new cassette for test

* fix: Call ChromaDB reset before removing storage directory to fix disk I/O errors

* feat: add workflow permissions to stale.yml

* revert rag_storage.py changes

* revert rag_storage.py changes

---------

Co-authored-by: Matt B <mattb@Matts-MacBook-Pro.local>
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -65,7 +65,6 @@ body:
         - '3.10'
         - '3.11'
         - '3.12'
-        - '3.13'
     validations:
       required: true
   - type: input
@@ -113,4 +112,4 @@ body:
       label: Additional context
       description: Add any other context about the problem here.
     validations:
-      required: true
+      required: true

.github/workflows/linter.yml

@@ -13,4 +13,4 @@ jobs:
           pip install ruff
 
       - name: Run Ruff Linter
-        run: ruff check --exclude "templates","__init__.py"
+        run: ruff check

.github/workflows/stale.yml

@@ -1,5 +1,10 @@
 name: Mark stale issues and pull requests
 
+permissions:
+  contents: write
+  issues: write
+  pull-requests: write
+
 on:
   schedule:
     - cron: '10 12 * * *'
@@ -8,9 +13,6 @@ on:
 jobs:
   stale:
     runs-on: ubuntu-latest
-    permissions:
-      issues: write
-      pull-requests: write
     steps:
     - uses: actions/stale@v9
       with:

.github/workflows/tests.yml

@@ -23,7 +23,7 @@ jobs:
 
 
       - name: Set up Python
-        run: uv python install 3.11.9
+        run: uv python install 3.12.8
 
       - name: Install the project
         run: uv sync --dev --all-extras

.pre-commit-config.yaml

@@ -1,9 +1,7 @@
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.4.4
+    rev: v0.8.2
     hooks:
       - id: ruff
         args: ["--fix"]
-        exclude: "templates"
       - id: ruff-format
-        exclude: "templates"

.ruff.toml

@@ -0,0 +1,9 @@
+exclude = [
+    "templates",
+    "__init__.py",
+]
+
+[lint]
+select = [
+    "I", # isort rules
+]

README.md

@@ -44,7 +44,7 @@ To get started with CrewAI, follow these simple steps:
 
 ### 1. Installation
 
-Ensure you have Python >=3.10 <=3.13 installed on your system. CrewAI uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
+Ensure you have Python >=3.10 <=3.12 installed on your system. CrewAI uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
 
 First, install CrewAI:
 

docs/concepts/crews.mdx

@@ -32,7 +32,6 @@ A crew in crewAI represents a collaborative group of agents working together to
 | **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.                                                                                                      |
 | **Output Log File** _(optional)_      | `output_log_file`      | Whether you want to have a file with the complete crew output and execution. You can set it using True and it will default to the folder you are currently in and it will be called logs.txt or passing a string with the full path and name of the file. |
 | **Manager Agent** _(optional)_        | `manager_agent`        | `manager` sets a custom agent that will be used as a manager.                                                                                                                                                                                             |
-| **Manager Callbacks** _(optional)_    | `manager_callbacks`    | `manager_callbacks` takes a list of callback handlers to be executed by the manager agent when a hierarchical process is used.                                                                                                                            |
 | **Prompt File** _(optional)_          | `prompt_file`          | Path to the prompt JSON file to be used for the crew.                                                                                                                                                                                                     |
 | **Planning** *(optional)*             | `planning`             | Adds planning ability to the Crew. When activated before each Crew iteration, all Crew data is sent to an AgentPlanner that will plan the tasks and this plan will be added to each task description.                                                     |
 | **Planning LLM** *(optional)*         | `planning_llm`         | The language model used by the AgentPlanner in a planning process.                                                                                                                                                                                        |
@@ -41,6 +40,155 @@ A crew in crewAI represents a collaborative group of agents working together to
 **Crew Max RPM**: The `max_rpm` attribute sets the maximum number of requests per minute the crew can perform to avoid rate limits and will override individual agents' `max_rpm` settings if you set it.
 </Tip>
 
+## Creating Crews
+
+There are two ways to create crews in CrewAI: using **YAML configuration (recommended)** or defining them **directly in code**.
+
+### YAML Configuration (Recommended)
+
+Using YAML configuration provides a cleaner, more maintainable way to define crews and is consistent with how agents and tasks are defined in CrewAI projects.
+
+After creating your CrewAI project as outlined in the [Installation](/installation) section, you can define your crew in a class that inherits from `CrewBase` and uses decorators to define agents, tasks, and the crew itself.
+
+#### Example Crew Class with Decorators
+
+```python code
+from crewai import Agent, Crew, Task, Process
+from crewai.project import CrewBase, agent, task, crew, before_kickoff, after_kickoff
+
+
+@CrewBase
+class YourCrewName:
+    """Description of your crew"""
+
+    # Paths to your YAML configuration files
+    # To see an example agent and task defined in YAML, checkout the following:
+    # - Task: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
+    # - Agents: https://docs.crewai.com/concepts/agents#yaml-configuration-recommended
+    agents_config = 'config/agents.yaml' 
+    tasks_config = 'config/tasks.yaml' 
+
+    @before_kickoff
+    def prepare_inputs(self, inputs):
+        # Modify inputs before the crew starts
+        inputs['additional_data'] = "Some extra information"
+        return inputs
+
+    @after_kickoff
+    def process_output(self, output):
+        # Modify output after the crew finishes
+        output.raw += "\nProcessed after kickoff."
+        return output
+
+    @agent
+    def agent_one(self) -> Agent:
+        return Agent(
+            config=self.agents_config['agent_one'],
+            verbose=True
+        )
+
+    @agent
+    def agent_two(self) -> Agent:
+        return Agent(
+            config=self.agents_config['agent_two'],
+            verbose=True
+        )
+
+    @task
+    def task_one(self) -> Task:
+        return Task(
+            config=self.tasks_config['task_one']
+        )
+
+    @task
+    def task_two(self) -> Task:
+        return Task(
+            config=self.tasks_config['task_two']
+        )
+
+    @crew
+    def crew(self) -> Crew:
+        return Crew(
+            agents=self.agents,  # Automatically collected by the @agent decorator
+            tasks=self.tasks,    # Automatically collected by the @task decorator. 
+            process=Process.sequential,
+            verbose=True,
+        )
+```
+
+<Note>
+Tasks will be executed in the order they are defined.
+</Note>
+
+The `CrewBase` class, along with these decorators, automates the collection of agents and tasks, reducing the need for manual management.
+
+#### Decorators overview from `annotations.py`
+
+CrewAI provides several decorators in the `annotations.py` file that are used to mark methods within your crew class for special handling:
+
+- `@CrewBase`: Marks the class as a crew base class.
+- `@agent`: Denotes a method that returns an `Agent` object.
+- `@task`: Denotes a method that returns a `Task` object.
+- `@crew`: Denotes the method that returns the `Crew` object.
+- `@before_kickoff`: (Optional) Marks a method to be executed before the crew starts.
+- `@after_kickoff`: (Optional) Marks a method to be executed after the crew finishes.
+
+These decorators help in organizing your crew's structure and automatically collecting agents and tasks without manually listing them.
+
+### Direct Code Definition (Alternative)
+
+Alternatively, you can define the crew directly in code without using YAML configuration files.
+
+```python code
+from crewai import Agent, Crew, Task, Process
+from crewai_tools import YourCustomTool
+
+class YourCrewName:
+    def agent_one(self) -> Agent:
+        return Agent(
+            role="Data Analyst",
+            goal="Analyze data trends in the market",
+            backstory="An experienced data analyst with a background in economics",
+            verbose=True,
+            tools=[YourCustomTool()]
+        )
+
+    def agent_two(self) -> Agent:
+        return Agent(
+            role="Market Researcher",
+            goal="Gather information on market dynamics",
+            backstory="A diligent researcher with a keen eye for detail",
+            verbose=True
+        )
+
+    def task_one(self) -> Task:
+        return Task(
+            description="Collect recent market data and identify trends.",
+            expected_output="A report summarizing key trends in the market.",
+            agent=self.agent_one()
+        )
+
+    def task_two(self) -> Task:
+        return Task(
+            description="Research factors affecting market dynamics.",
+            expected_output="An analysis of factors influencing the market.",
+            agent=self.agent_two()
+        )
+
+    def crew(self) -> Crew:
+        return Crew(
+            agents=[self.agent_one(), self.agent_two()],
+            tasks=[self.task_one(), self.task_two()],
+            process=Process.sequential,
+            verbose=True
+        )
+```
+
+In this example:
+
+- Agents and tasks are defined directly within the class without decorators.
+- We manually create and manage the list of agents and tasks.
+- This approach provides more control but can be less maintainable for larger projects.
 
 ## Crew Output
 
@@ -188,4 +336,4 @@ Then, to replay from a specific task, use:
 crewai replay -t <task_id>
 ```
 
-These commands let you replay from your latest kickoff tasks, still retaining context from previously executed tasks.
+These commands let you replay from your latest kickoff tasks, still retaining context from previously executed tasks.

docs/concepts/knowledge.mdx

@@ -8,8 +8,8 @@ icon: book
 
 ## What is Knowledge?
 
-Knowledge in CrewAI is a powerful system that allows AI agents to access and utilize external information sources during their tasks. 
-Think of it as giving your agents a reference library they can consult while working. 
+Knowledge in CrewAI is a powerful system that allows AI agents to access and utilize external information sources during their tasks.
+Think of it as giving your agents a reference library they can consult while working.
 
 <Info>
   Key benefits of using Knowledge:
@@ -47,8 +47,7 @@ from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSourc
 # Create a knowledge source
 content = "Users name is John. He is 30 years old and lives in San Francisco."
 string_source = StringKnowledgeSource(
-    content=content, 
-    metadata={"preference": "personal"}
+    content=content,
 )
 
 # Create an LLM with a temperature of 0 to ensure deterministic outputs
@@ -74,10 +73,7 @@ crew = Crew(
     tasks=[task],
     verbose=True,
     process=Process.sequential,
-    knowledge={
-      "sources": [string_source], 
-      "metadata": {"preference": "personal"}
-    }, # Enable knowledge by adding the sources here. You can also add more sources to the sources list.
+    knowledge_sources=[string_source], # Enable knowledge by adding the sources here. You can also add more sources to the sources list.
 )
 
 result = crew.kickoff(inputs={"question": "What city does John live in and how old is he?"})
@@ -85,17 +81,6 @@ result = crew.kickoff(inputs={"question": "What city does John live in and how o
 
 ## Knowledge Configuration
 
-### Metadata and Filtering
-
-Knowledge sources support metadata for better organization and filtering. Metadata is used to filter the knowledge sources when querying the knowledge store.
-
-```python Code
-knowledge_source = StringKnowledgeSource(
-    content="Users name is John. He is 30 years old and lives in San Francisco.",
-    metadata={"preference": "personal"} # Metadata is used to filter the knowledge sources
-)
-```
-
 ### Chunking Configuration
 
 Control how content is split for processing by setting the chunk size and overlap.
@@ -116,21 +101,27 @@ You can also configure the embedder for the knowledge store. This is useful if y
 ...
 string_source = StringKnowledgeSource(
     content="Users name is John. He is 30 years old and lives in San Francisco.",
-    metadata={"preference": "personal"}
 )
 crew = Crew(
     ...
-    knowledge={
-        "sources": [string_source],
-        "metadata": {"preference": "personal"},
-        "embedder_config": {
-          "provider": "openai", # Default embedder provider; can be "ollama", "gemini", e.t.c.
-          "config": {"model": "text-embedding-3-small"} # Default embedder model; can be "mxbai-embed-large", "nomic-embed-tex", e.t.c.
-        },
+    knowledge_sources=[string_source],
+    embedder={
+        "provider": "openai",
+        "config": {"model": "text-embedding-3-small"},
     },
 )
 ```
 
+## Clearing Knowledge
+
+If you need to clear the knowledge stored in CrewAI, you can use the `crewai reset-memories` command with the `--knowledge` option.
+
+```bash Command
+crewai reset-memories --knowledge
+```
+
+This is useful when you've updated your knowledge sources and want to ensure that the agents are using the most recent information.
+
 ## Custom Knowledge Sources
 
 CrewAI allows you to create custom knowledge sources for any type of data by extending the `BaseKnowledgeSource` class. Let's create a practical example that fetches and processes space news articles.
@@ -149,10 +140,10 @@ from pydantic import BaseModel, Field
 
 class SpaceNewsKnowledgeSource(BaseKnowledgeSource):
     """Knowledge source that fetches data from Space News API."""
-    
+
     api_endpoint: str = Field(description="API endpoint URL")
     limit: int = Field(default=10, description="Number of articles to fetch")
-    
+
     def load_content(self) -> Dict[Any, str]:
         """Fetch and format space news articles."""
         try:
@@ -160,26 +151,26 @@ class SpaceNewsKnowledgeSource(BaseKnowledgeSource):
                 f"{self.api_endpoint}?limit={self.limit}"
             )
             response.raise_for_status()
-            
+
             data = response.json()
             articles = data.get('results', [])
-            
+
             formatted_data = self._format_articles(articles)
             return {self.api_endpoint: formatted_data}
         except Exception as e:
             raise ValueError(f"Failed to fetch space news: {str(e)}")
-    
+
     def _format_articles(self, articles: list) -> str:
         """Format articles into readable text."""
         formatted = "Space News Articles:\n\n"
         for article in articles:
             formatted += f"""
-Title: {article['title']}
-Published: {article['published_at']}
-Summary: {article['summary']}
-News Site: {article['news_site']}
-URL: {article['url']}
--------------------"""
+                Title: {article['title']}
+                Published: {article['published_at']}
+                Summary: {article['summary']}
+                News Site: {article['news_site']}
+                URL: {article['url']}
+                -------------------"""
         return formatted
 
     def add(self) -> None:
@@ -188,25 +179,20 @@ URL: {article['url']}
         for _, text in content.items():
             chunks = self._chunk_text(text)
             self.chunks.extend(chunks)
-        
-        self.save_documents(metadata={
-            "source": "space_news_api",
-            "timestamp": datetime.now().isoformat(),
-            "article_count": self.limit
-        })
+
+        self._save_documents()
 
 # Create knowledge source
 recent_news = SpaceNewsKnowledgeSource(
     api_endpoint="https://api.spaceflightnewsapi.net/v4/articles",
     limit=10,
-    metadata={"category": "recent_news", "source": "spaceflight_news"}
 )
 
 # Create specialized agent
 space_analyst = Agent(
     role="Space News Analyst",
     goal="Answer questions about space news accurately and comprehensively",
-    backstory="""You are a space industry analyst with expertise in space exploration, 
+    backstory="""You are a space industry analyst with expertise in space exploration,
     satellite technology, and space industry trends. You excel at answering questions
     about space news and providing detailed, accurate information.""",
     knowledge_sources=[recent_news],
@@ -233,13 +219,14 @@ result = crew.kickoff(
     inputs={"user_question": "What are the latest developments in space exploration?"}
 )
 ```
+
 ```output Output
 # Agent: Space News Analyst
 ## Task: Answer this question about space news: What are the latest developments in space exploration?
 
 
 # Agent: Space News Analyst
-## Final Answer: 
+## Final Answer:
 The latest developments in space exploration, based on recent space news articles, include the following:
 
 1. SpaceX has received the final regulatory approvals to proceed with the second integrated Starship/Super Heavy launch, scheduled for as soon as the morning of Nov. 17, 2023. This is a significant step in SpaceX's ambitious plans for space exploration and colonization. [Source: SpaceNews](https://spacenews.com/starship-cleared-for-nov-17-launch/)
@@ -255,23 +242,27 @@ The latest developments in space exploration, based on recent space news article
 6. The National Natural Science Foundation of China has outlined a five-year project for researchers to study the assembly of ultra-large spacecraft. This could lead to significant advancements in spacecraft technology and space exploration capabilities. [Source: SpaceNews](https://spacenews.com/china-researching-challenges-of-kilometer-scale-ultra-large-spacecraft/)
 
 7. The Center for AEroSpace Autonomy Research (CAESAR) at Stanford University is focusing on spacecraft autonomy. The center held a kickoff event on May 22, 2024, to highlight the industry, academia, and government collaboration it seeks to foster. This could lead to significant advancements in autonomous spacecraft technology. [Source: SpaceNews](https://spacenews.com/stanford-center-focuses-on-spacecraft-autonomy/)
-``` 
+```
+
 </CodeGroup>
 #### Key Components Explained
 
 1. **Custom Knowledge Source (`SpaceNewsKnowledgeSource`)**:
+
    - Extends `BaseKnowledgeSource` for integration with CrewAI
    - Configurable API endpoint and article limit
    - Implements three key methods:
      - `load_content()`: Fetches articles from the API
      - `_format_articles()`: Structures the articles into readable text
-     - `add()`: Processes and stores the content with metadata
+     - `add()`: Processes and stores the content
 
 2. **Agent Configuration**:
+
    - Specialized role as a Space News Analyst
    - Uses the knowledge source to access space news
 
 3. **Task Setup**:
+
    - Takes a user question as input through `{user_question}`
    - Designed to provide detailed answers based on the knowledge source
 
@@ -280,6 +271,7 @@ The latest developments in space exploration, based on recent space news article
    - Handles input/output through the kickoff method
 
 This example demonstrates how to:
+
 - Create a custom knowledge source that fetches real-time data
 - Process and format external data for AI consumption
 - Use the knowledge source to answer specific user questions
@@ -287,26 +279,26 @@ This example demonstrates how to:
 
 #### About the Spaceflight News API
 
-The example uses the [Spaceflight News API](https://api.spaceflightnewsapi.net/v4/documentation), which:
+The example uses the [Spaceflight News API](https://api.spaceflightnewsapi.net/v4/docs/), which:
+
 - Provides free access to space-related news articles
 - Requires no authentication
 - Returns structured data about space news
 - Supports pagination and filtering
 
 You can customize the API query by modifying the endpoint URL:
+
 ```python
 # Fetch more articles
 recent_news = SpaceNewsKnowledgeSource(
     api_endpoint="https://api.spaceflightnewsapi.net/v4/articles",
     limit=20,  # Increase the number of articles
-    metadata={"category": "recent_news"}
 )
 
 # Add search parameters
 recent_news = SpaceNewsKnowledgeSource(
     api_endpoint="https://api.spaceflightnewsapi.net/v4/articles?search=NASA", # Search for NASA news
     limit=10,
-    metadata={"category": "nasa_news"}
 )
 ```
 
@@ -314,16 +306,14 @@ recent_news = SpaceNewsKnowledgeSource(
 
 <AccordionGroup>
   <Accordion title="Content Organization">
-    - Use descriptive metadata for better filtering
     - Keep chunk sizes appropriate for your content type
     - Consider content overlap for context preservation
     - Organize related information into separate knowledge sources
   </Accordion>
-  
+
   <Accordion title="Performance Tips">
-    - Use metadata filtering to narrow search scope
-    - Adjust chunk sizes based on content complexity
+    - Adjust chunk sizes based on content complexity 
     - Configure appropriate embedding models
     - Consider using local embedding providers for faster processing
   </Accordion>
-</AccordionGroup>
+</AccordionGroup>

docs/concepts/llms.mdx

@@ -29,7 +29,7 @@ Large Language Models (LLMs) are the core intelligence behind CrewAI agents. The
 
 ## Available Models and Their Capabilities
 
-Here's a detailed breakdown of supported models and their capabilities:
+Here's a detailed breakdown of supported models and their capabilities, you can compare performance at [lmarena.ai](https://lmarena.ai/):
 
 <Tabs>
   <Tab title="OpenAI">
@@ -43,6 +43,92 @@ Here's a detailed breakdown of supported models and their capabilities:
       1 token ≈ 4 characters in English. For example, 8,192 tokens ≈ 32,768 characters or about 6,000 words.
     </Note>
   </Tab>
+  <Tab title="Nvidia NIM">
+    | Model | Context Window | Best For |
+    |-------|---------------|-----------|
+    | nvidia/mistral-nemo-minitron-8b-8k-instruct | 8,192 tokens | State-of-the-art small language model delivering superior accuracy for chatbot, virtual assistants, and content generation. |
+    | nvidia/nemotron-4-mini-hindi-4b-instruct| 4,096 tokens | A bilingual Hindi-English SLM for on-device inference, tailored specifically for Hindi Language. |
+    | "nvidia/llama-3.1-nemotron-70b-instruct | 128k tokens | Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA in order to improve the helpfulness of LLM generated responses. |
+    | nvidia/llama3-chatqa-1.5-8b | 128k tokens | Advanced LLM to generate high-quality, context-aware responses for chatbots and search engines. |
+    | nvidia/llama3-chatqa-1.5-70b | 128k tokens | Advanced LLM to generate high-quality, context-aware responses for chatbots and search engines. |
+    | nvidia/vila | 128k tokens | Multi-modal vision-language model that understands text/img/video and creates informative responses |
+    | nvidia/neva-22| 4,096 tokens | Multi-modal vision-language model that understands text/images and generates informative responses |
+    | nvidia/nemotron-mini-4b-instruct | 8,192 tokens | General-purpose tasks |
+    | nvidia/usdcode-llama3-70b-instruct | 128k tokens | State-of-the-art LLM that answers OpenUSD knowledge queries and generates USD-Python code. |
+    | nvidia/nemotron-4-340b-instruct | 4,096 tokens | Creates diverse synthetic data that mimics the characteristics of real-world data. |
+    | meta/codellama-70b | 100k tokens | LLM capable of generating code from natural language and vice versa. |
+    | meta/llama2-70b | 4,096 tokens | Cutting-edge large language AI model capable of generating text and code in response to prompts. |
+    | meta/llama3-8b-instruct | 8,192 tokens | Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation. |
+    | meta/llama3-70b-instruct | 8,192 tokens | Powers complex conversations with superior contextual understanding, reasoning and text generation. |
+    | meta/llama-3.1-8b-instruct | 128k tokens | Advanced state-of-the-art model with language understanding, superior reasoning, and text generation. |
+    | meta/llama-3.1-70b-instruct | 128k tokens | Powers complex conversations with superior contextual understanding, reasoning and text generation. |
+    | meta/llama-3.1-405b-instruct | 128k tokens | Advanced LLM for synthetic data generation, distillation, and inference for chatbots, coding, and domain-specific tasks. |
+    | meta/llama-3.2-1b-instruct | 128k tokens | Advanced state-of-the-art small language model with language understanding, superior reasoning, and text generation. |
+    | meta/llama-3.2-3b-instruct | 128k tokens | Advanced state-of-the-art small language model with language understanding, superior reasoning, and text generation. |
+    | meta/llama-3.2-11b-vision-instruct | 128k tokens | Advanced state-of-the-art small language model with language understanding, superior reasoning, and text generation. |
+    | meta/llama-3.2-90b-vision-instruct | 128k tokens | Advanced state-of-the-art small language model with language understanding, superior reasoning, and text generation. |
+    | meta/llama-3.1-70b-instruct | 128k tokens | Powers complex conversations with superior contextual understanding, reasoning and text generation. |
+    | google/gemma-7b | 8,192 tokens | Cutting-edge text generation model text understanding, transformation, and code generation. |
+    | google/gemma-2b | 8,192 tokens | Cutting-edge text generation model text understanding, transformation, and code generation. |
+    | google/codegemma-7b | 8,192 tokens | Cutting-edge model built on Google's Gemma-7B specialized for code generation and code completion. |
+    | google/codegemma-1.1-7b | 8,192 tokens | Advanced programming model for code generation, completion, reasoning, and instruction following. |
+    | google/recurrentgemma-2b | 8,192 tokens | Novel recurrent architecture based language model for faster inference when generating long sequences. |
+    | google/gemma-2-9b-it | 8,192 tokens | Cutting-edge text generation model text understanding, transformation, and code generation. |
+    | google/gemma-2-27b-it | 8,192 tokens | Cutting-edge text generation model text understanding, transformation, and code generation. |
+    | google/gemma-2-2b-it | 8,192 tokens | Cutting-edge text generation model text understanding, transformation, and code generation. |
+    | google/deplot | 512 tokens | One-shot visual language understanding model that translates images of plots into tables. |
+    | google/paligemma | 8,192 tokens | Vision language model adept at comprehending text and visual inputs to produce informative responses. |
+    | mistralai/mistral-7b-instruct-v0.2 | 32k tokens | This LLM follows instructions, completes requests, and generates creative text. |
+    | mistralai/mixtral-8x7b-instruct-v0.1 | 8,192 tokens | An MOE LLM that follows instructions, completes requests, and generates creative text. |
+    | mistralai/mistral-large | 4,096 tokens | Creates diverse synthetic data that mimics the characteristics of real-world data. |
+    | mistralai/mixtral-8x22b-instruct-v0.1 | 8,192 tokens | Creates diverse synthetic data that mimics the characteristics of real-world data. |
+    | mistralai/mistral-7b-instruct-v0.3 | 32k tokens | This LLM follows instructions, completes requests, and generates creative text. |
+    | nv-mistralai/mistral-nemo-12b-instruct | 128k tokens | Most advanced language model for reasoning, code, multilingual tasks; runs on a single GPU. |
+    | mistralai/mamba-codestral-7b-v0.1 | 256k tokens | Model for writing and interacting with code across a wide range of programming languages and tasks. |
+    | microsoft/phi-3-mini-128k-instruct | 128K tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
+    | microsoft/phi-3-mini-4k-instruct | 4,096 tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
+    | microsoft/phi-3-small-8k-instruct | 8,192 tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
+    | microsoft/phi-3-small-128k-instruct | 128K tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
+    | microsoft/phi-3-medium-4k-instruct | 4,096 tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
+    | microsoft/phi-3-medium-128k-instruct | 128K tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
+    | microsoft/phi-3.5-mini-instruct | 128K tokens | Lightweight multilingual LLM powering AI applications in latency bound, memory/compute constrained environments |
+    | microsoft/phi-3.5-moe-instruct | 128K tokens | Advanced LLM based on Mixture of Experts architecure to deliver compute efficient content generation |
+    | microsoft/kosmos-2 | 1,024 tokens | Groundbreaking multimodal model designed to understand and reason about visual elements in images. |
+    | microsoft/phi-3-vision-128k-instruct | 128k tokens | Cutting-edge open multimodal model exceling in high-quality reasoning from images. |
+    | microsoft/phi-3.5-vision-instruct | 128k tokens | Cutting-edge open multimodal model exceling in high-quality reasoning from images. |
+    | databricks/dbrx-instruct | 12k tokens | A general-purpose LLM with state-of-the-art performance in language understanding, coding, and RAG. |
+    | snowflake/arctic | 1,024 tokens | Delivers high efficiency inference for enterprise applications focused on SQL generation and coding. |
+    | aisingapore/sea-lion-7b-instruct | 4,096 tokens | LLM to represent and serve the linguistic and cultural diversity of Southeast Asia |
+    | ibm/granite-8b-code-instruct | 4,096 tokens | Software programming LLM for code generation, completion, explanation, and multi-turn conversion. |
+    | ibm/granite-34b-code-instruct | 8,192 tokens | Software programming LLM for code generation, completion, explanation, and multi-turn conversion. |
+    | ibm/granite-3.0-8b-instruct | 4,096 tokens | Advanced Small Language Model supporting RAG, summarization, classification, code, and agentic AI |
+    | ibm/granite-3.0-3b-a800m-instruct | 4,096 tokens | Highly efficient Mixture of Experts model for RAG, summarization, entity extraction, and classification |
+    | mediatek/breeze-7b-instruct | 4,096 tokens | Creates diverse synthetic data that mimics the characteristics of real-world data. |
+    | upstage/solar-10.7b-instruct | 4,096 tokens | Excels in NLP tasks, particularly in instruction-following, reasoning, and mathematics. |
+    | writer/palmyra-med-70b-32k | 32k tokens | Leading LLM for accurate, contextually relevant responses in the medical domain. |
+    | writer/palmyra-med-70b | 32k tokens | Leading LLM for accurate, contextually relevant responses in the medical domain. |
+    | writer/palmyra-fin-70b-32k | 32k tokens | Specialized LLM for financial analysis, reporting, and data processing |
+    | 01-ai/yi-large | 32k tokens | Powerful model trained on English and Chinese for diverse tasks including chatbot and creative writing. |
+    | deepseek-ai/deepseek-coder-6.7b-instruct | 2k tokens | Powerful coding model offering advanced capabilities in code generation, completion, and infilling |
+    | rakuten/rakutenai-7b-instruct | 1,024 tokens | Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation. |
+    | rakuten/rakutenai-7b-chat | 1,024 tokens | Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation. |
+    | baichuan-inc/baichuan2-13b-chat | 4,096 tokens | Support Chinese and English chat, coding, math, instruction following, solving quizzes |
+
+    <Note>
+      NVIDIA's NIM support for models is expanding continuously! For the most up-to-date list of available models, please visit build.nvidia.com.
+    </Note>
+  </Tab>
+  <Tab title="Gemini">
+    | Model | Context Window | Best For |
+    |-------|---------------|-----------|
+    | Gemini 1.5 Flash | 1M tokens | Balanced multimodal model, good for most tasks |
+    | Gemini 1.5 Flash 8B | 1M tokens | Fastest, most cost-efficient, good for high-frequency tasks |
+    | Gemini 1.5 Pro | 2M tokens | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
+
+    <Tip>
+      Google's Gemini models are all multimodal, supporting audio, images, video and text, supporting context caching, json schema, function calling, etc.
+    </Tip>
+  </Tab>
   <Tab title="Groq">
     | Model | Context Window | Best For |
     |-------|---------------|-----------|
@@ -128,10 +214,10 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
         # llm: anthropic/claude-2.1
         # llm: anthropic/claude-2.0
 
-        # Google Models - Good for general tasks
-        # llm: gemini/gemini-pro
+        # Google Models - Strong reasoning, large cachable context window, multimodal
         # llm: gemini/gemini-1.5-pro-latest
-        # llm: gemini/gemini-1.0-pro-latest
+        # llm: gemini/gemini-1.5-flash-latest
+        # llm: gemini/gemini-1.5-flash-8b-latest
 
         # AWS Bedrock Models - Enterprise-grade
         # llm: bedrock/anthropic.claude-3-sonnet-20240229-v1:0
@@ -350,13 +436,18 @@ Learn how to get the most out of your LLM configuration:
 
   <Accordion title="Google">
     ```python Code
+    # Option 1. Gemini accessed with an API key.
+    # https://ai.google.dev/gemini-api/docs/api-key
     GEMINI_API_KEY=<your-api-key>
+
+    # Option 2. Vertex AI IAM credentials for Gemini, Anthropic, and anything in the Model Garden.
+    # https://cloud.google.com/vertex-ai/generative-ai/docs/overview
     ```
 
     Example usage:
     ```python Code
     llm = LLM(
-        model="gemini/gemini-pro",
+        model="gemini/gemini-1.5-pro-latest",
         temperature=0.7
     )
     ```
@@ -412,6 +503,20 @@ Learn how to get the most out of your LLM configuration:
     ```
   </Accordion>
 
+  <Accordion title="Nvidia NIM">
+    ```python Code
+    NVIDIA_API_KEY=<your-api-key>
+    ```
+
+    Example usage:
+    ```python Code
+    llm = LLM(
+        model="nvidia_nim/meta/llama3-70b-instruct",
+        temperature=0.7
+    )
+    ```
+  </Accordion>
+
   <Accordion title="Groq">
     ```python Code
     GROQ_API_KEY=<your-api-key>
@@ -502,20 +607,6 @@ Learn how to get the most out of your LLM configuration:
     ```
   </Accordion>
 
-  <Accordion title="Nvidia NIM">
-    ```python Code
-    NVIDIA_API_KEY=<your-api-key>
-    ```
-
-    Example usage:
-    ```python Code
-    llm = LLM(
-        model="nvidia_nim/meta/llama3-70b-instruct",
-        temperature=0.7
-    )
-    ```
-  </Accordion>
-
   <Accordion title="SambaNova">
     ```python Code
     SAMBANOVA_API_KEY=<your-api-key>

docs/concepts/tools.mdx

@@ -172,6 +172,48 @@ def my_tool(question: str) -> str:
     return "Result from your custom tool"
 ```
 
+### Structured Tools
+
+The `StructuredTool` class wraps functions as tools, providing flexibility and validation while reducing boilerplate. It supports custom schemas and dynamic logic for seamless integration of complex functionalities.
+
+#### Example:
+Using `StructuredTool.from_function`, you can wrap a function that interacts with an external API or system, providing a structured interface. This enables robust validation and consistent execution, making it easier to integrate complex functionalities into your applications as demonstrated in the following example:
+
+```python
+from crewai.tools.structured_tool import CrewStructuredTool
+from pydantic import BaseModel
+
+# Define the schema for the tool's input using Pydantic
+class APICallInput(BaseModel):
+    endpoint: str
+    parameters: dict
+
+# Wrapper function to execute the API call
+def tool_wrapper(*args, **kwargs):
+    # Here, you would typically call the API using the parameters
+    # For demonstration, we'll return a placeholder string
+    return f"Call the API at {kwargs['endpoint']} with parameters {kwargs['parameters']}"
+
+# Create and return the structured tool
+def create_structured_tool():
+    return CrewStructuredTool.from_function(
+        name='Wrapper API',
+        description="A tool to wrap API calls with structured input.",
+        args_schema=APICallInput,
+        func=tool_wrapper,
+    )
+
+# Example usage
+structured_tool = create_structured_tool()
+
+# Execute the tool with structured input
+result = structured_tool._run(**{
+    "endpoint": "https://example.com/api",
+    "parameters": {"key1": "value1", "key2": "value2"}
+})
+print(result)  # Output: Call the API at https://example.com/api with parameters {'key1': 'value1', 'key2': 'value2'}
+```
+
 ### Custom Caching Mechanism
 
 <Tip>

docs/how-to/agentops-observability.mdx

@@ -57,7 +57,7 @@ This feature is useful for debugging and understanding how agents interact with
    <Step title="Install AgentOps">
       Install AgentOps with:
       ```bash
-      pip install crewai[agentops]
+      pip install 'crewai[agentops]'
       ```
       or
       ```bash

docs/installation.mdx

@@ -7,7 +7,7 @@ icon: wrench
 <Note>
   **Python Version Requirements**
   
-  CrewAI requires `Python >=3.10 and <=3.13`. Here's how to check your version:
+  CrewAI requires `Python >=3.10 and <=3.12`. Here's how to check your version:
   ```bash
   python3 --version
   ```

pyproject.toml

@@ -1,9 +1,9 @@
 [project]
 name = "crewai"
-version = "0.85.0"
+version = "0.86.0"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
-requires-python = ">=3.10,<=3.13"
+requires-python = ">=3.10,<=3.12"
 authors = [
     { name = "Joao Moura", email = "joao@crewai.com" }
 ]
@@ -15,7 +15,6 @@ dependencies = [
     "opentelemetry-exporter-otlp-proto-http>=1.22.0",
     "instructor>=1.3.3",
     "regex>=2024.9.11",
-    "crewai-tools>=0.14.0",
     "click>=8.1.7",
     "python-dotenv>=1.0.0",
     "appdirs>=1.4.4",
@@ -27,9 +26,10 @@ dependencies = [
     "uv>=0.4.25",
     "tomli-w>=1.1.0",
     "tomli>=2.0.2",
-    "chromadb>=0.5.18",
+    "chromadb>=0.5.23",
     "pdfplumber>=0.11.4",
     "openpyxl>=3.1.5",
+    "blinker>=1.9.0",
 ]
 
 [project.urls]
@@ -38,7 +38,7 @@ Documentation = "https://docs.crewai.com"
 Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
-tools = ["crewai-tools>=0.14.0"]
+tools = ["crewai-tools>=0.17.0"]
 agentops = ["agentops>=0.3.0"]
 fastembed = ["fastembed>=0.4.1"]
 pdfplumber = [
@@ -54,7 +54,7 @@ mem0 = ["mem0ai>=0.1.29"]
 
 [tool.uv]
 dev-dependencies = [
-    "ruff>=0.4.10",
+    "ruff>=0.8.2",
     "mypy>=1.10.0",
     "pre-commit>=3.6.0",
     "mkdocs>=1.4.3",
@@ -64,7 +64,7 @@ dev-dependencies = [
     "mkdocs-material-extensions>=1.3.1",
     "pillow>=10.2.0",
     "cairosvg>=2.7.1",
-    "crewai-tools>=0.14.0",
+    "crewai-tools>=0.17.0",
     "pytest>=8.0.0",
     "pytest-vcr>=1.0.2",
     "python-dotenv>=1.0.0",

src/crewai/__init__.py

@@ -14,7 +14,7 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.85.0"
+__version__ = "0.86.0"
 __all__ = [
     "Agent",
     "Crew",

src/crewai/agent.py

@@ -8,7 +8,7 @@ from pydantic import Field, InstanceOf, PrivateAttr, model_validator
 from crewai.agents import CacheHandler
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.crew_agent_executor import CrewAgentExecutor
-from crewai.cli.constants import ENV_VARS
+from crewai.cli.constants import ENV_VARS, LITELLM_PARAMS
 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
@@ -23,27 +23,19 @@ from crewai.utilities.converter import generate_model_description
 from crewai.utilities.token_counter_callback import TokenCalcHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
 
+agentops = None
 
-def mock_agent_ops_provider():
-    def track_agent(*args, **kwargs):
+try:
+    import agentops  # type: ignore # Name "agentops" is already defined
+    from agentops import track_agent  # type: ignore
+except ImportError:
+
+    def track_agent():
         def noop(f):
             return f
 
         return noop
 
-    return track_agent
-
-
-agentops = None
-
-if os.environ.get("AGENTOPS_API_KEY"):
-    try:
-        from agentops import track_agent
-    except ImportError:
-        track_agent = mock_agent_ops_provider()
-else:
-    track_agent = mock_agent_ops_provider()
-
 
 @track_agent()
 class Agent(BaseAgent):
@@ -181,20 +173,11 @@ class Agent(BaseAgent):
                         if key_name and key_name not in unaccepted_attributes:
                             env_value = os.environ.get(key_name)
                             if env_value:
-                                # Map key names containing "API_KEY" to "api_key"
-                                key_name = (
-                                    "api_key" if "API_KEY" in key_name else key_name
-                                )
-                                # Map key names containing "API_BASE" to "api_base"
-                                key_name = (
-                                    "api_base" if "API_BASE" in key_name else key_name
-                                )
-                                # Map key names containing "API_VERSION" to "api_version"
-                                key_name = (
-                                    "api_version"
-                                    if "API_VERSION" in key_name
-                                    else key_name
-                                )
+                                key_name = key_name.lower()
+                                for pattern in LITELLM_PARAMS:
+                                    if pattern in key_name:
+                                        key_name = pattern
+                                        break
                                 llm_params[key_name] = env_value
                         # Check for default values if the environment variable is not set
                         elif env_var.get("default", False):

src/crewai/agents/crew_agent_executor.py

@@ -143,6 +143,9 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         tool_result = self._execute_tool_and_check_finality(
                             formatted_answer
                         )
+                        if self.step_callback:
+                            self.step_callback(tool_result)
+
                         formatted_answer.text += f"\nObservation: {tool_result.result}"
                         formatted_answer.result = tool_result.result
                         if tool_result.result_as_answer:
@@ -299,7 +302,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         self._i18n.slice("summarizer_system_message"), role="system"
                     ),
                     self._format_msg(
-                        self._i18n.slice("sumamrize_instruction").format(group=group),
+                        self._i18n.slice("summarize_instruction").format(group=group),
                     ),
                 ],
                 callbacks=self.callbacks,
@@ -410,7 +413,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         """
         while self.ask_for_human_input:
             human_feedback = self._ask_human_input(formatted_answer.output)
-            print("Human feedback: ", human_feedback)
 
             if self.crew and self.crew._train:
                 self._handle_crew_training_output(formatted_answer, human_feedback)

src/crewai/agents/parser.py

@@ -1,5 +1,6 @@
 import re
 from typing import Any, Union
+
 from json_repair import repair_json
 
 from crewai.utilities import I18N

src/crewai/cli/authentication/main.py

@@ -5,9 +5,10 @@ from typing import Any, Dict
 import requests
 from rich.console import Console
 
+from crewai.cli.tools.main import ToolCommand
+
 from .constants import AUTH0_AUDIENCE, AUTH0_CLIENT_ID, AUTH0_DOMAIN
 from .utils import TokenManager, validate_token
-from crewai.cli.tools.main import ToolCommand
 
 console = Console()
 
@@ -79,7 +80,9 @@ class AuthenticationCommand:
                         style="yellow",
                     )
 
-                console.print("\n[bold green]Welcome to CrewAI Enterprise![/bold green]\n")
+                console.print(
+                    "\n[bold green]Welcome to CrewAI Enterprise![/bold green]\n"
+                )
                 return
 
             if token_data["error"] not in ("authorization_pending", "slow_down"):

src/crewai/cli/authentication/token.py

@@ -1,10 +1,9 @@
 from .utils import TokenManager
 
+
 def get_auth_token() -> str:
     """Get the authentication token."""
     access_token = TokenManager().get_token()
     if not access_token:
         raise Exception()
     return access_token
-
-

src/crewai/cli/cli.py

@@ -1,7 +1,7 @@
+from importlib.metadata import version as get_version
 from typing import Optional
 
 import click
-import pkg_resources
 
 from crewai.cli.add_crew_to_flow import add_crew_to_flow
 from crewai.cli.create_crew import create_crew
@@ -25,6 +25,7 @@ from .update_crew import update_crew
 
 
 @click.group()
+@click.version_option(get_version("crewai"))
 def crewai():
     """Top-level command group for crewai."""
 
@@ -50,14 +51,17 @@ def create(type, name, provider, skip_provider=False):
 )
 def version(tools):
     """Show the installed version of crewai."""
-    crewai_version = pkg_resources.get_distribution("crewai").version
+    try:
+        crewai_version = get_version("crewai")
+    except Exception:
+        crewai_version = "unknown version"
     click.echo(f"crewai version: {crewai_version}")
 
     if tools:
         try:
-            tools_version = pkg_resources.get_distribution("crewai-tools").version
+            tools_version = get_version("crewai")
             click.echo(f"crewai tools version: {tools_version}")
-        except pkg_resources.DistributionNotFound:
+        except Exception:
             click.echo("crewai tools not installed")
 
 

src/crewai/cli/command.py

@@ -1,8 +1,9 @@
 import requests
 from requests.exceptions import JSONDecodeError
 from rich.console import Console
-from crewai.cli.plus_api import PlusAPI
+
 from crewai.cli.authentication.token import get_auth_token
+from crewai.cli.plus_api import PlusAPI
 from crewai.telemetry.telemetry import Telemetry
 
 console = Console()

src/crewai/cli/config.py

@@ -1,13 +1,19 @@
 import json
 from pathlib import Path
-from pydantic import BaseModel, Field
 from typing import Optional
 
+from pydantic import BaseModel, Field
+
 DEFAULT_CONFIG_PATH = Path.home() / ".config" / "crewai" / "settings.json"
 
+
 class Settings(BaseModel):
-    tool_repository_username: Optional[str] = Field(None, description="Username for interacting with the Tool Repository")
-    tool_repository_password: Optional[str] = Field(None, description="Password for interacting with the Tool Repository")
+    tool_repository_username: Optional[str] = Field(
+        None, description="Username for interacting with the Tool Repository"
+    )
+    tool_repository_password: Optional[str] = Field(
+        None, description="Password for interacting with the Tool Repository"
+    )
     config_path: Path = Field(default=DEFAULT_CONFIG_PATH, exclude=True)
 
     def __init__(self, config_path: Path = DEFAULT_CONFIG_PATH, **data):

src/crewai/cli/constants.py

@@ -159,3 +159,6 @@ MODELS = {
 }
 
 JSON_URL = "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json"
+
+
+LITELLM_PARAMS = ["api_key", "api_base", "api_version"]

src/crewai/cli/plus_api.py

@@ -1,9 +1,11 @@
-from typing import Optional
-import requests
 from os import getenv
-from crewai.cli.version import get_crewai_version
+from typing import Optional
 from urllib.parse import urljoin
 
+import requests
+
+from crewai.cli.version import get_crewai_version
+
 
 class PlusAPI:
     """

src/crewai/cli/reset_memories_command.py

@@ -1,11 +1,12 @@
 import subprocess
+
 import click
 
+from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
 from crewai.memory.entity.entity_memory import EntityMemory
 from crewai.memory.long_term.long_term_memory import LongTermMemory
 from crewai.memory.short_term.short_term_memory import ShortTermMemory
 from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
-from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
 
 
 def reset_memories_command(

src/crewai/cli/templates/crew/README.md

@@ -4,7 +4,7 @@ Welcome to the {{crew_name}} Crew project, powered by [crewAI](https://crewai.co
 
 ## Installation
 
-Ensure you have Python >=3.10 <=3.13 installed on your system. This project uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
+Ensure you have Python >=3.10 <=3.12 installed on your system. This project uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
 
 First, if you haven't already, install uv:
 

src/crewai/cli/templates/crew/config/tasks.yaml

@@ -12,6 +12,6 @@ reporting_task:
     Review the context you got and expand each topic into a full section for a report.
     Make sure the report is detailed and contains any and all relevant information.
   expected_output: >
-    A fully fledge reports with the mains topics, each with a full section of information.
+    A fully fledged report with the main topics, each with a full section of information.
     Formatted as markdown without '```'
   agent: reporting_analyst

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

@@ -1,37 +1,26 @@
 from crewai import Agent, Crew, Process, Task
-from crewai.project import CrewBase, agent, crew, task, before_kickoff, after_kickoff
-# Uncomment the following line to use an example of a custom tool
-# from {{folder_name}}.tools.custom_tool import MyCustomTool
-# Uncomment the following line to use an example of a knowledge source
-# from crewai.knowledge.source.text_file_knowledge_source import TextFileKnowledgeSource
+from crewai.project import CrewBase, agent, crew, task
 
-# Check our tools documentations for more information on how to use them
-# from crewai_tools import SerperDevTool
+# If you want to run a snippet of code before or after the crew starts, 
+# you can use the @before_kickoff and @after_kickoff decorators
+# https://docs.crewai.com/concepts/crews#example-crew-class-with-decorators
 
 @CrewBase
 class {{crew_name}}():
 	"""{{crew_name}} crew"""
 
+	# Learn more about YAML configuration files here:
+	# Agents: https://docs.crewai.com/concepts/agents#yaml-configuration-recommended
+	# Tasks: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
 	agents_config = 'config/agents.yaml'
 	tasks_config = 'config/tasks.yaml'
 
-	@before_kickoff # Optional hook to be executed before the crew starts
-	def pull_data_example(self, inputs):
-		# Example of pulling data from an external API, dynamically changing the inputs
-		inputs['extra_data'] = "This is extra data"
-		return inputs
-
-	@after_kickoff # Optional hook to be executed after the crew has finished
-	def log_results(self, output):
-		# Example of logging results, dynamically changing the output
-		print(f"Results: {output}")
-		return output
-
+	# If you would like to add tools to your agents, you can learn more about it here:
+	# https://docs.crewai.com/concepts/agents#agent-tools
 	@agent
 	def researcher(self) -> Agent:
 		return Agent(
 			config=self.agents_config['researcher'],
-			# tools=[MyCustomTool()], # Example of custom tool, loaded on the beginning of file
 			verbose=True
 		)
 
@@ -42,6 +31,9 @@ class {{crew_name}}():
 			verbose=True
 		)
 
+	# To learn more about structured task outputs, 
+	# task dependencies, and task callbacks, check out the documentation:
+	# https://docs.crewai.com/concepts/tasks#overview-of-a-task
 	@task
 	def research_task(self) -> Task:
 		return Task(
@@ -58,14 +50,8 @@ class {{crew_name}}():
 	@crew
 	def crew(self) -> Crew:
 		"""Creates the {{crew_name}} crew"""
-		# You can add knowledge sources here
-		# knowledge_path = "user_preference.txt"
-		# sources = [
-		# 	TextFileKnowledgeSource(
-		# 		file_path="knowledge/user_preference.txt",
-		# 		metadata={"preference": "personal"}
-		# 	),
-		# ]
+		# To learn how to add knowledge sources to your crew, check out the documentation:
+		# https://docs.crewai.com/concepts/knowledge#what-is-knowledge
 
 		return Crew(
 			agents=self.agents, # Automatically created by the @agent decorator
@@ -73,5 +59,4 @@ class {{crew_name}}():
 			process=Process.sequential,
 			verbose=True,
 			# process=Process.hierarchical, # In case you wanna use that instead https://docs.crewai.com/how-to/Hierarchical/
-			# knowledge_sources=sources, # In the case you want to add knowledge sources
 		)

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

@@ -3,9 +3,9 @@ name = "{{folder_name}}"
 version = "0.1.0"
 description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
-requires-python = ">=3.10,<=3.13"
+requires-python = ">=3.10,<=3.12"
 dependencies = [
-    "crewai[tools]>=0.85.0,<1.0.0"
+    "crewai[tools]>=0.86.0,<1.0.0"
 ]
 
 [project.scripts]

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

@@ -10,7 +10,7 @@ class MyCustomToolInput(BaseModel):
 class MyCustomTool(BaseTool):
     name: str = "Name of my tool"
     description: str = (
-        "Clear description for what this tool is useful for, you agent will need this information to use it."
+        "Clear description for what this tool is useful for, your agent will need this information to use it."
     )
     args_schema: Type[BaseModel] = MyCustomToolInput
 

src/crewai/cli/templates/flow/README.md

@@ -4,7 +4,7 @@ Welcome to the {{crew_name}} Crew project, powered by [crewAI](https://crewai.co
 
 ## Installation
 
-Ensure you have Python >=3.10 <=3.13 installed on your system. This project uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
+Ensure you have Python >=3.10 <=3.12 installed on your system. This project uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
 
 First, if you haven't already, install uv:
 

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

@@ -1,31 +1,47 @@
 from crewai import Agent, Crew, Process, Task
 from crewai.project import CrewBase, agent, crew, task
 
+# If you want to run a snippet of code before or after the crew starts,
+# you can use the @before_kickoff and @after_kickoff decorators
+# https://docs.crewai.com/concepts/crews#example-crew-class-with-decorators
+
+
 @CrewBase
-class PoemCrew():
-	"""Poem Crew"""
+class PoemCrew:
+    """Poem Crew"""
 
-	agents_config = 'config/agents.yaml'
-	tasks_config = 'config/tasks.yaml'
+    # Learn more about YAML configuration files here:
+    # Agents: https://docs.crewai.com/concepts/agents#yaml-configuration-recommended
+    # Tasks: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
+    agents_config = "config/agents.yaml"
+    tasks_config = "config/tasks.yaml"
 
-	@agent
-	def poem_writer(self) -> Agent:
-		return Agent(
-			config=self.agents_config['poem_writer'],
-		)
+    # If you would lik to add tools to your crew, you can learn more about it here:
+    # https://docs.crewai.com/concepts/agents#agent-tools
+    @agent
+    def poem_writer(self) -> Agent:
+        return Agent(
+            config=self.agents_config["poem_writer"],
+        )
 
-	@task
-	def write_poem(self) -> Task:
-		return Task(
-			config=self.tasks_config['write_poem'],
-		)
+    # To learn more about structured task outputs,
+    # task dependencies, and task callbacks, check out the documentation:
+    # https://docs.crewai.com/concepts/tasks#overview-of-a-task
+    @task
+    def write_poem(self) -> Task:
+        return Task(
+            config=self.tasks_config["write_poem"],
+        )
 
-	@crew
-	def crew(self) -> Crew:
-		"""Creates the Research Crew"""
-		return Crew(
-			agents=self.agents, # Automatically created by the @agent decorator
-			tasks=self.tasks, # Automatically created by the @task decorator
-			process=Process.sequential,
-			verbose=True,
-		)
+    @crew
+    def crew(self) -> Crew:
+        """Creates the Research Crew"""
+        # To learn how to add knowledge sources to your crew, check out the documentation:
+        # https://docs.crewai.com/concepts/knowledge#what-is-knowledge
+
+        return Crew(
+            agents=self.agents,  # Automatically created by the @agent decorator
+            tasks=self.tasks,  # Automatically created by the @task decorator
+            process=Process.sequential,
+            verbose=True,
+        )

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

@@ -3,9 +3,9 @@ name = "{{folder_name}}"
 version = "0.1.0"
 description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
-requires-python = ">=3.10,<=3.13"
+requires-python = ">=3.10,<=3.12"
 dependencies = [
-    "crewai[tools]>=0.85.0,<1.0.0",
+    "crewai[tools]>=0.86.0,<1.0.0",
 ]
 
 [project.scripts]

src/crewai/cli/templates/flow/tools/custom_tool.py

@@ -13,7 +13,7 @@ class MyCustomToolInput(BaseModel):
 class MyCustomTool(BaseTool):
     name: str = "Name of my tool"
     description: str = (
-        "Clear description for what this tool is useful for, you agent will need this information to use it."
+        "Clear description for what this tool is useful for, your agent will need this information to use it."
     )
     args_schema: Type[BaseModel] = MyCustomToolInput
 

src/crewai/cli/templates/tool/README.md

@@ -5,7 +5,7 @@ custom tools to power up your crews.
 
 ## Installing
 
-Ensure you have Python >=3.10 <=3.13 installed on your system. This project
+Ensure you have Python >=3.10 <=3.12 installed on your system. This project
 uses [UV](https://docs.astral.sh/uv/) for dependency management and package
 handling, offering a seamless setup and execution experience.
 

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

@@ -3,8 +3,8 @@ name = "{{folder_name}}"
 version = "0.1.0"
 description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
-requires-python = ">=3.10,<=3.13"
+requires-python = ">=3.10,<=3.12"
 dependencies = [
-    "crewai[tools]>=0.85.0"
+    "crewai[tools]>=0.86.0"
 ]
 

src/crewai/cli/tools/main.py

@@ -117,7 +117,7 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
 
         published_handle = publish_response.json()["handle"]
         console.print(
-            f"Succesfully published {published_handle} ({project_version}).\nInstall it in other projects with crewai tool install {published_handle}",
+            f"Successfully published {published_handle} ({project_version}).\nInstall it in other projects with crewai tool install {published_handle}",
             style="bold green",
         )
 
@@ -138,7 +138,7 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
 
         self._add_package(get_response.json())
 
-        console.print(f"Succesfully installed {handle}", style="bold green")
+        console.print(f"Successfully installed {handle}", style="bold green")
 
     def login(self):
         login_response = self.plus_api_client.login_to_tool_repository()

src/crewai/cli/utils.py

@@ -33,26 +33,6 @@ def copy_template(src, dst, name, class_name, folder_name):
     click.secho(f"  - Created {dst}", fg="green")
 
 
-# Drop the simple_toml_parser when we move to python3.11
-def simple_toml_parser(content):
-    result = {}
-    current_section = result
-    for line in content.split("\n"):
-        line = line.strip()
-        if line.startswith("[") and line.endswith("]"):
-            # New section
-            section = line[1:-1].split(".")
-            current_section = result
-            for key in section:
-                current_section = current_section.setdefault(key, {})
-        elif "=" in line:
-            key, value = line.split("=", 1)
-            key = key.strip()
-            value = value.strip().strip('"')
-            current_section[key] = value
-    return result
-
-
 def read_toml(file_path: str = "pyproject.toml"):
     """Read the content of a TOML file and return it as a dictionary."""
     with open(file_path, "rb") as f:
@@ -63,7 +43,7 @@ def read_toml(file_path: str = "pyproject.toml"):
 def parse_toml(content):
     if sys.version_info >= (3, 11):
         return tomllib.loads(content)
-    return simple_toml_parser(content)
+    return tomli.loads(content)
 
 
 def get_project_name(

src/crewai/cli/version.py

@@ -1,6 +1,6 @@
 import importlib.metadata
 
+
 def get_crewai_version() -> str:
     """Get the version number of CrewAI running the CLI"""
     return importlib.metadata.version("crewai")
-

src/crewai/crew.py

@@ -1,6 +1,5 @@
 import asyncio
 import json
-import os
 import uuid
 import warnings
 from concurrent.futures import Future
@@ -49,12 +48,10 @@ from crewai.utilities.planning_handler import CrewPlanner
 from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
 
-agentops = None
-if os.environ.get("AGENTOPS_API_KEY"):
-    try:
-        import agentops  # type: ignore
-    except ImportError:
-        pass
+try:
+    import agentops  # type: ignore
+except ImportError:
+    agentops = None
 
 
 warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")
@@ -1032,6 +1029,7 @@ class Crew(BaseModel):
             agentops.end_session(
                 end_state="Success",
                 end_state_reason="Finished Execution",
+                is_auto_end=True,
             )
         self._telemetry.end_crew(self, final_string_output)
 

src/crewai/flow/flow.py

@@ -14,8 +14,15 @@ from typing import (
     cast,
 )
 
+from blinker import Signal
 from pydantic import BaseModel, ValidationError
 
+from crewai.flow.flow_events import (
+    FlowFinishedEvent,
+    FlowStartedEvent,
+    MethodExecutionFinishedEvent,
+    MethodExecutionStartedEvent,
+)
 from crewai.flow.flow_visualizer import plot_flow
 from crewai.flow.utils import get_possible_return_constants
 from crewai.telemetry import Telemetry
@@ -159,6 +166,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
     _routers: Dict[str, str] = {}
     _router_paths: Dict[str, List[str]] = {}
     initial_state: Union[Type[T], T, None] = None
+    event_emitter = Signal("event_emitter")
 
     def __class_getitem__(cls: Type["Flow"], item: Type[T]) -> Type["Flow"]:
         class _FlowGeneric(cls):  # type: ignore
@@ -253,6 +261,14 @@ class Flow(Generic[T], metaclass=FlowMeta):
         Returns:
             The final output from the flow execution.
         """
+        self.event_emitter.send(
+            self,
+            event=FlowStartedEvent(
+                type="flow_started",
+                flow_name=self.__class__.__name__,
+            ),
+        )
+
         if inputs is not None:
             self._initialize_state(inputs)
         return asyncio.run(self.kickoff_async())
@@ -267,8 +283,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
         Returns:
             The final output from the flow execution.
         """
-        if inputs is not None:
-            self._initialize_state(inputs)
         if not self._start_methods:
             raise ValueError("No start method defined")
 
@@ -285,11 +299,19 @@ class Flow(Generic[T], metaclass=FlowMeta):
         # Run all start methods concurrently
         await asyncio.gather(*tasks)
 
-        # Return the final output (from the last executed method)
-        if self._method_outputs:
-            return self._method_outputs[-1]
-        else:
-            return None  # Or raise an exception if no methods were executed
+        # Determine the final output (from the last executed method)
+        final_output = self._method_outputs[-1] if self._method_outputs else None
+
+        self.event_emitter.send(
+            self,
+            event=FlowFinishedEvent(
+                type="flow_finished",
+                flow_name=self.__class__.__name__,
+                result=final_output,
+            ),
+        )
+
+        return final_output
 
     async def _execute_start_method(self, start_method_name: str) -> None:
         result = await self._execute_method(
@@ -352,6 +374,16 @@ class Flow(Generic[T], metaclass=FlowMeta):
     async def _execute_single_listener(self, listener_name: str, result: Any) -> None:
         try:
             method = self._methods[listener_name]
+
+            self.event_emitter.send(
+                self,
+                event=MethodExecutionStartedEvent(
+                    type="method_execution_started",
+                    method_name=listener_name,
+                    flow_name=self.__class__.__name__,
+                ),
+            )
+
             sig = inspect.signature(method)
             params = list(sig.parameters.values())
 
@@ -367,6 +399,15 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 # If listener does not expect parameters, call without arguments
                 listener_result = await self._execute_method(listener_name, method)
 
+            self.event_emitter.send(
+                self,
+                event=MethodExecutionFinishedEvent(
+                    type="method_execution_finished",
+                    method_name=listener_name,
+                    flow_name=self.__class__.__name__,
+                ),
+            )
+
             # Execute listeners of this listener
             await self._execute_listeners(listener_name, listener_result)
         except Exception as e:

src/crewai/flow/flow_events.py

@@ -0,0 +1,33 @@
+from dataclasses import dataclass, field
+from datetime import datetime
+from typing import Any, Optional
+
+
+@dataclass
+class Event:
+    type: str
+    flow_name: str
+    timestamp: datetime = field(init=False)
+
+    def __post_init__(self):
+        self.timestamp = datetime.now()
+
+
+@dataclass
+class FlowStartedEvent(Event):
+    pass
+
+
+@dataclass
+class MethodExecutionStartedEvent(Event):
+    method_name: str
+
+
+@dataclass
+class MethodExecutionFinishedEvent(Event):
+    method_name: str
+
+
+@dataclass
+class FlowFinishedEvent(Event):
+    result: Optional[Any] = None

src/crewai/knowledge/knowledge.py

@@ -1,11 +1,10 @@
 import os
+from typing import Any, Dict, List, Optional
 
-from typing import List, Optional, Dict, Any
 from pydantic import BaseModel, ConfigDict, Field
 
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
-from crewai.utilities.constants import DEFAULT_SCORE_THRESHOLD
 
 os.environ["TOKENIZERS_PARALLELISM"] = "false"  # removes logging from fastembed
 
@@ -46,9 +45,7 @@ class Knowledge(BaseModel):
             source.storage = self.storage
             source.add()
 
-    def query(
-        self, query: List[str], limit: int = 3, preference: Optional[str] = None
-    ) -> List[Dict[str, Any]]:
+    def query(self, query: List[str], limit: int = 3) -> List[Dict[str, Any]]:
         """
         Query across all knowledge sources to find the most relevant information.
         Returns the top_k most relevant chunks.
@@ -57,8 +54,6 @@ class Knowledge(BaseModel):
         results = self.storage.search(
             query,
             limit,
-            filter={"preference": preference} if preference else None,
-            score_threshold=DEFAULT_SCORE_THRESHOLD,
         )
         return results
 

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -1,13 +1,13 @@
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Union, List, Dict, Any
+from typing import Dict, List, Union
 
 from pydantic import Field
 
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
-from crewai.utilities.logger import Logger
 from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
 from crewai.utilities.constants import KNOWLEDGE_DIRECTORY
+from crewai.utilities.logger import Logger
 
 
 class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
@@ -38,7 +38,7 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
             if not path.exists():
                 self._logger.log(
                     "error",
-                    f"File not found: {path}. Try adding sources to the knowledge directory. If its inside the knowledge directory, use the relative path.",
+                    f"File not found: {path}. Try adding sources to the knowledge directory. If it's inside the knowledge directory, use the relative path.",
                     color="red",
                 )
                 raise FileNotFoundError(f"File not found: {path}")
@@ -49,10 +49,9 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
                     color="red",
                 )
 
-    def save_documents(self, metadata: Dict[str, Any]):
+    def _save_documents(self):
         """Save the documents to the storage."""
-        chunk_metadatas = [metadata.copy() for _ in self.chunks]
-        self.storage.save(self.chunks, chunk_metadatas)
+        self.storage.save(self.chunks)
 
     def convert_to_path(self, path: Union[Path, str]) -> Path:
         """Convert a path to a Path object."""

src/crewai/knowledge/source/base_knowledge_source.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import List, Dict, Any, Optional
+from typing import Any, Dict, List, Optional
 
 import numpy as np
 from pydantic import BaseModel, ConfigDict, Field
@@ -17,7 +17,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
     storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
-    metadata: Dict[str, Any] = Field(default_factory=dict)
+    metadata: Dict[str, Any] = Field(default_factory=dict)  # Currently unused
     collection_name: Optional[str] = Field(default=None)
 
     @abstractmethod
@@ -41,9 +41,10 @@ class BaseKnowledgeSource(BaseModel, ABC):
             for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
         ]
 
-    def save_documents(self, metadata: Dict[str, Any]):
+    def _save_documents(self):
         """
         Save the documents to the storage.
         This method should be called after the chunks and embeddings are generated.
         """
-        self.storage.save(self.chunks, metadata)
+        print("CHUNKS: ", self.chunks)
+        self.storage.save(self.chunks)

src/crewai/knowledge/source/csv_knowledge_source.py

@@ -1,6 +1,6 @@
 import csv
-from typing import Dict, List
 from pathlib import Path
+from typing import Dict, List
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -30,7 +30,7 @@ class CSVKnowledgeSource(BaseFileKnowledgeSource):
         )
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self._save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/excel_knowledge_source.py

@@ -1,5 +1,6 @@
-from typing import Dict, List
 from pathlib import Path
+from typing import Dict, List
+
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
 
@@ -44,7 +45,7 @@ class ExcelKnowledgeSource(BaseFileKnowledgeSource):
 
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self._save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/json_knowledge_source.py

@@ -1,6 +1,6 @@
 import json
-from typing import Any, Dict, List
 from pathlib import Path
+from typing import Any, Dict, List
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -42,7 +42,7 @@ class JSONKnowledgeSource(BaseFileKnowledgeSource):
         )
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self._save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/pdf_knowledge_source.py

@@ -1,5 +1,5 @@
-from typing import List, Dict
 from pathlib import Path
+from typing import Dict, List
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -43,7 +43,7 @@ class PDFKnowledgeSource(BaseFileKnowledgeSource):
         for _, text in self.content.items():
             new_chunks = self._chunk_text(text)
             self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self._save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/string_knowledge_source.py

@@ -24,7 +24,7 @@ class StringKnowledgeSource(BaseKnowledgeSource):
         """Add string content to the knowledge source, chunk it, compute embeddings, and save them."""
         new_chunks = self._chunk_text(self.content)
         self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self._save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/text_file_knowledge_source.py

@@ -1,5 +1,5 @@
-from typing import Dict, List
 from pathlib import Path
+from typing import Dict, List
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -24,7 +24,7 @@ class TextFileKnowledgeSource(BaseFileKnowledgeSource):
         for _, text in self.content.items():
             new_chunks = self._chunk_text(text)
             self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self._save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/storage/base_knowledge_storage.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import Dict, Any, List, Optional
+from typing import Any, Dict, List, Optional
 
 
 class BaseKnowledgeStorage(ABC):

src/crewai/knowledge/storage/knowledge_storage.py

@@ -1,18 +1,22 @@
 import contextlib
+import hashlib
 import io
 import logging
-import chromadb
 import os
+import shutil
+from typing import Any, Dict, List, Optional, Union, cast
 
+import chromadb
 import chromadb.errors
-from crewai.utilities.paths import db_storage_path
-from typing import Optional, List, Dict, Any, Union
-from crewai.utilities import EmbeddingConfigurator
-from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
-import hashlib
-from chromadb.config import Settings
 from chromadb.api import ClientAPI
+from chromadb.api.types import OneOrMany
+from chromadb.config import Settings
+
+from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
+from crewai.utilities import EmbeddingConfigurator
+from crewai.utilities.constants import KNOWLEDGE_DIRECTORY
 from crewai.utilities.logger import Logger
+from crewai.utilities.paths import db_storage_path
 
 
 @contextlib.contextmanager
@@ -103,53 +107,77 @@ class KnowledgeStorage(BaseKnowledgeStorage):
             raise Exception("Failed to create or get collection")
 
     def reset(self):
-        if self.app:
-            self.app.reset()
-        else:
-            base_path = os.path.join(db_storage_path(), "knowledge")
+        base_path = os.path.join(db_storage_path(), KNOWLEDGE_DIRECTORY)
+        if not self.app:
             self.app = chromadb.PersistentClient(
                 path=base_path,
                 settings=Settings(allow_reset=True),
             )
-            self.app.reset()
+
+        self.app.reset()
+        shutil.rmtree(base_path)
+        self.app = None
+        self.collection = None
 
     def save(
         self,
         documents: List[str],
-        metadata: Union[Dict[str, Any], List[Dict[str, Any]]],
+        metadata: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None,
     ):
-        if self.collection:
-            try:
-                metadatas = [metadata] if isinstance(metadata, dict) else metadata
-
-                ids = [
-                    hashlib.sha256(doc.encode("utf-8")).hexdigest() for doc in documents
-                ]
-
-                self.collection.upsert(
-                    documents=documents,
-                    metadatas=metadatas,
-                    ids=ids,
-                )
-            except chromadb.errors.InvalidDimensionException as e:
-                Logger(verbose=True).log(
-                    "error",
-                    "Embedding dimension mismatch. This usually happens when mixing different embedding models. Try resetting the collection using `crewai reset-memories -a`",
-                    "red",
-                )
-                raise ValueError(
-                    "Embedding dimension mismatch. Make sure you're using the same embedding model "
-                    "across all operations with this collection."
-                    "Try resetting the collection using `crewai reset-memories -a`"
-                ) from e
-            except Exception as e:
-                Logger(verbose=True).log(
-                    "error", f"Failed to upsert documents: {e}", "red"
-                )
-                raise
-        else:
+        if not self.collection:
             raise Exception("Collection not initialized")
 
+        try:
+            # Create a dictionary to store unique documents
+            unique_docs = {}
+
+            # Generate IDs and create a mapping of id -> (document, metadata)
+            for idx, doc in enumerate(documents):
+                doc_id = hashlib.sha256(doc.encode("utf-8")).hexdigest()
+                doc_metadata = None
+                if metadata is not None:
+                    if isinstance(metadata, list):
+                        doc_metadata = metadata[idx]
+                    else:
+                        doc_metadata = metadata
+                unique_docs[doc_id] = (doc, doc_metadata)
+
+            # Prepare filtered lists for ChromaDB
+            filtered_docs = []
+            filtered_metadata = []
+            filtered_ids = []
+
+            # Build the filtered lists
+            for doc_id, (doc, meta) in unique_docs.items():
+                filtered_docs.append(doc)
+                filtered_metadata.append(meta)
+                filtered_ids.append(doc_id)
+
+            # If we have no metadata at all, set it to None
+            final_metadata: Optional[OneOrMany[chromadb.Metadata]] = (
+                None if all(m is None for m in filtered_metadata) else filtered_metadata
+            )
+
+            self.collection.upsert(
+                documents=filtered_docs,
+                metadatas=final_metadata,
+                ids=filtered_ids,
+            )
+        except chromadb.errors.InvalidDimensionException as e:
+            Logger(verbose=True).log(
+                "error",
+                "Embedding dimension mismatch. This usually happens when mixing different embedding models. Try resetting the collection using `crewai reset-memories -a`",
+                "red",
+            )
+            raise ValueError(
+                "Embedding dimension mismatch. Make sure you're using the same embedding model "
+                "across all operations with this collection."
+                "Try resetting the collection using `crewai reset-memories -a`"
+            ) from e
+        except Exception as e:
+            Logger(verbose=True).log("error", f"Failed to upsert documents: {e}", "red")
+            raise
+
     def _create_default_embedding_function(self):
         from chromadb.utils.embedding_functions.openai_embedding_function import (
             OpenAIEmbeddingFunction,

src/crewai/llm.py

@@ -1,4 +1,5 @@
 import logging
+import os
 import sys
 import threading
 import warnings
@@ -42,6 +43,10 @@ LLM_CONTEXT_WINDOW_SIZES = {
     "gpt-4-turbo": 128000,
     "o1-preview": 128000,
     "o1-mini": 128000,
+    # gemini
+    "gemini-1.5-pro": 2097152,
+    "gemini-1.5-flash": 1048576,
+    "gemini-1.5-flash-8b": 1048576,
     # deepseek
     "deepseek-chat": 128000,
     # groq
@@ -60,6 +65,9 @@ LLM_CONTEXT_WINDOW_SIZES = {
     "mixtral-8x7b-32768": 32768,
 }
 
+DEFAULT_CONTEXT_WINDOW_SIZE = 8192
+CONTEXT_WINDOW_USAGE_RATIO = 0.75
+
 
 @contextmanager
 def suppress_warnings():
@@ -123,11 +131,13 @@ class LLM:
         self.api_version = api_version
         self.api_key = api_key
         self.callbacks = callbacks
+        self.context_window_size = 0
         self.kwargs = kwargs
 
         litellm.drop_params = True
         litellm.set_verbose = False
         self.set_callbacks(callbacks)
+        self.set_env_callbacks()
 
     def call(self, messages: List[Dict[str, str]], callbacks: List[Any] = []) -> str:
         with suppress_warnings():
@@ -189,7 +199,16 @@ class LLM:
 
     def get_context_window_size(self) -> int:
         # Only using 75% of the context window size to avoid cutting the message in the middle
-        return int(LLM_CONTEXT_WINDOW_SIZES.get(self.model, 8192) * 0.75)
+        if self.context_window_size != 0:
+            return self.context_window_size
+
+        self.context_window_size = int(
+            DEFAULT_CONTEXT_WINDOW_SIZE * CONTEXT_WINDOW_USAGE_RATIO
+        )
+        for key, value in LLM_CONTEXT_WINDOW_SIZES.items():
+            if self.model.startswith(key):
+                self.context_window_size = int(value * CONTEXT_WINDOW_USAGE_RATIO)
+        return self.context_window_size
 
     def set_callbacks(self, callbacks: List[Any]):
         callback_types = [type(callback) for callback in callbacks]
@@ -202,3 +221,39 @@ class LLM:
                 litellm._async_success_callback.remove(callback)
 
         litellm.callbacks = callbacks
+
+    def set_env_callbacks(self):
+        """
+        Sets the success and failure callbacks for the LiteLLM library from environment variables.
+
+        This method reads the `LITELLM_SUCCESS_CALLBACKS` and `LITELLM_FAILURE_CALLBACKS`
+        environment variables, which should contain comma-separated lists of callback names.
+        It then assigns these lists to `litellm.success_callback` and `litellm.failure_callback`,
+        respectively.
+
+        If the environment variables are not set or are empty, the corresponding callback lists
+        will be set to empty lists.
+
+        Example:
+            LITELLM_SUCCESS_CALLBACKS="langfuse,langsmith"
+            LITELLM_FAILURE_CALLBACKS="langfuse"
+
+        This will set `litellm.success_callback` to ["langfuse", "langsmith"] and
+        `litellm.failure_callback` to ["langfuse"].
+        """
+        success_callbacks_str = os.environ.get("LITELLM_SUCCESS_CALLBACKS", "")
+        success_callbacks = []
+        if success_callbacks_str:
+            success_callbacks = [
+                callback.strip() for callback in success_callbacks_str.split(",")
+            ]
+
+        failure_callbacks_str = os.environ.get("LITELLM_FAILURE_CALLBACKS", "")
+        failure_callbacks = []
+        if failure_callbacks_str:
+            failure_callbacks = [
+                callback.strip() for callback in failure_callbacks_str.split(",")
+            ]
+
+        litellm.success_callback = success_callbacks
+        litellm.failure_callback = failure_callbacks

src/crewai/memory/contextual/contextual_memory.py

@@ -1,4 +1,4 @@
-from typing import Optional, Dict, Any
+from typing import Any, Dict, Optional
 
 from crewai.memory import EntityMemory, LongTermMemory, ShortTermMemory, UserMemory
 

src/crewai/memory/memory.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict, Optional, List
+from typing import Any, Dict, List, Optional
 
 from crewai.memory.storage.rag_storage import RAGStorage
 

src/crewai/memory/short_term/short_term_memory.py

@@ -1,4 +1,5 @@
 from typing import Any, Dict, Optional
+
 from crewai.memory.memory import Memory
 from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
 from crewai.memory.storage.rag_storage import RAGStorage
@@ -32,7 +33,10 @@ class ShortTermMemory(Memory):
                 storage
                 if storage
                 else RAGStorage(
-                    type="short_term", embedder_config=embedder_config, crew=crew, path=path
+                    type="short_term",
+                    embedder_config=embedder_config,
+                    crew=crew,
+                    path=path,
                 )
             )
         super().__init__(storage)

src/crewai/memory/storage/mem0_storage.py

@@ -2,6 +2,7 @@ import os
 from typing import Any, Dict, List
 
 from mem0 import MemoryClient
+
 from crewai.memory.storage.interface import Storage
 
 

src/crewai/memory/storage/rag_storage.py

@@ -4,12 +4,14 @@ import logging
 import os
 import shutil
 import uuid
-
 from typing import Any, Dict, List, Optional
+
 from chromadb.api import ClientAPI
+
 from crewai.memory.storage.base_rag_storage import BaseRAGStorage
-from crewai.utilities.paths import db_storage_path
 from crewai.utilities import EmbeddingConfigurator
+from crewai.utilities.constants import MAX_FILE_NAME_LENGTH
+from crewai.utilities.paths import db_storage_path
 
 
 @contextlib.contextmanager
@@ -37,12 +39,15 @@ class RAGStorage(BaseRAGStorage):
 
     app: ClientAPI | None = None
 
-    def __init__(self, type, allow_reset=True, embedder_config=None, crew=None, path=None):
+    def __init__(
+        self, type, allow_reset=True, embedder_config=None, crew=None, path=None
+    ):
         super().__init__(type, allow_reset, embedder_config, crew)
         agents = crew.agents if crew else []
         agents = [self._sanitize_role(agent.role) for agent in agents]
         agents = "_".join(agents)
         self.agents = agents
+        self.storage_file_name = self._build_storage_file_name(type, agents)
 
         self.type = type
 
@@ -60,7 +65,7 @@ class RAGStorage(BaseRAGStorage):
 
         self._set_embedder_config()
         chroma_client = chromadb.PersistentClient(
-            path=self.path if self.path else f"{db_storage_path()}/{self.type}/{self.agents}",
+            path=self.path if self.path else self.storage_file_name,
             settings=Settings(allow_reset=self.allow_reset),
         )
 
@@ -81,6 +86,20 @@ class RAGStorage(BaseRAGStorage):
         """
         return role.replace("\n", "").replace(" ", "_").replace("/", "_")
 
+    def _build_storage_file_name(self, type: str, file_name: str) -> str:
+        """
+        Ensures file name does not exceed max allowed by OS
+        """
+        base_path = f"{db_storage_path()}/{type}"
+
+        if len(file_name) > MAX_FILE_NAME_LENGTH:
+            logging.warning(
+                f"Trimming file name from {len(file_name)} to {MAX_FILE_NAME_LENGTH} characters."
+            )
+            file_name = file_name[:MAX_FILE_NAME_LENGTH]
+
+        return f"{base_path}/{file_name}"
+
     def save(self, value: Any, metadata: Dict[str, Any]) -> None:
         if not hasattr(self, "app") or not hasattr(self, "collection"):
             self._initialize_app()
@@ -131,9 +150,11 @@ class RAGStorage(BaseRAGStorage):
 
     def reset(self) -> None:
         try:
-            shutil.rmtree(f"{db_storage_path()}/{self.type}")
             if self.app:
                 self.app.reset()
+                shutil.rmtree(f"{db_storage_path()}/{self.type}")
+                self.app = None
+                self.collection = None
         except Exception as e:
             if "attempt to write a readonly database" in str(e):
                 # Ignore this specific error

src/crewai/memory/user/user_memory.py

@@ -37,7 +37,7 @@ class UserMemory(Memory):
         limit: int = 3,
         score_threshold: float = 0.35,
     ):
-        results = super().search(
+        results = self.storage.search(
             query=query,
             limit=limit,
             score_threshold=score_threshold,

src/crewai/project/annotations.py

@@ -66,6 +66,8 @@ def cache_handler(func):
 
 
 def crew(func) -> Callable[..., Crew]:
+
+    @wraps(func)
     def wrapper(self, *args, **kwargs) -> Crew:
         instantiated_tasks = []
         instantiated_agents = []

src/crewai/project/crew_base.py

@@ -213,4 +213,8 @@ def CrewBase(cls: T) -> T:
                     callback_functions[callback]() for callback in callbacks
                 ]
 
+    # Include base class (qual)name in the wrapper class (qual)name.
+    WrappedClass.__name__ = CrewBase.__name__ + "(" + cls.__name__ + ")"
+    WrappedClass.__qualname__ = CrewBase.__qualname__ + "(" + cls.__name__ + ")"
+  
     return cast(T, WrappedClass)

src/crewai/project/utils.py

@@ -1,11 +1,14 @@
+from functools import wraps
+
+
 def memoize(func):
     cache = {}
 
+    @wraps(func)
     def memoized_func(*args, **kwargs):
         key = (args, tuple(kwargs.items()))
         if key not in cache:
             cache[key] = func(*args, **kwargs)
         return cache[key]
 
-    memoized_func.__dict__.update(func.__dict__)
     return memoized_func

src/crewai/task.py

@@ -1,11 +1,11 @@
 import datetime
 import json
-import os
 import threading
 import uuid
 from concurrent.futures import Future
 from copy import copy
 from hashlib import md5
+from pathlib import Path
 from typing import Any, Dict, List, Optional, Set, Tuple, Type, Union
 
 from opentelemetry.trace import Span
@@ -393,12 +393,13 @@ class Task(BaseModel):
         if self.output_file is None:
             raise ValueError("output_file is not set.")
 
-        directory = os.path.dirname(self.output_file)  # type: ignore # Value of type variable "AnyOrLiteralStr" of "dirname" cannot be "str | None"
+        resolved_path = Path(self.output_file).expanduser().resolve()
+        directory = resolved_path.parent
 
-        if directory and not os.path.exists(directory):
-            os.makedirs(directory)
+        if not directory.exists():
+            directory.mkdir(parents=True, exist_ok=True)
 
-        with open(self.output_file, "w", encoding="utf-8") as file:
+        with resolved_path.open("w", encoding="utf-8") as file:
             if isinstance(result, dict):
                 import json
 

src/crewai/telemetry/telemetry.py

@@ -6,6 +6,7 @@ import os
 import platform
 import warnings
 from contextlib import contextmanager
+from importlib.metadata import version
 from typing import TYPE_CHECKING, Any, Optional
 
 
@@ -16,12 +17,10 @@ def suppress_warnings():
         yield
 
 
-with suppress_warnings():
-    import pkg_resources
-
-
 from opentelemetry import trace  # noqa: E402
-from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter # noqa: E402
+from opentelemetry.exporter.otlp.proto.http.trace_exporter import (
+    OTLPSpanExporter,  # noqa: E402
+)
 from opentelemetry.sdk.resources import SERVICE_NAME, Resource  # noqa: E402
 from opentelemetry.sdk.trace import TracerProvider  # noqa: E402
 from opentelemetry.sdk.trace.export import BatchSpanProcessor  # noqa: E402
@@ -104,7 +103,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(span, "python_version", platform.python_version())
             self._add_attribute(span, "crew_key", crew.key)
@@ -306,7 +305,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(span, "tool_name", tool_name)
             self._add_attribute(span, "attempts", attempts)
@@ -326,7 +325,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(span, "tool_name", tool_name)
             self._add_attribute(span, "attempts", attempts)
@@ -346,7 +345,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             if llm:
                 self._add_attribute(span, "llm", llm.model)
@@ -365,7 +364,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(span, "crew_key", crew.key)
             self._add_attribute(span, "crew_id", str(crew.id))
@@ -391,7 +390,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(span, "crew_key", crew.key)
             self._add_attribute(span, "crew_id", str(crew.id))
@@ -472,7 +471,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(span, "crew_key", crew.key)
             self._add_attribute(span, "crew_id", str(crew.id))
@@ -541,7 +540,7 @@ class Telemetry:
             self._add_attribute(
                 crew._execution_span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(
                 crew._execution_span, "crew_output", final_string_output

src/crewai/tools/agent_tools/agent_tools.py

@@ -1,9 +1,9 @@
-from crewai.tools.base_tool import BaseTool
 from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.tools.base_tool import BaseTool
 from crewai.utilities import I18N
 
-from .delegate_work_tool import DelegateWorkTool
 from .ask_question_tool import AskQuestionTool
+from .delegate_work_tool import DelegateWorkTool
 
 
 class AgentTools:

src/crewai/tools/agent_tools/ask_question_tool.py

@@ -1,7 +1,9 @@
-from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
 from typing import Optional
+
 from pydantic import BaseModel, Field
 
+from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
+
 
 class AskQuestionToolSchema(BaseModel):
     question: str = Field(..., description="The question to ask")

src/crewai/tools/agent_tools/base_agent_tools.py

@@ -1,9 +1,10 @@
 from typing import Optional, Union
+
 from pydantic import Field
 
-from crewai.tools.base_tool import BaseTool
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.task import Task
+from crewai.tools.base_tool import BaseTool
 from crewai.utilities import I18N
 
 
@@ -44,14 +45,14 @@ class BaseAgentTool(BaseTool):
                 if available_agent.role.casefold().replace("\n", "") == agent_name
             ]
         except Exception as _:
-            return self.i18n.errors("agent_tool_unexsiting_coworker").format(
+            return self.i18n.errors("agent_tool_unexisting_coworker").format(
                 coworkers="\n".join(
                     [f"- {agent.role.casefold()}" for agent in self.agents]
                 )
             )
 
         if not agent:
-            return self.i18n.errors("agent_tool_unexsiting_coworker").format(
+            return self.i18n.errors("agent_tool_unexisting_coworker").format(
                 coworkers="\n".join(
                     [f"- {agent.role.casefold()}" for agent in self.agents]
                 )

src/crewai/tools/agent_tools/delegate_work_tool.py

@@ -1,8 +1,9 @@
-from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
 from typing import Optional
 
 from pydantic import BaseModel, Field
 
+from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
+
 
 class DelegateWorkToolSchema(BaseModel):
     task: str = Field(..., description="The task to delegate")

src/crewai/tools/tool_usage.py

@@ -1,6 +1,5 @@
 import ast
 import datetime
-import os
 import time
 from difflib import SequenceMatcher
 from textwrap import dedent
@@ -15,12 +14,10 @@ from crewai.tools.tool_calling import InstructorToolCalling, ToolCalling
 from crewai.tools.tool_usage_events import ToolUsageError, ToolUsageFinished
 from crewai.utilities import I18N, Converter, ConverterError, Printer
 
-agentops = None
-if os.environ.get("AGENTOPS_API_KEY"):
-    try:
-        import agentops  # type: ignore
-    except ImportError:
-        pass
+try:
+    import agentops  # type: ignore
+except ImportError:
+    agentops = None
 
 OPENAI_BIGGER_MODELS = ["gpt-4", "gpt-4o", "o1-preview", "o1-mini"]
 

src/crewai/tools/tool_usage_events.py

@@ -1,6 +1,7 @@
-from typing import Any, Dict
-from pydantic import BaseModel
 from datetime import datetime
+from typing import Any, Dict
+
+from pydantic import BaseModel
 
 
 class ToolUsageEvent(BaseModel):

src/crewai/translations/en.json

@@ -19,7 +19,7 @@
     "human_feedback": "You got human feedback on your work, re-evaluate it and give a new Final Answer when ready.\n {human_feedback}",
     "getting_input": "This is the agent's final answer: {final_answer}\n\n",
     "summarizer_system_message": "You are a helpful assistant that summarizes text.",
-    "sumamrize_instruction": "Summarize the following text, make sure to include all the important information: {group}",
+    "summarize_instruction": "Summarize the following text, make sure to include all the important information: {group}",
     "summary": "This is a summary of our conversation so far:\n{merged_summary}",
     "manager_request": "Your best answer to your coworker asking you this, accounting for the context shared.",
     "formatted_task_instructions": "Ensure your final answer contains only the content in the following format: {output_format}\n\nEnsure the final output does not include any code block markers like ```json or ```python.",
@@ -28,7 +28,7 @@
   "errors": {
     "force_final_answer_error": "You can't keep going, this was the best you could do.\n {formatted_answer.text}",
     "force_final_answer": "Now it's time you MUST give your absolute best final answer. You'll ignore all previous instructions, stop using any tools, and just return your absolute BEST Final answer.",
-    "agent_tool_unexsiting_coworker": "\nError executing tool. coworker mentioned not found, it must be one of the following options:\n{coworkers}\n",
+    "agent_tool_unexisting_coworker": "\nError executing tool. coworker mentioned not found, it must be one of the following options:\n{coworkers}\n",
     "task_repeated_usage": "I tried reusing the same input, I must stop using this action input. I'll try something else instead.\n\n",
     "tool_usage_error": "I encountered an error: {error}",
     "tool_arguments_error": "Error: the Action Input is not a valid key, value dictionary.",

src/crewai/utilities/constants.py

@@ -3,3 +3,4 @@ TRAINED_AGENTS_DATA_FILE = "trained_agents_data.pkl"
 DEFAULT_SCORE_THRESHOLD = 0.35
 KNOWLEDGE_DIRECTORY = "knowledge"
 MAX_LLM_RETRY = 3
+MAX_FILE_NAME_LENGTH = 255

src/crewai/utilities/crew_json_encoder.py

@@ -1,8 +1,9 @@
-from datetime import datetime, date
 import json
-from uuid import UUID
-from pydantic import BaseModel
+from datetime import date, datetime
 from decimal import Decimal
+from uuid import UUID
+
+from pydantic import BaseModel
 
 
 class CrewJSONEncoder(json.JSONEncoder):

src/crewai/utilities/crew_pydantic_output_parser.py

@@ -1,10 +1,11 @@
 import json
-import regex
 from typing import Any, Type
 
-from crewai.agents.parser import OutputParserException
+import regex
 from pydantic import BaseModel, ValidationError
 
+from crewai.agents.parser import OutputParserException
+
 
 class CrewPydanticOutputParser:
     """Parses the text into pydantic models"""

src/crewai/utilities/embedding_configurator.py

@@ -1,6 +1,7 @@
 import os
 from typing import Any, Dict, cast
-from chromadb import EmbeddingFunction, Documents, Embeddings
+
+from chromadb import Documents, EmbeddingFunction, Embeddings
 from chromadb.api.types import validate_embedding_function
 
 

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -1,13 +1,14 @@
 from collections import defaultdict
 
+from pydantic import BaseModel, Field
+from rich.box import HEAVY_EDGE
+from rich.console import Console
+from rich.table import Table
+
 from crewai.agent import Agent
 from crewai.task import Task
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry import Telemetry
-from pydantic import BaseModel, Field
-from rich.box import HEAVY_EDGE
-from rich.console import Console
-from rich.table import Table
 
 
 class TaskEvaluationPydanticOutput(BaseModel):

src/crewai/utilities/evaluators/task_evaluator.py

@@ -1,4 +1,3 @@
-import os
 from typing import List
 
 from pydantic import BaseModel, Field
@@ -6,27 +5,17 @@ from pydantic import BaseModel, Field
 from crewai.utilities import Converter
 from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 
+agentops = None
+try:
+    from agentops import track_agent  # type: ignore
+except ImportError:
 
-def mock_agent_ops_provider():
-    def track_agent(*args, **kwargs):
+    def track_agent(name):
         def noop(f):
             return f
 
         return noop
 
-    return track_agent
-
-
-agentops = None
-
-if os.environ.get("AGENTOPS_API_KEY"):
-    try:
-        from agentops import track_agent
-    except ImportError:
-        track_agent = mock_agent_ops_provider()
-else:
-    track_agent = mock_agent_ops_provider()
-
 
 class Entity(BaseModel):
     name: str = Field(description="The name of the entity.")

src/crewai/utilities/events.py

@@ -1,7 +1,7 @@
-from typing import Any, Callable, Generic, List, Dict, Type, TypeVar
 from functools import wraps
-from pydantic import BaseModel
+from typing import Any, Callable, Dict, Generic, List, Type, TypeVar
 
+from pydantic import BaseModel
 
 T = TypeVar("T")
 EVT = TypeVar("EVT", bound=BaseModel)

src/crewai/utilities/planning_handler.py

@@ -1,4 +1,5 @@
 from typing import Any, List, Optional
+
 from pydantic import BaseModel, Field
 
 from crewai.agent import Agent

src/crewai/utilities/prompts.py

@@ -1,5 +1,7 @@
-from pydantic import BaseModel, Field
 from typing import Any, Optional
+
+from pydantic import BaseModel, Field
+
 from crewai.utilities import I18N
 
 

src/crewai/utilities/pydantic_schema_parser.py

@@ -1,4 +1,4 @@
-from typing import Type, get_args, get_origin, Union
+from typing import Type, Union, get_args, get_origin
 
 from pydantic import BaseModel
 

src/crewai/utilities/task_output_storage_handler.py

@@ -1,6 +1,8 @@
-from pydantic import BaseModel, Field
 from datetime import datetime
-from typing import Dict, Any, Optional, List
+from typing import Any, Dict, List, Optional
+
+from pydantic import BaseModel, Field
+
 from crewai.memory.storage.kickoff_task_outputs_storage import (
     KickoffTaskOutputsSQLiteStorage,
 )

src/crewai/utilities/token_counter_callback.py

@@ -1,5 +1,6 @@
 from litellm.integrations.custom_logger import CustomLogger
 from litellm.types.utils import Usage
+
 from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
 
 
@@ -11,7 +12,7 @@ class TokenCalcHandler(CustomLogger):
         if self.token_cost_process is None:
             return
 
-        usage : Usage = response_obj["usage"]
+        usage: Usage = response_obj["usage"]
         self.token_cost_process.sum_successful_requests(1)
         self.token_cost_process.sum_prompt_tokens(usage.prompt_tokens)
         self.token_cost_process.sum_completion_tokens(usage.completion_tokens)

tests/agent_test.py

@@ -1595,19 +1595,15 @@ def test_agent_execute_task_with_ollama():
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_with_knowledge_sources():
     # Create a knowledge source with some content
-    content = "Brandon's favorite color is blue and he likes Mexican food."
-    string_source = StringKnowledgeSource(
-        content=content, metadata={"preference": "personal"}
-    )
+    content = "Brandon's favorite color is red and he likes Mexican food."
+    string_source = StringKnowledgeSource(content=content)
 
     with patch(
         "crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"
     ) as MockKnowledge:
         mock_knowledge_instance = MockKnowledge.return_value
         mock_knowledge_instance.sources = [string_source]
-        mock_knowledge_instance.query.return_value = [
-            {"content": content, "metadata": {"preference": "personal"}}
-        ]
+        mock_knowledge_instance.query.return_value = [{"content": content}]
 
         agent = Agent(
             role="Information Agent",
@@ -1628,4 +1624,4 @@ def test_agent_with_knowledge_sources():
         result = crew.kickoff()
 
         # Assert that the agent provides the correct information
-        assert "blue" in result.raw.lower()
+        assert "red" in result.raw.lower()

tests/agents/agent_builder/base_agent_test.py

@@ -1,9 +1,10 @@
 import hashlib
 from typing import Any, List, Optional
 
+from pydantic import BaseModel
+
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.tools.base_tool import BaseTool
-from pydantic import BaseModel
 
 
 class TestAgent(BaseAgent):

tests/agents/test_crew_agent_parser.py

@@ -1,10 +1,11 @@
 import pytest
-from crewai.agents.parser import CrewAgentParser
+
 from crewai.agents.crew_agent_executor import (
     AgentAction,
     AgentFinish,
     OutputParserException,
 )
+from crewai.agents.parser import CrewAgentParser
 
 
 @pytest.fixture

tests/cassettes/test_agent_with_knowledge_sources.yaml

@@ -1,6 +1,6 @@
 interactions:
 - request:
-    body: '{"input": ["Brandon''s favorite color is blue and he likes Mexican food."],
+    body: '{"input": ["Brandon''s favorite color is red and he likes Mexican food."],
       "model": "text-embedding-3-small", "encoding_format": "base64"}'
     headers:
       accept:
@@ -10,7 +10,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '138'
+      - '137'
       content-type:
       - application/json
       host:
@@ -36,122 +36,15 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/embeddings
   response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6SxOyurrmfP+KVWtKn5KLkGTNuIuABAFRu7q6QJGLIAKSQE6d/96l367T3RMH
-        EEpI8j63N//5r7/++rvPm+L2+fufv/5u6+nz9//4Xrtnn+zvf/76n//666+//vrP3+//N7Lo8uJ+
-        r1/lb/jvZv26F8vf//zF//eV/zvon7/+jq6vjKh9O4J16w0pDD6Sje2RqsYS44hDcWl9cPKQzIYP
-        H8KK5NDZkVu+3eVi0B0ntNmvzxlIl3fM8DMLoM+bIy5Ux2e0iE4p2g/aRIr0JXu0ntIb1N1dFLDx
-        vowUa0+I7jsjmhXu9AKr4lIODLV4wOaJfUaWM6xD7yWLWAN5O64qLkxZGDl1trNOzJmJMxdZUpbh
-        AEQuW8BVVtEHpGdsyZmZi5p5NBE+0gc+HuXJmyk6l1ADg42tKQ9y0Xw/fPh63+7EZnXH2OF8HODb
-        G0ZiuboPWMlffRCXuw/WsMAD5omxiNpX0c7bfPUNcYtoClEq74JJuHfjcnknNjrPtoEjd5FZ9zjC
-        AVrdxyOH6fUEzJUVBxl740z2mWwCQRrXHp128E5uN6UxlmI1IcJucCR76ebE0t6UAiW/imdsTI9P
-        vJbUKpCY+SI2z0YdLwN0dODkyCe5qUYetTe0R/PoaiSXjz5Y5wSY0OLiS7A62gxWWYlUsOmVDdkJ
-        6p3xb28p0et2+BDtVdFmQU5JZe58UcmDNi0j8Bqm6NpxyvxeMx8ICbhPf74n/+y5ZlHOvgnfA7MD
-        fnPaeWTIqg5VoZrOfaJazaeOjhdErOOeRNNUNnT/5ETITnxGwvfrFbOukCMYDeEb37I7x0ikyTMQ
-        RqiS073hgQTTJoNR7gREraukkYKqjZDw4iNi4EUASxTJIfi+Dy4CIcqlzUd6wpFuP/g2hed8ZUvl
-        ImSmhwBpWwDmy92BSnD3pBmMYW7wz4Wm8JiNJ2ycGziyOAo7NFwNOG/GNI1Fa/IdMPZjSCzmXWM2
-        XbcBykOSEi+vroy5Lc+hoTpe8f1xVwDdP0URzdltxfErujMeKFoK92QKZkELhpH2e/MJJXg1sc1h
-        f+TpCnz45CoZBwduGNlukp/w8fzYRMWeGovT5ZiBA2fcsNayyiA1Vbaw3h+35FJ2QSPa7l0FjYNR
-        sGZlbgiZeBsgV8AD0ept7bHdtHTQp71P8kKwgOT1bwWcac8RCzgxY5zjmOhb/9hF8Pv+99BFvirW
-        RBdO2PjdV+hV90jxfb/nhswZbPHBwdnc2Q1/3SYOOk8VJnGmqkB4j28XlIZQ4WKeNLboB0uBNr+M
-        OHfNvUdgOmaKogm3AKJM86jkeyqULOOA3Z23b4TbyiWwGqcjuWkGG1cbjiqc9W2LI77Y5TxnNAPS
-        l7s7z9v9yhbbEQNU05GSfVPHMZPPCUXdLsJEm2bVkPrdncJPs7pEl7n7uF5TYUacPS3kxuucQa/b
-        mwsWyRzJ+WSWDb0Ogw85zuxJEQhrvJJHMMHU3tbkIgbM+K6/D6mJg5mpOg/WBMISnt8mJSH2ypjd
-        02UFV32PsG0H9jiFXNDBIg522Iw0G/C6qWaoql9hIH1eptEb1HPh+Z7xZDcXHhO28FgDf7M7EzNZ
-        ImPZT/0WJjCqiHF/xYC/8+YNlqU/4XQKckNQtixAerZW+EB86C2+gRzltegj1pygNtjKmRBO5/aE
-        PXYQxvVxhD2Us8dz5sxYbZYeyheY93FDHEWVwezpRIduv1kCoGxgTkMueMJtXj3m6n6/jsO4W2uU
-        ctGVaNaCWB89/At8noUj9l7v3qDhA1HYRGqAo3F4MjLurwlsnAOaFWojbzrLVgkGQ2/w93kw303e
-        hJNzU7D33Z/irv/w4Mxbd2LVbZhTqrY+Wo+Yke/8MVaVNx0KZ8/AarA3mYSkt/vbXwSzmAJWzRaE
-        WwNFWCPxOWYv5NpQKL6rg5Gf8wWdHZC6Z42408M1hMYPXLhB6mfmXN8An/OkZJALQg7nryLJ+dNl
-        t8IT97ZI5Pv6KMQcr8P47c8kF+yrMafQc+ByhiF5OMfKeDc1jRB0xBfRzivJ+/e1KZC5OccEb0Iv
-        pp9WGeCzNTUSgavtSZ8NmeQnuRbYEyutYdd8f4PVQsbZlJoyZ9qiDGg7jArZ9a0zCicaTkgqnICc
-        goM6So9ligBneYiol/t9XL1n6kDbsFOciI4EmKA6HZRFnuCgS7OYmkeVgyJ/5oK2mp1G6AJtRuKw
-        tX71PFKS1BdoF5ZOsOuasXCoLQ5lYhcEm3u5HUnxuvRQ5/QBm77TNCs6diEK0kjGh8TUYvEqBDXg
-        dw3B6vZRMipxVx3eNneT3PqCNst12utwpMoHu88aj3/4d9yXQtB7fuMJxlhMIM3VkNyPL+SRbmp8
-        dNYzhxykvdj86lFxA/4dyOd2y97+eU2Q62UutqcAGFTYbhxwPYsP7J6hnYvv546ibjU7nGxOO4N+
-        dm8RNuU9w/up2jerfBI4FBoPfqbzW2df/FhBD8twVgrJyufLduKhYT235AoC7AmCcuLQjz+9bdYa
-        LCxsCJuPqmArEolBTrfJh8Ham8TFG4+x4EVrpFWCiK8xW73P8S5G6HBOeLJ7XWTjM1abJ2zKR0b2
-        ERximhSxCphsNwEyT6qxXu4qhAfxgYkXPx/xcBXsEup1Qr77TfMEAEoXSafphsO+9YDkyyqFV91D
-        2LNkIZ4QfVAo+/qFuKos58uhvwYgMZUB+59yMoi1D7agcW8qvlZ8wwTKZzoIFk4IxHlX5OzQGh3S
-        C6xif653jeAbgou4k+QH0sbkAbmKbQIn4tXEL5idr5xdRei3vvrecPOvHtMh2tEJX6L2BiQQczfI
-        nTMVa5qDY6qc2hCapeIQ/Oy8mNojuMHWSVziOV7L6O295ZFlPPRAnILce+9eOx1ujU1EDhv76JGZ
-        rye0X1olWFH0Hmku1StaQHANqPCswCInDwfah5zN4nCSxlmr31uQX/kzdsikGbQhXgbBe/KJ7vt1
-        Mx1K4kC3Rwv2QfoGbHoNLhA9O8deXslswcJxBenpPM/1STXZCt7aCt6P9Ups6ITGOl2OF1S7/IT3
-        Q995rPkkHfhczIBkYZ81LEVvCJVr/sZ4yT7N8uNL/pio2FgbM2b7vErQsBW62WukKmaOp98gPvQU
-        746UH1dasUFZjwdGsiGPGM0cZqIfflivl8eEQ38MYKSdOOLNz5fBskQM4DG2HHLcRp+G5tJA4cZO
-        LHJqbhfv7VjnLaxje4+1YNfm7GFVNdS74o4xf/JHaZu8eDidX6dZfnduw8pUvaB2M2kk1E5681Gf
-        7wy6Wd3OG2BJ47I9owJuaXInZ+5wMBa9oSp6JpcVWweejUvwXBX0fqWvmTOOT0CvQ+0j6c27+HLS
-        K0/yzIP40+fESDgrpgXtHESseE/MC2x//gDCLz/gI4mleDAmoYaJFAfYyCRnFBLtrSrcJ78GpXKg
-        +Wp6doaWMxfO8EJIzqposMH5Ck9fPdQyUeTeM+yVzY24F073/vAjRrcsAEuyxixnOxWyN3TwowCa
-        x9/elEcEvlVyxX2RC+tNLEFGVBXvPq+nQfXjmiJtN814N7oPsGizoAMsqD1JoUO95bYvS5i12w35
-        +iuPTw7QhbZXOsQSTAjYpgsVNNsnk1jqWQdCBLGp/Nbr8Z1fihKgwCDiM3LsGz+mPz3RMreaueOu
-        ZhOMbAi+84V9HYqAGGWdQUeFJdkJ1wHQGN19+NVPJP/iA9l04RZ2gXcIVplD49xu9k/w9SfYtPQQ
-        TFna6vIXD3GRXR+MlqKjwo2dWlgFd8tjcenWUFsrK+A5a82JLzsrPImHGIeusAWf0gp5REa0EKfs
-        5mb96gtAmReT3Z4pBhOL4wUmWE5JCG3GPjHOOCBp3UyyL/5OSzVAcFfgQFQAHuxTxLyLfvW/fyWZ
-        wdjtzsNrJPkkQN4cU2LTG8LLc49vjyHwlh1aHHR9XKYgUaW78UxkcQvuUu1h9dYfY1Y2a4LUZ9Fi
-        mz7rZo4Ig2hRGndeY+5t0NO8KBCbDZlFzR+9z0/PHorDik351jA2no0QUn7eYQ/d1FFKyVaF6TLJ
-        AZxCKR7icFkhON4oca/CGzBzEHV47aBCwjMfgM9eiUQUdaJL9L7ywdI+jhC+7ms1z02HPcnwPz4s
-        9HI70+C1aT6H+sDBjIJpbp6fblwSrVKRATmC7Xbae8tYSR0q0DnAvrPv4tX0ggsUBWXF9u0hg9Wa
-        TAfOH22aKd3L8XJIEh0pIZICGCKn+SjrC8JyXxrkV1+rkFkDsPK5+OJ9wliEmx4STRyIfrty46R7
-        LxP6UuViH4OJzb0lQrCiJ8KHjb0Ys9PiGvpS42JcjVM81cFhgI/EkAg2gBzTodmY8PEk9jySPADC
-        Dy/KMpjwjq8bY3GCi40sIvozSvkpXuK7qYBfXsDp+B2TXVBSdPRKBSelrMb0MjslFHAn4MAzvEa4
-        TnsVivbOwXtH8xq2U8YanquywY8dbuPFCUIbaVJ9IWb9wmC98XcHXIHdY/OrFz5zZftIpU6Fo+Ql
-        AfY6vFXQ9MYLY+dYeZ+V9QNMpGOA3eMW5yy9HraQls8r9rN7wWZcg4uiH98lMUu5jBmHOwr4KZ1m
-        sNsPBnsbUgEv28nEafKJjekyOzVcdrFGnJTScfnyO3zHvvzFgxqML3JxoQr1dQbpdoyXhWt70KBp
-        T45W3Hj0c8opPGbv0x/8FHkZi6CUVpm4MBjzKd2EK1SUdUfMNT16C3s0NxhAVGFzTReDlI2S/vT+
-        zw+wZb1x9c+fBP3SPkdB2YIA6nbPcGDG5bhQ/psnHA4GSbrVaCi/0S/oi1fYkK00nhXepuCnP01j
-        //nlFeoffZcZqsDWttxS2BuvNhB1JWuW/aWZ4Hs9JcRjh1Oz5kqZgTGoHeyV8z4Wu3t0g0IXF9jX
-        DNasb0VWlDO/u8+0b0dGq+SiQCjt7mSX59zIfFld0V6KbsRQ9YTRQlwu6Dw1GBuHbTQu751lw6y+
-        lWQfs9WYBcBT+Oa2PH5o/A18wk17gZy1R0S73+VxDOGDQqepsrn+6oXVnmUb2u0YzjLaReMY2FqG
-        zlfuFFBfDg1yhdsOJnv1go8oeXvrLgNb2L5uLbmZQhZPfDanym7y6mCm/jamoXncwstHd4hGYilf
-        HOuxhb551LD9nR+haqoB8Ql9zGUXg3yqQ6WDUe4G2PVFBtZ9ppeovAwFMT6VA+ijrVx08i6QnJAm
-        xQQ6SwFgUjfE3B+ezQLjz6qU4HCZ0TBrsQjlsoen9PrGxo1Oxvp6zTa88cUl4EQrHyldQfDT77O0
-        Z5nBnnRfwifsgyD16bahp7CyEf9gHta/+dfg6S8Vqv7BIbiKNvnin9cUWqkGMZbPvUcBE02UFcmC
-        bd47NQvtevtP/Rxi3RqF7OKJysU4bIl1Uex4ZtlGh226pD89bazVRBxoAoXH3qtIYkHTlRAWw5rM
-        Xf/qDXaZrjO8QbWd+5PcgzWLzxn45o/ELaQ2JpkcRWizuLfg43DzuJzRMUKb6Vxg+7K1GSlTJ/vp
-        nz954h88IZlpY1OV7t4snxCEFLQWUbs4jz950tZQ8J30h7dsjtBHgd4phbP8xZ+JHk3zT97JU8yP
-        7f21pD8/MG8sp2dsyN5P+F2fH54CVoRzDb3w/CYOXzbjRAtRh5rnHcjesqdx+uGnWssL9lV/ZMOi
-        miWMrm1GvCsb4uGrZ5T98lKwNdQD+zydlwg3yXIk3zwlFsugSKF+TnWiAf3SfIbzCOE3P8G7+1YH
-        c9HKInS9i0vuVcrlP/xTbvtBI8ZJOBj89UYj+PUHxFfsk8FIBJ6wqNN6Xr75AH3d9yuM1U1EDM/Z
-        xVT8KM6PL8gjkdw/zwPOCCMc5pt6ZK3a32Cp5voffqHy1ejg8bW1/uQJs3hbO3gJb/08c7rokXog
-        PTx4wzZYVdx7c4HxDFuirgTPQ51Pe7tTUUVc+uXHt0E39qUDM75Z+ARdMpL7eh9++UcAszsHxovi
-        9ZALIg7/9uuHNMCFUzmfsbtUVrOOUvwEjw+/w0cIoLFOilrCMqkpwa2oGqK7zROQfzgrAPTuNqtv
-        5Rxc/DAJlP7TxCy63zuF3ophfrpYNaRrrhVQvSln7BT1OV/iJnSh+zJtHGz3EZBOwXc/36sn/vkL
-        +tHSDgbtNZmnKTzHC0n3AaDx6Y09x7MYH3J2By3pkuH4sI2atToaEeqekhjU1rFpvvpY/9V3MH/x
-        e7ot5/q3f4iWo8abL8O6RVe54cnhtFI2teHeh21xaogZdly8Nutehffi9cD+M4bsu17/5q+oFvWG
-        8qX8hF99jC097Ixl3jxUmL3PxTzPMQ9oeRw5cJiBNvOzh3KKdhqHtlMwYz2An6YDIpvhNx/8g+8M
-        xFzxy2/IzpvuMZX5VwF/eYMhF02+zvVHhbW8q7H5HF/ewqvvCLatvGBNCo+M78rehFmrbIhbvydv
-        dcAygFwPXewlSwCeQNmncMcIxe63/7Cc0TWEm367ITvZW0bqP60CXJfNK+D9jZf3C7JFIOCngHH+
-        EgymPdUJ/fT/1+8Za6ChAaT1s8DOwbKbuRkF+qfedBrHIz10ykWRDsUGa/ONNPR11yhK/EIKWlCV
-        bJ06LwHUYzlxj9qu+fBqFUEVzhoxqqsyvr/5E0qIsXzzJZwTc+B0eE0yNfjpo6+euMEXf3eJ81z0
-        fNnCYwm0iOSzEBzKkemhUUNIGhwsp/Jh0G9+98tLyK493sbJGy4T3EFxCaauPRjT+3XK0M8P2unG
-        yIn2VGcwLFyPMSdx8RRwEoR9KJ6+/BMz6d12Hbg7Txvb5fAZV3GbFmhz30Y4PxyqfBl7nYdD5HA/
-        PjQ+vutcgLwJK/yA0c4gnnng4YGpdBZ2kdaw2k9FuDkmK/bbuY3Z4Xzt4VzPGPu3Kv2TD0Gef+6J
-        ulwDY8nEWw8P55SfWz20DSkwkgKam1McCM3tYqyWur+AL37O1TtLDOb17y0cIpeb++5xZF8+N0HF
-        ogfGUvEcmXfxdHjaJEnw81eLME06/OlFjZYdm++nDMKuywbsJGrbLKW/qaGbZhL++klDUA+bEKgx
-        SwP+rLgerWqdh6B8ecReo8ggQQxS+Jblilgypg2t1XwG6Q2AWawbCsj4RAHgYMWTn///9ss4+O2P
-        Eb35uLk4vqseLuvugvdiW46fpdFWCG/caUaq68fSLQtt9NVPxE+e+fjGxWuA3zyFHKqUi//4QXOH
-        bvj+7U+txKh5ePZJO0uvi+ytKTRcCK3M+fr3eGT7/J2CP36HdXXz1acO8jsJYEcMmDdonkThKLHx
-        33x5kWz1h9dkp2dlvGR9PSFtN8+BWFzuxsd5Mwi++DYjIzZzgtM+BN+8nHjf/owoS635wxtiCDEZ
-        yTiqBUKoJcH6JJ3BBFINaOqjZ4CyjWoIgZqKCl66/Q+/wPLLN0svn4lKazsXrSIL5Az7KSmcJY9X
-        zZNW2BX8LUD06jWrlJIUNoft49tPWvNVM682JFWfEGuoXbBUeCpgf5s6op3KjUffg5v8/CHR19YA
-        i2vONXBKGwR8RXuP5cfHVzGjKrjMx21D8+uRg0pUj1jP5N744Te8aMkB7z+XJV/uQhMi0TPzWc7p
-        NK5nQdpC6i15cGblLl9Rf7lA/E6mWf7ll3654aGWi7d51i7aKGbedgKHXjWIOd0PQOh76ENtbSxs
-        IU3K2WpeInibmUAOdzLGc5m8n1C3B4Z12xljKtzzEP70o688dE/imhGCKjf0WXad3vj5fUCCizsT
-        tA+AOF2uF/jt1+H7xj4aPGCcCWtuNfEh26ger39SH0aV12PfDmuwHprn+ut3BcJ4XZvuujcoEqP+
-        TX54wbbjEf70a8B9+8Xffm0NE/8mkW9e5/HS9kC3v/zZIL0VC+HCbuiL7zNnuX38m1+E5keCv3yR
-        s8DeZ6DvLzXOdt5+pGP3VCE+rg+yM469t66VHiFcKkqgfPO0n/9Gv/5JUCC1EU3PvqC2ODfYmY+X
-        hixMTmDYcyrO80oGFOxYCg311QZL8ZlzlqIKomN9aDA+wtF7/+rfbt8hDrcPlYlWEQXo1z+9j+3b
-        WGperSFz2oHsv/ky/X4f4GDDY5Xur9/9uVnhYyvy2AoOarOGLIr+9Ce0JoWA4WcUIIFkD+yfNk9v
-        CeOhB1HHu/j266/J3rH/zR9+nOYjWKPaVYF7FVLiKRsY08joa/D371TAf/3rr7/+1++EQdffi/Z7
-        MOBTLJ//+O+jAv8h/cfUZW375xjCPGVl8fc//z6B8Pd77Lv3539/+mfxmv7+5y9B/HPW4O9P/8na
-        //f6v75/9V//+j8AAAD//wMAOXBqMeAgAAA=
+    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
+      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"RAzvvNZhB72TKMC6vj3KPByxsDvjnSG9nod0Pf28RT27Fx693vMfvX5KQ72FkxU9DuF2vAc8Dj1ip8m7VLkOPY5+vjxIiCW9wdyavemQabzGSAc92tD5OzbQ1Lzmw009/kAbvPi5s7ymwHw7udFdPMuJrrvQjMC8anf3O3hHsbyIucG68QSBu6RcO702oom9othlu30f/jsR6aE9BEQtPImp97y44Sc9FToTPeDQBTrIYwI8FWhePCn9FL24iJc8oY+fvGVGmjyFKru8vk0UvbiIFzuK1Dw89+d+PJI4irx0nS+9kxh2PDw8QT0IV4m8Ih2dPALQobyan129bPtMPYo9Fzs0bBO96ZBpvBlQ9bxiTrk96N5IvDBJ7bxWLRo983gMvfUaYzuSDUU9slrAvIJdHz1szYE6avAbPDbgnjyKlie9PnI3PE0ypzxyKaS7ii1NvRie1LxYz/A8FTqTvVbvhLu4H708BV8oO5mEYrxpxVY8N4L1vPWDPT0AtSY9Z7qlvCoYkDx+SkO84yR9vIqWpzu4tuK8EgQdvM6/JL3C95U8vfSDvRKbwjw6MRA9Kf0UubarMbx4R7G8tM7Lu2GMzrvJrMg8ppIxvTxnBjwmxx69GJ5UvTDdDDyKLc284yT9PCZexDxHbSq7IJnHvKYp171wDqm8hZOVO5UFJj0y6D29WgVnvB9QAb2+1G87Xr8yPZpxEr2SOAo75+4SPQX2zbvGdlK99YO9OSGJfbyuYl+7R9YEvNSy7DytsL68Gnu6PLjhp7x1uCq9E8YHvAWNcz2jbIU7zA2EvMCDijylDly9UYOYvMkVozw20FS9qfZyPbNl8bwgmUe9pvsLPU1gcj3GHcK8MWRovAZ6o7x6y4Y70gDMO4Mfir0MfbU8b/OtPB4lPLvxm6Y8BhHJvPUa4zz4UNm6BNtSPFGxYzyX4os8aNWgvHDjYz3rP4Q8xkgHOy18UT2k8+C8JCjOuSwzi7x9iNi8iPfWvJVuAL0syjC8wIOKvNIATDxSRYM9FB8YPFyJvLxYYxC9bCYSvVD/Qjzdb0q7YreTvTFk6Ls0bJO80pdxPTz+Kz3mlQI91TZCvcj6J70xzcK8/KFKPfT/5zvuk/u7qTGCPeq7rryc5R07uvyiPBRNY7tGuwk8vAdUPMuJLj0oEOU8IJnHvMlDbrzZhzM8gJADPdoLCb3ZhzO9Zd0/PFLM3jz0aEK9L8KRvInkBj09wBY9WbygOm7I6Dw8/qs8JvVpvOAOm7w6yDW98BfRvLDmtDzIUzi8rFcuvQr53ztKKvw85tMXvVbvBD3Vn5w8DlobvQ0BCz3mar07gCcpPNKnu7zmaj09/GM1ve++QDz8ocq75mq9PJ7wzrsidi29INfcPEa7Cb0VOhO9MHSyu9JppjwOStG8h478vD3u4TygC0q85I3XvHKCtDxQaJ08I8+9vKLoL73WYYc86N5IPe++QD0O4Xa9Pe7hPPgSxLvAgwq7DBTbPBR4qDzEqTY83FRPumXdv7zNlN88lQWmvMO5gDwp/RQ8QvHzvFaGqrxPpjK9BY3zu5Jm1byqesg7iPfWOsHcGjzP2h+9YHHTvNo5VDpv8608AtChPEu+mzyGrpA8Vu8EPSLfhzx4HGw81EaMuxPGhztl3b+7h55GPFAqiDoKy5Q8qAa9POBnK7300Zw6/SWgO3gc7LzFLQw9lZzLvMYdQjsDcvi8xzi9PCpWJT0a5JS8IKmRvEoq/LyK/wE9URo+PI+pAz3o3si8I7/zPPpYBL1ygjQ84VdhvCSRKD04FhW9DBRbvHvmAbzKx0M7r40kPU0yJ71NmwG9ob3qvJy62LzZ8I28sE+PvHkJnDsNmLA8NuAevWy9N7tOTSK9tm0cvDJRGDzsmBS9hHiavPlrVLrxMsy8ij0XvYQ6Bb0r+Ps57MZfvOaVAjpBEQg9GuQUPPhQ2by+5Lm9Ih0dvcrHw7xbmQY9TNkWvcIl4bx+Onk8WAoAva5yqbvgZys8BiGTPR1zG7xfGEO8OrjrPIHZyTfHoZc7It+HPPT/Zz1w4+O8pinXPOjeyLzhwLs8Tw8NvdDK1Tz67ym9yFO4O1P3I7ySOIo8u67DPKhvFzxmYRU9zhg1PAEONz1fCHm8lQWmPC4+PDw0ml68Zo9gvZUFpjwCV/27WtcbPYgiHL3ictw8YqfJO8O5gL3Saaa7tYDsvHKw/7t6UmI9bRZIu8wNhDz0/2c8RSdqvMBYxboevOE8SXjbPEu+Gz2byqK6lrfGPPCAK72A6ZM9NbVZPclD7jzSEJa8TcnMPFjPcLrSEBa93W/KOw91ljwwG6K79P/nu+mQ6bqsLGk8PzQivbDmNL3QMzC9bpqdvOS4nDyPQCk82APeO8kVozzVnxw90eVQO0X5njwcGou8YDM+PYUqO7yKLU29shwrvMO5ALwniQk954W4vEoqfDyAgDk8WM9wOsiRTTzMeeQ7oAvKvAw/IDyOFeQ7ERdtvZZO7LyY/Qa9UjU5PSXabr3B3Jo8NtDUPPqWmbusVy49FHiovMwNBL1szYG7W5mGPIbcW7zDuQC8oDYPPPJdkT2qEe47aodBuUqT1ryiQUC9OW+lPEqjID0PDDy9ALWmPFg4SzxS3Kg8soWFvITRKrwaPaW82YezPHIZ2jq3xqy78EIWPVa0db3MDQQ9dnoVPDE2HbsjOJg7XTvduR41hjtEDO88RhQaPLnR3TyqipI9N5K/u/lrVDzDUKa8nxsUvTqKoLyDti89c0SfO3q7PLy5Oji9btgyPNU2QrzSEBY9KKSEuppxkjoF9k08yaxIPI4V5Dsh8le854W4u9IQFrxOi7c8ZO2JPB1zG7x+dYi8OL2EPAhXCT3xyXG8fG1dOsrHwztzy/q7bPvMvJlWFzubUf483H8UPIkS0rzAgwo8jucYvZUFpjuFk5U88vS2PHQ01TwkUxO8BciCPGFeAzxtFsg8tgRCu0HWeDw7TAu8srPQO/dgo7wJ3mS8/VNrvSoYkDonIC899RrjO6Y5IT2gC0q8AFwWuxCQETzOv6S8pMUVvc9hezyqipI8bCYSvfSTBzuYlKw87652PCn9FLwitMI7gvREPPgiDr0Ckow8Ho6Wu+hHIzlOTSI9J4kJvdvrdDsM1sW8EGXMu4O2r7yWXra8EM4mvZAw3zzGhhw92R7ZOvUaY7zaoi69sD/Fu0JqmLzB3Bo9htzbPEpli73kXwy9acXWvKz+nTuPqYM9+lgEvVoFZ7xJeNs7ulUzPWaP4DsdCkG8KkZbPIrE8ryVboC7LCPBOuSN17zRt4W9mJSsvL49yrxgMz48Vh3QvPaugj3uk3u8BNvSvB41hrtpXPw82jlUPGK3Ez2OFWS7kg1FPbXpxrycutg83opFvW5Bjb0zqii7JPoCPAiVnjuwqB+9eQmcPND1GryvjSQ7bRZIva+NJLw+Cd089eyXuxVo3rxgcdO8Pgldu8Z20rzGSAe9liChvARErbzeIWu8Mo8tvYHZyblqh8G8pFw7vUERiDzJQ+68kxj2O6s8s7ry9LY7z3HFPKSHALwUeKi7A3J4OmKnSbw2Z/o85ahSvXFnuTo2Z3o8Z7qlPO3h2rwYntQ7acXWPPQqrbsmXkS8pB4mPcL3lTz4EkQ85T94OvlrVLxYCoC8ZCsfPKz+nbuRS1q8zf05PTaiCbwjv/M85E/CvFuZhjxyGdq6aNUgvX6zHT3kuJw8dbgqvQJnx7svWTe8LIybvZWcyzvSaaY8VOfZu2b4OrnJFSO9p+tBuwF3kTxmj2A8jEjIvIZFtjwILMQ8ZO0JPZj9BrybyiI9OQbLOjMTAzykXDu7olGKPBAntzzcfxQ96iSJPB7MKzsqViU9QCTYuxmLhDu4tuI7oAtKO7arsbsmxx68f2W+PBDOpjx1T1A85sPNPLJK9ryMsaI8wQpmu6frwbvURoy75ajSuyGJfbysLGm8CUc/vbEve7y2BEK9CCzEu3Rfmrv8OPA7+lgEO6UOXL3i27Y8qzyzu5yMDTyeh/S8naeIuBKbwrzi2zY9gpu0PPT/57sr+Hu9IYl9PPUaYzxEdck8JdruPCn9FL1u2LI7v2iPu9F89jzCNSu9HjWGu5SBUDxOTaI8pvsLvSKk+DwE21K86qtkO4xIyDzdBnA8N4J1vLLDGrwhiX08It+HPPHJ8TsrcSA74SkWvLabZzzOgY+8EkIyPA0vVrq4tuK8i1gSveM0xzxqsoY8TZsBO7LDGr2kxRU94DzmPHpSYjwWg1m9+7GUvFjP8Dy4tmI7EGVMO7mjkjuMsSI9oAtKPcmsSDywqB87gIC5PHVPUD2/aI88e32nPNTdMTzWYYe8pvsLPeRPwjz2Nd68GuSUvJ1s+bokkSi6elLiPDZn+ru0oIA9+HsePWXdv7yPQKm7ppKxPGH1qLvmLKi7qERSPPSTh7xiPu88okHAO7rs2Dp+o9M6me28vGBx0zzy5Gw7mNLBu+jeyDyAkIO8RN4jPeFX4Tud1VO85ajSvFy0gbxUEh88mNLBO7SQNjy2m2e8Kf0UvOp9GTyQApQ7vfSDvHKw/7u7rsM8iGAxvIrUPD01tVm8fqPTvKfrwbqVM3G8wdyaO+LbNrygNo88+h11PCeJCTyzdbu8lOoqvLPelTxOe+28aS4xOy4Ap70+CV28NndEPMrXjbyIuUE7yJFNvc9hezwQkJE8ty8HPPWDPTuySnY8jueYPJMowDwgAiI8QREIvVgKAD2Wx5A8QI2yO2ZhlTygdKQ8vj3KObEvezqMCjM8iRJSPJUFJj1H1gQ8oKLvPJj9hjwoeb+7EptCvLFqijt09r+8YYzOvJJm1bxTfv+8pB6mvKNshTw1HrQ8d5WQPJy6WLxBP9O77C86PD4Zp7q/aI87XaQ3PXzWt7sl2u42DOaPvALQITsi3wc9VdQJvJ6HdDxcSyc8+paZOLine truncated
+      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
+      12,\n    \"total_tokens\": 12\n  }\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8e94839cd9e9967f-SJC
+      - 8f1042f3ac7867dd-SJC
       Connection:
       - keep-alive
       Content-Encoding:
@@ -159,14 +52,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 27 Nov 2024 19:27:11 GMT
+      - Thu, 12 Dec 2024 19:53:37 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=XviX9Hjm.Uy8aR.6KFXUsi._PlZSGHz_33BG8yN1gNU-1732735631-1.0.1.1-xpDmkFSh5aO2fugj8VCyrc23NL7wf6Q8eq_yaxcwutJZAO5nSx9Eeqko_4UhxH4IQBfS8cJSaEmHnXWPD6lTJg;
-        path=/; expires=Wed, 27-Nov-24 19:57:11 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=PyJpKeiIPAL09jhZ7TAVgnQ5YB7Ha4MplnRyZkvQvDs-1734033217-1.0.1.1-mA.DBohqAynypzvd3K.0J2JY6_HWQcv6SdHAowE18qI9SJ2IsiSScEKWTGPAC3erWYzVwkYFa.cETaf9EhpyAA;
+        path=/; expires=Thu, 12-Dec-24 20:23:37 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=Xz2QlgphZCJYG8KTd5zZKB.lSwPBCu24Nwv2aB6FkeE-1732735631371-0.0.1.1-604800000;
+      - _cfuvid=o.8CU3JYqdXlO9ULnGn2to.2TlmlWc6i1_64SoVhZFA-1734033217203-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -183,7 +76,7 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '272'
+      - '104'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -201,15 +94,12 @@ interactions:
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_5cba1175a36bccbbad92e3ef21b7021d
-    status:
-      code: 200
-      message: OK
+      - req_85d126466fc11bbf5ef4ee743d0c157a
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
-    body: '{"input": ["What is Brandon''s favorite color?  This is the expect criteria
-      for your final answer: Brandon''s favorite color. you MUST return the actual
-      complete content as the final answer, not a summary."], "model": "text-embedding-3-small",
-      "encoding_format": "base64"}'
+    body: '{"input": ["Brandon''s favorite color is red and he likes Mexican food."],
+      "model": "text-embedding-3-small", "encoding_format": "base64"}'
     headers:
       accept:
       - application/json
@@ -218,12 +108,9 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '270'
+      - '137'
       content-type:
       - application/json
-      cookie:
-      - __cf_bm=XviX9Hjm.Uy8aR.6KFXUsi._PlZSGHz_33BG8yN1gNU-1732735631-1.0.1.1-xpDmkFSh5aO2fugj8VCyrc23NL7wf6Q8eq_yaxcwutJZAO5nSx9Eeqko_4UhxH4IQBfS8cJSaEmHnXWPD6lTJg;
-        _cfuvid=Xz2QlgphZCJYG8KTd5zZKB.lSwPBCu24Nwv2aB6FkeE-1732735631371-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
@@ -247,122 +134,15 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/embeddings
   response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SaW6+6Srfm799PsbJu6R05SVWtO84gIIXgATudDiCiICKHKqB29nfv6P/N7u6b
-        mUwmM0YY4xm/5xn1n//666+/u7wui+nvf/76+/Ucp7//x/faLZuyv//563/+66+//vrrP38//787
-        yzYvb7fnu/rd/vvj830rl7//+Yv/7yv/96Z//vrbVLoSHzk5BMtWoT1gp3eFzUA0a2ZdPBt1Tqni
-        qC3bejWaQoT7x7TDxVCH9XwNkgppWjPT01tv/PlmCzGAy97HjkOVehnWOEbb0/tE3fEjAtoiL4RQ
-        1Tuqe2UNFusgp8hF3ZbGcqkPM55dD3oW14QiPL6M5STtPXg4WB+qSkPoL0FezEr0oQa1QWb7pA21
-        M/IfsocN8pRrmozbCH4+4wVrougOq6UdI+j2OkftUt36i58tPNr6XYcv5dgl62H7sNHVFrRQvkk6
-        E98Cb0MzqS/USK92LRjvi4uKZykRpFod621tE8IYKnesXk/nemmyxUNbtkPhKX6eAH+HzYruRgBw
-        FgbHgaj3voflwJ/oOWCHepWjU4WOY0OxPRJhYHIgR8g/lgcamp5ufH7ft9kUFmHxq2OST9RIObvP
-        E7aEdcxXWfIyiMb9gP2evcHq3GaC0pyvaIpELl+O3auAPkkRPd2iNZ8d7xkjAB85vWp+BNg4yg20
-        vGWPjZovfLLcPxFUOINQPNkfRqL4GsPTra+xbjivYV6CTIRBvS8Ia0acME+ORgRV/0JtX7LBzI1x
-        gcZs2mI3TDbGx2cfDh3FbMKm9Vj9pZXkCj1926b6mzv6y7JLnyhq9xJNx7dvsNB/9uh1rR/Yv+xU
-        xs9NpSNguSJNl/o08K9ENRFMlhinyf7GVo14Z+h3p56a3tXyRbtrTNh7qx9uww3JV+ZsdEiEXUCA
-        p0aMvIuHCnzhaRGxVSRAQoFfoRsU55A/jxNb7a6xYXrqSnratDswVHnUI3NGEY6ndWGLz7/FraaV
-        Gqnj97GeWCrayEr3Nj5kFkrmV+LaaCW2j4scbfxF2TkZmtrnTIRbaNe87FUKOrc2CpkhVMN6Y+cZ
-        eh8J0b3+dH2RS6EKT+93RIPlMuak1PIWbk9li7WGbQEJi8cIz/F7wf505BhFTqxCFFZHqpouNoSb
-        karg6Zs2Dje2b/A21J8w0wijxgm+jYVElxaas/j41fPAO14fw+Z5GGis9m1OIw25UEW8hWOrKwb2
-        wdsQJe/5QB3b1WvpKUc61E7BQDOy8Wu2Owwi/NYTjobUSvi0qUbEKVNKo41a1Xy0eY1wubclNvNG
-        BeKJ10XUlqcNvvkVlzO69DMkHJ/h2NkdcmkCaQyDa0zDw9k4DPNterqok5eY7nPzaQx8ckyRW7ws
-        fBTMQyLtek6Bo3Dc40O5KYxVtZUnxI38ouddefcX7sNM9AgkiYDCueQiWrQQprpa02N/3Pm8e91x
-        0EweFxoUUmmw8tKc0VFMJ5rvL9hYpNGBiLpADOVgdAzGTJ7A1L0cv+8nSKjwvKvQ7wKArZrekqkc
-        9Bkik1zIcnAcX7g+mxhGReJRFd1UY7mMh1U53pMXDi7aceDxYusI+MGOWvLhMsypP7conxaHXrZ6
-        ZUi7z1aF1lMzablEDzAjS+8gKCGjxXi/5mt1m1W0N70HAVDWh/U53Voo27xHT6XA1UN2m57gp4fX
-        +BzUNXdaRmWKVxs7+zpN5g042fAePS1q37gpJ9ymk8E5HC9kVcfYWLqpM0HpBhnNLu7GXy11OUM9
-        2gfU6ZGVTyfxGaKL8RSJUFOUrGjZBbAj/Aur8zEyZvCuop+e4ov7ngB9ndYUusXbwmq2/9Qz/8kC
-        kDLzEo6h5Rn8M5R52MksJvnqtQbTx70CP2xhNE6KzCDP6dRAOSstqqu9nfBQ7GWlMSeDiF895aFk
-        8fATGTsCmrM7iGHYcGjOVhXvJB8n0vMweJAIB0B3Tg/AIghZBdjVHqkPlTBfN++EoFLYLnj/4vtk
-        Pet9Ay4RR8nC7VsgFUqjoP0x34Tw+/wXZYczqGfGjjrORADrpRqC8tUn2H6Kaj7uH1WJwsp2KC7P
-        j3ou5NsTSrqXk0LjJ38e+08Ip/l2o7mbm4OEqpcJp5Gs2GGhnn/7t0LYEJdw3usT4K9ZFKNeMxE9
-        rbctWDeh2qHD/jaR/iHmg3D1LiYsNgql5vqy/XEJYhEN1/SNi+zs+NKmuabw9MjD8J42lE12zMXg
-        8nBK7CD7Msx7hT2RuVgbfIOsZms04hg4e+5Dw8/WGERw1ER0zY57ihspHebEiM0/+v99nuxThH6K
-        1ACohMsOXSLct88CHcdCxcVyqgb6KMonLARo0LBvIaN8sjnCQzM1Yf3VI1HSkAh3ub1SYz+dgPDt
-        P4Bes08PHF7r73zo0NRmGrVcIiczXmwVSSMWcVgQh5GMNC38zlOqK5phMIljBfy9Lxa/XCA5e6lC
-        t7fb4jsklr/m53sGC/9EaWx1cFgHqihgHrQyfJXL21gPCuEAMgUb2+eXkazNoslINfYrvdjucxDe
-        lR3/qc8Ad3391dcGxGiHaPkYOYMlx50HN1vzTDam0oFVvHYmbB8bEM5GGPkzy08lMrQrxXF/2yQU
-        9FkDn/mlCeVX+DCk0SYdhEBzsX21lWRxHjcIh3vzIcr91AzrTplt5NXpjUbWlOfSb15BdXfBp6nO
-        fWHZRRUonwcRX779LorXyoRekJxC3tBtNpHbNoPJ0mB8y93rsCyA60GAi4U0NHTY8rbTGK5ZGVH/
-        oZ395TLyIzyLeMRB+26MtfA1GzWD6BH4Mut6oaUUw+/7oOHGPQOW2EEGKpkryVh5DVtpnulwimUB
-        G/pmmy9tVBGIH9crtu+PiX3MQuWR3116jLNNnYwzFY+I7NcWBzbxGcuGZ4SeRJypq+aeIejtIUbv
-        6t5Rd3l8ADPpGoDjHAzUIlc9Z3Iwx2ir8QMtVmUEy+vDZqBwGsHOJ2vAPMUiB9PXsqfYhPyw4tu7
-        RXGND1TbJq4vmMWwwl8/75PJAGu9W234QDMkgNI4kcSdAeF75+jhvDFlY/HZg0OdM5XUfEu7gV5U
-        4sKwTWUi/Hj4/fRGUIj7B/3Nb3Ze1AqW5aCQ5axZTPz1G6VyiHPhYSbSQdoRuNk8RLx3ihbMNxvF
-        0NWZi1XFnYZ5oyge6JxCpUkpL/XCv28zaA/kRr+8VrP1NvLwurQmVtGtMqh371rgnuuVekYRJGsU
-        wxA25YfSMlY8QwSAb+G96niqmnadLEXoZ5B/t1dsIV/M1xA7MmTi80XV+QzYCELZg+8dXqjx5SFy
-        vJAM8Msg0N37tQHMuug2IqaT0n3s1fm0PwRHOBusI/XB5P15eekcDF24CbeaP//uN2EpgAU7dIuB
-        RNc9gRe+7ak+JG098a3Cwzdv1TQMVT+fuKhToTmFr3DrPrGxzkYgwkfva9R36iVfLXV7BGWYFjQ9
-        tBbgX8McopdStNj2pRbMpp3ocKESpCYN30y8GFYFr43nh9xQYsDGKa/g8e6KWMU3LRFGrYDg3/1o
-        hoOYOZsR5sA+0NKiJGdffQP9qur4YIqeIYALteGaUYJN9fWuV3ZKeViUqKeHzyQPC2RdA8X3NcW6
-        XD6H6WZEOvryPjUzrcoXWm7iH99Q3WpePtHhU//xSXgr9HT47LjTGYnGcqNaRfWcPw4mD6zjpIQC
-        j30g7Q6uDA9yOFO9E9/5CndLBsMYjOGK0kc+X9lwhNzuKVCPbPxByNu0AV9eCuvNxCcfWm4i2F7k
-        OzX7M8+W6Dj3yJN2Dtad3SGZn+HMw3kwSuoiscwXafBseCDZig2XST7ty1SGx7g3sCvDzTA9L+8Z
-        nuNzQv0XODI2PTsPcEZo0n2Q3RL2PKgB5G669u2/zpgLaW1gfH+daDY2qTG/xtwDd8MMfjzgrx5A
-        HBTGuiXbZDsZPV/PFaryzxEfwv49THnLntAy3z4O7fcjXxzXk+H3/7967LLlXYWxYplFgbVmIcaK
-        zeIJbnxzxzuhI2BIpmMA0+1DImttCgm15pMLovgFsdFpGlg/MaggOaRPXIbqkLMJgED+8bB34eyc
-        XVQ/VH48FNzjZVgX+ZD9mW+WdJEHFnW9CtvhmVH9GkmASa8ug1+/HQLJhcm868wGJu/1gLEJjwOf
-        mHcI7MSWqcZfd8mcGJkN+WnrkXZXbgyWvnMd/D7vUG8zRhYZnqHcRAaOBR8wOsihDP0yDkPus62H
-        1agXBf708Os/vv4h0tEnyPd4vy1eNT1EhQgy2DYUf5ZL8meeXrPzHmvsIRprsOljUMRHF2epbOWi
-        mPkqkF7zGe+6ewnmYJBlMHovL9y6VZ1QNppPJSGOTnduo7D5OJgipOjoUO0uUWM95/EIQQcqrEuN
-        MfCPDLu/+sI72zDYvLw8DhUbmeJ7I6U1Pa9hBo2T0RNUqAFg4syN8M7ZI1Fua2OsCWUtbF/nNASh
-        XDPxUM0Q/fjbwdwAmjPZejBiDw1fvnozJ8XkwZARnV7kQGbDYFUr/PF5KL9Vn1fZzoTFs5Dorlfi
-        XAgPNIY/Xryz1xEsT67o4d67x9gpRzcfA4tAyD/SC83zfZr3pza0YQZpQlW51hLhZdgy1O3oju2j
-        a/oizSGE4iX+hNv60eVTvGYcrO39OZTWM84Z6FEFp/l+o6b4PjDSqvQJvzwYbufRzJcIqgX68aS9
-        1bjk8/pEPKyTZ0VN87Mx1q/fRfvLWlDMHaxakLefFcKHXZBNkKyA7fqEg5E74JDzBhkwzcxd4Em+
-        Q8C1rZKZPMoeVq9jjctVCH1JcB/qH971JbfIF4UezqjbrwvZHPwXmF+DHMBqnQtsrbcto40j9JBP
-        YIl3OjkkAksTD5WvLqHRJJhM2Cq0g/tHm1HVCJrkj99dl83r933yUVFZCqvXLaa5Uy/Jui1RCD10
-        k0OlnZXkO18JnEbpQS3kn3P2yEELHlKj0PzbT2x+x2cI/KOMteBwZ0sKjinwOzP49q+f86LNt4r4
-        MN94l8cXn4BjM8PDqhJ868nHp+G6lvA1LykuUtbWKwCHDm1pHoegS/mELcKqwvYw3qijhQb49LXS
-        Qv38QHj/EUWDYPP4RHyWc4S3HrExX6ikw9dNn6jhsovxy9ugYPkaocGJqxc93RQwOXpnaj5RD5ha
-        VEeU0SQLZSSWyeyJ2hF+9FdEtd3ssnFuKhVW+XDEO2mf//zaEUaf9hhuv/5Pcg3TQ87rgkmSqeWw
-        ZmTXg3t/1KmtVh1bV6ewof9QPGzviiTh9Q/3BLp0TrAxArX++jMRcm/nFnLFzAYWkCGA6QtAUtb7
-        GCw+T3n44+v4FKg5I17MweGavb/5EjRGLunPsBDtFYfZoctniQQpRJtRwjmd7JqpOKwgubRNKM2M
-        sMULBPPH16TVLcHojGgolZS+PfI5stH4+nsbvploYV94NMnYLdYRjsJ5T6rooiai4NdHODuuRbGf
-        b2qaKxoH98LFDO0wRWAezXsEJBZgeiHHepjrjojw61+wHyp0WL88AL75Vfj65nnMUPQeHbHq4ETL
-        Jn/piKGiLy/TUJv0gb8GYgHNJOvozmmbhP0+r5YOHr42+Tuf9Q9XwVa4OXTPpZEh5Ju6g/zR2WOv
-        nZV8PXJ5DA9NI2CXlzvjW69H9LqpEw2VMDWWHXc7Kz9/oyreNl+NRlrBfVePpFkmZtw6m4UgV8Mq
-        7HrPHySH35VKmm8wdYrDka1oxSb0NYvHfrXxcnLHIIbF6FrUq7BRM0QeImqeLqTBh9Nz0dakEHZy
-        X1Pn3ZfDYm/VAPTe7NMgO7/9mbNeLRTS7UCd5rkAohH9qLyrW0exqvYG2zfZDL95cUhOVyFZbbES
-        EUVnh+rTbBsSdy56cOhs7ad/hnArahtyZ45gqx4sNivXoQJom9r0ui/2QMwcaVQoqzxazplSM+TE
-        OnijXqeWMvrf/EZL0bfffvyfSMjJdKi825Ba7BSwxamYin55cL4GB7bcY9QqIO10fJGDlK22JgUQ
-        lKJJvV3k+WJfzRHsHFr+8orhlzduXb27Ev6wUmOR4isHg/u7CuUn2ydsOtlH8PmQCxGa91zP7nrS
-        oXoWJqyXnliT/pEEf/TBG7p9It03F/NPPaLDEfof2NozLMaYxxq7ewnF7JRC/0hpKKRnNqzumGaw
-        0kiH9/PTZu2Zf83QRf02lHj3kQ/318eEvKDH2IhfLvtYhzn9w+96gLCxfMjEQTsxZfzl8YQv5FMF
-        O7mr6a7JnZx1WdOClO3tbz3U9RhtphEuenIiYn5/Gn/yiuVT+2Tzjkdj3U1lBMEpeYXcxh6M+YIi
-        EU1tNeOfP18e54cCz3T1Kf7q2S+/QnvhZOLd+3Vny/4DS3ASjB1ZyPuSzK2iiD9/EM7eWzFm8264
-        qDSn8I/fX7GxbYGcFRY9hyli5Jt/QFfvr9gEj3lYVXutgO91Cb7nhgLGK1MzeMg6FyeX+7tezqXE
-        wWPK8TgsZlaTV8oTcL+pMtVL7zxMDf/2lOWTFlhttHdOXiteYdJc+VDBVPDXZml4SA7ZE+8LXR66
-        LD+78LmWI3UPrcXWzxg2kEHpTIOoOSWsePAz3GmeTeD391U/ZQE0ymZHz1f9CdaptTIkR6tElmNp
-        JfypOhTocnEXsj++n4zB7S2EsnGbQp5Tc8D377sIhbhR6KXfLMZv3wEHax7pbk1gwurtSYbXqIrw
-        7hIN+eqOUQom7HnY06TKYNZ88iBPtC01DrqbzPwnDhTQrQs2dzViU+z7LqBFvYTvcuzy1YnOMhgk
-        hyOMFZdkdS21RT7gRWyRnBij4z0j+NVPfOYWM18Al0Po6kAi1Ll0xuxeNQiA9ulxoCQi+FjmuUV4
-        z24hnezd1++7PGw33imUEz/214MSqODCZe9QENYgX4U1DeAj+NYvSrX8l3fLwD/LWO2fpbEcO71C
-        uz3rqG5qTU0Kf9Sh5B5v9Ld/WM7lSf3pb/j4zvs/vClfrI5+87VE0gZVRYeGNmT0ZmlY7nHcwcl6
-        D1j75n2ren92QIoPHrYGE4PVKfP+D//iiml+t13zHshcSL/1niZrDVCs7OTnEE4VvOTUfj1mcDg4
-        H+wVymIsm4MOoWzcJ/zL0+a+hQq43O5PatySVz4tz7oBOy0WiPIcdcAnxctTfvnsrlfW5E++8C4I
-        wvsKSvl4r2EPm6e6p0fwiAbRaDarYuP3gA1SaoakFDcRJqAC2C6umiG89Boi9tnnNBYcM5fCBhHQ
-        r+5CHV/Xkt8+YKuepQk7n2Ie5msWRT++/PESWPpaaaAblGfqB3fozxLUPGRXqR7O+L43WOMIHfTu
-        IML7c6gwejxhHTZlesA72XgOYyEpDTRgUuFgVUa2lOZNhoQTM9IluzZfKtcLlWu0EGqfX3VOu0zr
-        0LnwImo0BBizeG9GtJy2ETVntwXLhK8EZndvoHrpekBYQE5gQiydqo2RGBIbzQqKO36mh5P/b96B
-        mrw5UX9+W8O6VmYIvnpE02/eNnx58c/z9JtzNzSa7q/w2kQKtj4P/K3vhIP3XYq++y/69XfEg0ex
-        LsKNqvb+4tJshDoaTIpzI2OEUw35l3dRYxt+8l8+BYe5L4nwuRs1PyNgw03e30KkNwmb1WDjgXJT
-        Rli/hqO/vlI4wjqpql8+nSzhXTPB5yPYf3hysWMxUr7zGtve0U7EUwBU8Nv/ubwq+GtnyArK38UZ
-        7yGrweJS1MFpPhNsDVBndFZfJQzxYSbbcyony6gqKgxxMmNnKmHOGvKswDev+O7/rEECPXrCctNu
-        qJahOV8e7uTBVV308HFLTZ+f4qMK34UwYlyj7UCeR72CaEMkrJmyAFh2e1VQsHYadi6XE6Cn2ljR
-        d/8UVviRAvbdb6KwCsQ/ebzIHEmF+40aU1V+7Q3GnbYEqOcWf/1A+W99+voN7KWylZB9qKswdMWI
-        qht9TBizLh3Ye+cau7b8ydnJyzv41R9sSvcGzD8/7aHTjkST0IDhu39VNptaJO/fPBUv6oigIl+p
-        fxy1WsjbqIHwYRZf3hj8oZc0FelXOcMnh9/m62/fsNnure/+McwXa/AL8N2X/clj6VACEXzrC5/k
-        gzTQildX+GGD+eVFMxHmoy8rbk321K7yEbBNc8hgqus11me8JJ++XtvffhLfaOcwAaCtDj6RtsN7
-        2r3BfHIeZ5RPXYpDVaDDeEfOCO99ufzqxV9tzDj4mLo9xWdnzv/4DS1PJxxGd7FerSxI4d+/UwH/
-        9a+//vpfvxMGbXcrX9+DAVO5TP/x30cF/kP6j7HNXq8/xxDImFXl3//8+wTC35+haz/T/566pnyP
-        f//zl4T+nDX4e+qm7PX/Xv/X96P+61//BwAA//8DAFT8PaLgIAAA
+    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-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8e9483a10d7c967f-SJC
+      - 8f1042f89e85cf2b-SJC
       Connection:
       - keep-alive
       Content-Encoding:
@@ -370,7 +150,110 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 27 Nov 2024 19:27:11 GMT
+      - Thu, 12 Dec 2024 19:53:37 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=OEqOxpPl0XuTSedCFKlaysHtx3Xbo9entNjNd5SahSU-1734033217-1.0.1.1-a.bCXL5.lBOiCyjue9I01oG8aqQHT7tbU0REUBpUu7xMNr7b32iqefcgm6O1l2ToQ_oUtDhAzSBTK7Espxgykg;
+        path=/; expires=Thu, 12-Dec-24 20:23:37 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=8eVoktQyZSE413nzKx4zVo82AF3MS96DjnHQeN.E6Pk-1734033217682-0.0.1.1-604800000;
+        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
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '75'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999986'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_531afeb97985d1513eb1c8f311a1d62a
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"input": ["What is Brandon''s favorite color?  This is the expect criteria
+      for your final answer: Brandon''s favorite color. you MUST return the actual
+      complete content as the final answer, not a summary."], "model": "text-embedding-3-small",
+      "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '270'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=OEqOxpPl0XuTSedCFKlaysHtx3Xbo9entNjNd5SahSU-1734033217-1.0.1.1-a.bCXL5.lBOiCyjue9I01oG8aqQHT7tbU0REUBpUu7xMNr7b32iqefcgm6O1l2ToQ_oUtDhAzSBTK7Espxgykg;
+        _cfuvid=8eVoktQyZSE413nzKx4zVo82AF3MS96DjnHQeN.E6Pk-1734033217682-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.9
+    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\":
+      39,\n    \"total_tokens\": 39\n  }\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f1042fb580acf2b-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 12 Dec 2024 19:53:38 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -388,7 +271,7 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '68'
+      - '85'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -406,10 +289,9 @@ interactions:
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_09708939ca92f32d9d7143e8b7843b12
-    status:
-      code: 200
-      message: OK
+      - req_52a59c31ea2beb8578511f56da5ea2dd
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
     body: '{"messages": [{"role": "system", "content": "You are Information Agent.
       You have access to specific knowledge sources.\nYour personal goal is: Provide
@@ -420,10 +302,10 @@ interactions:
       depends on it!"}, {"role": "user", "content": "\nCurrent Task: What is Brandon''s
       favorite color?\n\nThis is the expect criteria for your final answer: Brandon''s
       favorite color.\nyou MUST return the actual complete content as the final answer,
-      not a summary.Additional Information: Brandon''s favorite color is blue and
-      he likes Mexican food.\n\nBegin! This is VERY important to you, use the tools
-      available and give your best Final Answer, your job depends on it!\n\nThought:"}],
-      "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
+      not a summary.Additional Information: Brandon''s favorite color is red and he
+      likes Mexican food.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
     headers:
       accept:
       - application/json
@@ -432,7 +314,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1014'
+      - '1013'
       content-type:
       - application/json
       host:
@@ -460,21 +342,23 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4xSwY7TMBS85yuefOHSrNJ0l1S5bVdCLHAHBChy7Zf0geNnbGeX1ar/jpxmm1SA
-        xCVSZt6MZ579nAEI0qIGoQ4yqt6Z/Pbz26efjNXW+0/64917r82H3W64f9fpOxKrpOD9d1TxRXWl
-        uHcGI7E90cqjjJhc19WmrDY3rzflSPSs0SRZ52J+zXlPlvKyKK/zosrX20l9YFIYRA1fMgCA5/Gb
-        clqNv0QNxeoF6TEE2aGoz0MAwrNJiJAhUIjSRrGaScU2oh2j34PlR1DSQkcPCBK6FBukDY/oAb7a
-        N2Slgdvxv4adl1azfRWglQ/sKSIoNuyBAuzNgFfLYzy2Q5Cpqh2MmfDjObfhznneh4k/4y1ZCofG
-        owxsU8YQ2YmRPWYA38b9DBeVhfPcu9hE/oE2Ga635clPzNeyZCcycpRmxsti2uqlX6MxSjJhsWGh
-        pDqgnqXzdchBEy+IbNH6zzR/8z41J9v9j/1MKIUuom6cR03qsvE85jG92n+Nnbc8BhbhKUTsm5Zs
-        h955Or2Z1jVFVdzs222lCpEds98AAAD//wMAfDYBg0EDAAA=
+    content: "{\n  \"id\": \"chatcmpl-AdjXeg7urmMdz087X2AhPdSsqamzb\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734033218,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: Brandon's favorite color is red.\",\n        \"refusal\": null\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 182,\n    \"completion_tokens\": 18,\n
+      \   \"total_tokens\": 200,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_bba3c8e70b\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8e9483a44b2fcf51-SJC
+      - 8f1042fffca367e8-SJC
       Connection:
       - keep-alive
       Content-Encoding:
@@ -482,14 +366,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 27 Nov 2024 19:27:12 GMT
+      - Thu, 12 Dec 2024 19:53:39 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=pBzYx.9r7fU6srtt2lLWBrgojr5QFAfVuDKoOwUKCK4-1732735632-1.0.1.1-jYgG33D0s.RUVr6OV4fPXS7bQR9Yp5AwbbIAqdxaZCrcisNIYqPqOqxNO9.Lo3Ok7K8FXfSBrrnAOOJDVLa6bA;
-        path=/; expires=Wed, 27-Nov-24 19:57:12 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=klZf7yZ0CFfDo9eLCfStVSScD0mVgsmNrSz6Ud9on_I-1734033219-1.0.1.1-ar.FWpGgFvtFOTAbByMA5fp9JAycsUeRzBSv6anze.RFpxDOtJVYWslYhhCFIdPyPiHAZGPcuQJxlRbkyr8vRw;
+        path=/; expires=Thu, 12-Dec-24 20:23:39 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=TYAi3OpktKJu15t1e4y3VbRnbHK6QYaCeSYJuT6e5Sk-1732735632634-0.0.1.1-604800000;
+      - _cfuvid=xecEkmr_qTiKn7EKC7aeGN5bpsbPM9ofyIsipL4VCYM-1734033219265-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -502,7 +386,7 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '535'
+      - '412'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -520,8 +404,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_8501f29c09575f05c51fdec5c1c36090
-    status:
-      code: 200
-      message: OK
+      - req_15b9d1b27239c538a259e964b502f4d9
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1

tests/cassettes/test_crew_kickoff_usage_metrics.yaml

@@ -28,13 +28,13 @@ interactions:
       user-agent:
       - OpenAI/Python 1.52.1
       x-stainless-arch:
-      - x64
+      - arm64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - Linux
+      - MacOS
       x-stainless-package-version:
       - 1.52.1
       x-stainless-raw-response:
@@ -44,26 +44,27 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.9
+      - 3.12.7
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4xSy27bMBC86ysWPEuB7ciV7VuAIkUObQ+59QFhTa0kttQuS9Jx08D/XkhyLAVJ
-        gV4EaGdnMLPDpwRAmUrtQOkWo+6czW7u41q2t3+cvCvuPvxafSG+58XHTzXlxWeV9gzZ/yAdn1lX
-        WjpnKRrhEdaeMFKvuiyul3m+uV7lA9BJRbanNS5muWSdYZOtFqs8WxTZcnNmt2I0BbWDrwkAwNPw
-        7X1yRb/VDhbp86SjELAhtbssASgvtp8oDMGEiBxVOoFaOBIP1u+A5QgaGRrzQIDQ9LYBORzJA3zj
-        W8No4Wb438F7aQKgJ7DyiBb6zMhGOKRA3CJrww10xBEttIQ2toBcgTyQR2vhSNZmezLcXM39eKoP
-        Afub8MHa8/x0CWilcV724Yxf5rVhE9rSEwbhPkyI4tSAnhKA78MhDy9uo5yXzsUyyk/iMHSzHvXU
-        1N+Ejo0BqCgR7Yy13aZv6JUVRTQ2zKpQGnVL1USdesNDZWQGJLPUr928pT0mN9z8j/wEaE0uUlU6
-        T5XRLxNPa5765/2vtcuVB8MqPIZIXVkbbsg7b8bHVbuyXm9xs8xXRa2SU/IXAAD//wMAq2ZCBWoD
-        AAA=
+    content: "{\n  \"id\": \"chatcmpl-AcdAr57gPSeXoBUvpM7ihR5ocSg8K\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1733770413,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: Dogs are loyal companions, enhancing human lives with love and joy.\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 175,\n    \"completion_tokens\":
+      24,\n    \"total_tokens\": 199,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_bba3c8e70b\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8e19bf36db158761-GRU
+      - 8ef732d93c754554-ATL
       Connection:
       - keep-alive
       Content-Encoding:
@@ -71,14 +72,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 12 Nov 2024 21:52:04 GMT
+      - Mon, 09 Dec 2024 18:53:33 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=MkvcnvacGpTyn.y0OkFRoFXuAwg4oxjMhViZJTt9mw0-1731448324-1.0.1.1-oekkH_B0xOoPnIFw15LpqFCkZ2cu7VBTJVLDGylan4I67NjX.tlPvOiX9kvtP5Acewi28IE2IwlwtrZWzCH3vw;
-        path=/; expires=Tue, 12-Nov-24 22:22:04 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=zftDGzMKnU559gRET72hds3.GZV1di4sti_Q8aIdqPg-1733770413-1.0.1.1-AXqWYLVe2ClCqIFObmsZXfjYEbJ8Ahbl74TpjGzyxfP1UsSB3HisukLyoXLq52raWViSlB3tLosiLnNEWwWMdw;
+        path=/; expires=Mon, 09-Dec-24 19:23:33 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=4.17346mfw5npZfYNbCx3Vj1VAVPy.tH0Jm2gkTteJ8-1731448324998-0.0.1.1-604800000;
+      - _cfuvid=eff7OIkJ0zWRunpA6z67LHqscmSe6XjNxXiPw1R3xCc-1733770413538-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -89,30 +90,29 @@ interactions:
       alt-svc:
       - h3=":443"; ma=86400
       openai-organization:
-      - user-tqfegqsiobpvvjmn0giaipdq
+      - crewai-iuxna1
       openai-processing-ms:
-      - '601'
+      - '476'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
       x-ratelimit-limit-requests:
-      - '10000'
+      - '30000'
       x-ratelimit-limit-tokens:
-      - '200000'
+      - '150000000'
       x-ratelimit-remaining-requests:
-      - '9999'
+      - '29999'
       x-ratelimit-remaining-tokens:
-      - '199793'
+      - '149999793'
       x-ratelimit-reset-requests:
-      - 8.64s
+      - 2ms
       x-ratelimit-reset-tokens:
-      - 62ms
+      - 0s
       x-request-id:
-      - req_77fb166b4e272bfd45c37c08d2b93b0c
-    status:
-      code: 200
-      message: OK
+      - req_0d2fbea0013ad1ad0768fcdd457f5be3
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
     body: '{"messages": [{"role": "system", "content": "You are cat Researcher. You
       have a lot of experience with cat.\nYour personal goal is: Express hot takes
@@ -138,20 +138,20 @@ interactions:
       content-type:
       - application/json
       cookie:
-      - __cf_bm=MkvcnvacGpTyn.y0OkFRoFXuAwg4oxjMhViZJTt9mw0-1731448324-1.0.1.1-oekkH_B0xOoPnIFw15LpqFCkZ2cu7VBTJVLDGylan4I67NjX.tlPvOiX9kvtP5Acewi28IE2IwlwtrZWzCH3vw;
-        _cfuvid=4.17346mfw5npZfYNbCx3Vj1VAVPy.tH0Jm2gkTteJ8-1731448324998-0.0.1.1-604800000
+      - __cf_bm=zftDGzMKnU559gRET72hds3.GZV1di4sti_Q8aIdqPg-1733770413-1.0.1.1-AXqWYLVe2ClCqIFObmsZXfjYEbJ8Ahbl74TpjGzyxfP1UsSB3HisukLyoXLq52raWViSlB3tLosiLnNEWwWMdw;
+        _cfuvid=eff7OIkJ0zWRunpA6z67LHqscmSe6XjNxXiPw1R3xCc-1733770413538-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
       - OpenAI/Python 1.52.1
       x-stainless-arch:
-      - x64
+      - arm64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - Linux
+      - MacOS
       x-stainless-package-version:
       - 1.52.1
       x-stainless-raw-response:
@@ -161,26 +161,27 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.9
+      - 3.12.7
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4xSy27bMBC86ysWPFuB7MhN6ltQIGmBnlL00BcEmlxJ21JLhlzFLQL/eyH5IRlt
-        gV4EaGZnMLPLlwxAkVUbUKbVYrrg8rsPsg4P+Orxs9XvPz0U8eP966dS6sdo3wa1GBR++x2NnFRX
-        xnfBoZDnA20iasHBdXlzvSzL2+vVeiQ6b9ENsiZIXvq8I6Z8VazKvLjJl7dHdevJYFIb+JIBALyM
-        3yEnW/ypNlAsTkiHKekG1eY8BKCidwOidEqURLOoxUQaz4I8Rn8H7HdgNENDzwgamiE2aE47jABf
-        +Z5YO7gb/zfwRksCHRGGGAHZIg/D1GmXFiBtpGfiBjyDtEgR/I5BMHYJNFvomZ56hIAxedaOhDBd
-        zYNFrPukh+Vw79wR35+bOt+E6LfpyJ/xmphSW0XUyfPQKokPamT3GcC3caP9xZJUiL4LUon/gZzG
-        I60Pfmo65MSuTqR40W6GF8c7XPpVFkWTS7ObKKNNi3aSTgfUvSU/I7JZ6z/T/M370Jy4+R/7iTAG
-        g6CtQkRL5rLxNBZxeOf/GjtveQys0q8k2FU1cYMxRDq8sjpUxVYXdrkq66XK9tlvAAAA//8DAIjK
-        KzJzAwAA
+    content: "{\n  \"id\": \"chatcmpl-AcdArzlm4vKRhN7P4mtNE7X3UrCb3\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1733770413,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: Cats are independent yet affectionate, making them unique companions
+      for humans.\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      175,\n    \"completion_tokens\": 24,\n    \"total_tokens\": 199,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_818c284075\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8e19bf3fae118761-GRU
+      - 8ef732dcfadf4554-ATL
       Connection:
       - keep-alive
       Content-Encoding:
@@ -188,7 +189,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 12 Nov 2024 21:52:05 GMT
+      - Mon, 09 Dec 2024 18:53:34 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -200,30 +201,29 @@ interactions:
       alt-svc:
       - h3=":443"; ma=86400
       openai-organization:
-      - user-tqfegqsiobpvvjmn0giaipdq
+      - crewai-iuxna1
       openai-processing-ms:
-      - '464'
+      - '418'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
       x-ratelimit-limit-requests:
-      - '10000'
+      - '30000'
       x-ratelimit-limit-tokens:
-      - '200000'
+      - '150000000'
       x-ratelimit-remaining-requests:
-      - '9998'
+      - '29999'
       x-ratelimit-remaining-tokens:
-      - '199792'
+      - '149999793'
       x-ratelimit-reset-requests:
-      - 16.369s
+      - 2ms
       x-ratelimit-reset-tokens:
-      - 62ms
+      - 0s
       x-request-id:
-      - req_91706b23d0ef23458ba63ec18304cd28
-    status:
-      code: 200
-      message: OK
+      - req_483f4fc624bef1034c884b5d0e847aee
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
     body: '{"messages": [{"role": "system", "content": "You are apple Researcher.
       You have a lot of experience with apple.\nYour personal goal is: Express hot
@@ -249,20 +249,20 @@ interactions:
       content-type:
       - application/json
       cookie:
-      - __cf_bm=MkvcnvacGpTyn.y0OkFRoFXuAwg4oxjMhViZJTt9mw0-1731448324-1.0.1.1-oekkH_B0xOoPnIFw15LpqFCkZ2cu7VBTJVLDGylan4I67NjX.tlPvOiX9kvtP5Acewi28IE2IwlwtrZWzCH3vw;
-        _cfuvid=4.17346mfw5npZfYNbCx3Vj1VAVPy.tH0Jm2gkTteJ8-1731448324998-0.0.1.1-604800000
+      - __cf_bm=zftDGzMKnU559gRET72hds3.GZV1di4sti_Q8aIdqPg-1733770413-1.0.1.1-AXqWYLVe2ClCqIFObmsZXfjYEbJ8Ahbl74TpjGzyxfP1UsSB3HisukLyoXLq52raWViSlB3tLosiLnNEWwWMdw;
+        _cfuvid=eff7OIkJ0zWRunpA6z67LHqscmSe6XjNxXiPw1R3xCc-1733770413538-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
       - OpenAI/Python 1.52.1
       x-stainless-arch:
-      - x64
+      - arm64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - Linux
+      - MacOS
       x-stainless-package-version:
       - 1.52.1
       x-stainless-raw-response:
@@ -272,26 +272,27 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.9
+      - 3.12.7
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4xSPW/bMBDd9SsOXLpIgeTITarNS4t26JJubSHQ5IliSh1ZHv0RBP7vhSTHctAU
-        6CJQ7909vHd3zxmAsFo0IFQvkxqCKzYPaf1b2/hhW+8PR9N9Kh9W5Zdhjebr4zeRjx1++4gqvXTd
-        KD8Eh8l6mmkVUSYcVau726qu729X7ydi8Brd2GZCKmpfDJZssSpXdVHeFdX9ubv3ViGLBr5nAADP
-        03f0SRqPooEyf0EGZJYGRXMpAhDRuxERktlykpREvpDKU0KarH8G8gdQksDYPYIEM9oGSXzACPCD
-        PlqSDjbTfwObEBy+Y0Dl+YkTDmApoYkyIUMvoz7IiDmw79L8kqSBMe7HMMAoB4fM7ikHpF6SsmRg
-        xxgBjwGjRVJ4c+00YrdjOU6Lds6d8dMluvMmRL/lM3/BO0uW+zaiZE9jTE4+iIk9ZQA/pxHvXk1N
-        hOiHkNrkfyHxtLX1rCeWzS7svEsAkXyS7govq/wNvVZjktbx1ZKEkqpHvbQuG5U7bf0VkV2l/tvN
-        W9pzckvmf+QXQikMCXUbImqrXideyiKOh/+vssuUJ8NiPpO2s2Qwhmjns+tCW25lqatV3VUiO2V/
-        AAAA//8DAPtpFJCEAwAA
+    content: "{\n  \"id\": \"chatcmpl-AcdAsHWkJ3K1sBl3O6XYMZZ3BhHx4\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1733770414,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: Apple consistently innovates, leading the tech industry with flagship
+      products.\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      175,\n    \"completion_tokens\": 24,\n    \"total_tokens\": 199,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_818c284075\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8e19bf447ba48761-GRU
+      - 8ef732e028194554-ATL
       Connection:
       - keep-alive
       Content-Encoding:
@@ -299,7 +300,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 12 Nov 2024 21:52:06 GMT
+      - Mon, 09 Dec 2024 18:53:34 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -311,28 +312,27 @@ interactions:
       alt-svc:
       - h3=":443"; ma=86400
       openai-organization:
-      - user-tqfegqsiobpvvjmn0giaipdq
+      - crewai-iuxna1
       openai-processing-ms:
-      - '655'
+      - '393'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
       x-ratelimit-limit-requests:
-      - '10000'
+      - '30000'
       x-ratelimit-limit-tokens:
-      - '200000'
+      - '150000000'
       x-ratelimit-remaining-requests:
-      - '9997'
+      - '29999'
       x-ratelimit-remaining-tokens:
-      - '199791'
+      - '149999791'
       x-ratelimit-reset-requests:
-      - 24.239s
+      - 2ms
       x-ratelimit-reset-tokens:
-      - 62ms
+      - 0s
       x-request-id:
-      - req_a228208b0e965ecee334a6947d6c9e7c
-    status:
-      code: 200
-      message: OK
+      - req_01df88b62376d0b63fb3fa2761bc9c2b
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1

tests/cassettes/test_llm_callback_replacement.yaml

@@ -18,13 +18,13 @@ interactions:
       user-agent:
       - OpenAI/Python 1.52.1
       x-stainless-arch:
-      - x64
+      - arm64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - Linux
+      - MacOS
       x-stainless-package-version:
       - 1.52.1
       x-stainless-raw-response:
@@ -34,25 +34,26 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.9
+      - 3.12.7
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4xSwWrcMBS8+ytedY6LvWvYZi8lpZSkBJLSQiChGK307FUi66nSc9Ml7L8H2e56
-        l7bQiw8zb8Yzg14yAGG0WINQW8mq8za/+Oqv5MUmXv+8+/Hl3uO3j59u1efreHO+/PAszpKCNo+o
-        +LfqraLOW2RDbqRVQMmYXMvVsqyWy1VVDERHGm2StZ7zivLOOJMvikWVF6u8fDept2QURrGGhwwA
-        4GX4ppxO4y+xhsFrQDqMUbYo1ocjABHIJkTIGE1k6ViczaQix+iG6JdoLb2BS3oGJR1cwSiAHfXA
-        pOXu/bEwYNNHmcK73toJ3x+SWGp9oE2c+APeGGfitg4oI7n018jkxcDuM4DvQ+P+pITwgTrPNdMT
-        umRYlqOdmHeeyfOJY2JpZ3gxjXRqVmtkaWw8GkwoqbaoZ+W8ruy1oSMiO6r8Z5a/eY+1jWv/x34m
-        lELPqGsfUBt12nc+C5ge4b/ODhMPgUXcRcauboxrMfhgxifQ+LrYyEKXi6opRbbPXgEAAP//AwAM
-        DMWoEAMAAA==
+    content: "{\n  \"id\": \"chatcmpl-AcdBV2knOF2soWLszceiA08K8W8nE\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1733770453,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Hello! How can I assist you today?\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 11,\n    \"completion_tokens\":
+      9,\n    \"total_tokens\": 20,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_bba3c8e70b\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8e185b2c1b790303-GRU
+      - 8ef733d51801bada-ATL
       Connection:
       - keep-alive
       Content-Encoding:
@@ -60,14 +61,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 12 Nov 2024 17:49:00 GMT
+      - Mon, 09 Dec 2024 18:54:13 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=l.QrRLcNZkML_KSfxjir6YCV35B8GNTitBTNh7cPGc4-1731433740-1.0.1.1-j1ejlmykyoI8yk6i6pQjtPoovGzfxI2f5vG6u0EqodQMjCvhbHfNyN_wmYkeT._BMvFi.zDQ8m_PqEHr8tSdEQ;
-        path=/; expires=Tue, 12-Nov-24 18:19:00 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=_fEt57lre0.E_IZaebjaDAcrpBbzGhLWW6KtQ4FjLxo-1733770453-1.0.1.1-ndzEQCfExSp1asSdBXxS0fGYQnKVTivInc1MHN.ZjnmGmkAmEp0EPwiJlcAMvQaMCMZ7a_vKqAEMbz8ZbzTYYg;
+        path=/; expires=Mon, 09-Dec-24 19:24:13 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=jcCDyMK__Fd0V5DMeqt9yXdlKc7Hsw87a1K01pZu9l0-1731433740848-0.0.1.1-604800000;
+      - _cfuvid=2gTS3no9rova7t6URcfR30yzeZdKkL.9.lvsZXgmbVw-1733770453657-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -78,30 +79,29 @@ interactions:
       alt-svc:
       - h3=":443"; ma=86400
       openai-organization:
-      - user-tqfegqsiobpvvjmn0giaipdq
+      - crewai-iuxna1
       openai-processing-ms:
-      - '322'
+      - '275'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
       x-ratelimit-limit-requests:
-      - '10000'
+      - '30000'
       x-ratelimit-limit-tokens:
-      - '200000'
+      - '150000000'
       x-ratelimit-remaining-requests:
-      - '9999'
+      - '29999'
       x-ratelimit-remaining-tokens:
-      - '199978'
+      - '149999979'
       x-ratelimit-reset-requests:
-      - 8.64s
+      - 2ms
       x-ratelimit-reset-tokens:
-      - 6ms
+      - 0s
       x-request-id:
-      - req_037288753767e763a51a04eae757ca84
-    status:
-      code: 200
-      message: OK
+      - req_82ef8940a3291813e6a347535ab6bf26
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
     body: '{"messages": [{"role": "user", "content": "Hello, world from another agent!"}],
       "model": "gpt-4o-mini", "stream": false}'
@@ -117,20 +117,20 @@ interactions:
       content-type:
       - application/json
       cookie:
-      - __cf_bm=l.QrRLcNZkML_KSfxjir6YCV35B8GNTitBTNh7cPGc4-1731433740-1.0.1.1-j1ejlmykyoI8yk6i6pQjtPoovGzfxI2f5vG6u0EqodQMjCvhbHfNyN_wmYkeT._BMvFi.zDQ8m_PqEHr8tSdEQ;
-        _cfuvid=jcCDyMK__Fd0V5DMeqt9yXdlKc7Hsw87a1K01pZu9l0-1731433740848-0.0.1.1-604800000
+      - __cf_bm=_fEt57lre0.E_IZaebjaDAcrpBbzGhLWW6KtQ4FjLxo-1733770453-1.0.1.1-ndzEQCfExSp1asSdBXxS0fGYQnKVTivInc1MHN.ZjnmGmkAmEp0EPwiJlcAMvQaMCMZ7a_vKqAEMbz8ZbzTYYg;
+        _cfuvid=2gTS3no9rova7t6URcfR30yzeZdKkL.9.lvsZXgmbVw-1733770453657-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
       - OpenAI/Python 1.52.1
       x-stainless-arch:
-      - x64
+      - arm64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - Linux
+      - MacOS
       x-stainless-package-version:
       - 1.52.1
       x-stainless-raw-response:
@@ -140,25 +140,26 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.9
+      - 3.12.7
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4xSy27bMBC86yu2PFuBZAt14UvRU5MA7aVAEKAIBJpcSUwoLkuu6jiB/z3QI5aM
-        tkAvPMzsDGZ2+ZoACKPFDoRqJKvW2/TLD3+z//oiD8dfL7d339zvW125x9zX90/3mVj1Cto/ouJ3
-        1ZWi1ltkQ26kVUDJ2Lvm201ebDbbIh+IljTaXlZ7TgtKW+NMus7WRZpt0/zTpG7IKIxiBz8TAIDX
-        4e1zOo3PYgfZ6h1pMUZZo9idhwBEINsjQsZoIkvHYjWTihyjG6Jfo7X0Ab4bhcAEipxDxXAw3IB0
-        xA0GkDU6voJrOoCSDm5gNIUjdcCk5fHz0jxg1UXZF3SdtRN+Oqe1VPtA+zjxZ7wyzsSmDCgjuT5Z
-        ZPJiYE8JwMOwle6iqPCBWs8l0xO63jAvRjsx32JBfpxIJpZ2xjfTJi/dSo0sjY2LrQolVYN6Vs4n
-        kJ02tCCSRec/w/zNe+xtXP0/9jOhFHpGXfqA2qjLwvNYwP6n/mvsvOMhsIjHyNiWlXE1Bh/M+E8q
-        X2Z7mel8XVS5SE7JGwAAAP//AwA/cK4yNQMAAA==
+    content: "{\n  \"id\": \"chatcmpl-AcdBWMAembczwWDLdjIRYwtbMLONh\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1733770454,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Hello! It\u2019s great to connect with
+      you. How can I assist you today?\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      14,\n    \"completion_tokens\": 17,\n    \"total_tokens\": 31,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_bba3c8e70b\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8e185b31398a0303-GRU
+      - 8ef733d7bc41bada-ATL
       Connection:
       - keep-alive
       Content-Encoding:
@@ -166,7 +167,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 12 Nov 2024 17:49:02 GMT
+      - Mon, 09 Dec 2024 18:54:14 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -178,28 +179,27 @@ interactions:
       alt-svc:
       - h3=":443"; ma=86400
       openai-organization:
-      - user-tqfegqsiobpvvjmn0giaipdq
+      - crewai-iuxna1
       openai-processing-ms:
-      - '889'
+      - '659'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
       x-ratelimit-limit-requests:
-      - '10000'
+      - '30000'
       x-ratelimit-limit-tokens:
-      - '200000'
+      - '150000000'
       x-ratelimit-remaining-requests:
-      - '9998'
+      - '29999'
       x-ratelimit-remaining-tokens:
-      - '199975'
+      - '149999974'
       x-ratelimit-reset-requests:
-      - 16.489s
+      - 2ms
       x-ratelimit-reset-tokens:
-      - 7ms
+      - 0s
       x-request-id:
-      - req_bde3810b36a4859688e53d1df64bdd20
-    status:
-      code: 200
-      message: OK
+      - req_da24049df911504f5102825db6b4aea9
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1

tests/cli/authentication/test_auth_main.py

@@ -2,6 +2,7 @@ import unittest
 from unittest.mock import MagicMock, patch
 
 import requests
+
 from crewai.cli.authentication.main import AuthenticationCommand
 
 
@@ -47,7 +48,9 @@ class TestAuthenticationCommand(unittest.TestCase):
     @patch("crewai.cli.authentication.main.requests.post")
     @patch("crewai.cli.authentication.main.validate_token")
     @patch("crewai.cli.authentication.main.console.print")
-    def test_poll_for_token_success(self, mock_print, mock_validate_token, mock_post, mock_tool):
+    def test_poll_for_token_success(
+        self, mock_print, mock_validate_token, mock_post, mock_tool
+    ):
         mock_response = MagicMock()
         mock_response.status_code = 200
         mock_response.json.return_value = {
@@ -62,7 +65,9 @@ class TestAuthenticationCommand(unittest.TestCase):
         self.auth_command._poll_for_token({"device_code": "123456"})
 
         mock_validate_token.assert_called_once_with("TOKEN")
-        mock_print.assert_called_once_with("\n[bold green]Welcome to CrewAI Enterprise![/bold green]\n")
+        mock_print.assert_called_once_with(
+            "\n[bold green]Welcome to CrewAI Enterprise![/bold green]\n"
+        )
 
     @patch("crewai.cli.authentication.main.requests.post")
     @patch("crewai.cli.authentication.main.console.print")

tests/cli/authentication/test_utils.py

@@ -3,9 +3,10 @@ import unittest
 from datetime import datetime, timedelta
 from unittest.mock import MagicMock, patch
 
-from crewai.cli.authentication.utils import TokenManager, validate_token
 from cryptography.fernet import Fernet
 
+from crewai.cli.authentication.utils import TokenManager, validate_token
+
 
 class TestValidateToken(unittest.TestCase):
     @patch("crewai.cli.authentication.utils.AsymmetricSignatureVerifier")

tests/cli/cli_test.py

@@ -131,6 +131,13 @@ def test_reset_no_memory_flags(runner):
     )
 
 
+def test_version_flag(runner):
+    result = runner.invoke(version)
+
+    assert result.exit_code == 0
+    assert "crewai version:" in result.output
+
+
 def test_version_command(runner):
     result = runner.invoke(version)
 

tests/cli/config_test.py

@@ -1,10 +1,12 @@
-import unittest
 import json
-import tempfile
 import shutil
+import tempfile
+import unittest
 from pathlib import Path
+
 from crewai.cli.config import Settings
 
+
 class TestSettings(unittest.TestCase):
     def setUp(self):
         self.test_dir = Path(tempfile.mkdtemp())
@@ -20,8 +22,7 @@ class TestSettings(unittest.TestCase):
 
     def test_initialization_with_data(self):
         settings = Settings(
-            config_path=self.config_path,
-            tool_repository_username="user1"
+            config_path=self.config_path, tool_repository_username="user1"
         )
         self.assertEqual(settings.tool_repository_username, "user1")
         self.assertIsNone(settings.tool_repository_password)
@@ -37,22 +38,23 @@ class TestSettings(unittest.TestCase):
     def test_merge_file_and_input_data(self):
         self.config_path.parent.mkdir(parents=True, exist_ok=True)
         with self.config_path.open("w") as f:
-            json.dump({
-                "tool_repository_username": "file_user",
-                "tool_repository_password": "file_pass"
-            }, f)
+            json.dump(
+                {
+                    "tool_repository_username": "file_user",
+                    "tool_repository_password": "file_pass",
+                },
+                f,
+            )
 
         settings = Settings(
-            config_path=self.config_path,
-            tool_repository_username="new_user"
+            config_path=self.config_path, tool_repository_username="new_user"
         )
         self.assertEqual(settings.tool_repository_username, "new_user")
         self.assertEqual(settings.tool_repository_password, "file_pass")
 
     def test_dump_new_settings(self):
         settings = Settings(
-            config_path=self.config_path,
-            tool_repository_username="user1"
+            config_path=self.config_path, tool_repository_username="user1"
         )
         settings.dump()
 
@@ -67,8 +69,7 @@ class TestSettings(unittest.TestCase):
             json.dump({"existing_setting": "value"}, f)
 
         settings = Settings(
-            config_path=self.config_path,
-            tool_repository_username="user1"
+            config_path=self.config_path, tool_repository_username="user1"
         )
         settings.dump()
 
@@ -79,10 +80,7 @@ class TestSettings(unittest.TestCase):
         self.assertEqual(saved_data["tool_repository_username"], "user1")
 
     def test_none_values(self):
-        settings = Settings(
-            config_path=self.config_path,
-            tool_repository_username=None
-        )
+        settings = Settings(config_path=self.config_path, tool_repository_username=None)
         settings.dump()
 
         with self.config_path.open("r") as f:

tests/cli/deploy/test_deploy_main.py

@@ -228,17 +228,18 @@ class TestDeployCommand(unittest.TestCase):
         "builtins.open",
         new_callable=unittest.mock.mock_open,
         read_data="""
-    [project]
-    name = "test_project"
-    version = "0.1.0"
-    requires-python = ">=3.10,<=3.13"
-    dependencies = ["crewai"]
-    """,
+        [project]
+        name = "test_project"
+        version = "0.1.0"
+        requires-python = ">=3.10,<=3.12"
+        dependencies = ["crewai"]
+        """,
     )
     def test_get_project_name_python_310(self, mock_open):
         from crewai.cli.utils import get_project_name
 
         project_name = get_project_name()
+        print("project_name", project_name)
         self.assertEqual(project_name, "test_project")
 
     @unittest.skipIf(sys.version_info < (3, 11), "Requires Python 3.11+")
@@ -249,7 +250,7 @@ class TestDeployCommand(unittest.TestCase):
     [project]
     name = "test_project"
     version = "0.1.0"
-    requires-python = ">=3.10,<=3.13"
+    requires-python = ">=3.10,<=3.12"
     dependencies = ["crewai"]
     """,
     )

tests/cli/test_git.py

@@ -1,6 +1,7 @@
-from crewai.cli.git import Repository
 import pytest
 
+from crewai.cli.git import Repository
+
 
 @pytest.fixture()
 def repository(fp):

tests/cli/test_plus_api.py

@@ -1,6 +1,7 @@
 import os
 import unittest
 from unittest.mock import MagicMock, patch
+
 from crewai.cli.plus_api import PlusAPI
 
 

tests/cli/test_utils.py

@@ -1,7 +1,9 @@
-import pytest
+import os
 import shutil
 import tempfile
-import os
+
+import pytest
+
 from crewai.cli import utils