
-        
-        Returns:
-            I18N: An internationalization instance configured with the crew's settings.
-        """
-        return I18N(prompt_file=self.prompt_file, language=self.language)
-        
     def _create_manager_agent(self):
-        i18n = self._create_i18n()
+        i18n = I18N(prompt_file=self.prompt_file)
         if self.manager_agent is not None:
             self.manager_agent.allow_delegation = True
             manager = self.manager_agent
@@ -1184,6 +1179,7 @@ class Crew(BaseModel):
             "_short_term_memory",
             "_long_term_memory",
             "_entity_memory",
+            "_external_memory",
             "_telemetry",
             "agents",
             "tasks",
@@ -1330,7 +1326,15 @@ 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:
@@ -1356,6 +1360,7 @@ 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)),
@@ -1383,6 +1388,7 @@ 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/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

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))
@@ -106,3 +115,24 @@ 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, Self
+
+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) -> Self:
+        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

@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, Self
 
 from pydantic import BaseModel
 
@@ -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) -> Self:
+        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 or 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")
@@ -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/utilities/i18n.py

@@ -1,15 +1,11 @@
 import json
 import os
-from functools import lru_cache
-from pathlib import Path
-from typing import Dict, Literal, Optional, Union
+from typing import Dict, Optional, Union
 
 from pydantic import BaseModel, Field, PrivateAttr, model_validator
 
 """Internationalization support for CrewAI prompts and messages."""
 
-SUPPORTED_LANGUAGES = Literal["en", "fr", "es", "pt"]
-
 class I18N(BaseModel):
     """Handles loading and retrieving internationalized prompts."""
     _prompts: Dict[str, Dict[str, str]] = PrivateAttr()
@@ -17,57 +13,22 @@ class I18N(BaseModel):
         default=None,
         description="Path to the prompt_file file to load",
     )
-    language: Optional[str] = Field(
-        default="en",
-        description="Language to use for translations. Defaults to English.",
-    )
-    
-    @model_validator(mode="before")
-    @classmethod
-    def validate_language(cls, data):
-        """
-        Validate the language parameter.
-        
-        If the language is not supported, it will fall back to English.
-        """
-        if isinstance(data, dict) and "language" in data:
-            lang = data["language"]
-            if lang and lang not in ["en", "fr", "es", "pt"]:
-                print(f"Warning: Language '{lang}' not supported. Falling back to English.")
-                data["language"] = "en"
-        return data
 
     @model_validator(mode="after")
     def load_prompts(self) -> "I18N":
-        """
-        Load prompts from a JSON file.
-        
-        If prompt_file is provided, loads from that file.
-        Otherwise, attempts to load from the language-specific translation file.
-        Falls back to English if the specified language file doesn't exist.
-        
-        Raises:
-            Exception: If the prompt file is not found or contains invalid JSON.
-        
-        Returns:
-            I18N: The instance with loaded prompts.
-        """
+        """Load prompts from a JSON file."""
         try:
             if self.prompt_file:
                 with open(self.prompt_file, "r", encoding="utf-8") as f:
                     self._prompts = json.load(f)
             else:
-                base_path = Path(__file__).parent / "../translations"
-                lang = self.language or "en"
-                lang_file = base_path / f"{lang}.json"
-                
-                if not lang_file.exists():
-                    lang_file = base_path / "en.json"
-                
-                with open(lang_file.resolve(), "r", encoding="utf-8") as f:
+                dir_path = os.path.dirname(os.path.realpath(__file__))
+                prompts_path = os.path.join(dir_path, "../translations/en.json")
+
+                with open(prompts_path, "r", encoding="utf-8") as f:
                     self._prompts = json.load(f)
         except FileNotFoundError:
-            raise Exception(f"Prompt file '{self.prompt_file or lang_file}' not found.")
+            raise Exception(f"Prompt file '{self.prompt_file}' not found.")
         except json.JSONDecodeError:
             raise Exception("Error decoding JSON from the prompts file.")
 
@@ -77,31 +38,15 @@ class I18N(BaseModel):
         return self
 
     def slice(self, slice: str) -> str:
-        """Get a slice prompt by key."""
         return self.retrieve("slices", slice)
 
     def errors(self, error: str) -> str:
-        """Get an error message by key."""
         return self.retrieve("errors", error)
 
     def tools(self, tool: str) -> Union[str, Dict[str, str]]:
-        """Get a tool prompt by key."""
         return self.retrieve("tools", tool)
 
-    def retrieve(self, kind: str, key: str) -> str:
-        """
-        Retrieve a prompt by section and key.
-        
-        Args:
-            kind: The section in the prompts file (e.g., "slices", "errors")
-            key: The specific key within the section
-            
-        Returns:
-            The prompt text
-            
-        Raises:
-            Exception: If the prompt is not found
-        """
+    def retrieve(self, kind, key) -> str:
         try:
             return self._prompts[kind][key]
         except Exception as _:

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/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_language_test.py

@@ -1,41 +0,0 @@
-from unittest.mock import patch
-
-import pytest
-
-from crewai import Agent, Crew, Process, Task
-from crewai.utilities.i18n import I18N
-
-
-def test_crew_with_language():
-    i18n = I18N(language="en")
-    
-    agent = Agent(
-        role="Test Agent",
-        goal="Test Goal",
-        backstory="Test Backstory",
-        verbose=True
-    )
-    
-    task = Task(
-        description="Test Task",
-        expected_output="Test Output",
-        agent=agent
-    )
-    
-    with patch('crewai.crew.I18N') as mock_i18n:
-        mock_i18n.return_value = i18n
-        
-        crew = Crew(
-            agents=[agent],
-            tasks=[task],
-            process=Process.sequential,
-            verbose=True,
-            language="fr"  # Use French as an example
-        )
-        
-        with patch.object(crew, '_run_sequential_process'):
-            with patch.object(crew, '_set_tasks_callbacks'):
-                with patch('crewai.agent.Agent.create_agent_executor'):
-                    crew.kickoff()
-                    
-                    mock_i18n.assert_called_with(prompt_file=None, language="fr")

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/memory/external/cassettes/test_crew_external_memory_save.yaml

@@ -0,0 +1,652 @@
+interactions:
+- request:
+    body: '{"input": ["Perform a search on specific topics."], "model": "text-embedding-3-small",
+      "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '115'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
+      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
+      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
+      7,\n    \"total_tokens\": 7\n  }\n}\n"
+    headers:
+      CF-RAY:
+      - 929ab3937d457e01-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:05:28 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=kDn7w.xxhfUOdeywOX91X.QPh7jJ.MWIdK59RMswo4I-1743537928-1.0.1.1-fsXh4ayfrGxPX9d7yv7wOTJao.R7zWidYJkbOjSnLbNrs5DIziftd8U4EkvHFafefe4dS33kmwVZZvBBsSA0iTNy8kTCh4ouZCTCBGdqiJM;
+        path=/; expires=Tue, 01-Apr-25 20:35:28 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=jlKaHr6Qf4Cpn7uR7FBiNw0lhnPCPxgSGLHX33FTNZY-1743537928631-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '196'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-68459c4c98-rcmtr
+      x-envoy-upstream-service-time:
+      - '165'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999991'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_4e0afe109cad076a0738b5c0cf2d3325
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"input": ["Perform a search on specific topics."], "model": "text-embedding-3-small",
+      "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '115'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
+      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
+      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
+      7,\n    \"total_tokens\": 7\n  }\n}\n"
+    headers:
+      CF-RAY:
+      - 929ab3965ba47dfb-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:05:28 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=5_dVmaW1w6ShSd0cQsx_6UToMPBGZYGCn4AuQqRKApI-1743537928-1.0.1.1-YIeREsG1o9zTcT.Da4V5YgMnEFTLJSubxSv2Xcrby4js5WOWsqkwEmd0mTErAR4yN_tlR_lkbq6eyVvjW4Qr9qCtlB1sdZR9q9sKHTfQTLc;
+        path=/; expires=Tue, 01-Apr-25 20:35:28 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=NCI5ttxt2Z4JzyWS0cwOIKu4mvXXODEDgwZ4n6e3Bw4-1743537928979-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '103'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-779fc7d87c-zw8xf
+      x-envoy-upstream-service-time:
+      - '74'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999991'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_d5345faa4b8024f93e46c9695cff0375
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CtoMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSsQwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKXCAoQm8h3kcZlX+KG8GXz4BaguxIIpiZBM32xbrMqDENyZXcgQ3JlYXRlZDABOagr
+      ERR8SjIYQdgDQBR8SjIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTA4LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIDA3YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhk
+      MjgzMmM2SjEKB2NyZXdfaWQSJgokY2EyZDBlMmUtMDY3NS00Yjk3LTljNGItMjllN2UxMGY3YTE5
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAUoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
+      X2ZpbmdlcnByaW50EiYKJDVhYzNjN2JlLWMxZWUtNDRmYS1iMzEzLTVmMzRjODA3ZDAwYko7Chtj
+      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0wMVQxNzowNTowMS45OTIwODlK
+      ywIKC2NyZXdfYWdlbnRzErsCCrgCW3sia2V5IjogIjAyZGYxM2UzNjcxMmFiZjUxZDIzOGZlZWJh
+      YjFjYTI2IiwgImlkIjogIjJiZDZmZTY1LTRkYWItNDVhYy04ZTMxLTljNzU2NThlOTdiOCIsICJy
+      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAyNSwgIm1h
+      eF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8i
+      LCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/Ijog
+      ZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSv8BCgpjcmV3
+      X3Rhc2tzEvABCu0BW3sia2V5IjogIjdiNDJkZjNjM2M3NGMyMWM4OTQ4MGUwYzA3MDUzODVmIiwg
+      ImlkIjogIjcwMTEzZTAwLWRlN2EtNGY0Ny1iZTBmLTU2ZWE1YmFhYTA4MiIsICJhc3luY19leGVj
+      dXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiUmVz
+      ZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiMDJkZjEzZTM2NzEyYWJmNTFkMjM4ZmVlYmFiMWNhMjYi
+      LCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQUIi202VgKCuffOL3MDckcxIIvGhx
+      5lv94IYqDFRhc2sgQ3JlYXRlZDABOVDbgRR8SjIYQWjLgxR8SjIYSi4KCGNyZXdfa2V5EiIKIDA3
+      YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhkMjgzMmM2SjEKB2NyZXdfaWQSJgokY2EyZDBlMmUtMDY3
+      NS00Yjk3LTljNGItMjllN2UxMGY3YTE5Si4KCHRhc2tfa2V5EiIKIDdiNDJkZjNjM2M3NGMyMWM4
+      OTQ4MGUwYzA3MDUzODVmSjEKB3Rhc2tfaWQSJgokNzAxMTNlMDAtZGU3YS00ZjQ3LWJlMGYtNTZl
+      YTViYWFhMDgySjoKEGNyZXdfZmluZ2VycHJpbnQSJgokNWFjM2M3YmUtYzFlZS00NGZhLWIzMTMt
+      NWYzNGM4MDdkMDBiSjoKEHRhc2tfZmluZ2VycHJpbnQSJgokZTFiNGYwNTUtNTI4Ny00YmQ1LWJh
+      YzUtOGE0MjQ2M2I0OTRmSjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0
+      LTAxVDE3OjA1OjAxLjk5MTM1NEo7ChFhZ2VudF9maW5nZXJwcmludBImCiRiM2M0ODhkOC1kOTEz
+      LTQ0ZTEtYWE4NC05ZWRlMmY4ZmQ1N2V6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1629'
+      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:
+      - Tue, 01 Apr 2025 20:05:29 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", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '984'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      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-BHc9RXfB5Sj2QaKl5AVUIW2X08Lfc\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1743537929,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+      Answer: I am unable to access external websites directly to extract URLs or
+      search the internet; however, I can guide you on how to search for the required
+      topics using search engines like Google. You would typically input your specific
+      query into the search engine to receive a list of URLs and content related to
+      your topic. Here\u2019s a step-by-step approach:\\n\\n1. Go to a search engine
+      like Google.\\n2. Enter your specific search query in the search bar.\\n3. Review
+      the search results and identify URLs that are relevant to your topic.\\n4. Click
+      on the links to access the actual content from those URLs.\\n\\nRemember to
+      use specific keywords and phrases that are closely related to your research
+      topic to narrow down your search results for more relevant URLs.\",\n        \"refusal\":
+      null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 185,\n    \"completion_tokens\":
+      161,\n    \"total_tokens\": 346,\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_898ac29719\"\n}\n"
+    headers:
+      CF-RAY:
+      - 929ab399fe8d7dee-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:05:31 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=Hxm6ignpjzUPY4_F0hNOxDI6blf0OOBnlpX09HJLkXw-1743537931-1.0.1.1-EnMojyC4HcsGaIfLZ3AM11JeKT5P2fCrPy4P_cEuqem7t6aJ66exdhSjbXn7cY_0WGDzFZMXOd2FiX1cdOOotV7bTaiKamm_kbxZ2AeH0DI;
+        path=/; expires=Tue, 01-Apr-25 20:35:31 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=0tT0dhP6be3yJlOYI.zGaiYhO_s63uZ7L9h2mjFuTUI-1743537931401-0.0.1.1-604800000;
+        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:
+      - '1966'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '50000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '49999'
+      x-ratelimit-remaining-tokens:
+      - '149999788'
+      x-ratelimit-reset-requests:
+      - 1ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_868c5ea7787c0215cc80eb9106f87605
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"input": ["Thought: I now can give a great answer Final Answer: I am unable
+      to access external websites directly to extract URLs or search the internet;
+      however, I can guide you on how to search for the required topics using search
+      engines like Google. You would typically input your specific query into the
+      search engine to receive a list of URLs and content related to your topic. Here\u2019s
+      a step-by-step approach:  1. Go to a search engine like Google. 2. Enter your
+      specific search query in the search bar. 3. Review the search results and identify
+      URLs that are relevant to your topic. 4. Click on the links to access the actual
+      content from those URLs.  Remember to use specific keywords and phrases that
+      are closely related to your research topic to narrow down your search results
+      for more relevant URLs."], "model": "text-embedding-3-small", "encoding_format":
+      "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '883'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=kDn7w.xxhfUOdeywOX91X.QPh7jJ.MWIdK59RMswo4I-1743537928-1.0.1.1-fsXh4ayfrGxPX9d7yv7wOTJao.R7zWidYJkbOjSnLbNrs5DIziftd8U4EkvHFafefe4dS33kmwVZZvBBsSA0iTNy8kTCh4ouZCTCBGdqiJM;
+        _cfuvid=jlKaHr6Qf4Cpn7uR7FBiNw0lhnPCPxgSGLHX33FTNZY-1743537928631-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
+      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
+      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
+      165,\n    \"total_tokens\": 165\n  }\n}\n"
+    headers:
+      CF-RAY:
+      - 929ab3a78f7f7e01-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:05:31 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '304'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-7c6fb6444f-lqx4h
+      x-envoy-upstream-service-time:
+      - '224'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999800'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 1ms
+      x-request-id:
+      - req_19ca925c719a9aa87da5ac6e9daf0f40
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
+      completed based on the description, expected output, and actual results.\n\nTask
+      Description:\nPerform a search on specific topics.\n\nExpected Output:\nA list
+      of relevant URLs based on the search query.\n\nActual Output:\nThought: I now
+      can give a great answer\nFinal Answer: I am unable to access external websites
+      directly to extract URLs or search the internet; however, I can guide you on
+      how to search for the required topics using search engines like Google. You
+      would typically input your specific query into the search engine to receive
+      a list of URLs and content related to your topic. Here\u2019s a step-by-step
+      approach:\n\n1. Go to a search engine like Google.\n2. Enter your specific search
+      query in the search bar.\n3. Review the search results and identify URLs that
+      are relevant to your topic.\n4. Click on the links to access the actual content
+      from those URLs.\n\nRemember to use specific keywords and phrases that are closely
+      related to your research topic to narrow down your search results for more relevant
+      URLs.\n\nPlease provide:\n- Bullet points suggestions to improve future similar
+      tasks\n- A score from 0 to 10 evaluating on completion, quality, and overall
+      performance- Entities extracted from the task output, if any, their type, description,
+      and relationships"}], "model": "gpt-4o", "tool_choice": {"type": "function",
+      "function": {"name": "TaskEvaluation"}}, "tools": [{"type": "function", "function":
+      {"name": "TaskEvaluation", "description": "Correctly extracted `TaskEvaluation`
+      with all the required parameters with correct types", "parameters": {"$defs":
+      {"Entity": {"properties": {"name": {"description": "The name of the entity.",
+      "title": "Name", "type": "string"}, "type": {"description": "The type of the
+      entity.", "title": "Type", "type": "string"}, "description": {"description":
+      "Description of the entity.", "title": "Description", "type": "string"}, "relationships":
+      {"description": "Relationships of the entity.", "items": {"type": "string"},
+      "title": "Relationships", "type": "array"}}, "required": ["name", "type", "description",
+      "relationships"], "title": "Entity", "type": "object"}}, "properties": {"suggestions":
+      {"description": "Suggestions to improve future similar tasks.", "items": {"type":
+      "string"}, "title": "Suggestions", "type": "array"}, "quality": {"description":
+      "A score from 0 to 10 evaluating on completion, quality, and overall performance,
+      all taking into account the task description, expected output, and the result
+      of the task.", "title": "Quality", "type": "number"}, "entities": {"description":
+      "Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
+      "title": "Entities", "type": "array"}}, "required": ["entities", "quality",
+      "suggestions"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2840'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=Hxm6ignpjzUPY4_F0hNOxDI6blf0OOBnlpX09HJLkXw-1743537931-1.0.1.1-EnMojyC4HcsGaIfLZ3AM11JeKT5P2fCrPy4P_cEuqem7t6aJ66exdhSjbXn7cY_0WGDzFZMXOd2FiX1cdOOotV7bTaiKamm_kbxZ2AeH0DI;
+        _cfuvid=0tT0dhP6be3yJlOYI.zGaiYhO_s63uZ7L9h2mjFuTUI-1743537931401-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      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-BHc9UaTUKHm9gIb6VtuzFmJ3Iyr5x\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1743537932,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+      \           \"id\": \"call_AB2zpwuaUHg5nDz8O27x9EGw\",\n            \"type\":
+      \"function\",\n            \"function\": {\n              \"name\": \"TaskEvaluation\",\n
+      \             \"arguments\": \"{\\\"suggestions\\\":[\\\"Ensure that the system
+      has the capability to access external websites or clarify such limitations in
+      the task description.\\\",\\\"Consider using web scraping tools or APIs to fetch
+      URLs directly if direct access is not possible.\\\",\\\"If the task only involves
+      providing guidance, make sure to adjust the expectations to match the output
+      type.\\\",\\\"Provide a clear and realistic expected output based on the known
+      capabilities of the system.\\\"],\\\"quality\\\":3,\\\"entities\\\":[]}\"\n
+      \           }\n          }\n        ],\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 443,\n    \"completion_tokens\":
+      87,\n    \"total_tokens\": 530,\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_898ac29719\"\n}\n"
+    headers:
+      CF-RAY:
+      - 929ab3ab8cf37dee-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:05:34 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:
+      - '2114'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '50000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '49999'
+      x-ratelimit-remaining-tokens:
+      - '149999672'
+      x-ratelimit-reset-requests:
+      - 1ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_0a3d97c857f26c689ef0840a21ad6dc3
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

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

@@ -0,0 +1,650 @@
+interactions:
+- request:
+    body: '{"input": ["Perform a search on specific topics."], "model": "text-embedding-3-small",
+      "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '115'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
+      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
+      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
+      7,\n    \"total_tokens\": 7\n  }\n}\n"
+    headers:
+      CF-RAY:
+      - 929abaf15acd7df9-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:10:30 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=JcjzeNadYektCKxz.qAt_Iu9W82BXw8zXu9IzahTzL4-1743538230-1.0.1.1-zltiq2Kl.WZlrShHKUBPQrPv0dX2jM_mrIEDEv58Na6s2GSfEgAQbiffMTPHtElo6HoDyJX5g8sjIacSnLyZSswTCjtL4C75K1IK09Or9mo;
+        path=/; expires=Tue, 01-Apr-25 20:40:30 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=cqy59cJ9.MxM3ogPzubxDJvueA5vj1ZPlpD5x5e3hdA-1743538230508-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '66'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-7c6fb6444f-cxmk8
+      x-envoy-upstream-service-time:
+      - '32'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999991'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_8ec9a4a21a4dda1d560d7002327e9bf5
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"input": ["Perform a search on specific topics."], "model": "text-embedding-3-small",
+      "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '115'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
+      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
+      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
+      7,\n    \"total_tokens\": 7\n  }\n}\n"
+    headers:
+      CF-RAY:
+      - 929abaf509b47deb-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:10:30 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=xm0wOFZcQAyJrMSiOz3MZOr_g5T3TyUhPvPR4mQpdeA-1743538230-1.0.1.1-kOKoGCRupMuPeKOGl9Uu0Gwt07QZKWJwMBg7JzariAfNaVs.AnqEQ__712GZsReNyqiOzUE0Qeykvt11gEEyFHX9VyyvNJcb6uHADLpyLLI;
+        path=/; expires=Tue, 01-Apr-25 20:40:30 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=.x6X1bgu02i.2_qawj3TiVXv0.G8azhdA2QeTcj83tY-1743538230900-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '108'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-8486ff7cdd-dskkc
+      x-envoy-upstream-service-time:
+      - '93'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999991'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_7570e7930cbf7583a5c482bc9a9829cd
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CtoMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSsQwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKXCAoQoIk4ztsSW1VcQBoGyvUEwRII42yueEHaLpkqDENyZXcgQ3JlYXRlZDABOaDB
+      SlvCSjIYQai+bVvCSjIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTA4LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIDA3YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhk
+      MjgzMmM2SjEKB2NyZXdfaWQSJgokMWI2YjUxZGEtMzgxMy00YjI1LTljN2EtOGM1ODkwM2NkMjk1
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAUoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
+      X2ZpbmdlcnByaW50EiYKJDFjNGQ3MTZhLTA3YjktNDFjNi05NTk0LWI2ZDJmZmJiNDMxZEo7Chtj
+      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0wMVQxNzoxMDowMy45NTQwNjRK
+      ywIKC2NyZXdfYWdlbnRzErsCCrgCW3sia2V5IjogIjAyZGYxM2UzNjcxMmFiZjUxZDIzOGZlZWJh
+      YjFjYTI2IiwgImlkIjogIjFmNzNlM2ZiLThmMWEtNGVjYy05ZWY0LWMxZjgxMWU3ZGQ1MyIsICJy
+      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAyNSwgIm1h
+      eF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8i
+      LCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/Ijog
+      ZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSv8BCgpjcmV3
+      X3Rhc2tzEvABCu0BW3sia2V5IjogIjdiNDJkZjNjM2M3NGMyMWM4OTQ4MGUwYzA3MDUzODVmIiwg
+      ImlkIjogImU0OGY1MDYwLWM5MjYtNGQ3ZC04M2NhLTk4MzQ0ZDU5OGJmMyIsICJhc3luY19leGVj
+      dXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiUmVz
+      ZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiMDJkZjEzZTM2NzEyYWJmNTFkMjM4ZmVlYmFiMWNhMjYi
+      LCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQWFKbmOfdsTZ4sp84HAkrQRIIQ5oa
+      A8zScp4qDFRhc2sgQ3JlYXRlZDABOaiGoFvCSjIYQbBPolvCSjIYSi4KCGNyZXdfa2V5EiIKIDA3
+      YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhkMjgzMmM2SjEKB2NyZXdfaWQSJgokMWI2YjUxZGEtMzgx
+      My00YjI1LTljN2EtOGM1ODkwM2NkMjk1Si4KCHRhc2tfa2V5EiIKIDdiNDJkZjNjM2M3NGMyMWM4
+      OTQ4MGUwYzA3MDUzODVmSjEKB3Rhc2tfaWQSJgokZTQ4ZjUwNjAtYzkyNi00ZDdkLTgzY2EtOTgz
+      NDRkNTk4YmYzSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokMWM0ZDcxNmEtMDdiOS00MWM2LTk1OTQt
+      YjZkMmZmYmI0MzFkSjoKEHRhc2tfZmluZ2VycHJpbnQSJgokNDY1NmIwOTctMDdkMy00Zjg2LWE1
+      OTgtYWQ1YmJiN2YwM2JlSjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0
+      LTAxVDE3OjEwOjAzLjk1MjM3NUo7ChFhZ2VudF9maW5nZXJwcmludBImCiRkNGQyYzEzMy1hNmE4
+      LTQ5YjktYTI0OS1iNzcwNDlkZjZlZWV6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1629'
+      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:
+      - Tue, 01 Apr 2025 20:10:32 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", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '984'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=26AntG8LjHgDcgN0MYB7TgUTXmoUsQqg8yChWws9CAE-1743538222-1.0.1.1-jo5QRov4A_6L5CaGwhXx2I2aGHzSN6wvrS5Lt2yDpcV5vfTu3FlroYl2d4LBq.ySrtNMDxGQgpsA6fMg0z4iEOXpD5DT7CrJKWRNr4H7Y_k;
+        _cfuvid=.HNP7WFC.O40eZMPSJZ4USQu9SYczq5v794aRx34sZg-1743538222787-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      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-BHcEJeQt9RxZ492mqpQIcZVupQH1c\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1743538231,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"My current task is to perform a search
+      on specific topics and return a list of relevant URLs. I don't have access to
+      external internet tools to fetch live data, but I can guide on how to find information
+      based on specific search queries.\\n\\n1. Identify the specific topics or keywords
+      for the search.\\n2. Use a search engine like Google to input these keywords.\\n3.
+      Look for credible sources, such as academic publications, news outlets, or specialized
+      websites, that provide relevant and reliable information.\\n4. Compile the URLs
+      from credible sources that directly relate to your search query.\\n\\nThought:
+      I now can give a great answer\\nFinal Answer: To obtain a list of relevant URLs,
+      you would need to perform a live search on a search engine using the specific
+      keywords related to your topics of interest and collect URLs from credible sources
+      such as academic journals, government websites, or reputable news outlets.\",\n
+      \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      185,\n    \"completion_tokens\": 177,\n    \"total_tokens\": 362,\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_898ac29719\"\n}\n"
+    headers:
+      CF-RAY:
+      - 929abaf84c1a7dfa-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:10:34 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:
+      - '2937'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '50000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '49999'
+      x-ratelimit-remaining-tokens:
+      - '149999788'
+      x-ratelimit-reset-requests:
+      - 1ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_c8e37cceac4fcca65da1c883d29cd816
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"input": ["My current task is to perform a search on specific topics and
+      return a list of relevant URLs. I don''t have access to external internet tools
+      to fetch live data, but I can guide on how to find information based on specific
+      search queries.  1. Identify the specific topics or keywords for the search.
+      2. Use a search engine like Google to input these keywords. 3. Look for credible
+      sources, such as academic publications, news outlets, or specialized websites,
+      that provide relevant and reliable information. 4. Compile the URLs from credible
+      sources that directly relate to your search query.  Thought: I now can give
+      a great answer Final Answer: To obtain a list of relevant URLs, you would need
+      to perform a live search on a search engine using the specific keywords related
+      to your topics of interest and collect URLs from credible sources such as academic
+      journals, government websites, or reputable news outlets."], "model": "text-embedding-3-small",
+      "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '995'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=JcjzeNadYektCKxz.qAt_Iu9W82BXw8zXu9IzahTzL4-1743538230-1.0.1.1-zltiq2Kl.WZlrShHKUBPQrPv0dX2jM_mrIEDEv58Na6s2GSfEgAQbiffMTPHtElo6HoDyJX5g8sjIacSnLyZSswTCjtL4C75K1IK09Or9mo;
+        _cfuvid=cqy59cJ9.MxM3ogPzubxDJvueA5vj1ZPlpD5x5e3hdA-1743538230508-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
+      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
+      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
+      182,\n    \"total_tokens\": 182\n  }\n}\n"
+    headers:
+      CF-RAY:
+      - 929abb0bee737df9-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:10:34 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '86'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-bbb94bf85-txxsl
+      x-envoy-upstream-service-time:
+      - '78'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999770'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 1ms
+      x-request-id:
+      - req_7ea6db6200478758c413eeb853e93f15
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
+      completed based on the description, expected output, and actual results.\n\nTask
+      Description:\nPerform a search on specific topics.\n\nExpected Output:\nA list
+      of relevant URLs based on the search query.\n\nActual Output:\nMy current task
+      is to perform a search on specific topics and return a list of relevant URLs.
+      I don''t have access to external internet tools to fetch live data, but I can
+      guide on how to find information based on specific search queries.\n\n1. Identify
+      the specific topics or keywords for the search.\n2. Use a search engine like
+      Google to input these keywords.\n3. Look for credible sources, such as academic
+      publications, news outlets, or specialized websites, that provide relevant and
+      reliable information.\n4. Compile the URLs from credible sources that directly
+      relate to your search query.\n\nThought: I now can give a great answer\nFinal
+      Answer: To obtain a list of relevant URLs, you would need to perform a live
+      search on a search engine using the specific keywords related to your topics
+      of interest and collect URLs from credible sources such as academic journals,
+      government websites, or reputable news outlets.\n\nPlease provide:\n- Bullet
+      points suggestions to improve future similar tasks\n- A score from 0 to 10 evaluating
+      on completion, quality, and overall performance- Entities extracted from the
+      task output, if any, their type, description, and relationships"}], "model":
+      "gpt-4o", "tool_choice": {"type": "function", "function": {"name": "TaskEvaluation"}},
+      "tools": [{"type": "function", "function": {"name": "TaskEvaluation", "description":
+      "Correctly extracted `TaskEvaluation` with all the required parameters with
+      correct types", "parameters": {"$defs": {"Entity": {"properties": {"name": {"description":
+      "The name of the entity.", "title": "Name", "type": "string"}, "type": {"description":
+      "The type of the entity.", "title": "Type", "type": "string"}, "description":
+      {"description": "Description of the entity.", "title": "Description", "type":
+      "string"}, "relationships": {"description": "Relationships of the entity.",
+      "items": {"type": "string"}, "title": "Relationships", "type": "array"}}, "required":
+      ["name", "type", "description", "relationships"], "title": "Entity", "type":
+      "object"}}, "properties": {"suggestions": {"description": "Suggestions to improve
+      future similar tasks.", "items": {"type": "string"}, "title": "Suggestions",
+      "type": "array"}, "quality": {"description": "A score from 0 to 10 evaluating
+      on completion, quality, and overall performance, all taking into account the
+      task description, expected output, and the result of the task.", "title": "Quality",
+      "type": "number"}, "entities": {"description": "Entities extracted from the
+      task output.", "items": {"$ref": "#/$defs/Entity"}, "title": "Entities", "type":
+      "array"}}, "required": ["entities", "quality", "suggestions"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2952'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=26AntG8LjHgDcgN0MYB7TgUTXmoUsQqg8yChWws9CAE-1743538222-1.0.1.1-jo5QRov4A_6L5CaGwhXx2I2aGHzSN6wvrS5Lt2yDpcV5vfTu3FlroYl2d4LBq.ySrtNMDxGQgpsA6fMg0z4iEOXpD5DT7CrJKWRNr4H7Y_k;
+        _cfuvid=.HNP7WFC.O40eZMPSJZ4USQu9SYczq5v794aRx34sZg-1743538222787-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      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-BHcEMcdhPRL3gLo2olJ4aUutrNfLv\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1743538234,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+      \           \"id\": \"call_rzy02tsLLurMdGuEiul9lHF8\",\n            \"type\":
+      \"function\",\n            \"function\": {\n              \"name\": \"TaskEvaluation\",\n
+      \             \"arguments\": \"{\\\"suggestions\\\":[\\\"Ensure access to the
+      internet or appropriate APIs to perform live searches in future tasks.\\\",\\\"Consider
+      simulating a response with example URLs if live search capability is unavailable.\\\",\\\"Provide
+      a disclaimer regarding the unavailability of live data retrieval.\\\",\\\"Indicate
+      clearly that the task cannot be completed as expected due to limitations.\\\"],\\\"quality\\\":3,\\\"entities\\\":[]}\"\n
+      \           }\n          }\n        ],\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 459,\n    \"completion_tokens\":
+      71,\n    \"total_tokens\": 530,\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_898ac29719\"\n}\n"
+    headers:
+      CF-RAY:
+      - 929abb0f2d587dfa-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:10:36 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:
+      - '1657'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '50000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '49999'
+      x-ratelimit-remaining-tokens:
+      - '149999644'
+      x-ratelimit-reset-requests:
+      - 1ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_ff90eb4514605cbdd86933a230691b6b
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

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

@@ -0,0 +1,836 @@
+interactions:
+- request:
+    body: '{"input": ["Perform a search on specific topics."], "model": "text-embedding-3-small",
+      "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '115'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
+      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
+      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
+      7,\n    \"total_tokens\": 7\n  }\n}\n"
+    headers:
+      CF-RAY:
+      - 929abab459817e07-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:10:20 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=wQNqc3BNcaCzhFR4owoCJRMIvs7PWqvy7xmWaIr4k.A-1743538220-1.0.1.1-AIxSGyU_kRiSsc4DYqsunqMwAlAn0fhT.P.7_bBBWTyHeVrexxOSRpm5yj6QmiIVcYwEgdJqk9EsHBy9LfadhgMJ5w8LIrHF_sxBFAXOOxc;
+        path=/; expires=Tue, 01-Apr-25 20:40:20 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=g5w7.LJsKZSYhPzW6M1n.OyrMWQSUF5zX.cFK1vZrQI-1743538220809-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '308'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-68459c4c98-bfmcm
+      x-envoy-upstream-service-time:
+      - '243'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999991'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_51cfe3e45d22af953af55f6708e77623
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"input": ["Perform a search on specific topics."], "model": "text-embedding-3-small",
+      "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '115'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
+      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
+      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
+      7,\n    \"total_tokens\": 7\n  }\n}\n"
+    headers:
+      CF-RAY:
+      - 929abab86d4a7e1b-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:10:21 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=MCDkRAmvHC26iz7BEoKzXwq4j5v_FEX5IQepnW5ARp4-1743538221-1.0.1.1-GXJkwk8HCFy9W0tA9R.s3NWzCNJ7wCiaUFu4YCbra4nQNVJa_mN3jdnmfREeET4QfWbYGCQXuM5GHffwtQZ_W1EV3mUC4JFa3w5CCDqO41Y;
+        path=/; expires=Tue, 01-Apr-25 20:40:21 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=mRF3.ZghYObsvTKqmSfcqSbJFV0SBPVk2Psc.9DVGlE-1743538221434-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '156'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-7c6fb6444f-m8b65
+      x-envoy-upstream-service-time:
+      - '132'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999991'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_463b788a4cc327763e9544976b2fe7ce
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CtoMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSsQwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKXCAoQllrSJs4siWPoysCAkdyzdhIIeP9LvWGg1D0qDENyZXcgQ3JlYXRlZDABOeAu
+      xRLASjIYQUh77RLASjIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTA4LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIDA3YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhk
+      MjgzMmM2SjEKB2NyZXdfaWQSJgokOWUwNDE3NDgtZTg2MS00M2YzLWE4ZTYtMTA4N2I3NjA1MTE1
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAUoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
+      X2ZpbmdlcnByaW50EiYKJDlhODQwMjI3LTQwY2UtNDU4OC1iYTAzLTBlYzZlMjQzMDdjMUo7Chtj
+      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0wMVQxNzowOTo1NC4xMzIwMzlK
+      ywIKC2NyZXdfYWdlbnRzErsCCrgCW3sia2V5IjogIjAyZGYxM2UzNjcxMmFiZjUxZDIzOGZlZWJh
+      YjFjYTI2IiwgImlkIjogImNlMjE2ZTU4LTY1MDgtNDQ0My1iZTY0LWUwNzVhNTQ5YzMzZCIsICJy
+      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAyNSwgIm1h
+      eF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8i
+      LCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/Ijog
+      ZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSv8BCgpjcmV3
+      X3Rhc2tzEvABCu0BW3sia2V5IjogIjdiNDJkZjNjM2M3NGMyMWM4OTQ4MGUwYzA3MDUzODVmIiwg
+      ImlkIjogImVmMDNjMDliLTIwNGQtNGU2Yy04NDIwLTQyNmNmOWM4OGFmYyIsICJhc3luY19leGVj
+      dXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiUmVz
+      ZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiMDJkZjEzZTM2NzEyYWJmNTFkMjM4ZmVlYmFiMWNhMjYi
+      LCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQZo4JZzOQlEm7ZP/lMPxN9hIIymaC
+      IpHXF4cqDFRhc2sgQ3JlYXRlZDABObhUIRPASjIYQQgSIxPASjIYSi4KCGNyZXdfa2V5EiIKIDA3
+      YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhkMjgzMmM2SjEKB2NyZXdfaWQSJgokOWUwNDE3NDgtZTg2
+      MS00M2YzLWE4ZTYtMTA4N2I3NjA1MTE1Si4KCHRhc2tfa2V5EiIKIDdiNDJkZjNjM2M3NGMyMWM4
+      OTQ4MGUwYzA3MDUzODVmSjEKB3Rhc2tfaWQSJgokZWYwM2MwOWItMjA0ZC00ZTZjLTg0MjAtNDI2
+      Y2Y5Yzg4YWZjSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokOWE4NDAyMjctNDBjZS00NTg4LWJhMDMt
+      MGVjNmUyNDMwN2MxSjoKEHRhc2tfZmluZ2VycHJpbnQSJgokNzcwMDBjZjktZjVlNC00MDJhLTg1
+      MTgtNzFhMzZhZTc2MmQwSjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0
+      LTAxVDE3OjA5OjU0LjEzMTE4NUo7ChFhZ2VudF9maW5nZXJwcmludBImCiQ0Y2Y4OTc4Yy1iN2M4
+      LTRiMjUtODYxMC1lNWE4NmMxOTYwNzB6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1629'
+      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:
+      - Tue, 01 Apr 2025 20:10:22 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", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '984'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      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-BHcE9342OpU72PR82mknhgcVzhK5H\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1743538221,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I need to gather relevant URLs
+      based on the search query provided in order to fulfill the task requirements.\\n\\nFinal
+      Answer: The search query or topics were not specified. Please provide specific
+      topics or search query to perform a search for relevant URLs.\",\n        \"refusal\":
+      null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 185,\n    \"completion_tokens\":
+      50,\n    \"total_tokens\": 235,\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_898ac29719\"\n}\n"
+    headers:
+      CF-RAY:
+      - 929ababcdf9c7dfa-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:10:22 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=26AntG8LjHgDcgN0MYB7TgUTXmoUsQqg8yChWws9CAE-1743538222-1.0.1.1-jo5QRov4A_6L5CaGwhXx2I2aGHzSN6wvrS5Lt2yDpcV5vfTu3FlroYl2d4LBq.ySrtNMDxGQgpsA6fMg0z4iEOXpD5DT7CrJKWRNr4H7Y_k;
+        path=/; expires=Tue, 01-Apr-25 20:40:22 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=.HNP7WFC.O40eZMPSJZ4USQu9SYczq5v794aRx34sZg-1743538222787-0.0.1.1-604800000;
+        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:
+      - '860'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '50000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '49999'
+      x-ratelimit-remaining-tokens:
+      - '149999788'
+      x-ratelimit-reset-requests:
+      - 1ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_bf03af6c68765e4393cb60521c5d99ec
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"input": ["Thought: I need to gather relevant URLs based on the search
+      query provided in order to fulfill the task requirements.  Final Answer: The
+      search query or topics were not specified. Please provide specific topics or
+      search query to perform a search for relevant URLs."], "model": "text-embedding-3-small",
+      "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '344'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=wQNqc3BNcaCzhFR4owoCJRMIvs7PWqvy7xmWaIr4k.A-1743538220-1.0.1.1-AIxSGyU_kRiSsc4DYqsunqMwAlAn0fhT.P.7_bBBWTyHeVrexxOSRpm5yj6QmiIVcYwEgdJqk9EsHBy9LfadhgMJ5w8LIrHF_sxBFAXOOxc;
+        _cfuvid=g5w7.LJsKZSYhPzW6M1n.OyrMWQSUF5zX.cFK1vZrQI-1743538220809-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
+      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
+      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
+      50,\n    \"total_tokens\": 50\n  }\n}\n"
+    headers:
+      CF-RAY:
+      - 929abac4a8fc7e07-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:10:24 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1403'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-69ff67f767-88tkx
+      x-envoy-upstream-service-time:
+      - '1369'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999934'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_5a1b9f49c2d200641e58e8cd95ef063a
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
+      completed based on the description, expected output, and actual results.\n\nTask
+      Description:\nPerform a search on specific topics.\n\nExpected Output:\nA list
+      of relevant URLs based on the search query.\n\nActual Output:\nThought: I need
+      to gather relevant URLs based on the search query provided in order to fulfill
+      the task requirements.\n\nFinal Answer: The search query or topics were not
+      specified. Please provide specific topics or search query to perform a search
+      for relevant URLs.\n\nPlease provide:\n- Bullet points suggestions to improve
+      future similar tasks\n- A score from 0 to 10 evaluating on completion, quality,
+      and overall performance- Entities extracted from the task output, if any, their
+      type, description, and relationships"}], "model": "gpt-4o", "tool_choice": {"type":
+      "function", "function": {"name": "TaskEvaluation"}}, "tools": [{"type": "function",
+      "function": {"name": "TaskEvaluation", "description": "Correctly extracted `TaskEvaluation`
+      with all the required parameters with correct types", "parameters": {"$defs":
+      {"Entity": {"properties": {"name": {"description": "The name of the entity.",
+      "title": "Name", "type": "string"}, "type": {"description": "The type of the
+      entity.", "title": "Type", "type": "string"}, "description": {"description":
+      "Description of the entity.", "title": "Description", "type": "string"}, "relationships":
+      {"description": "Relationships of the entity.", "items": {"type": "string"},
+      "title": "Relationships", "type": "array"}}, "required": ["name", "type", "description",
+      "relationships"], "title": "Entity", "type": "object"}}, "properties": {"suggestions":
+      {"description": "Suggestions to improve future similar tasks.", "items": {"type":
+      "string"}, "title": "Suggestions", "type": "array"}, "quality": {"description":
+      "A score from 0 to 10 evaluating on completion, quality, and overall performance,
+      all taking into account the task description, expected output, and the result
+      of the task.", "title": "Quality", "type": "number"}, "entities": {"description":
+      "Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
+      "title": "Entities", "type": "array"}}, "required": ["entities", "quality",
+      "suggestions"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2295'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=26AntG8LjHgDcgN0MYB7TgUTXmoUsQqg8yChWws9CAE-1743538222-1.0.1.1-jo5QRov4A_6L5CaGwhXx2I2aGHzSN6wvrS5Lt2yDpcV5vfTu3FlroYl2d4LBq.ySrtNMDxGQgpsA6fMg0z4iEOXpD5DT7CrJKWRNr4H7Y_k;
+        _cfuvid=.HNP7WFC.O40eZMPSJZ4USQu9SYczq5v794aRx34sZg-1743538222787-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      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-BHcEDk89V0nWfSxs0BaUsqqVYrVxj\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1743538225,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+      \           \"id\": \"call_39zVeoea7WZ0hceVZTcAut7Z\",\n            \"type\":
+      \"function\",\n            \"function\": {\n              \"name\": \"TaskEvaluation\",\n
+      \             \"arguments\": \"{\\\"suggestions\\\":[\\\"Ensure that the search
+      query or specific topics are provided before starting the task.\\\",\\\"Implement
+      error handling to provide more useful output or alternatives when input is insufficient.\\\",\\\"Provide
+      a fallback or a default set of topics in case none are provided.\\\",\\\"Clarify
+      task requirements with stakeholders if the input parameters are unclear.\\\"],\\\"quality\\\":2,\\\"entities\\\":[{\\\"name\\\":\\\"search
+      query\\\",\\\"type\\\":\\\"Requirement\\\",\\\"description\\\":\\\"A parameter
+      needed to perform the search operation.\\\",\\\"relationships\\\":[\\\"Without
+      this entity, the task cannot be completed.\\\"]},{\\\"name\\\":\\\"URLs\\\",\\\"type\\\":\\\"Output\\\",\\\"description\\\":\\\"The
+      expected result from executing the search.\\\",\\\"relationships\\\":[\\\"Expected
+      output when the search query is provided.\\\"]}]}\"\n            }\n          }\n
+      \       ],\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 332,\n    \"completion_tokens\": 137,\n
+      \   \"total_tokens\": 469,\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_898ac29719\"\n}\n"
+    headers:
+      CF-RAY:
+      - 929abad21a6b7dfa-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:10:27 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:
+      - '2597'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '50000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '49999'
+      x-ratelimit-remaining-tokens:
+      - '149999807'
+      x-ratelimit-reset-requests:
+      - 1ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_a5c36be883759cbc3fec575604f8746e
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"input": ["search query(Requirement): A parameter needed to perform the
+      search operation."], "model": "text-embedding-3-small", "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '157'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=MCDkRAmvHC26iz7BEoKzXwq4j5v_FEX5IQepnW5ARp4-1743538221-1.0.1.1-GXJkwk8HCFy9W0tA9R.s3NWzCNJ7wCiaUFu4YCbra4nQNVJa_mN3jdnmfREeET4QfWbYGCQXuM5GHffwtQZ_W1EV3mUC4JFa3w5CCDqO41Y;
+        _cfuvid=mRF3.ZghYObsvTKqmSfcqSbJFV0SBPVk2Psc.9DVGlE-1743538221434-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
+      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"ROL0PMORej0t0sg8z6KUO+Y8VzzWD4m8in05vbWPNz09YVO85LgTO9OzH7zaA2O9kaWivP3zyjzM0EG7szNOPD7Dj7zMiza8KQbJO6gXCz0/FnU9z10JvTIoX70N+T68tS37vKoRuLxLxdI8Ql6xO25cgj0ECIe9bvpFu8gEQr3cLm667/EHvKw8QzsUv+s7QIxeuxCGBryaDMQ7aS7GvJzyw7zGChW9l5ytPDAaBT2B0Yy8K9gbvOFwV71gxyS9v1iVPGJoGb2OovE8J8eQvQ/fvrylMQs9FL9rPVe5u7twmzq8XLYZvUmGGj0rMdQ85uOevGUdu7vvex69yqU2POy9+Lt8BY28XLYZPIXiFz18Shi9FsIcOsyf47xZs+g8IpnUPJew2rzx/+E8XLYZPRLFPj2J1vE7RoNpvVDzjrtgUbs8idZxuWA9Dr0r2Bu9tQUhvVCuA7zPXYm9IFqcuqFlC72JTFu98yptvRZMMzz49mw9s5UKPcVjzTw29F49o0sLO9ZUlDwS9py7mm6APd92qryZ2+W8aV+kPLoWLL07rDE8gKCuOzvAXr2oK7g8JiDJPP2uv7zqCNe8YFE7vNXB+bxLsSU9vJrvPFRx/zsr2Bu8h6tmvf3C7LwdV+s85P2evPjOkrwEHDS7o3NlvX6J0LwiI2s8MBoFPLrRoLzdwQi80UOJvMqlNj1wEaQ8Fn0RPYDlOb2/J7e8ER73u5DNfL0bLGC7QKkPvYC02zuC3+Y8TtwwPFTn6Lw7wF49H/hfvdbeqjxUcX+89EcevKNLCz3oDiq9nPJDPDBzPb1jI469d8OjO586gDxuK6S88f9hO0Cpj7xLsaW7IoUnPEcqsbr2Qcu73cEIPU3wXb2hqhY88RwTvQjos7zYk0w81lSUvX7rjLo0+rG87alLvXofDbxVBBq8UDiavGWTJDxXiN088TBAPEkQsbxZs+i8nqdlPF4mMDx5vdA8wfmJPB1X6zyu3bc7dSIvPIokgTyj/Xu8yupBPJyZCz1df2g9BGG/PFCRUjrOyu48J4KFu7wQWTys44q8ROL0PKrg2TwIhnc8fI+jvP2aEj30jCk9WSlSvRSXEbyKJAE8brU6vAYCtLzPQFi9IkCcO+H6bbvKG6A8rt03uw9p1bvVwfk86vSpPIWdjDxQOJq8/4CSvVBMRzyHg4y8ZzQZPZFglzyHyBe9qmpwPXwFjTwYi+u7pTGLvLXUwrz6l+E7scO3utaZHzx+idA7Qi3TO4WA2zujkBY9d6ZyPJWigLvBgyC9IiNrvX66LrwitoU75p4TvECpDz0imVQ8gCpFPVve8zuMCgE9w33NPFmz6Lyx1+Q8HbknOWUJDr3PQFi6nDfPvAbuBr0GRz89o6RDubi6wrwpN6c8cEKCvFk9fzwGvai86N1LvagruDvdSx88MC4yvOFw17zrJYi7xtm2vJAvOT24ppU9jr8ivcWoWL1nSMa7KBp2PTTmBD3aqqo7wzjCPP9PNL1NevQ6PetpO8rqQTteJjA9Vb8OPAbuBj0/FnW9uP/NOWWTJD2hqpY85sZtuz3XPD3YOpS7Gxgzvfu0kjzFqFg9iq4XvXV7Zz2VLBc9FGYzPYlMWz1+nf081CmJvOY817yOehc9hVgBPR+C9rwUl5G86pJtuy40hTwG0VU9S9n/O/1ptLyDQaO7H25Jvchd+jvxMMA7o0uLPLE5obwWYOA88TDAvKPVIbwbtva8w31NvNFDiTtVjrC7Yq2kvN3BiLvtCwi7dwgvPYcNI72z7kK83dU1vWR287yeCaK8IlRJvTsiGz2AtNs7fBm6PEvF0ryAKsW86PH4OOtqE7yONYw8RTCEPOZttbsNUvc63C7uPCBanDvK1pQ8cJs6O6pCFj1+/zm73wBBuzebJr2jc+U8gD7yvHpkmLyHg4w8k4uiPBJshr1wr2e7hZ0MvSvsSLwrMdQ7jqLxu6ihIb1uXAI8GwSGO9HNnzw7Ihu9fv+5vHyPI70iyrK85iiqPGtt/rxcLAM9dzkNPXc5DT2hIAA9G9MnvULUGrp62gG9xsUJPIfIl7witoU8vsV6PSsxVDzWrUy9AY9sPLyab7wpBkk9VQQavFtUXby+xXo9FsKcPXV7Zz11mBg8aS7GvGdIxjp18VC9RoPpvEB4MTxXiN28fqaBPK428Lt+iVC8fjCYO6pCFjxuDnO7D98+PCiQ3ztFMAQ9BoxKPZPkWr1Ezkc7FsKcPTmVUz2c8kM8YsFRPH66rjzm4x69GAFVPcPfibxnSMY8g/wXPSJUybv4J0s9mWV8vfQCk7yVooA7KTenvMbZtrwUNVW9xahYvYO3DDzK/m48TXp0u46icbzB3Fi8S9l/vGLVfjxgUbs81Tfjug8QnTzajXk845viPBZ9kTzPcba4GAFVvW6hDb0+CBs9dwgvPEJeMT0WYOC8oSAAPWTs3LzvwKm80RIrPQ35vjxSMsc8d5JFPbWjZDyMAf08h4MMvTC4yLwtvhu88f/hu4rzIjwUv+u7Pn4EPBY4hj300TQ8Bkc/vMUyb7w+ww+9jnoXvTIoX72KJIG9lXGiPAbRVTwknAU9gdGMvGmkrzntM+I9Tg2PPL6xzbw0cBu7XQn/PECMXjxpkIK7njH8O4chULzK/m463C5uPaihIb2OGNu7heKXPPoheD0PJMq8SfyDPBljEb0bBAY9CV4dPJWZ/LpyUNw8XvVRvE5Smjw29F66ATa0PJfhOD1N8N08JlEnvLGvCjyh7yE9WT3/OytOhTxwr+e8C/8RvF6wRjzv1NY8kRsMPczQQb3PcTa8cODFvDJZvbzB+Ym9715tvCJUSb3PQFg8czyvvAEF1jv9mhI9MHM9OzSEyLwokN+8ZWLGOykGybycfNo8k1rEu16cGTwmUae8rJV7vERY3jwEMOE8RM7HO5Usl7y/bEI9VY6wvOp+wDzfz+K7rCiWvOuvHrs2akg6kdYAPQiG97uXsNq8wySVPI4YW7wDuvc7XhIDPZnb5TzYCba8cK9nvSZlVDx39AG8rjZwvO2py7zFY828J8cQvUBkBLwdiEm84RcfPbgwrDzFY827jhhbvB/kMjyTiyK9rAtlvGcX6DyT5Nq7bIqvui15ED03ERC9WZ87vdPHTDwknIU8Y94CvUREsbvdGsG6vPyrvM7K7jxwVi873C5uPDIUMr2sgc680fX5vNhi7jsLRB0962oTPfQWwLw0Pz09ZQkOPQ9VqLxOlyW8Fup2PTKKm7wJXh09pXYWvOy9eLz6l2G8C0QdvW6hjbz4bNa7GaicPEkQsbzDriu90ZzBPGCq8zu6+fo8riLDuz8WdbspN6c8R+Ulu8H5iTxLJw88W/ukvETidLyVmfw8pc/Ou+/xBz0NyGA9jHdmvaNfOLyK8yI8mM2LPLpv5LxXdLC8emSYvMrWlDzBg6A8JOGQPMbFib3INSA8ZzSZvE3w3by8tyC8/zsHu2A9jruRG4y8l7DaPPoheLvBDTe87ZUePbHDtzyMHi696GfiPB8pvjtHoBq8pTELPDBfEDy/Ewo9lbYtvUtsGr1bykY9brU6PP9PtLr7bwc9vLcgvFDzDr0SCso74ebAPOoI1zt+E+e8hfbEvB1X6zycfNq8CIZ3u2dIxjyJTFu8O90PuyuTkLo5gSa9aRqZPJUPZjxl2K88cJu6O76xTTxVegM9717tOnccXLxdf2g8tnuKvPRbyzs+foS8mM2LO/u0kjxgPQ68k7wAPDS1JrzDOEI9MF+QuzBfkLpS2Q69YtX+vCSwsruAtFs8C4moPD4IGzyzqTc84frtO8Uewrw29F67ytYUO1DCMDz0ApM7vMvNuU7IgzzqObU83dW1u/gTnrwSsZG8ROL0vFK83by11MK6YFE7PLh1NzucVIC8HUO+vGtZ0Ttgghk8eb1QvCDQhT23zu85QhmmvNjY17wP8+s8XuEkPU7Ig7xuKyQ9frouvDb0XrzqCFc8EvacOqWKQzsprRC6zJ9ju2DHpDsw6aa8csbFvLbAFTxk7Fy82u81vfoheD05PBu9WZ87vC+HarsEHDS9Qi3TO3wZurwyRZA8qoehu9qNeTzWaEE7Jgycu+Y8V71HoBq9GWMRPIcNo7zUKQk92jTBulIyRzzkuBO8NMnTuj8W9TstXF+8BnidPBLFPjyQuU89R2+8vIPLOTza7zU8ZcSCvHVTDb0PJEo50RKrvINV0Lv7+Z28l2vPO3WYGLz2o4e8PgibPB25J72T5No8uhasPA2gBrxM4oO9MkUQO6P9+zyFnQw8h8gXPVlasLsyips8AiKHvOoIVzxzKII76PF4utgJtjwuNIU886DWPDJZvTuxOaE8sa8KPaDS8Lww6aa63C7uvFtUXTt+nf27ob7DvCKZVDuKOC68h6tmvNHNn7yhvsM89qMHPHNtjbyVti08z3G2vG6E3LpwzJg9LVxfvN3BCL1NevS8msc4vTfMhLwSxb669AITPeS4E72zeNk7Y94CPch6K7yVD+Y7SYaauu82E7pXYAM9AXs/u5O8ALyVQEQ9LXmQOUflpbwNb6i89vy/OpwjojxAvTw8MF+QPCDQBb3FY028oSCAvKPpzjs5sgS8QtQavBJsBr26+fo6PevpvCunPTwGMxI9QAJIOo4ELrsGAjS9yv5uPY4Y2zxZn7u82o15vUC9PLyKJAG8Ge0nvQRNkj2eHU+8AY9svIUK8jyQQ2a9Z0hGPOrDS737Pqm82MSqvKOQFr2j1aE8aV8kvTn3Dzx3fpg8UpQDvMr+7jz6Dcu8+iH4vFDzjjxAqQ86IvuQO6Flizz4E548sU1OvTfgsTyqzKy8MC6yO9GcwbtJmse7W97zOrUZTjo7ZyY8V/7Gu36J0LwPmrO8aaQvPZw3zzwdLxE970rAvN/P4rz4nTS8W4W7PDLPJj1Ol6U81g8JvSfHkLwnx5C7jvCAvLine truncated
+      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
+      14,\n    \"total_tokens\": 14\n  }\n}\n"
+    headers:
+      CF-RAY:
+      - 929abae38c117df4-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:10:28 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '557'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-d44cf9799-vc45q
+      x-envoy-upstream-service-time:
+      - '531'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999980'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_91c495419e7c55b5f7396854da1588bc
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"input": ["URLs(Output): The expected result from executing the search."],
+      "model": "text-embedding-3-small", "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '139'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=MCDkRAmvHC26iz7BEoKzXwq4j5v_FEX5IQepnW5ARp4-1743538221-1.0.1.1-GXJkwk8HCFy9W0tA9R.s3NWzCNJ7wCiaUFu4YCbra4nQNVJa_mN3jdnmfREeET4QfWbYGCQXuM5GHffwtQZ_W1EV3mUC4JFa3w5CCDqO41Y;
+        _cfuvid=mRF3.ZghYObsvTKqmSfcqSbJFV0SBPVk2Psc.9DVGlE-1743538221434-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
+      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
+      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
+      12,\n    \"total_tokens\": 12\n  }\n}\n"
+    headers:
+      CF-RAY:
+      - 929abae938887df4-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 01 Apr 2025 20:10:29 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '199'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-f47df6cdf-hhnd7
+      x-envoy-upstream-service-time:
+      - '105'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999984'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_cfdd836532f45e9c2f03d332153438f6
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/memory/external/test_external_memory.py

@@ -0,0 +1,180 @@
+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
+
+
+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(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
+
+
+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

@@ -2,7 +2,16 @@ import pytest
 
 from crewai.agent import Agent
 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
 
 
@@ -31,6 +40,13 @@ class InternalCrew:
     agents_config = "config/agents.yaml"
     tasks_config = "config/tasks.yaml"
 
+    @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"])
@@ -105,6 +121,20 @@ 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()

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):
         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
@@ -92,23 +83,73 @@ 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/utilities/test_i18n.py

@@ -42,13 +42,3 @@ def test_prompt_file():
     i18n.load_prompts()
     assert isinstance(i18n.retrieve("slices", "role_playing"), str)
     assert i18n.retrieve("slices", "role_playing") == "Lorem ipsum dolor sit amet"
-
-
-def test_language_parameter():
-    i18n = I18N(language="en")
-    i18n.load_prompts()
-    assert isinstance(i18n.slice("role_playing"), str)
-
-    i18n = I18N(language="nonexistent")
-    i18n.load_prompts()
-    assert isinstance(i18n.slice("role_playing"), str)

uv.lock

@@ -695,7 +695,7 @@ 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" },
@@ -745,7 +745,7 @@ dev = [
 
 [[package]]
 name = "crewai-tools"
-version = "0.38.1"
+version = "0.40.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "chromadb" },
@@ -760,9 +760,9 @@ 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]]