Fix lint error and validation error in test_markdown_task.py

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

.github/security.md

@@ -1,19 +1,27 @@
-CrewAI takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organization.
-If you believe you have found a security vulnerability in any CrewAI product or service, please report it to us as described below.
+## CrewAI Security Vulnerability Reporting Policy
 
- ## Reporting a Vulnerability
- Please do not report security vulnerabilities through public GitHub issues.
- To report a vulnerability, please email us at security@crewai.com.
- Please include the requested information listed below so that we can triage your report more quickly
+CrewAI prioritizes the security of our software products, services, and GitHub repositories. To promptly address vulnerabilities, follow these steps for reporting security issues:
 
- - Type of issue (e.g. SQL injection, cross-site scripting, etc.)
- - Full paths of source file(s) related to the manifestation of the issue
- - The location of the affected source code (tag/branch/commit or direct URL)
- - Any special configuration required to reproduce the issue
- - Step-by-step instructions to reproduce the issue (please include screenshots if needed)
- - Proof-of-concept or exploit code (if possible)
- - Impact of the issue, including how an attacker might exploit the issue
+### Reporting Process
+Do **not** report vulnerabilities via public GitHub issues.
 
- Once we have received your report, we will respond to you at the email address you provide. If the issue is confirmed, we will release a patch as soon as possible depending on the complexity of the issue.
+Email all vulnerability reports directly to:  
+**security@crewai.com**
 
- At this time, we are not offering a bug bounty program. Any rewards will be at our discretion.
+### Required Information
+To help us quickly validate and remediate the issue, your report must include:
+
+- **Vulnerability Type:** Clearly state the vulnerability type (e.g., SQL injection, XSS, privilege escalation).
+- **Affected Source Code:** Provide full file paths and direct URLs (branch, tag, or commit).
+- **Reproduction Steps:** Include detailed, step-by-step instructions. Screenshots are recommended.
+- **Special Configuration:** Document any special settings or configurations required to reproduce.
+- **Proof-of-Concept (PoC):** Provide exploit or PoC code (if available).
+- **Impact Assessment:** Clearly explain the severity and potential exploitation scenarios.
+
+### Our Response
+- We will acknowledge receipt of your report promptly via your provided email.
+- Confirmed vulnerabilities will receive priority remediation based on severity.
+- Patches will be released as swiftly as possible following verification.
+
+### Reward Notice
+Currently, we do not offer a bug bounty program. Rewards, if issued, are discretionary.

.github/workflows/linter.yml

@@ -5,12 +5,29 @@ on: [pull_request]
 jobs:
   lint:
     runs-on: ubuntu-latest
+    env:
+      TARGET_BRANCH: ${{ github.event.pull_request.base.ref }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
-      - name: Install Requirements
+      - name: Fetch Target Branch
+        run: git fetch origin $TARGET_BRANCH --depth=1
+
+      - name: Install Ruff
+        run: pip install ruff
+
+      - name: Get Changed Python Files
+        id: changed-files
         run: |
-          pip install ruff
+          merge_base=$(git merge-base origin/"$TARGET_BRANCH" HEAD)
+          changed_files=$(git diff --name-only --diff-filter=ACMRTUB "$merge_base" | grep '\.py$' || true)
+          echo "files<<EOF" >> $GITHUB_OUTPUT
+          echo "$changed_files" >> $GITHUB_OUTPUT
+          echo "EOF" >> $GITHUB_OUTPUT
 
-      - name: Run Ruff Linter
-        run: ruff check
+      - name: Run Ruff on Changed Files
+        if: ${{ steps.changed-files.outputs.files != '' }}
+        run: |
+          echo "${{ steps.changed-files.outputs.files }}" | tr " " "\n" | xargs -I{} ruff check "{}"

.github/workflows/tests.yml

@@ -31,4 +31,4 @@ jobs:
         run: uv sync --dev --all-extras
 
       - name: Run tests
-        run: uv run pytest tests -vv
+        run: uv run pytest --block-network --timeout=60 -vv

.ruff.toml

@@ -2,8 +2,3 @@ exclude = [
     "templates",
     "__init__.py",
 ]
-
-[lint]
-select = [
-    "I", # isort rules
-]

README.md

@@ -504,7 +504,7 @@ This example demonstrates how to:
 
 CrewAI supports using various LLMs through a variety of connection options. By default your agents will use the OpenAI API when querying the model. However, there are several other ways to allow your agents to connect to models. For example, you can configure your agents to use a local model via the Ollama tool.
 
-Please refer to the [Connect CrewAI to LLMs](https://docs.crewai.com/how-to/LLM-Connections/) page for details on configuring you agents' connections to models.
+Please refer to the [Connect CrewAI to LLMs](https://docs.crewai.com/how-to/LLM-Connections/) page for details on configuring your agents' connections to models.
 
 ## How CrewAI Compares
 

docs/concepts/cli.mdx

@@ -110,6 +110,8 @@ crewai reset-memories [OPTIONS]
 - `-s, --short`: Reset SHORT TERM memory
 - `-e, --entities`: Reset ENTITIES memory
 - `-k, --kickoff-outputs`: Reset LATEST KICKOFF TASK OUTPUTS
+- `-kn, --knowledge`: Reset KNOWLEDGE storage
+- `-akn, --agent-knowledge`: Reset AGENT KNOWLEDGE storage
 - `-a, --all`: Reset ALL memories
 
 Example:

docs/concepts/crews.mdx

@@ -27,7 +27,7 @@ A crew in crewAI represents a collaborative group of agents working together to
 | **Step Callback** _(optional)_        | `step_callback`        | A function that is called after each step of every agent. This can be used to log the agent's actions or to perform other operations; it won't override the agent-specific `step_callback`.                                                               |
 | **Task Callback** _(optional)_        | `task_callback`        | A function that is called after the completion of each task. Useful for monitoring or additional operations post-task execution.                                                                                                                          |
 | **Share Crew** _(optional)_           | `share_crew`           | Whether you want to share the complete crew information and execution with the crewAI team to make the library better, and allow us to train models.                                                                                                      |
-| **Output Log File** _(optional)_      | `output_log_file`      | Set to True to save logs as logs.txt in the current directory or provide a file path. Logs will be in JSON format if the filename ends in .json, otherwise .txt. Defautls to `None`.                                                                      |
+| **Output Log File** _(optional)_      | `output_log_file`      | Set to True to save logs as logs.txt in the current directory or provide a file path. Logs will be in JSON format if the filename ends in .json, otherwise .txt. Defaults to `None`.                                                                      |
 | **Manager Agent** _(optional)_        | `manager_agent`        | `manager` sets a custom agent that will be used as a manager.                                                                                                                                                                                             |
 | **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.                                                     |
@@ -117,6 +117,12 @@ class YourCrewName:
         )
 ```
 
+How to run the above code:
+
+```python code
+YourCrewName().crew().kickoff(inputs={"any": "input here"})
+```
+
 <Note>
 Tasks will be executed in the order they are defined.
 </Note>
@@ -184,6 +190,11 @@ class YourCrewName:
             verbose=True
         )
 ```
+How to run the above code:
+
+```python code
+YourCrewName().crew().kickoff(inputs={})
+```
 
 In this example:
 
@@ -246,7 +257,7 @@ print(f"Token Usage: {crew_output.token_usage}")
 You can see real time log of the crew execution, by setting `output_log_file` as a `True(Boolean)` or a `file_name(str)`. Supports logging of events as both `file_name.txt` and `file_name.json`.
 In case of `True(Boolean)` will save as `logs.txt`.
 
-In case of `output_log_file` is set as `False(Booelan)` or `None`, the logs will not be populated.
+In case of `output_log_file` is set as `False(Boolean)` or `None`, the logs will not be populated.
 
 ```python Code
 # Save crew logs

docs/concepts/flows.mdx

@@ -75,11 +75,12 @@ class ExampleFlow(Flow):
 
 
 flow = ExampleFlow()
+flow.plot()
 result = flow.kickoff()
 
 print(f"Generated fun fact: {result}")
 ```
-
+![Flow Visual image](/images/crewai-flow-1.png)
 In the above example, we have created a simple Flow that generates a random city using OpenAI and then generates a fun fact about that city. The Flow consists of two tasks: `generate_city` and `generate_fun_fact`. The `generate_city` task is the starting point of the Flow, and the `generate_fun_fact` task listens for the output of the `generate_city` task.
 
 Each Flow instance automatically receives a unique identifier (UUID) in its state, which helps track and manage flow executions. The state can also store additional data (like the generated city and fun fact) that persists throughout the flow's execution.
@@ -146,6 +147,7 @@ class OutputExampleFlow(Flow):
 
 
 flow = OutputExampleFlow()
+flow.plot("my_flow_plot")
 final_output = flow.kickoff()
 
 print("---- Final Output ----")
@@ -158,9 +160,10 @@ Second method received: Output from first_method
 ```
 
 </CodeGroup>
+![Flow Visual image](/images/crewai-flow-2.png)
 
 In this example, the `second_method` is the last method to complete, so its output will be the final output of the Flow.
-The `kickoff()` method will return the final output, which is then printed to the console.
+The `kickoff()` method will return the final output, which is then printed to the console. The `plot()` method will generate the HTML file, which will help you understand the flow.
 
 #### Accessing and Updating State
 
@@ -192,6 +195,7 @@ class StateExampleFlow(Flow[ExampleState]):
         return self.state.message
 
 flow = StateExampleFlow()
+flow.plot("my_flow_plot")
 final_output = flow.kickoff()
 print(f"Final Output: {final_output}")
 print("Final State:")
@@ -206,6 +210,8 @@ counter=2 message='Hello from first_method - updated by second_method'
 
 </CodeGroup>
 
+![Flow Visual image](/images/crewai-flow-2.png)
+
 In this example, the state is updated by both `first_method` and `second_method`.
 After the Flow has run, you can access the final state to see the updates made by these methods.
 
@@ -249,9 +255,12 @@ class UnstructuredExampleFlow(Flow):
 
 
 flow = UnstructuredExampleFlow()
+flow.plot("my_flow_plot")
 flow.kickoff()
 ```
 
+![Flow Visual image](/images/crewai-flow-3.png)
+
 **Note:** The `id` field is automatically generated and preserved throughout the flow's execution. You don't need to manage or set it manually, and it will be maintained even when updating the state with new data.
 
 **Key Points:**
@@ -302,6 +311,8 @@ flow = StructuredExampleFlow()
 flow.kickoff()
 ```
 
+![Flow Visual image](/images/crewai-flow-3.png)
+
 **Key Points:**
 
 - **Defined Schema:** `ExampleState` clearly outlines the state structure, enhancing code readability and maintainability.
@@ -436,6 +447,7 @@ class OrExampleFlow(Flow):
 
 
 flow = OrExampleFlow()
+flow.plot("my_flow_plot")
 flow.kickoff()
 ```
 
@@ -446,6 +458,8 @@ Logger: Hello from the second method
 
 </CodeGroup>
 
+![Flow Visual image](/images/crewai-flow-4.png)
+
 When you run this Flow, the `logger` method will be triggered by the output of either the `start_method` or the `second_method`.
 The `or_` function is used to listen to multiple methods and trigger the listener method when any of the specified methods emit an output.
 
@@ -474,6 +488,7 @@ class AndExampleFlow(Flow):
         print(self.state)
 
 flow = AndExampleFlow()
+flow.plot()
 flow.kickoff()
 ```
 
@@ -484,6 +499,8 @@ flow.kickoff()
 
 </CodeGroup>
 
+![Flow Visual image](/images/crewai-flow-5.png)
+
 When you run this Flow, the `logger` method will be triggered only when both the `start_method` and the `second_method` emit an output.
 The `and_` function is used to listen to multiple methods and trigger the listener method only when all the specified methods emit an output.
 
@@ -527,6 +544,7 @@ class RouterFlow(Flow[ExampleState]):
 
 
 flow = RouterFlow()
+flow.plot("my_flow_plot")
 flow.kickoff()
 ```
 
@@ -538,6 +556,8 @@ Fourth method running
 
 </CodeGroup>
 
+![Flow Visual image](/images/crewai-flow-6.png)
+
 In the above example, the `start_method` generates a random boolean value and sets it in the state.
 The `second_method` uses the `@router()` decorator to define conditional routing logic based on the value of the boolean.
 If the boolean is `True`, the method returns `"success"`, and if it is `False`, the method returns `"failed"`.
@@ -641,6 +661,7 @@ class MarketResearchFlow(Flow[MarketResearchState]):
 # Usage example
 async def run_flow():
     flow = MarketResearchFlow()
+    flow.plot("MarketResearchFlowPlot")
     result = await flow.kickoff_async(inputs={"product": "AI-powered chatbots"})
     return result
 
@@ -650,6 +671,8 @@ if __name__ == "__main__":
     asyncio.run(run_flow())
 ```
 
+![Flow Visual image](/images/crewai-flow-7.png)
+
 This example demonstrates several key features of using Agents in flows:
 
 1. **Structured Output**: Using Pydantic models to define the expected output format (`MarketAnalysis`) ensures type safety and structured data throughout the flow.
@@ -746,13 +769,16 @@ def kickoff():
 
 def plot():
     poem_flow = PoemFlow()
-    poem_flow.plot()
+    poem_flow.plot("PoemFlowPlot")
 
 if __name__ == "__main__":
     kickoff()
+    plot()
 ```
 
-In this example, the `PoemFlow` class defines a flow that generates a sentence count, uses the `PoemCrew` to generate a poem, and then saves the poem to a file. The flow is kicked off by calling the `kickoff()` method.
+In this example, the `PoemFlow` class defines a flow that generates a sentence count, uses the `PoemCrew` to generate a poem, and then saves the poem to a file. The flow is kicked off by calling the `kickoff()` method. The PoemFlowPlot will be generated by `plot()` method.
+
+![Flow Visual image](/images/crewai-flow-8.png)
 
 ### Running the Flow
 

docs/concepts/knowledge.mdx

@@ -397,6 +397,53 @@ result = crew.kickoff(inputs={"question": "What city does John live in and how o
 John is 30 years old and lives in San Francisco.
 ```
 </CodeGroup>
+
+## Query Rewriting
+
+CrewAI implements an intelligent query rewriting mechanism to optimize knowledge retrieval. When an agent needs to search through knowledge sources, the raw task prompt is automatically transformed into a more effective search query.
+
+### How Query Rewriting Works
+
+1. When an agent executes a task with knowledge sources available, the `_get_knowledge_search_query` method is triggered
+2. The agent's LLM is used to transform the original task prompt into an optimized search query
+3. This optimized query is then used to retrieve relevant information from knowledge sources
+
+### Benefits of Query Rewriting
+
+<CardGroup cols={2}>
+  <Card title="Improved Retrieval Accuracy" icon="bullseye-arrow">
+    By focusing on key concepts and removing irrelevant content, query rewriting helps retrieve more relevant information.
+  </Card>
+  <Card title="Context Awareness" icon="brain">
+    The rewritten queries are designed to be more specific and context-aware for vector database retrieval.
+  </Card>
+</CardGroup>
+
+### Implementation Details
+
+Query rewriting happens transparently using a system prompt that instructs the LLM to:
+
+- Focus on key words of the intended task
+- Make the query more specific and context-aware
+- Remove irrelevant content like output format instructions
+- Generate only the rewritten query without preamble or postamble
+
+<Tip>
+  This mechanism is fully automatic and requires no configuration from users. The agent's LLM is used to perform the query rewriting, so using a more capable LLM can improve the quality of rewritten queries.
+</Tip>
+
+### Example
+
+```python
+# Original task prompt
+task_prompt = "Answer the following questions about the user's favorite movies: What movie did John watch last week? Format your answer in JSON."
+
+# Behind the scenes, this might be rewritten as:
+rewritten_query = "What movies did John watch last week?"
+```
+
+The rewritten query is more focused on the core information need and removes irrelevant instructions about output formatting.
+
 ## Clearing Knowledge
 
 If you need to clear the knowledge stored in CrewAI, you can use the `crewai reset-memories` command with the `--knowledge` option.
@@ -450,6 +497,13 @@ crew = Crew(
 result = crew.kickoff(
     inputs={"question": "What is the storage capacity of the XPS 13?"}
 )
+
+# Resetting the agent specific knowledge via crew object
+crew.reset_memories(command_type = 'agent_knowledge')
+
+# Resetting the agent specific knowledge via CLI
+crewai reset-memories --agent-knowledge 
+crewai reset-memories -akn
 ```
 
 <Info>
@@ -653,4 +707,11 @@ recent_news = SpaceNewsKnowledgeSource(
     - Configure appropriate embedding models
     - Consider using local embedding providers for faster processing
   </Accordion>
+
+  <Accordion title="One Time Knowledge">
+    - With the typical file structure provided by CrewAI, knowledge sources are embedded every time the kickoff is triggered.
+    - If the knowledge sources are large, this leads to inefficiency and increased latency, as the same data is embedded each time.
+    - To resolve this, directly initialize the knowledge parameter instead of the knowledge_sources parameter.
+    - Link to the issue to get complete idea [Github Issue](https://github.com/crewAIInc/crewAI/issues/2755)
+  </Accordion>  
 </AccordionGroup>

docs/concepts/llms.mdx

@@ -27,23 +27,19 @@ Large Language Models (LLMs) are the core intelligence behind CrewAI agents. The
   </Card>
 </CardGroup>
 
-## Setting Up Your LLM
+## Setting up your LLM
 
-There are three ways to configure LLMs in CrewAI. Choose the method that best fits your workflow:
+There are different places in CrewAI code where you can specify the model to use. Once you specify the model you are using, you will need to provide the configuration (like an API key) for each of the model providers you use. See the [provider configuration examples](#provider-configuration-examples) section for your provider.
 
 <Tabs>
   <Tab title="1. Environment Variables">
-    The simplest way to get started. Set these variables in your environment:
+    The simplest way to get started. Set the model in your environment directly, through an `.env` file or in your app code. If you used `crewai create` to bootstrap your project, it will be set already.
 
-    ```bash
-    # Required: Your API key for authentication
-    OPENAI_API_KEY=<your-api-key>
+    ```bash .env
+    MODEL=model-id  # e.g. gpt-4o, gemini-2.0-flash, claude-3-sonnet-...
 
-    # Optional: Default model selection
-    OPENAI_MODEL_NAME=gpt-4o-mini  # Default if not set
-
-    # Optional: Organization ID (if applicable)
-    OPENAI_ORGANIZATION_ID=<your-org-id>
+    # Be sure to set your API keys here too. See the Provider
+    # section below.
     ```
 
     <Warning>
@@ -53,13 +49,13 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
   <Tab title="2. YAML Configuration">
     Create a YAML file to define your agent configurations. This method is great for version control and team collaboration:
 
-    ```yaml
+    ```yaml agents.yaml {6}
     researcher:
         role: Research Specialist
         goal: Conduct comprehensive research and analysis
         backstory: A dedicated research professional with years of experience
         verbose: true
-        llm: openai/gpt-4o-mini # your model here
+        llm: provider/model-id  # e.g. openai/gpt-4o, google/gemini-2.0-flash, anthropic/claude...
         # (see provider configuration examples below for more)
     ```
 
@@ -74,23 +70,23 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
   <Tab title="3. Direct Code">
     For maximum flexibility, configure LLMs directly in your Python code:
 
-    ```python
+    ```python {4,8}
     from crewai import LLM
 
     # Basic configuration
-    llm = LLM(model="gpt-4")
+    llm = LLM(model="model-id-here")  # gpt-4o, gemini-2.0-flash, anthropic/claude...
 
     # Advanced configuration with detailed parameters
     llm = LLM(
-        model="gpt-4o-mini",
+        model="model-id-here",  # gpt-4o, gemini-2.0-flash, anthropic/claude...
         temperature=0.7,        # Higher for more creative outputs
-        timeout=120,           # Seconds to wait for response
-        max_tokens=4000,       # Maximum length of response
-        top_p=0.9,            # Nucleus sampling parameter
-        frequency_penalty=0.1, # Reduce repetition
-        presence_penalty=0.1,  # Encourage topic diversity
+        timeout=120,            # Seconds to wait for response
+        max_tokens=4000,        # Maximum length of response
+        top_p=0.9,              # Nucleus sampling parameter
+        frequency_penalty=0.1 , # Reduce repetition
+        presence_penalty=0.1,   # Encourage topic diversity
         response_format={"type": "json"},  # For structured outputs
-        seed=42               # For reproducible results
+        seed=42                 # For reproducible results
     )
     ```
 
@@ -110,7 +106,6 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
 
 ## Provider Configuration Examples
 
-
 CrewAI supports a multitude of LLM providers, each offering unique features, authentication methods, and model capabilities.
 In this section, you'll find detailed examples that help you select, configure, and optimize the LLM that best fits your project's needs.
 
@@ -174,19 +169,55 @@ In this section, you'll find detailed examples that help you select, configure,
     ```
   </Accordion>
 
-  <Accordion title="Google">
-    Set the following environment variables in your `.env` file:
+  <Accordion title="Google (Gemini API)">
+    Set your API key in your `.env` file. If you need a key, or need to find an
+    existing key, check [AI Studio](https://aistudio.google.com/apikey).
 
-    ```toml Code
-    # Option 1: Gemini accessed with an API key.
+    ```toml .env
     # 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 Model Garden.
-    # https://cloud.google.com/vertex-ai/generative-ai/docs/overview
     ```
 
-    Get credentials from your Google Cloud Console and save it to a JSON file with the following code:
+    Example usage in your CrewAI project:
+    ```python Code
+    from crewai import LLM
+
+    llm = LLM(
+        model="gemini/gemini-2.0-flash",
+        temperature=0.7,
+    )
+    ```
+
+    ### Gemini models
+
+    Google offers a range of powerful models optimized for different use cases.
+
+    | Model                          | Context Window | Best For                                                          |
+    |--------------------------------|----------------|-------------------------------------------------------------------|
+    | gemini-2.5-flash-preview-04-17 | 1M tokens      | Adaptive thinking, cost efficiency                                |
+    | gemini-2.5-pro-preview-05-06   | 1M tokens      | Enhanced thinking and reasoning, multimodal understanding, advanced coding, and more |
+    | gemini-2.0-flash               | 1M tokens      | Next generation features, speed, thinking, and realtime streaming |
+    | gemini-2.0-flash-lite          | 1M tokens      | Cost efficiency and low latency                                   |
+    | 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 |
+
+    The full list of models is available in the [Gemini model docs](https://ai.google.dev/gemini-api/docs/models).
+
+    ### Gemma
+
+    The Gemini API also allows you to use your API key to access [Gemma models](https://ai.google.dev/gemma/docs) hosted on Google infrastructure.
+
+    | Model          | Context Window |
+    |----------------|----------------|
+    | gemma-3-1b-it  | 32k tokens     |
+    | gemma-3-4b-it  | 32k tokens     |
+    | gemma-3-12b-it | 32k tokens     |
+    | gemma-3-27b-it | 128k tokens    |
+
+  </Accordion>
+  <Accordion title="Google (Vertex AI)">
+    Get credentials from your Google Cloud Console and save it to a JSON file, then load it with the following code:
     ```python Code
     import json
 
@@ -210,14 +241,18 @@ In this section, you'll find detailed examples that help you select, configure,
         vertex_credentials=vertex_credentials_json
     )
     ```
+
     Google offers a range of powerful models optimized for different use cases:
 
-    | Model                  | Context Window | Best For                                                          |
-    |-----------------------|----------------|------------------------------------------------------------------|
-    | gemini-2.0-flash-exp  | 1M tokens      | Higher quality at faster speed, multimodal model, good for most tasks |
-    | gemini-1.5-flash      | 1M tokens      | Balanced multimodal model, good for most tasks                    |
-    | gemini-1.5-flash-8B   | 1M tokens      | Fastest, most cost-efficient, good for high-frequency tasks       |
-    | gemini-1.5-pro        | 2M tokens      | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
+    | Model                          | Context Window | Best For                                                          |
+    |--------------------------------|----------------|-------------------------------------------------------------------|
+    | gemini-2.5-flash-preview-04-17 | 1M tokens      | Adaptive thinking, cost efficiency                                |
+    | gemini-2.5-pro-preview-05-06   | 1M tokens      | Enhanced thinking and reasoning, multimodal understanding, advanced coding, and more |
+    | gemini-2.0-flash               | 1M tokens      | Next generation features, speed, thinking, and realtime streaming |
+    | gemini-2.0-flash-lite          | 1M tokens      | Cost efficiency and low latency                                   |
+    | 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 |
   </Accordion>
 
   <Accordion title="Azure">
@@ -383,7 +418,7 @@ In this section, you'll find detailed examples that help you select, configure,
     | 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/phi-3.5-moe-instruct                                      | 128K tokens    | Advanced LLM based on Mixture of Experts architecture 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. |
@@ -407,19 +442,19 @@ In this section, you'll find detailed examples that help you select, configure,
   </Accordion>
 
   <Accordion title="Local NVIDIA NIM Deployed using WSL2">
-    
-    NVIDIA NIM enables you to run powerful LLMs locally on your Windows machine using WSL2 (Windows Subsystem for Linux). 
-    This approach allows you to leverage your NVIDIA GPU for private, secure, and cost-effective AI inference without relying on cloud services. 
+
+    NVIDIA NIM enables you to run powerful LLMs locally on your Windows machine using WSL2 (Windows Subsystem for Linux).
+    This approach allows you to leverage your NVIDIA GPU for private, secure, and cost-effective AI inference without relying on cloud services.
     Perfect for development, testing, or production scenarios where data privacy or offline capabilities are required.
-    
+
     Here is a step-by-step guide to setting up a local NVIDIA NIM model:
-    
+
     1. Follow installation instructions from [NVIDIA Website](https://docs.nvidia.com/nim/wsl2/latest/getting-started.html)
 
     2. Install the local model. For Llama 3.1-8b follow [instructions](https://build.nvidia.com/meta/llama-3_1-8b-instruct/deploy)
 
     3. Configure your crewai local models:
-  
+
     ```python Code
     from crewai.llm import LLM
 
@@ -441,7 +476,7 @@ In this section, you'll find detailed examples that help you select, configure,
                 config=self.agents_config['researcher'], # type: ignore[index]
                 llm=local_nvidia_nim_llm
             )
-        
+
         # ...
     ```
   </Accordion>
@@ -637,23 +672,29 @@ CrewAI supports streaming responses from LLMs, allowing your application to rece
 
     When streaming is enabled, responses are delivered in chunks as they're generated, creating a more responsive user experience.
   </Tab>
-  
+
   <Tab title="Event Handling">
     CrewAI emits events for each chunk received during streaming:
-    
+
     ```python
-    from crewai import LLM
-    from crewai.utilities.events import EventHandler, LLMStreamChunkEvent
-    
-    class MyEventHandler(EventHandler):
-        def on_llm_stream_chunk(self, event: LLMStreamChunkEvent):
-            # Process each chunk as it arrives
-            print(f"Received chunk: {event.chunk}")
-    
-    # Register the event handler
-    from crewai.utilities.events import crewai_event_bus
-    crewai_event_bus.register_handler(MyEventHandler())
+    from crewai.utilities.events import (
+      LLMStreamChunkEvent
+    )
+    from crewai.utilities.events.base_event_listener import BaseEventListener
+
+    class MyCustomListener(BaseEventListener):
+        def setup_listeners(self, crewai_event_bus):
+            @crewai_event_bus.on(LLMStreamChunkEvent)
+            def on_llm_stream_chunk(self, event: LLMStreamChunkEvent):
+              # Process each chunk as it arrives
+              print(f"Received chunk: {event.chunk}")
+
+    my_listener = MyCustomListener()
     ```
+
+    <Tip>
+      [Click here](https://docs.crewai.com/concepts/event-listener#event-listeners) for more details 
+    </Tip>
   </Tab>
 </Tabs>
 
@@ -750,6 +791,24 @@ Learn how to get the most out of your LLM configuration:
       Remember to regularly monitor your token usage and adjust your configuration as needed to optimize costs and performance.
     </Info>
   </Accordion>
+  
+  <Accordion title="Drop Additional Parameters">
+    CrewAI internally uses Litellm for LLM calls, which allows you to drop additional parameters that are not needed for your specific use case. This can help simplify your code and reduce the complexity of your LLM configuration.
+    For example, if you don't need to send the <code>stop</code> parameter, you can simply omit it from your LLM call:
+
+    ```python
+    from crewai import LLM
+    import os
+
+    os.environ["OPENAI_API_KEY"] = "<api-key>"
+
+    o3_llm = LLM(
+        model="o3",
+        drop_params=True,
+        additional_drop_params=["stop"]
+    )
+    ```
+  </Accordion>
 </AccordionGroup>
 
 ## Common Issues and Solutions
@@ -785,7 +844,7 @@ Learn how to get the most out of your LLM configuration:
     <Tip>
       Use larger context models for extensive tasks
     </Tip>
-    
+
     ```python
     # Large context model
     llm = LLM(model="openai/gpt-4o")  # 128K tokens

docs/concepts/memory.mdx

@@ -679,6 +679,7 @@ crewai reset-memories [OPTIONS]
 | `-e`, `--entities` | Reset ENTITIES memory.           | Flag (boolean) | False   |
 | `-k`, `--kickoff-outputs` | Reset LATEST KICKOFF TASK OUTPUTS. | Flag (boolean) | False   |
 | `-kn`, `--knowledge` | Reset KNOWLEDEGE storage | Flag (boolean) | False   |
+| `-akn`, `--agent-knowledge` | Reset AGENT KNOWLEDGE storage | Flag (boolean) | False   |
 | `-a`, `--all`      | Reset ALL memories.              | Flag (boolean) | False   |
 
 Note: To use the cli command you need to have your crew in a file called crew.py in the same directory.
@@ -716,9 +717,11 @@ my_crew.reset_memories(command_type = 'all') # Resets all the memory
 | `entities`         | Reset ENTITIES memory.           | 
 | `kickoff_outputs`  | Reset LATEST KICKOFF TASK OUTPUTS. |
 | `knowledge`        | Reset KNOWLEDGE memory.          |
+| `agent_knowledge`  | Reset AGENT KNOWLEDGE memory.    |
 | `all`              | Reset ALL memories.              |
 
 
+
 ## Benefits of Using CrewAI's Memory System
 
 - 🦾 **Adaptive Learning:** Crews become more efficient over time, adapting to new information and refining their approach to tasks.

docs/docs.json

@@ -129,6 +129,7 @@
               "tools/seleniumscrapingtool",
               "tools/snowflakesearchtool",
               "tools/spidertool",
+              "tools/stagehandtool",
               "tools/txtsearchtool",
               "tools/visiontool",
               "tools/weaviatevectorsearchtool",

docs/guides/advanced/customizing-prompts.mdx

@@ -4,8 +4,6 @@ description: Dive deeper into low-level prompt customization for CrewAI, enablin
 icon: message-pen
 ---
 
-# Customizing Prompts at a Low Level
-
 ## Why Customize Prompts?
 
 Although CrewAI's default prompts work well for many scenarios, low-level customization opens the door to significantly more flexible and powerful agent behavior. Here’s why you might want to take advantage of this deeper control:

docs/guides/advanced/fingerprinting.mdx

@@ -4,8 +4,6 @@ description: Learn how to use CrewAI's fingerprinting system to uniquely identif
 icon: fingerprint
 ---
 
-# Fingerprinting in CrewAI
-
 ## Overview
 
 Fingerprints in CrewAI provide a way to uniquely identify and track components throughout their lifecycle. Each `Agent`, `Crew`, and `Task` automatically receives a unique fingerprint when created, which cannot be manually overridden.

docs/guides/agents/crafting-effective-agents.mdx

@@ -4,8 +4,6 @@ description: Learn best practices for designing powerful, specialized AI agents
 icon: robot
 ---
 
-# Crafting Effective Agents
-
 ## The Art and Science of Agent Design
 
 At the heart of CrewAI lies the agent - a specialized AI entity designed to perform specific roles within a collaborative framework. While creating basic agents is simple, crafting truly effective agents that produce exceptional results requires understanding key design principles and best practices.

docs/guides/concepts/evaluating-use-cases.mdx

@@ -4,8 +4,6 @@ description: Learn how to assess your AI application needs and choose the right
 icon: scale-balanced
 ---
 
-# Evaluating Use Cases for CrewAI
-
 ## Understanding the Decision Framework
 
 When building AI applications with CrewAI, one of the most important decisions you'll make is choosing the right approach for your specific use case. Should you use a Crew? A Flow? A combination of both? This guide will help you evaluate your requirements and make informed architectural decisions.

docs/guides/crews/first-crew.mdx

@@ -4,8 +4,6 @@ description: Step-by-step tutorial to create a collaborative AI team that works
 icon: users-gear
 ---
 
-# Build Your First Crew
-
 ## Unleashing the Power of Collaborative AI
 
 Imagine having a team of specialized AI agents working together seamlessly to solve complex problems, each contributing their unique skills to achieve a common goal. This is the power of CrewAI - a framework that enables you to create collaborative AI systems that can accomplish tasks far beyond what a single AI could achieve alone.
@@ -35,7 +33,8 @@ Let's get started building your first crew!
 Before starting, make sure you have:
 
 1. Installed CrewAI following the [installation guide](/installation)
-2. Set up your OpenAI API key in your environment variables
+2. Set up your LLM API key in your environment, following the [LLM setup
+   guide](/concepts/llms#setting-up-your-llm)
 3. Basic understanding of Python
 
 ## Step 1: Create a New CrewAI Project
@@ -92,7 +91,8 @@ For our research crew, we'll create two agents:
 1. A **researcher** who excels at finding and organizing information
 2. An **analyst** who can interpret research findings and create insightful reports
 
-Let's modify the `agents.yaml` file to define these specialized agents:
+Let's modify the `agents.yaml` file to define these specialized agents. Be sure
+to set `llm` to the provider you are using.
 
 ```yaml
 # src/research_crew/config/agents.yaml
@@ -107,7 +107,7 @@ researcher:
     finding relevant information from various sources. You excel at
     organizing information in a clear and structured manner, making
     complex topics accessible to others.
-  llm: openai/gpt-4o-mini
+  llm: provider/model-id  # e.g. openai/gpt-4o, google/gemini-2.0-flash, anthropic/claude...
 
 analyst:
   role: >
@@ -120,7 +120,7 @@ analyst:
     and technical writing. You have a talent for identifying patterns
     and extracting meaningful insights from research data, then
     communicating those insights effectively through well-crafted reports.
-  llm: openai/gpt-4o-mini
+  llm: provider/model-id  # e.g. openai/gpt-4o, google/gemini-2.0-flash, anthropic/claude...
 ```
 
 Notice how each agent has a distinct role, goal, and backstory. These elements aren't just descriptive - they actively shape how the agent approaches its tasks. By crafting these carefully, you can create agents with specialized skills and perspectives that complement each other.
@@ -282,12 +282,12 @@ This script prepares the environment, specifies our research topic, and kicks of
 
 Create a `.env` file in your project root with your API keys:
 
-```
-OPENAI_API_KEY=your_openai_api_key
+```sh
 SERPER_API_KEY=your_serper_api_key
+# Add your provider's API key here too.
 ```
 
-You can get a Serper API key from [Serper.dev](https://serper.dev/).
+See the [LLM Setup guide](/concepts/llms#setting-up-your-llm) for details on configuring your provider of choice. You can get a Serper API key from [Serper.dev](https://serper.dev/).
 
 ## Step 8: Install Dependencies
 

docs/guides/flows/first-flow.mdx

@@ -4,8 +4,6 @@ description: Learn how to create structured, event-driven workflows with precise
 icon: diagram-project
 ---
 
-# Build Your First Flow
-
 ## Taking Control of AI Workflows with Flows
 
 CrewAI Flows represent the next level in AI orchestration - combining the collaborative power of AI agent crews with the precision and flexibility of procedural programming. While crews excel at agent collaboration, flows give you fine-grained control over exactly how and when different components of your AI system interact.
@@ -45,7 +43,8 @@ Let's dive in and build your first flow!
 Before starting, make sure you have:
 
 1. Installed CrewAI following the [installation guide](/installation)
-2. Set up your OpenAI API key in your environment variables
+2. Set up your LLM API key in your environment, following the [LLM setup
+   guide](/concepts/llms#setting-up-your-llm)
 3. Basic understanding of Python
 
 ## Step 1: Create a New CrewAI Flow Project
@@ -107,6 +106,8 @@ Now, let's modify the generated files for the content writer crew. We'll set up
 
 1. First, update the agents configuration file to define our content creation team:
 
+   Remember to set `llm` to the provider you are using.
+
 ```yaml
 # src/guide_creator_flow/crews/content_crew/config/agents.yaml
 content_writer:
@@ -119,7 +120,7 @@ content_writer:
     You are a talented educational writer with expertise in creating clear, engaging
     content. You have a gift for explaining complex concepts in accessible language
     and organizing information in a way that helps readers build their understanding.
-  llm: openai/gpt-4o-mini
+  llm: provider/model-id  # e.g. openai/gpt-4o, google/gemini-2.0-flash, anthropic/claude...
 
 content_reviewer:
   role: >
@@ -132,7 +133,7 @@ content_reviewer:
     content. You have an eye for detail, clarity, and coherence. You excel at
     improving content while maintaining the original author's voice and ensuring
     consistent quality across multiple sections.
-  llm: openai/gpt-4o-mini
+  llm: provider/model-id  # e.g. openai/gpt-4o, google/gemini-2.0-flash, anthropic/claude...
 ```
 
 These agent definitions establish the specialized roles and perspectives that will shape how our AI agents approach content creation. Notice how each agent has a distinct purpose and expertise.
@@ -441,10 +442,15 @@ This is the power of flows - combining different types of processing (user inter
 
 ## Step 6: Set Up Your Environment Variables
 
-Create a `.env` file in your project root with your API keys:
+Create a `.env` file in your project root with your API keys. See the [LLM setup
+guide](/concepts/llms#setting-up-your-llm) for details on configuring a provider.
 
-```
+```sh .env
 OPENAI_API_KEY=your_openai_api_key
+# or
+GEMINI_API_KEY=your_gemini_api_key
+# or
+ANTHROPIC_API_KEY=your_anthropic_api_key
 ```
 
 ## Step 7: Install Dependencies
@@ -547,7 +553,10 @@ Let's break down the key components of flows to help you understand how to build
 Flows allow you to make direct calls to language models when you need simple, structured responses:
 
 ```python
-llm = LLM(model="openai/gpt-4o-mini", response_format=GuideOutline)
+llm = LLM(
+    model="model-id-here",  # gpt-4o, gemini-2.0-flash, anthropic/claude...
+    response_format=GuideOutline
+)
 response = llm.call(messages=messages)
 ```
 

docs/guides/flows/mastering-flow-state.mdx

@@ -4,8 +4,6 @@ description: A comprehensive guide to managing, persisting, and leveraging state
 icon: diagram-project
 ---
 
-# Mastering Flow State Management
-
 ## Understanding the Power of State in Flows
 
 State management is the backbone of any sophisticated AI workflow. In CrewAI Flows, the state system allows you to maintain context, share data between steps, and build complex application logic. Mastering state management is essential for creating reliable, maintainable, and powerful AI applications.

docs/how-to/arize-phoenix-observability.mdx

@@ -68,7 +68,13 @@ We'll create a CrewAI application where two agents collaborate to research and w
 ```python
 from crewai import Agent, Crew, Process, Task
 from crewai_tools import SerperDevTool
+from openinference.instrumentation.crewai import CrewAIInstrumentor
+from phoenix.otel import register
 
+# setup monitoring for your crew
+tracer_provider = register(
+    endpoint="http://localhost:6006/v1/traces")
+CrewAIInstrumentor().instrument(skip_dep_check=True, tracer_provider=tracer_provider)
 search_tool = SerperDevTool()
 
 # Define your agents with roles and goals

docs/installation.mdx

@@ -71,6 +71,10 @@ If you haven't installed `uv` yet, follow **step 1** to quickly get it set up on
             ```
           </Warning>
 
+          <Warning>
+            If you encounter the `chroma-hnswlib==0.7.6` build error (`fatal error C1083: Cannot open include file: 'float.h'`) on Windows, install (Visual Studio Build Tools)[https://visualstudio.microsoft.com/downloads/] with *Desktop development with C++*.
+          </Warning>
+
       - To verify that `crewai` is installed, run:
         ```shell
         uv tool list

docs/quickstart.mdx

@@ -180,8 +180,9 @@ Follow the steps below to get Crewing! 🚣‍♂️
   </Step>
   <Step title="Set your environment variables">
   Before running your crew, make sure you have the following keys set as environment variables in your `.env` file:
-    - An [OpenAI API key](https://platform.openai.com/account/api-keys) (or other LLM API key): `OPENAI_API_KEY=sk-...`
     - A [Serper.dev](https://serper.dev/) API key: `SERPER_API_KEY=YOUR_KEY_HERE`
+    - The configuration for your choice of model, such as an API key. See the
+        [LLM setup guide](/concepts/llms#setting-up-your-llm) to learn how to configure models from any provider.
   </Step>
   <Step title="Lock and install the dependencies">
     - Lock the dependencies and install them by using the CLI command:
@@ -317,7 +318,7 @@ email_summarizer:
       Summarize emails into a concise and clear summary
     backstory: >
       You will create a 5 bullet point summary of the report
-    llm: openai/gpt-4o
+    llm: provider/model-id  # Add your choice of model here
 ```
 
 <Tip>

docs/tools/docxsearchtool.mdx

@@ -22,7 +22,7 @@ streamlining the process of finding specific information within large document c
 Install the crewai_tools package by running the following command in your terminal:
 
 ```shell
-pip install 'crewai[tools]'
+uv pip install docx2txt 'crewai[tools]'
 ```
 
 ## Example
@@ -76,4 +76,4 @@ tool = DOCXSearchTool(
         ),
     )
 )
-```
+```

docs/tools/nl2sqltool.mdx

@@ -8,10 +8,10 @@ icon: language
 
 ## Description
 
-This tool is used to convert natural language to SQL queries. When passsed to the agent it will generate queries and then use them to interact with the database.
+This tool is used to convert natural language to SQL queries. When passed to the agent it will generate queries and then use them to interact with the database.
 
 This enables multiple workflows like having an Agent to access the database fetch information based on the goal and then use the information to generate a response, report or any other output. 
-Along with that proivdes the ability for the Agent to update the database based on its goal.
+Along with that provides the ability for the Agent to update the database based on its goal.
 
 **Attention**: Make sure that the Agent has access to a Read-Replica or that is okay for the Agent to run insert/update queries on the database.
 
@@ -81,4 +81,4 @@ The Tool provides endless possibilities on the logic of the Agent and how it can
 
 ```md
  DB -> Agent -> ... -> Agent -> DB
-```
+```

docs/tools/ragtool.mdx

@@ -143,12 +143,30 @@ config = {
         "config": {
             "model": "text-embedding-ada-002"
         }
+    },
+    "vectordb": {
+        "provider": "elasticsearch",
+        "config": {
+            "collection_name": "my-collection",
+            "cloud_id": "deployment-name:xxxx",
+            "api_key": "your-key",
+            "verify_certs": False
+        }
+    },
+    "chunker": {
+        "chunk_size": 400,
+        "chunk_overlap": 100,
+        "length_function": "len",
+        "min_chunk_size": 0
     }
 }
 
 rag_tool = RagTool(config=config, summarize=True)
 ```
 
-## Conclusion
+The internal RAG tool utilizes the Embedchain adapter, allowing you to pass any configuration options that are supported by Embedchain.
+You can refer to the [Embedchain documentation](https://docs.embedchain.ai/components/introduction) for details.
+Make sure to review the configuration options available in the .yaml file.
 
+## Conclusion
 The `RagTool` provides a powerful way to create and query knowledge bases from various data sources. By leveraging Retrieval-Augmented Generation, it enables agents to access and retrieve relevant information efficiently, enhancing their ability to provide accurate and contextually appropriate responses.

docs/tools/stagehandtool.mdx

@@ -0,0 +1,244 @@
+---
+title: Stagehand Tool
+description: Web automation tool that integrates Stagehand with CrewAI for browser interaction and automation
+icon: hand
+---
+
+
+# Overview
+
+The `StagehandTool` integrates the [Stagehand](https://docs.stagehand.dev/get_started/introduction) framework with CrewAI, enabling agents to interact with websites and automate browser tasks using natural language instructions.
+
+## Overview
+
+Stagehand is a powerful browser automation framework built by Browserbase that allows AI agents to:
+
+- Navigate to websites
+- Click buttons, links, and other elements
+- Fill in forms
+- Extract data from web pages
+- Observe and identify elements
+- Perform complex workflows
+
+The StagehandTool wraps the Stagehand Python SDK to provide CrewAI agents with browser control capabilities through three core primitives:
+
+1. **Act**: Perform actions like clicking, typing, or navigating
+2. **Extract**: Extract structured data from web pages
+3. **Observe**: Identify and analyze elements on the page
+
+## Prerequisites
+
+Before using this tool, ensure you have:
+
+1. A [Browserbase](https://www.browserbase.com/) account with API key and project ID
+2. An API key for an LLM (OpenAI or Anthropic Claude)
+3. The Stagehand Python SDK installed
+
+Install the required dependency:
+
+```bash
+pip install stagehand-py
+```
+
+## Usage
+
+### Basic Implementation
+
+The StagehandTool can be implemented in two ways:
+
+#### 1. Using Context Manager (Recommended)
+<Tip>
+  The context manager approach is recommended as it ensures proper cleanup of resources even if exceptions occur.
+</Tip>
+
+```python
+from crewai import Agent, Task, Crew
+from crewai_tools import StagehandTool
+from stagehand.schemas import AvailableModel
+
+# Initialize the tool with your API keys using a context manager
+with StagehandTool(
+    api_key="your-browserbase-api-key",
+    project_id="your-browserbase-project-id",
+    model_api_key="your-llm-api-key",  # OpenAI or Anthropic API key
+    model_name=AvailableModel.CLAUDE_3_7_SONNET_LATEST,  # Optional: specify which model to use
+) as stagehand_tool:
+    # Create an agent with the tool
+    researcher = Agent(
+        role="Web Researcher",
+        goal="Find and summarize information from websites",
+        backstory="I'm an expert at finding information online.",
+        verbose=True,
+        tools=[stagehand_tool],
+    )
+
+    # Create a task that uses the tool
+    research_task = Task(
+        description="Go to https://www.example.com and tell me what you see on the homepage.",
+        agent=researcher,
+    )
+
+    # Run the crew
+    crew = Crew(
+        agents=[researcher],
+        tasks=[research_task],
+        verbose=True,
+    )
+
+    result = crew.kickoff()
+    print(result)
+```
+
+#### 2. Manual Resource Management
+
+```python
+from crewai import Agent, Task, Crew
+from crewai_tools import StagehandTool
+from stagehand.schemas import AvailableModel
+
+# Initialize the tool with your API keys
+stagehand_tool = StagehandTool(
+    api_key="your-browserbase-api-key",
+    project_id="your-browserbase-project-id",
+    model_api_key="your-llm-api-key",
+    model_name=AvailableModel.CLAUDE_3_7_SONNET_LATEST,
+)
+
+try:
+    # Create an agent with the tool
+    researcher = Agent(
+        role="Web Researcher",
+        goal="Find and summarize information from websites",
+        backstory="I'm an expert at finding information online.",
+        verbose=True,
+        tools=[stagehand_tool],
+    )
+
+    # Create a task that uses the tool
+    research_task = Task(
+        description="Go to https://www.example.com and tell me what you see on the homepage.",
+        agent=researcher,
+    )
+
+    # Run the crew
+    crew = Crew(
+        agents=[researcher],
+        tasks=[research_task],
+        verbose=True,
+    )
+
+    result = crew.kickoff()
+    print(result)
+finally:
+    # Explicitly clean up resources
+    stagehand_tool.close()
+```
+
+## Command Types
+
+The StagehandTool supports three different command types for specific web automation tasks:
+
+### 1. Act Command
+
+The `act` command type (default) enables webpage interactions like clicking buttons, filling forms, and navigation.
+
+```python
+# Perform an action (default behavior)
+result = stagehand_tool.run(
+    instruction="Click the login button", 
+    url="https://example.com",
+    command_type="act"  # Default, so can be omitted
+)
+
+# Fill out a form
+result = stagehand_tool.run(
+    instruction="Fill the contact form with name 'John Doe', email 'john@example.com', and message 'Hello world'", 
+    url="https://example.com/contact"
+)
+```
+
+### 2. Extract Command
+
+The `extract` command type retrieves structured data from webpages.
+
+```python
+# Extract all product information
+result = stagehand_tool.run(
+    instruction="Extract all product names, prices, and descriptions", 
+    url="https://example.com/products",
+    command_type="extract"
+)
+
+# Extract specific information with a selector
+result = stagehand_tool.run(
+    instruction="Extract the main article title and content", 
+    url="https://example.com/blog/article",
+    command_type="extract",
+    selector=".article-container"  # Optional CSS selector
+)
+```
+
+### 3. Observe Command
+
+The `observe` command type identifies and analyzes webpage elements.
+
+```python
+# Find interactive elements
+result = stagehand_tool.run(
+    instruction="Find all interactive elements in the navigation menu", 
+    url="https://example.com",
+    command_type="observe"
+)
+
+# Identify form fields
+result = stagehand_tool.run(
+    instruction="Identify all the input fields in the registration form", 
+    url="https://example.com/register",
+    command_type="observe",
+    selector="#registration-form"
+)
+```
+
+## Configuration Options
+
+Customize the StagehandTool behavior with these parameters:
+
+```python
+stagehand_tool = StagehandTool(
+    api_key="your-browserbase-api-key",
+    project_id="your-browserbase-project-id",
+    model_api_key="your-llm-api-key",
+    model_name=AvailableModel.CLAUDE_3_7_SONNET_LATEST,
+    dom_settle_timeout_ms=5000,  # Wait longer for DOM to settle
+    headless=True,  # Run browser in headless mode
+    self_heal=True,  # Attempt to recover from errors
+    wait_for_captcha_solves=True,  # Wait for CAPTCHA solving
+    verbose=1,  # Control logging verbosity (0-3)
+)
+```
+
+## Best Practices
+
+1. **Be Specific**: Provide detailed instructions for better results
+2. **Choose Appropriate Command Type**: Select the right command type for your task
+3. **Use Selectors**: Leverage CSS selectors to improve accuracy
+4. **Break Down Complex Tasks**: Split complex workflows into multiple tool calls
+5. **Implement Error Handling**: Add error handling for potential issues
+
+## Troubleshooting
+
+
+Common issues and solutions:
+
+- **Session Issues**: Verify API keys for both Browserbase and LLM provider
+- **Element Not Found**: Increase `dom_settle_timeout_ms` for slower pages
+- **Action Failures**: Use `observe` to identify correct elements first
+- **Incomplete Data**: Refine instructions or provide specific selectors
+
+
+## Additional Resources
+
+For questions about the CrewAI integration:
+- Join Stagehand's [Slack community](https://stagehand.dev/slack)
+- Open an issue in the [Stagehand repository](https://github.com/browserbase/stagehand)
+- Visit [Stagehand documentation](https://docs.stagehand.dev/)

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.118.0"
+version = "0.120.1"
 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"
@@ -11,7 +11,7 @@ dependencies = [
     # Core Dependencies
     "pydantic>=2.4.2",
     "openai>=1.13.3",
-    "litellm==1.67.1",
+    "litellm==1.68.0",
     "instructor>=1.3.3",
     # Text Processing
     "pdfplumber>=0.11.4",
@@ -45,7 +45,7 @@ Documentation = "https://docs.crewai.com"
 Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
-tools = ["crewai-tools~=0.42.2"]
+tools = ["crewai-tools~=0.45.0"]
 embeddings = [
     "tiktoken~=0.7.0"
 ]
@@ -85,6 +85,8 @@ dev-dependencies = [
     "pytest-asyncio>=0.23.7",
     "pytest-subprocess>=1.5.2",
     "pytest-recording>=0.13.2",
+    "pytest-randomly>=3.16.0",
+    "pytest-timeout>=2.3.1",
 ]
 
 [project.scripts]

src/crewai/__init__.py

@@ -17,7 +17,7 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.118.0"
+__version__ = "0.120.1"
 __all__ = [
     "Agent",
     "Crew",

src/crewai/agent.py

@@ -20,6 +20,7 @@ from crewai.tools.agent_tools.agent_tools import AgentTools
 from crewai.utilities import Converter, Prompts
 from crewai.utilities.agent_utils import (
     get_tool_names,
+    load_agent_from_repository,
     parse_tools,
     render_text_description_and_args,
 )
@@ -31,6 +32,14 @@ from crewai.utilities.events.agent_events import (
     AgentExecutionStartedEvent,
 )
 from crewai.utilities.events.crewai_event_bus import crewai_event_bus
+from crewai.utilities.events.knowledge_events import (
+    KnowledgeQueryCompletedEvent,
+    KnowledgeQueryFailedEvent,
+    KnowledgeQueryStartedEvent,
+    KnowledgeRetrievalCompletedEvent,
+    KnowledgeRetrievalStartedEvent,
+    KnowledgeSearchQueryFailedEvent,
+)
 from crewai.utilities.llm_utils import create_llm
 from crewai.utilities.token_counter_callback import TokenCalcHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
@@ -122,6 +131,20 @@ class Agent(BaseAgent):
         default=None,
         description="Knowledge context for the crew.",
     )
+    knowledge_search_query: Optional[str] = Field(
+        default=None,
+        description="Knowledge search query for the agent dynamically generated by the agent.",
+    )
+    from_repository: Optional[str] = Field(
+        default=None,
+        description="The Agent's role to be used from your repository.",
+    )
+
+    @model_validator(mode="before")
+    def validate_from_repository(cls, v):
+        if v is not None and (from_repository := v.get("from_repository")):
+            return load_agent_from_repository(from_repository) | v
+        return v
 
     @model_validator(mode="after")
     def post_init_setup(self):
@@ -185,7 +208,7 @@ class Agent(BaseAgent):
         self,
         task: Task,
         context: Optional[str] = None,
-        tools: Optional[List[BaseTool]] = None
+        tools: Optional[List[BaseTool]] = None,
     ) -> str:
         """Execute a task with the agent.
 
@@ -245,27 +268,65 @@ class Agent(BaseAgent):
         knowledge_config = (
             self.knowledge_config.model_dump() if self.knowledge_config else {}
         )
-        if self.knowledge:
-            agent_knowledge_snippets = self.knowledge.query(
-                [task.prompt()], **knowledge_config
-            )
-            if agent_knowledge_snippets:
-                self.agent_knowledge_context = extract_knowledge_context(
-                    agent_knowledge_snippets
-                )
-                if self.agent_knowledge_context:
-                    task_prompt += self.agent_knowledge_context
 
-        if self.crew:
-            knowledge_snippets = self.crew.query_knowledge(
-                [task.prompt()], **knowledge_config
+        if self.knowledge:
+            crewai_event_bus.emit(
+                self,
+                event=KnowledgeRetrievalStartedEvent(
+                    agent=self,
+                ),
             )
-            if knowledge_snippets:
-                self.crew_knowledge_context = extract_knowledge_context(
-                    knowledge_snippets
+            try:
+                self.knowledge_search_query = self._get_knowledge_search_query(
+                    task_prompt
+                )
+                if self.knowledge_search_query:
+                    agent_knowledge_snippets = self.knowledge.query(
+                        [self.knowledge_search_query], **knowledge_config
+                    )
+                    if agent_knowledge_snippets:
+                        self.agent_knowledge_context = extract_knowledge_context(
+                            agent_knowledge_snippets
+                        )
+                        if self.agent_knowledge_context:
+                            task_prompt += self.agent_knowledge_context
+                    if self.crew:
+                        knowledge_snippets = self.crew.query_knowledge(
+                            [self.knowledge_search_query], **knowledge_config
+                        )
+                        if knowledge_snippets:
+                            self.crew_knowledge_context = extract_knowledge_context(
+                                knowledge_snippets
+                            )
+                            if self.crew_knowledge_context:
+                                task_prompt += self.crew_knowledge_context
+
+                    crewai_event_bus.emit(
+                        self,
+                        event=KnowledgeRetrievalCompletedEvent(
+                            query=self.knowledge_search_query,
+                            agent=self,
+                            retrieved_knowledge=(
+                                (self.agent_knowledge_context or "")
+                                + (
+                                    "\n"
+                                    if self.agent_knowledge_context
+                                    and self.crew_knowledge_context
+                                    else ""
+                                )
+                                + (self.crew_knowledge_context or "")
+                            ),
+                        ),
+                    )
+            except Exception as e:
+                crewai_event_bus.emit(
+                    self,
+                    event=KnowledgeSearchQueryFailedEvent(
+                        query=self.knowledge_search_query or "",
+                        agent=self,
+                        error=str(e),
+                    ),
                 )
-                if self.crew_knowledge_context:
-                    task_prompt += self.crew_knowledge_context
 
         tools = tools or self.tools or []
         self.create_agent_executor(tools=tools, task=task)
@@ -288,12 +349,19 @@ class Agent(BaseAgent):
 
             # Determine execution method based on timeout setting
             if self.max_execution_time is not None:
-                if not isinstance(self.max_execution_time, int) or self.max_execution_time <= 0:
-                    raise ValueError("Max Execution time must be a positive integer greater than zero")
-                result = self._execute_with_timeout(task_prompt, task, self.max_execution_time)
+                if (
+                    not isinstance(self.max_execution_time, int)
+                    or self.max_execution_time <= 0
+                ):
+                    raise ValueError(
+                        "Max Execution time must be a positive integer greater than zero"
+                    )
+                result = self._execute_with_timeout(
+                    task_prompt, task, self.max_execution_time
+                )
             else:
                 result = self._execute_without_timeout(task_prompt, task)
-                
+
         except TimeoutError as e:
             # Propagate TimeoutError without retry
             crewai_event_bus.emit(
@@ -345,54 +413,46 @@ class Agent(BaseAgent):
         )
         return result
 
-    def _execute_with_timeout(
-        self,
-        task_prompt: str,
-        task: Task,
-        timeout: int
-    ) -> str:
+    def _execute_with_timeout(self, task_prompt: str, task: Task, timeout: int) -> str:
         """Execute a task with a timeout.
-        
+
         Args:
             task_prompt: The prompt to send to the agent.
             task: The task being executed.
             timeout: Maximum execution time in seconds.
-            
+
         Returns:
             The output of the agent.
-            
+
         Raises:
             TimeoutError: If execution exceeds the timeout.
             RuntimeError: If execution fails for other reasons.
         """
         import concurrent.futures
+
         with concurrent.futures.ThreadPoolExecutor() as executor:
             future = executor.submit(
-                self._execute_without_timeout,
-                task_prompt=task_prompt,
-                task=task
+                self._execute_without_timeout, task_prompt=task_prompt, task=task
             )
-            
+
             try:
                 return future.result(timeout=timeout)
             except concurrent.futures.TimeoutError:
                 future.cancel()
-                raise TimeoutError(f"Task '{task.description}' execution timed out after {timeout} seconds. Consider increasing max_execution_time or optimizing the task.")
+                raise TimeoutError(
+                    f"Task '{task.description}' execution timed out after {timeout} seconds. Consider increasing max_execution_time or optimizing the task."
+                )
             except Exception as e:
                 future.cancel()
                 raise RuntimeError(f"Task execution failed: {str(e)}")
 
-    def _execute_without_timeout(
-        self,
-        task_prompt: str,
-        task: Task
-    ) -> str:
+    def _execute_without_timeout(self, task_prompt: str, task: Task) -> str:
         """Execute a task without a timeout.
-        
+
         Args:
             task_prompt: The prompt to send to the agent.
             task: The task being executed.
-            
+
         Returns:
             The output of the agent.
         """
@@ -560,6 +620,61 @@ class Agent(BaseAgent):
     def set_fingerprint(self, fingerprint: Fingerprint):
         self.security_config.fingerprint = fingerprint
 
+    def _get_knowledge_search_query(self, task_prompt: str) -> str | None:
+        """Generate a search query for the knowledge base based on the task description."""
+        crewai_event_bus.emit(
+            self,
+            event=KnowledgeQueryStartedEvent(
+                task_prompt=task_prompt,
+                agent=self,
+            ),
+        )
+        query = self.i18n.slice("knowledge_search_query").format(
+            task_prompt=task_prompt
+        )
+        rewriter_prompt = self.i18n.slice("knowledge_search_query_system_prompt")
+        if not isinstance(self.llm, BaseLLM):
+            self._logger.log(
+                "warning",
+                f"Knowledge search query failed: LLM for agent '{self.role}' is not an instance of BaseLLM",
+            )
+            crewai_event_bus.emit(
+                self,
+                event=KnowledgeQueryFailedEvent(
+                    agent=self,
+                    error="LLM is not compatible with knowledge search queries",
+                ),
+            )
+            return None
+
+        try:
+            rewritten_query = self.llm.call(
+                [
+                    {
+                        "role": "system",
+                        "content": rewriter_prompt,
+                    },
+                    {"role": "user", "content": query},
+                ]
+            )
+            crewai_event_bus.emit(
+                self,
+                event=KnowledgeQueryCompletedEvent(
+                    query=query,
+                    agent=self,
+                ),
+            )
+            return rewritten_query
+        except Exception as e:
+            crewai_event_bus.emit(
+                self,
+                event=KnowledgeQueryFailedEvent(
+                    agent=self,
+                    error=str(e),
+                ),
+            )
+            return None
+
     def kickoff(
         self,
         messages: Union[str, List[Dict[str, str]]],

src/crewai/cli/authentication/token.py

@@ -5,5 +5,5 @@ def get_auth_token() -> str:
     """Get the authentication token."""
     access_token = TokenManager().get_token()
     if not access_token:
-        raise Exception()
+        raise Exception("No token found, make sure you are logged in")
     return access_token

src/crewai/cli/cli.py

@@ -1,6 +1,5 @@
-import os
 from importlib.metadata import version as get_version
-from typing import Optional, Tuple
+from typing import Optional
 
 import click
 
@@ -138,12 +137,8 @@ def log_tasks_outputs() -> None:
 @click.option("-s", "--short", is_flag=True, help="Reset SHORT TERM memory")
 @click.option("-e", "--entities", is_flag=True, help="Reset ENTITIES memory")
 @click.option("-kn", "--knowledge", is_flag=True, help="Reset KNOWLEDGE storage")
-@click.option(
-    "-k",
-    "--kickoff-outputs",
-    is_flag=True,
-    help="Reset LATEST KICKOFF TASK OUTPUTS",
-)
+@click.option("-akn", "--agent-knowledge", is_flag=True, help="Reset AGENT KNOWLEDGE storage")
+@click.option("-k","--kickoff-outputs",is_flag=True,help="Reset LATEST KICKOFF TASK OUTPUTS")
 @click.option("-a", "--all", is_flag=True, help="Reset ALL memories")
 def reset_memories(
     long: bool,
@@ -151,18 +146,20 @@ def reset_memories(
     entities: bool,
     knowledge: bool,
     kickoff_outputs: bool,
+    agent_knowledge: bool,
     all: bool,
 ) -> None:
     """
-    Reset the crew memories (long, short, entity, latest_crew_kickoff_ouputs). This will delete all the data saved.
+    Reset the crew memories (long, short, entity, latest_crew_kickoff_ouputs, knowledge, agent_knowledge). This will delete all the data saved.
     """
     try:
-        if not all and not (long or short or entities or knowledge or kickoff_outputs):
+        memory_types = [long, short, entities, knowledge, agent_knowledge, kickoff_outputs, all]
+        if not any(memory_types):
             click.echo(
                 "Please specify at least one memory type to reset using the appropriate flags."
             )
             return
-        reset_memories_command(long, short, entities, knowledge, kickoff_outputs, all)
+        reset_memories_command(long, short, entities, knowledge, agent_knowledge, kickoff_outputs, all)
     except Exception as e:
         click.echo(f"An error occurred while resetting memories: {e}", err=True)
 

src/crewai/cli/constants.py

@@ -13,7 +13,7 @@ ENV_VARS = {
     ],
     "gemini": [
         {
-            "prompt": "Enter your GEMINI API key (press Enter to skip)",
+            "prompt": "Enter your GEMINI API key from https://ai.dev/apikey (press Enter to skip)",
             "key_name": "GEMINI_API_KEY",
         }
     ],

src/crewai/cli/install_crew.py

@@ -4,7 +4,7 @@ import click
 
 
 # Be mindful about changing this.
-# on some enviorments we don't use this command but instead uv sync directly
+# on some environments we don't use this command but instead uv sync directly
 # so if you expect this to support more things you will need to replicate it there
 # ask @joaomdmoura if you are unsure
 def install_crew(proxy_options: list[str]) -> None:

src/crewai/cli/plus_api.py

@@ -14,6 +14,7 @@ class PlusAPI:
 
     TOOLS_RESOURCE = "/crewai_plus/api/v1/tools"
     CREWS_RESOURCE = "/crewai_plus/api/v1/crews"
+    AGENTS_RESOURCE = "/crewai_plus/api/v1/agents"
 
     def __init__(self, api_key: str) -> None:
         self.api_key = api_key
@@ -37,6 +38,9 @@ class PlusAPI:
     def get_tool(self, handle: str):
         return self._make_request("GET", f"{self.TOOLS_RESOURCE}/{handle}")
 
+    def get_agent(self, handle: str):
+        return self._make_request("GET", f"{self.AGENTS_RESOURCE}/{handle}")
+
     def publish_tool(
         self,
         handle: str,

src/crewai/cli/reset_memories_command.py

@@ -2,7 +2,7 @@ import subprocess
 
 import click
 
-from crewai.cli.utils import get_crew
+from crewai.cli.utils import get_crews
 
 
 def reset_memories_command(
@@ -10,6 +10,7 @@ def reset_memories_command(
     short,
     entity,
     knowledge,
+    agent_knowledge,
     kickoff_outputs,
     all,
 ) -> None:
@@ -23,38 +24,56 @@ def reset_memories_command(
       kickoff_outputs (bool): Whether to reset the latest kickoff task outputs.
       all (bool): Whether to reset all memories.
       knowledge (bool): Whether to reset the knowledge.
+      agent_knowledge (bool): Whether to reset the agents knowledge.
     """
 
     try:
-        crew = get_crew()
-        if not crew:
-            raise ValueError("No crew found.")
-        if all:
-            crew.reset_memories(command_type="all")
-            click.echo("All memories have been reset.")
-            return
-
-        if not any([long, short, entity, kickoff_outputs, knowledge]):
+        if not any([long, short, entity, kickoff_outputs, knowledge, agent_knowledge, all]):
             click.echo(
                 "No memory type specified. Please specify at least one type to reset."
             )
             return
 
-        if long:
-            crew.reset_memories(command_type="long")
-            click.echo("Long term memory has been reset.")
-        if short:
-            crew.reset_memories(command_type="short")
-            click.echo("Short term memory has been reset.")
-        if entity:
-            crew.reset_memories(command_type="entity")
-            click.echo("Entity memory has been reset.")
-        if kickoff_outputs:
-            crew.reset_memories(command_type="kickoff_outputs")
-            click.echo("Latest Kickoff outputs stored has been reset.")
-        if knowledge:
-            crew.reset_memories(command_type="knowledge")
-            click.echo("Knowledge has been reset.")
+        crews = get_crews()
+        if not crews:
+            raise ValueError("No crew found.")
+        for crew in crews:
+            if all:
+                crew.reset_memories(command_type="all")
+                click.echo(
+                    f"[Crew ({crew.name if crew.name else crew.id})] Reset memories command has been completed."
+                )
+                continue
+            if long:
+                crew.reset_memories(command_type="long")
+                click.echo(
+                    f"[Crew ({crew.name if crew.name else crew.id})] Long term memory has been reset."
+                )
+            if short:
+                crew.reset_memories(command_type="short")
+                click.echo(
+                    f"[Crew ({crew.name if crew.name else crew.id})] Short term memory has been reset."
+                )
+            if entity:
+                crew.reset_memories(command_type="entity")
+                click.echo(
+                    f"[Crew ({crew.name if crew.name else crew.id})] Entity memory has been reset."
+                )
+            if kickoff_outputs:
+                crew.reset_memories(command_type="kickoff_outputs")
+                click.echo(
+                    f"[Crew ({crew.name if crew.name else crew.id})] Latest Kickoff outputs stored has been reset."
+                )
+            if knowledge:
+                crew.reset_memories(command_type="knowledge")
+                click.echo(
+                    f"[Crew ({crew.name if crew.name else crew.id})] Knowledge has been reset."
+                )
+            if agent_knowledge:
+                crew.reset_memories(command_type="agent_knowledge")
+                click.echo(
+                    f"[Crew ({crew.name if crew.name else crew.id})] Agents knowledge has been reset."
+                )
 
     except subprocess.CalledProcessError as e:
         click.echo(f"An error occurred while resetting the memories: {e}", err=True)

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

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.118.0,<1.0.0"
+    "crewai[tools]>=0.120.1,<1.0.0"
 ]
 
 [project.scripts]

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

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.118.0,<1.0.0",
+    "crewai[tools]>=0.120.1,<1.0.0",
 ]
 
 [project.scripts]

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

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.118.0"
+    "crewai[tools]>=0.120.1"
 ]
 
 [tool.crewai]

src/crewai/cli/utils.py

@@ -2,7 +2,8 @@ import os
 import shutil
 import sys
 from functools import reduce
-from typing import Any, Dict, List
+from inspect import isfunction, ismethod
+from typing import Any, Dict, List, get_type_hints
 
 import click
 import tomli
@@ -10,6 +11,7 @@ from rich.console import Console
 
 from crewai.cli.constants import ENV_VARS
 from crewai.crew import Crew
+from crewai.flow import Flow
 
 if sys.version_info >= (3, 11):
     import tomllib
@@ -250,11 +252,11 @@ def write_env_file(folder_path, env_vars):
             file.write(f"{key}={value}\n")
 
 
-def get_crew(crew_path: str = "crew.py", require: bool = False) -> Crew | None:
-    """Get the crew instance from the crew.py file."""
+def get_crews(crew_path: str = "crew.py", require: bool = False) -> list[Crew]:
+    """Get the crew instances from the a file."""
+    crew_instances = []
     try:
         import importlib.util
-        import os
 
         for root, _, files in os.walk("."):
             if crew_path in files:
@@ -271,12 +273,10 @@ def get_crew(crew_path: str = "crew.py", require: bool = False) -> Crew | None:
                         spec.loader.exec_module(module)
 
                         for attr_name in dir(module):
-                            attr = getattr(module, attr_name)
-                            try:
-                                if callable(attr) and hasattr(attr, "crew"):
-                                    crew_instance = attr().crew()
-                                    return crew_instance
+                            module_attr = getattr(module, attr_name)
 
+                            try:
+                                crew_instances.extend(fetch_crews(module_attr))
                             except Exception as e:
                                 print(f"Error processing attribute {attr_name}: {e}")
                                 continue
@@ -286,7 +286,6 @@ def get_crew(crew_path: str = "crew.py", require: bool = False) -> Crew | None:
                         import traceback
 
                         print(f"Traceback: {traceback.format_exc()}")
-
                 except (ImportError, AttributeError) as e:
                     if require:
                         console.print(
@@ -300,7 +299,6 @@ def get_crew(crew_path: str = "crew.py", require: bool = False) -> Crew | None:
         if require:
             console.print("No valid Crew instance found in crew.py", style="bold red")
             raise SystemExit
-        return None
 
     except Exception as e:
         if require:
@@ -308,4 +306,36 @@ def get_crew(crew_path: str = "crew.py", require: bool = False) -> Crew | None:
                 f"Unexpected error while loading crew: {str(e)}", style="bold red"
             )
             raise SystemExit
+    return crew_instances
+
+
+def get_crew_instance(module_attr) -> Crew | None:
+    if (
+        callable(module_attr)
+        and hasattr(module_attr, "is_crew_class")
+        and module_attr.is_crew_class
+    ):
+        return module_attr().crew()
+    if (ismethod(module_attr) or isfunction(module_attr)) and get_type_hints(
+        module_attr
+    ).get("return") is Crew:
+        return module_attr()
+    elif isinstance(module_attr, Crew):
+        return module_attr
+    else:
         return None
+
+
+def fetch_crews(module_attr) -> list[Crew]:
+    crew_instances: list[Crew] = []
+
+    if crew_instance := get_crew_instance(module_attr):
+        crew_instances.append(crew_instance)
+
+    if isinstance(module_attr, type) and issubclass(module_attr, Flow):
+        instance = module_attr()
+        for attr_name in dir(instance):
+            attr = getattr(instance, attr_name)
+            if crew_instance := get_crew_instance(attr):
+                crew_instances.append(crew_instance)
+    return crew_instances

src/crewai/crew.py

@@ -6,7 +6,17 @@ import warnings
 from concurrent.futures import Future
 from copy import copy as shallow_copy
 from hashlib import md5
-from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Union, cast
+from typing import (
+    Any,
+    Callable,
+    Dict,
+    List,
+    Optional,
+    Set,
+    Tuple,
+    Union,
+    cast,
+)
 
 from pydantic import (
     UUID4,
@@ -24,6 +34,7 @@ from crewai.agent import Agent
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.cache import CacheHandler
 from crewai.crews.crew_output import CrewOutput
+from crewai.flow.flow_trackable import FlowTrackable
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.llm import LLM, BaseLLM
@@ -41,7 +52,7 @@ from crewai.tools.agent_tools.agent_tools import AgentTools
 from crewai.tools.base_tool import BaseTool, Tool
 from crewai.types.usage_metrics import UsageMetrics
 from crewai.utilities import I18N, FileHandler, Logger, RPMController
-from crewai.utilities.constants import TRAINING_DATA_FILE
+from crewai.utilities.constants import NOT_SPECIFIED, TRAINING_DATA_FILE
 from crewai.utilities.evaluators.crew_evaluator_handler import CrewEvaluator
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
 from crewai.utilities.events.crew_events import (
@@ -69,7 +80,7 @@ from crewai.utilities.training_handler import CrewTrainingHandler
 warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")
 
 
-class Crew(BaseModel):
+class Crew(FlowTrackable, BaseModel):
     """
     Represents a group of agents, defining how they should collaborate and the tasks they should perform.
 
@@ -304,7 +315,9 @@ class Crew(BaseModel):
         """Initialize private memory attributes."""
         self._external_memory = (
             # External memory doesn’t support a default value since it was designed to be managed entirely externally
-            self.external_memory.set_crew(self) if self.external_memory else None
+            self.external_memory.set_crew(self)
+            if self.external_memory
+            else None
         )
 
         self._long_term_memory = self.long_term_memory
@@ -333,6 +346,7 @@ class Crew(BaseModel):
                         embedder=self.embedder,
                         collection_name="crew",
                     )
+                    self.knowledge.add_sources()
 
             except Exception as e:
                 self._logger.log(
@@ -464,7 +478,7 @@ class Crew(BaseModel):
         separated by a synchronous task.
         """
         for i, task in enumerate(self.tasks):
-            if task.async_execution and task.context:
+            if task.async_execution and isinstance(task.context, list):
                 for context_task in task.context:
                     if context_task.async_execution:
                         for j in range(i - 1, -1, -1):
@@ -482,7 +496,7 @@ class Crew(BaseModel):
         task_indices = {id(task): i for i, task in enumerate(self.tasks)}
 
         for task in self.tasks:
-            if task.context:
+            if isinstance(task.context, list):
                 for context_task in task.context:
                     if id(context_task) not in task_indices:
                         continue  # Skip context tasks not in the main tasks list
@@ -1020,11 +1034,14 @@ class Crew(BaseModel):
                 )
         return cast(List[BaseTool], tools)
 
-    def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
+    def _get_context(self, task: Task, task_outputs: List[TaskOutput]) -> str:
+        if not task.context:
+            return ""
+
         context = (
-            aggregate_raw_outputs_from_tasks(task.context)
-            if task.context
-            else aggregate_raw_outputs_from_task_outputs(task_outputs)
+            aggregate_raw_outputs_from_task_outputs(task_outputs)
+            if task.context is NOT_SPECIFIED
+            else aggregate_raw_outputs_from_tasks(task.context)
         )
         return context
 
@@ -1212,7 +1229,7 @@ class Crew(BaseModel):
             task_mapping[task.key] = cloned_task
 
         for cloned_task, original_task in zip(cloned_tasks, self.tasks):
-            if original_task.context:
+            if isinstance(original_task.context, list):
                 cloned_context = [
                     task_mapping[context_task.key]
                     for context_task in original_task.context
@@ -1339,7 +1356,7 @@ class Crew(BaseModel):
 
         Args:
             command_type: Type of memory to reset.
-                Valid options: 'long', 'short', 'entity', 'knowledge',
+                Valid options: 'long', 'short', 'entity', 'knowledge', 'agent_knowledge'
                 'kickoff_outputs', or 'all'
 
         Raises:
@@ -1352,6 +1369,7 @@ class Crew(BaseModel):
                 "short",
                 "entity",
                 "knowledge",
+                "agent_knowledge",
                 "kickoff_outputs",
                 "all",
                 "external",
@@ -1369,8 +1387,6 @@ class Crew(BaseModel):
             else:
                 self._reset_specific_memory(command_type)
 
-            self._logger.log("info", f"{command_type} memory has been reset")
-
         except Exception as e:
             error_msg = f"Failed to reset {command_type} memory: {str(e)}"
             self._logger.log("error", error_msg)
@@ -1378,21 +1394,22 @@ class Crew(BaseModel):
 
     def _reset_all_memories(self) -> None:
         """Reset all available memory systems."""
-        memory_systems = [
-            ("short term", getattr(self, "_short_term_memory", None)),
-            ("entity", getattr(self, "_entity_memory", None)),
-            ("external", getattr(self, "_external_memory", None)),
-            ("long term", getattr(self, "_long_term_memory", None)),
-            ("task output", getattr(self, "_task_output_handler", None)),
-            ("knowledge", getattr(self, "knowledge", None)),
-        ]
+        memory_systems = self._get_memory_systems()
 
-        for name, system in memory_systems:
-            if system is not None:
+        for memory_type, config in memory_systems.items():
+            if (system := config.get('system')) is not None:
+                name = config.get('name')
                 try:
-                    system.reset()
+                    reset_fn: Callable = cast(Callable, config.get('reset'))
+                    reset_fn(system)
+                    self._logger.log(
+                        "info",
+                        f"[Crew ({self.name if self.name else self.id})] {name} memory has been reset",
+                    )
                 except Exception as e:
-                    raise RuntimeError(f"Failed to reset {name} memory") from e
+                    raise RuntimeError(
+                        f"[Crew ({self.name if self.name else self.id})] Failed to reset {name} memory: {str(e)}"
+                    ) from e
 
     def _reset_specific_memory(self, memory_type: str) -> None:
         """Reset a specific memory system.
@@ -1403,23 +1420,83 @@ class Crew(BaseModel):
         Raises:
             RuntimeError: If the specified memory system fails to reset
         """
-        reset_functions = {
-            "long": (getattr(self, "_long_term_memory", None), "long term"),
-            "short": (getattr(self, "_short_term_memory", None), "short term"),
-            "entity": (getattr(self, "_entity_memory", None), "entity"),
-            "knowledge": (getattr(self, "knowledge", None), "knowledge"),
-            "kickoff_outputs": (
-                getattr(self, "_task_output_handler", None),
-                "task output",
-            ),
-            "external": (getattr(self, "_external_memory", None), "external"),
+        memory_systems = self._get_memory_systems()
+        config = memory_systems[memory_type]
+        system = config.get('system')
+        name = config.get('name')
+
+        if system is None:
+            raise RuntimeError(f"{name} memory system is not initialized")
+        
+        try:
+            reset_fn: Callable = cast(Callable, config.get('reset'))
+            reset_fn(system)
+            self._logger.log(
+                "info",
+                f"[Crew ({self.name if self.name else self.id})] {name} memory has been reset",
+            )
+        except Exception as e:
+            raise RuntimeError(
+                f"[Crew ({self.name if self.name else self.id})] Failed to reset {name} memory: {str(e)}"
+            ) from e
+
+    def _get_memory_systems(self):
+        """Get all available memory systems with their configuration.
+        
+        Returns:
+            Dict containing all memory systems with their reset functions and display names.
+        """
+        def default_reset(memory):
+            return memory.reset()
+        def knowledge_reset(memory):
+            return self.reset_knowledge(memory)
+        
+        # Get knowledge for agents 
+        agent_knowledges = [getattr(agent, "knowledge", None) for agent in self.agents 
+                                    if getattr(agent, "knowledge", None) is not None]
+        # Get knowledge for crew and agents
+        crew_knowledge = getattr(self, "knowledge", None)
+        crew_and_agent_knowledges = ([crew_knowledge] if crew_knowledge is not None else []) + agent_knowledges
+
+        return {
+            'short': {
+                'system': getattr(self, "_short_term_memory", None),
+                'reset': default_reset,
+                'name': 'Short Term'
+            },
+            'entity': {
+                'system': getattr(self, "_entity_memory", None),
+                'reset': default_reset,
+                'name': 'Entity'
+            },
+            'external': {
+                'system': getattr(self, "_external_memory", None),
+                'reset': default_reset,
+                'name': 'External'
+            },
+            'long': {
+                'system': getattr(self, "_long_term_memory", None),
+                'reset': default_reset,
+                'name': 'Long Term'
+            },
+            'kickoff_outputs': {
+                'system': getattr(self, "_task_output_handler", None),
+                'reset': default_reset,
+                'name': 'Task Output'
+            },
+            'knowledge': {
+                'system': crew_and_agent_knowledges if crew_and_agent_knowledges else None,
+                'reset': knowledge_reset,
+                'name': 'Crew Knowledge and Agent Knowledge'
+            },
+            'agent_knowledge': {
+                'system': agent_knowledges if agent_knowledges else None,
+                'reset': knowledge_reset,
+                'name': 'Agent Knowledge'
+            }
         }
 
-        memory_system, name = reset_functions[memory_type]
-        if memory_system is None:
-            raise RuntimeError(f"{name} memory system is not initialized")
-
-        try:
-            memory_system.reset()
-        except Exception as e:
-            raise RuntimeError(f"Failed to reset {name} memory") from e
+    def reset_knowledge(self, knowledges: List[Knowledge]) -> None:
+        """Reset crew and agent knowledge storage."""
+        for ks in knowledges:
+            ks.reset()

src/crewai/flow/flow_trackable.py

@@ -0,0 +1,44 @@
+import inspect
+from typing import Optional
+
+from pydantic import BaseModel, Field, InstanceOf, model_validator
+
+from crewai.flow import Flow
+
+
+class FlowTrackable(BaseModel):
+    """Mixin that tracks the Flow instance that instantiated the object, e.g. a
+    Flow instance that created a Crew or Agent.
+
+    Automatically finds and stores a reference to the parent Flow instance by
+    inspecting the call stack.
+    """
+
+    parent_flow: Optional[InstanceOf[Flow]] = Field(
+        default=None,
+        description="The parent flow of the instance, if it was created inside a flow.",
+    )
+
+    @model_validator(mode="after")
+    def _set_parent_flow(self, max_depth: int = 5) -> "FlowTrackable":
+        frame = inspect.currentframe()
+
+        try:
+            if frame is None:
+                return self
+
+            frame = frame.f_back
+            for _ in range(max_depth):
+                if frame is None:
+                    break
+
+                candidate = frame.f_locals.get("self")
+                if isinstance(candidate, Flow):
+                    self.parent_flow = candidate
+                    break
+
+                frame = frame.f_back
+        finally:
+            del frame
+
+        return self

src/crewai/knowledge/knowledge.py

@@ -41,7 +41,6 @@ class Knowledge(BaseModel):
             )
         self.sources = sources
         self.storage.initialize_knowledge_storage()
-        self._add_sources()
 
     def query(
         self, query: List[str], results_limit: int = 3, score_threshold: float = 0.35
@@ -63,7 +62,7 @@ class Knowledge(BaseModel):
         )
         return results
 
-    def _add_sources(self):
+    def add_sources(self):
         try:
             for source in self.sources:
                 source.storage = self.storage

src/crewai/lite_agent.py

@@ -13,6 +13,7 @@ from crewai.agents.parser import (
     AgentFinish,
     OutputParserException,
 )
+from crewai.flow.flow_trackable import FlowTrackable
 from crewai.llm import LLM
 from crewai.tools.base_tool import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
@@ -80,7 +81,7 @@ class LiteAgentOutput(BaseModel):
         return self.raw
 
 
-class LiteAgent(BaseModel):
+class LiteAgent(FlowTrackable, BaseModel):
     """
     A lightweight agent that can process messages and use tools.
 
@@ -162,7 +163,7 @@ class LiteAgent(BaseModel):
     _messages: List[Dict[str, str]] = PrivateAttr(default_factory=list)
     _iterations: int = PrivateAttr(default=0)
     _printer: Printer = PrivateAttr(default_factory=Printer)
-    
+
     @model_validator(mode="after")
     def setup_llm(self):
         """Set up the LLM and other components after initialization."""

src/crewai/llm.py

@@ -5,8 +5,7 @@ import sys
 import threading
 import warnings
 from collections import defaultdict
-from contextlib import contextmanager
-from types import SimpleNamespace
+from contextlib import contextmanager, redirect_stderr, redirect_stdout
 from typing import (
     Any,
     DefaultDict,
@@ -31,7 +30,6 @@ from crewai.utilities.events.llm_events import (
     LLMCallType,
     LLMStreamChunkEvent,
 )
-from crewai.utilities.events.tool_usage_events import ToolExecutionErrorEvent
 
 with warnings.catch_warnings():
     warnings.simplefilter("ignore", UserWarning)
@@ -45,6 +43,9 @@ with warnings.catch_warnings():
     from litellm.utils import supports_response_schema
 
 
+import io
+from typing import TextIO
+
 from crewai.llms.base_llm import BaseLLM
 from crewai.utilities.events import crewai_event_bus
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
@@ -54,12 +55,17 @@ from crewai.utilities.exceptions.context_window_exceeding_exception import (
 load_dotenv()
 
 
-class FilteredStream:
-    def __init__(self, original_stream):
+class FilteredStream(io.TextIOBase):
+    _lock = None
+
+    def __init__(self, original_stream: TextIO):
         self._original_stream = original_stream
         self._lock = threading.Lock()
 
-    def write(self, s) -> int:
+    def write(self, s: str) -> int:
+        if not self._lock:
+            self._lock = threading.Lock()
+
         with self._lock:
             # Filter out extraneous messages from LiteLLM
             if (
@@ -214,15 +220,11 @@ def suppress_warnings():
         )
 
         # Redirect stdout and stderr
-        old_stdout = sys.stdout
-        old_stderr = sys.stderr
-        sys.stdout = FilteredStream(old_stdout)
-        sys.stderr = FilteredStream(old_stderr)
-        try:
+        with (
+            redirect_stdout(FilteredStream(sys.stdout)),
+            redirect_stderr(FilteredStream(sys.stderr)),
+        ):
             yield
-        finally:
-            sys.stdout = old_stdout
-            sys.stderr = old_stderr
 
 
 class Delta(TypedDict):

src/crewai/task.py

@@ -2,7 +2,6 @@ import datetime
 import inspect
 import json
 import logging
-import re
 import threading
 import uuid
 from concurrent.futures import Future
@@ -41,6 +40,7 @@ from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
 from crewai.tools.base_tool import BaseTool
 from crewai.utilities.config import process_config
+from crewai.utilities.constants import NOT_SPECIFIED
 from crewai.utilities.converter import Converter, convert_to_model
 from crewai.utilities.events import (
     TaskCompletedEvent,
@@ -97,7 +97,7 @@ class Task(BaseModel):
     )
     context: Optional[List["Task"]] = Field(
         description="Other tasks that will have their output used as context for this task.",
-        default=None,
+        default=NOT_SPECIFIED,
     )
     async_execution: Optional[bool] = Field(
         description="Whether the task should be executed asynchronously or not.",
@@ -135,6 +135,10 @@ class Task(BaseModel):
         description="Whether the task should have a human review the final answer of the agent",
         default=False,
     )
+    markdown: Optional[bool] = Field(
+        description="Whether the task should instruct the agent to return the final answer formatted in Markdown",
+        default=False,
+    )
     converter_cls: Optional[Type[Converter]] = Field(
         description="A converter class used to export structured output",
         default=None,
@@ -522,10 +526,14 @@ class Task(BaseModel):
         return guardrail_result
 
     def prompt(self) -> str:
-        """Prompt the task.
-
+        """Generates the task prompt with optional markdown formatting.
+        
+        When the markdown attribute is True, instructions for formatting the
+        response in Markdown syntax will be added to the prompt.
+        
         Returns:
-            Prompt of the task.
+            str: The formatted prompt string containing the task description,
+                 expected output, and optional markdown formatting instructions.
         """
         tasks_slices = [self.description]
 
@@ -533,6 +541,17 @@ class Task(BaseModel):
             expected_output=self.expected_output
         )
         tasks_slices = [self.description, output]
+        
+        if self.markdown:
+            markdown_instruction = """Your final answer MUST be formatted in Markdown syntax.
+Follow these guidelines:
+- Use # for headers
+- Use ** for bold text
+- Use * for italic text
+- Use - or * for bullet points
+- Use `code` for inline code
+- Use ```language for code blocks"""
+            tasks_slices.append(markdown_instruction)
         return "\n".join(tasks_slices)
 
     def interpolate_inputs_and_add_conversation_history(
@@ -643,7 +662,7 @@ class Task(BaseModel):
 
         cloned_context = (
             [task_mapping[context_task.key] for context_task in self.context]
-            if self.context
+            if isinstance(self.context, list)
             else None
         )
 

src/crewai/telemetry/telemetry.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import asyncio
 import json
+import logging
 import os
 import platform
 import warnings
@@ -9,11 +10,25 @@ from contextlib import contextmanager
 from importlib.metadata import version
 from typing import TYPE_CHECKING, Any, Optional
 
+from opentelemetry import trace
+from opentelemetry.exporter.otlp.proto.http.trace_exporter import (
+    OTLPSpanExporter,
+)
+from opentelemetry.sdk.resources import SERVICE_NAME, Resource
+from opentelemetry.sdk.trace import TracerProvider
+from opentelemetry.sdk.trace.export import (
+    BatchSpanProcessor,
+    SpanExportResult,
+)
+from opentelemetry.trace import Span, Status, StatusCode
+
 from crewai.telemetry.constants import (
     CREWAI_TELEMETRY_BASE_URL,
     CREWAI_TELEMETRY_SERVICE_NAME,
 )
 
+logger = logging.getLogger(__name__)
+
 
 @contextmanager
 def suppress_warnings():
@@ -22,20 +37,20 @@ def suppress_warnings():
         yield
 
 
-from opentelemetry import trace  # 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
-from opentelemetry.trace import Span, Status, StatusCode  # noqa: E402
-
 if TYPE_CHECKING:
     from crewai.crew import Crew
     from crewai.task import Task
 
 
+class SafeOTLPSpanExporter(OTLPSpanExporter):
+    def export(self, spans) -> SpanExportResult:
+        try:
+            return super().export(spans)
+        except Exception as e:
+            logger.error(e)
+            return SpanExportResult.FAILURE
+
+
 class Telemetry:
     """A class to handle anonymous telemetry for the crewai package.
 
@@ -64,7 +79,7 @@ class Telemetry:
                 self.provider = TracerProvider(resource=self.resource)
 
             processor = BatchSpanProcessor(
-                OTLPSpanExporter(
+                SafeOTLPSpanExporter(
                     endpoint=f"{CREWAI_TELEMETRY_BASE_URL}/v1/traces",
                     timeout=30,
                 )
@@ -217,7 +232,7 @@ class Telemetry:
                                 "agent_key": task.agent.key if task.agent else None,
                                 "context": (
                                     [task.description for task in task.context]
-                                    if task.context
+                                    if isinstance(task.context, list)
                                     else None
                                 ),
                                 "tools_names": [
@@ -733,7 +748,7 @@ class Telemetry:
                             "agent_key": task.agent.key if task.agent else None,
                             "context": (
                                 [task.description for task in task.context]
-                                if task.context
+                                if isinstance(task.context, list)
                                 else None
                             ),
                             "tools_names": [

src/crewai/translations/en.json

@@ -27,7 +27,9 @@
     "feedback_instructions": "User feedback: {feedback}\nInstructions: Use this feedback to enhance the next output iteration.\nNote: Do not respond or add commentary.",
     "lite_agent_system_prompt_with_tools": "You are {role}. {backstory}\nYour personal goal is: {goal}\n\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\n{tools}\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [{tool_names}], just the name, exactly as it's written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n```",
     "lite_agent_system_prompt_without_tools": "You are {role}. {backstory}\nYour personal goal is: {goal}\n\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!",
-    "lite_agent_response_format": "\nIMPORTANT: Your final answer MUST contain all the information requested in the following format: {response_format}\n\nIMPORTANT: Ensure the final output does not include any code block markers like ```json or ```python."
+    "lite_agent_response_format": "\nIMPORTANT: Your final answer MUST contain all the information requested in the following format: {response_format}\n\nIMPORTANT: Ensure the final output does not include any code block markers like ```json or ```python.",
+    "knowledge_search_query": "The original query is: {task_prompt}.",
+    "knowledge_search_query_system_prompt": "Your goal is to rewrite the user query so that it is optimized for retrieval from a vector database. Consider how the query will be used to find relevant documents, and aim to make it more specific and context-aware. \n\n Do not include any other text than the rewritten query, especially any preamble or postamble and only add expected output format if its relevant to the rewritten query. \n\n Focus on the key words of the intended task and to retrieve the most relevant information. \n\n There will be some extra context provided that might need to be removed such as expected_output formats structured_outputs and other instructions."
   },
   "errors": {
     "force_final_answer_error": "You can't keep going, here is the best final answer you generated:\n\n {formatted_answer}",

src/crewai/utilities/agent_utils.py

@@ -16,6 +16,7 @@ from crewai.tools.base_tool import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.tools.tool_types import ToolResult
 from crewai.utilities import I18N, Printer
+from crewai.utilities.errors import AgentRepositoryError
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
 )
@@ -428,3 +429,41 @@ def show_agent_logs(
             printer.print(
                 content=f"\033[95m## Final Answer:\033[00m \033[92m\n{formatted_answer.output}\033[00m\n\n"
             )
+
+
+def load_agent_from_repository(from_repository: str) -> Dict[str, Any]:
+    attributes: Dict[str, Any] = {}
+    if from_repository:
+        import importlib
+
+        from crewai.cli.authentication.token import get_auth_token
+        from crewai.cli.plus_api import PlusAPI
+
+        client = PlusAPI(api_key=get_auth_token())
+        response = client.get_agent(from_repository)
+        if response.status_code == 404:
+            raise AgentRepositoryError(
+                f"Agent {from_repository} does not exist, make sure the name is correct or the agent is available on your organization"
+            )
+
+        if response.status_code != 200:
+            raise AgentRepositoryError(
+                f"Agent {from_repository} could not be loaded: {response.text}"
+            )
+
+        agent = response.json()
+        for key, value in agent.items():
+            if key == "tools":
+                attributes[key] = []
+                for tool in value:
+                    try:
+                        module = importlib.import_module("crewai_tools")
+                        tool_class = getattr(module, tool["name"])
+                        attributes[key].append(tool_class())
+                    except Exception as e:
+                        raise AgentRepositoryError(
+                            f"Tool {tool['name']} could not be loaded: {e}"
+                        ) from e
+            else:
+                attributes[key] = value
+    return attributes

src/crewai/utilities/constants.py

@@ -5,3 +5,14 @@ KNOWLEDGE_DIRECTORY = "knowledge"
 MAX_LLM_RETRY = 3
 MAX_FILE_NAME_LENGTH = 255
 EMITTER_COLOR = "bold_blue"
+
+
+class _NotSpecified:
+    def __repr__(self):
+        return "NOT_SPECIFIED"
+
+
+# Sentinel value used to detect when no value has been explicitly provided.
+# Unlike `None`, which might be a valid value from the user, `NOT_SPECIFIED` allows
+# us to distinguish between "not passed at all" and "explicitly passed None" or "[]".
+NOT_SPECIFIED = _NotSpecified()

src/crewai/utilities/errors.py

@@ -1,4 +1,5 @@
 """Error message definitions for CrewAI database operations."""
+
 from typing import Optional
 
 
@@ -37,3 +38,9 @@ class DatabaseError:
             The formatted error message
         """
         return template.format(str(error))
+
+
+class AgentRepositoryError(Exception):
+    """Exception raised when an agent repository is not found."""
+
+    ...

src/crewai/utilities/events/crewai_event_bus.py

@@ -70,7 +70,12 @@ class CrewAIEventsBus:
         for event_type, handlers in self._handlers.items():
             if isinstance(event, event_type):
                 for handler in handlers:
-                    handler(source, event)
+                    try:
+                        handler(source, event)
+                    except Exception as e:
+                        print(
+                            f"[EventBus Error] Handler '{handler.__name__}' failed for event '{event_type.__name__}': {e}"
+                        )
 
         self._signal.send(source, event=event)
 

src/crewai/utilities/events/event_listener.py

@@ -8,6 +8,14 @@ from crewai.telemetry.telemetry import Telemetry
 from crewai.utilities import Logger
 from crewai.utilities.constants import EMITTER_COLOR
 from crewai.utilities.events.base_event_listener import BaseEventListener
+from crewai.utilities.events.knowledge_events import (
+    KnowledgeQueryCompletedEvent,
+    KnowledgeQueryFailedEvent,
+    KnowledgeQueryStartedEvent,
+    KnowledgeRetrievalCompletedEvent,
+    KnowledgeRetrievalStartedEvent,
+    KnowledgeSearchQueryFailedEvent,
+)
 from crewai.utilities.events.llm_events import (
     LLMCallCompletedEvent,
     LLMCallFailedEvent,
@@ -57,6 +65,8 @@ class EventListener(BaseEventListener):
     execution_spans: Dict[Task, Any] = Field(default_factory=dict)
     next_chunk = 0
     text_stream = StringIO()
+    knowledge_retrieval_in_progress = False
+    knowledge_query_in_progress = False
 
     def __new__(cls):
         if cls._instance is None:
@@ -342,5 +352,59 @@ class EventListener(BaseEventListener):
         def on_crew_test_failed(source, event: CrewTestFailedEvent):
             self.formatter.handle_crew_test_failed(event.crew_name or "Crew")
 
+        @crewai_event_bus.on(KnowledgeRetrievalStartedEvent)
+        def on_knowledge_retrieval_started(
+            source, event: KnowledgeRetrievalStartedEvent
+        ):
+            if self.knowledge_retrieval_in_progress:
+                return
+
+            self.knowledge_retrieval_in_progress = True
+
+            self.formatter.handle_knowledge_retrieval_started(
+                self.formatter.current_agent_branch,
+                self.formatter.current_crew_tree,
+            )
+
+        @crewai_event_bus.on(KnowledgeRetrievalCompletedEvent)
+        def on_knowledge_retrieval_completed(
+            source, event: KnowledgeRetrievalCompletedEvent
+        ):
+            if not self.knowledge_retrieval_in_progress:
+                return
+
+            self.knowledge_retrieval_in_progress = False
+            self.formatter.handle_knowledge_retrieval_completed(
+                self.formatter.current_agent_branch,
+                self.formatter.current_crew_tree,
+                event.retrieved_knowledge,
+            )
+
+        @crewai_event_bus.on(KnowledgeQueryStartedEvent)
+        def on_knowledge_query_started(source, event: KnowledgeQueryStartedEvent):
+            pass
+
+        @crewai_event_bus.on(KnowledgeQueryFailedEvent)
+        def on_knowledge_query_failed(source, event: KnowledgeQueryFailedEvent):
+            self.formatter.handle_knowledge_query_failed(
+                self.formatter.current_agent_branch,
+                event.error,
+                self.formatter.current_crew_tree,
+            )
+
+        @crewai_event_bus.on(KnowledgeQueryCompletedEvent)
+        def on_knowledge_query_completed(source, event: KnowledgeQueryCompletedEvent):
+            pass
+
+        @crewai_event_bus.on(KnowledgeSearchQueryFailedEvent)
+        def on_knowledge_search_query_failed(
+            source, event: KnowledgeSearchQueryFailedEvent
+        ):
+            self.formatter.handle_knowledge_search_query_failed(
+                self.formatter.current_agent_branch,
+                event.error,
+                self.formatter.current_crew_tree,
+            )
+
 
 event_listener = EventListener()

src/crewai/utilities/events/knowledge_events.py

@@ -0,0 +1,56 @@
+from typing import TYPE_CHECKING, Any
+
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.utilities.events.base_events import BaseEvent
+
+if TYPE_CHECKING:
+    from crewai.agents.agent_builder.base_agent import BaseAgent
+
+
+class KnowledgeRetrievalStartedEvent(BaseEvent):
+    """Event emitted when a knowledge retrieval is started."""
+
+    type: str = "knowledge_search_query_started"
+    agent: BaseAgent
+
+
+class KnowledgeRetrievalCompletedEvent(BaseEvent):
+    """Event emitted when a knowledge retrieval is completed."""
+
+    query: str
+    type: str = "knowledge_search_query_completed"
+    agent: BaseAgent
+    retrieved_knowledge: Any
+
+
+class KnowledgeQueryStartedEvent(BaseEvent):
+    """Event emitted when a knowledge query is started."""
+
+    task_prompt: str
+    type: str = "knowledge_query_started"
+    agent: BaseAgent
+
+
+class KnowledgeQueryFailedEvent(BaseEvent):
+    """Event emitted when a knowledge query fails."""
+
+    type: str = "knowledge_query_failed"
+    agent: BaseAgent
+    error: str
+
+
+class KnowledgeQueryCompletedEvent(BaseEvent):
+    """Event emitted when a knowledge query is completed."""
+
+    query: str
+    type: str = "knowledge_query_completed"
+    agent: BaseAgent
+
+
+class KnowledgeSearchQueryFailedEvent(BaseEvent):
+    """Event emitted when a knowledge search query fails."""
+
+    query: str
+    type: str = "knowledge_search_query_failed"
+    agent: BaseAgent
+    error: str

src/crewai/utilities/events/utils/console_formatter.py

@@ -783,3 +783,202 @@ class ConsoleFormatter:
             self.update_lite_agent_status(
                 self.current_lite_agent_branch, lite_agent_role, status, **fields
             )
+
+    def handle_knowledge_retrieval_started(
+        self,
+        agent_branch: Optional[Tree],
+        crew_tree: Optional[Tree],
+    ) -> Optional[Tree]:
+        """Handle knowledge retrieval started event."""
+        if not self.verbose:
+            return None
+
+        branch_to_use = agent_branch or self.current_lite_agent_branch
+        tree_to_use = branch_to_use or crew_tree
+
+        if branch_to_use is None or tree_to_use is None:
+            # If we don't have a valid branch, use crew_tree as the branch if available
+            if crew_tree is not None:
+                branch_to_use = tree_to_use = crew_tree
+            else:
+                return None
+
+        knowledge_branch = branch_to_use.add("")
+        self.update_tree_label(
+            knowledge_branch, "🔍", "Knowledge Retrieval Started", "blue"
+        )
+
+        self.print(tree_to_use)
+        self.print()
+        return knowledge_branch
+
+    def handle_knowledge_retrieval_completed(
+        self,
+        agent_branch: Optional[Tree],
+        crew_tree: Optional[Tree],
+        retrieved_knowledge: Any,
+    ) -> None:
+        """Handle knowledge retrieval completed event."""
+        if not self.verbose:
+            return None
+
+        branch_to_use = self.current_lite_agent_branch or agent_branch
+        tree_to_use = branch_to_use or crew_tree
+
+        if branch_to_use is None and tree_to_use is not None:
+            branch_to_use = tree_to_use
+
+        if branch_to_use is None or tree_to_use is None:
+            if retrieved_knowledge:
+                knowledge_text = str(retrieved_knowledge)
+                if len(knowledge_text) > 500:
+                    knowledge_text = knowledge_text[:497] + "..."
+
+                knowledge_panel = Panel(
+                    Text(knowledge_text, style="white"),
+                    title="📚 Retrieved Knowledge",
+                    border_style="green",
+                    padding=(1, 2),
+                )
+                self.print(knowledge_panel)
+                self.print()
+            return None
+
+        knowledge_branch_found = False
+        for child in branch_to_use.children:
+            if "Knowledge Retrieval Started" in str(child.label):
+                self.update_tree_label(
+                    child, "✅", "Knowledge Retrieval Completed", "green"
+                )
+                knowledge_branch_found = True
+                break
+
+        if not knowledge_branch_found:
+            for child in branch_to_use.children:
+                if (
+                    "Knowledge Retrieval" in str(child.label)
+                    and "Started" not in str(child.label)
+                    and "Completed" not in str(child.label)
+                ):
+                    self.update_tree_label(
+                        child, "✅", "Knowledge Retrieval Completed", "green"
+                    )
+                    knowledge_branch_found = True
+                    break
+
+        if not knowledge_branch_found:
+            knowledge_branch = branch_to_use.add("")
+            self.update_tree_label(
+                knowledge_branch, "✅", "Knowledge Retrieval Completed", "green"
+            )
+
+        self.print(tree_to_use)
+
+        if retrieved_knowledge:
+            knowledge_text = str(retrieved_knowledge)
+            if len(knowledge_text) > 500:
+                knowledge_text = knowledge_text[:497] + "..."
+
+            knowledge_panel = Panel(
+                Text(knowledge_text, style="white"),
+                title="📚 Retrieved Knowledge",
+                border_style="green",
+                padding=(1, 2),
+            )
+            self.print(knowledge_panel)
+
+        self.print()
+
+    def handle_knowledge_query_started(
+        self,
+        agent_branch: Optional[Tree],
+        task_prompt: str,
+        crew_tree: Optional[Tree],
+    ) -> None:
+        """Handle knowledge query generated event."""
+        if not self.verbose:
+            return None
+
+        branch_to_use = self.current_lite_agent_branch or agent_branch
+        tree_to_use = branch_to_use or crew_tree
+        if branch_to_use is None or tree_to_use is None:
+            return None
+
+        query_branch = branch_to_use.add("")
+        self.update_tree_label(
+            query_branch, "🔎", f"Query: {task_prompt[:50]}...", "yellow"
+        )
+
+        self.print(tree_to_use)
+        self.print()
+
+    def handle_knowledge_query_failed(
+        self,
+        agent_branch: Optional[Tree],
+        error: str,
+        crew_tree: Optional[Tree],
+    ) -> None:
+        """Handle knowledge query failed event."""
+        if not self.verbose:
+            return
+
+        tree_to_use = self.current_lite_agent_branch or crew_tree
+        branch_to_use = self.current_lite_agent_branch or agent_branch
+
+        if branch_to_use and tree_to_use:
+            query_branch = branch_to_use.add("")
+            self.update_tree_label(query_branch, "❌", "Knowledge Query Failed", "red")
+            self.print(tree_to_use)
+            self.print()
+
+        # Show error panel
+        error_content = self.create_status_content(
+            "Knowledge Query Failed", "Query Error", "red", Error=error
+        )
+        self.print_panel(error_content, "Knowledge Error", "red")
+
+    def handle_knowledge_query_completed(
+        self,
+        agent_branch: Optional[Tree],
+        crew_tree: Optional[Tree],
+    ) -> None:
+        """Handle knowledge query completed event."""
+        if not self.verbose:
+            return None
+
+        branch_to_use = self.current_lite_agent_branch or agent_branch
+        tree_to_use = branch_to_use or crew_tree
+
+        if branch_to_use is None or tree_to_use is None:
+            return None
+
+        query_branch = branch_to_use.add("")
+        self.update_tree_label(query_branch, "✅", "Knowledge Query Completed", "green")
+
+        self.print(tree_to_use)
+        self.print()
+
+    def handle_knowledge_search_query_failed(
+        self,
+        agent_branch: Optional[Tree],
+        error: str,
+        crew_tree: Optional[Tree],
+    ) -> None:
+        """Handle knowledge search query failed event."""
+        if not self.verbose:
+            return
+
+        tree_to_use = self.current_lite_agent_branch or crew_tree
+        branch_to_use = self.current_lite_agent_branch or agent_branch
+
+        if branch_to_use and tree_to_use:
+            query_branch = branch_to_use.add("")
+            self.update_tree_label(query_branch, "❌", "Knowledge Search Failed", "red")
+            self.print(tree_to_use)
+            self.print()
+
+        # Show error panel
+        error_content = self.create_status_content(
+            "Knowledge Search Failed", "Search Error", "red", Error=error
+        )
+        self.print_panel(error_content, "Search Error", "red")

src/crewai/utilities/formatter.py

@@ -1,6 +1,6 @@
-import re
 from typing import TYPE_CHECKING, List
 
+
 if TYPE_CHECKING:
     from crewai.task import Task
     from crewai.tasks.task_output import TaskOutput
@@ -17,6 +17,11 @@ def aggregate_raw_outputs_from_task_outputs(task_outputs: List["TaskOutput"]) ->
 
 def aggregate_raw_outputs_from_tasks(tasks: List["Task"]) -> str:
     """Generate string context from the tasks."""
-    task_outputs = [task.output for task in tasks if task.output is not None]
+
+    task_outputs = (
+        [task.output for task in tasks if task.output is not None]
+        if isinstance(tasks, list)
+        else []
+    )
 
     return aggregate_raw_outputs_from_task_outputs(task_outputs)

src/crewai/utilities/string_utils.py

@@ -59,7 +59,7 @@ def interpolate_only(
     # The regex pattern to find valid variable placeholders
     # Matches {variable_name} where variable_name starts with a letter/underscore
     # and contains only letters, numbers, and underscores
-    pattern = r"\{([A-Za-z_][A-Za-z0-9_]*)\}"
+    pattern = r"\{([A-Za-z_][A-Za-z0-9_\-]*)\}"
 
     # Find all matching variables in the input string
     variables = re.findall(pattern, input_string)

tests/agent_test.py

@@ -2,14 +2,13 @@
 
 import os
 from unittest import mock
-from unittest.mock import patch
+from unittest.mock import MagicMock, patch
 
 import pytest
 
 from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
 from crewai.agents.crew_agent_executor import AgentFinish, CrewAgentExecutor
-from crewai.agents.parser import CrewAgentParser, OutputParserException
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.knowledge_config import KnowledgeConfig
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
@@ -19,6 +18,7 @@ from crewai.tools import tool
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
 from crewai.utilities import RPMController
+from crewai.utilities.errors import AgentRepositoryError
 from crewai.utilities.events import crewai_event_bus
 from crewai.utilities.events.tool_usage_events import ToolUsageFinishedEvent
 
@@ -73,6 +73,7 @@ def test_agent_creation():
     assert agent.goal == "test goal"
     assert agent.backstory == "test backstory"
 
+
 def test_agent_with_only_system_template():
     """Test that an agent with only system_template works without errors."""
     agent = Agent(
@@ -88,6 +89,7 @@ def test_agent_with_only_system_template():
     assert agent.goal == "Test Goal"
     assert agent.backstory == "Test Backstory"
 
+
 def test_agent_with_only_prompt_template():
     """Test that an agent with only system_template works without errors."""
     agent = Agent(
@@ -119,7 +121,8 @@ def test_agent_with_missing_response_template():
     assert agent.role == "Test Role"
     assert agent.goal == "Test Goal"
     assert agent.backstory == "Test Backstory"
-    
+
+
 def test_agent_default_values():
     agent = Agent(role="test role", goal="test goal", backstory="test backstory")
     assert agent.llm.model == "gpt-4o-mini"
@@ -306,9 +309,7 @@ def test_cache_hitting():
     def handle_tool_end(source, event):
         received_events.append(event)
 
-    with (
-        patch.object(CacheHandler, "read") as read,
-    ):
+    with (patch.object(CacheHandler, "read") as read,):
         read.return_value = "0"
         task = Task(
             description="What is 2 times 6? Ignore correctness and just return the result of the multiplication tool, you must use the tool.",
@@ -1038,7 +1039,7 @@ def test_agent_human_input():
             CrewAgentExecutor,
             "_invoke_loop",
             return_value=AgentFinish(output="Hello", thought="", text=""),
-        ) as mock_invoke_loop,
+        ),
     ):
         # Execute the task
         output = agent.execute_task(task)
@@ -1630,13 +1631,10 @@ def test_agent_with_knowledge_sources():
     # Create a knowledge source with some content
     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:
+    with patch("crewai.knowledge") as MockKnowledge:
         mock_knowledge_instance = MockKnowledge.return_value
         mock_knowledge_instance.sources = [string_source]
-        mock_knowledge_instance.query.return_value = [{"content": content}]
+        mock_knowledge_instance.search.return_value = [{"content": content}]
 
         agent = Agent(
             role="Information Agent",
@@ -1690,7 +1688,7 @@ def test_agent_with_knowledge_sources_with_query_limit_and_score_threshold():
 
             assert agent.knowledge is not None
             mock_knowledge_query.assert_called_once_with(
-                [task.prompt()],
+                ["Brandon's favorite color"],
                 **knowledge_config.model_dump(),
             )
 
@@ -1727,7 +1725,7 @@ def test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_defau
 
             assert agent.knowledge is not None
             mock_knowledge_query.assert_called_once_with(
-                [task.prompt()],
+                ["Brandon's favorite color"],
                 **knowledge_config.model_dump(),
             )
 
@@ -1737,9 +1735,7 @@ def test_agent_with_knowledge_sources_extensive_role():
     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:
+    with patch("crewai.knowledge") as MockKnowledge:
         mock_knowledge_instance = MockKnowledge.return_value
         mock_knowledge_instance.sources = [string_source]
         mock_knowledge_instance.query.return_value = [{"content": content}]
@@ -1803,6 +1799,40 @@ def test_agent_with_knowledge_sources_works_with_copy():
             assert isinstance(agent_copy.llm, LLM)
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_with_knowledge_sources_generate_search_query():
+    content = "Brandon's favorite color is red and he likes Mexican food."
+    string_source = StringKnowledgeSource(content=content)
+
+    with patch("crewai.knowledge") as MockKnowledge:
+        mock_knowledge_instance = MockKnowledge.return_value
+        mock_knowledge_instance.sources = [string_source]
+        mock_knowledge_instance.query.return_value = [{"content": content}]
+
+        agent = Agent(
+            role="Information Agent with extensive role description that is longer than 80 characters",
+            goal="Provide information based on knowledge sources",
+            backstory="You have access to specific knowledge sources.",
+            llm=LLM(model="gpt-4o-mini"),
+            knowledge_sources=[string_source],
+        )
+
+        task = Task(
+            description="What is Brandon's favorite color?",
+            expected_output="The answer to the question, in a format like this: `{{name: str, favorite_color: str}}`",
+            agent=agent,
+        )
+
+        crew = Crew(agents=[agent], tasks=[task])
+        result = crew.kickoff()
+
+        # Updated assertion to check the JSON content
+        assert "Brandon" in str(agent.knowledge_search_query)
+        assert "favorite color" in str(agent.knowledge_search_query)
+
+        assert "red" in result.raw.lower()
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_litellm_auth_error_handling():
     """Test that LiteLLM authentication errors are handled correctly and not retried."""
@@ -1940,3 +1970,153 @@ def test_litellm_anthropic_error_handling():
 
     # Verify the LLM call was only made once (no retries)
     mock_llm_call.assert_called_once()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_get_knowledge_search_query():
+    """Test that _get_knowledge_search_query calls the LLM with the correct prompts."""
+    from crewai.utilities.i18n import I18N
+
+    content = "The capital of France is Paris."
+    string_source = StringKnowledgeSource(content=content)
+
+    agent = Agent(
+        role="Information Agent",
+        goal="Provide information based on knowledge sources",
+        backstory="I have access to knowledge sources",
+        llm=LLM(model="gpt-4"),
+        knowledge_sources=[string_source],
+    )
+
+    task = Task(
+        description="What is the capital of France?",
+        expected_output="The capital of France is Paris.",
+        agent=agent,
+    )
+
+    i18n = I18N()
+    task_prompt = task.prompt()
+
+    with patch.object(agent, "_get_knowledge_search_query") as mock_get_query:
+        mock_get_query.return_value = "Capital of France"
+
+        crew = Crew(agents=[agent], tasks=[task])
+        crew.kickoff()
+
+        mock_get_query.assert_called_once_with(task_prompt)
+
+    with patch.object(agent.llm, "call") as mock_llm_call:
+        agent._get_knowledge_search_query(task_prompt)
+
+        mock_llm_call.assert_called_once_with(
+            [
+                {
+                    "role": "system",
+                    "content": i18n.slice(
+                        "knowledge_search_query_system_prompt"
+                    ).format(task_prompt=task.description),
+                },
+                {
+                    "role": "user",
+                    "content": i18n.slice("knowledge_search_query").format(
+                        task_prompt=task_prompt
+                    ),
+                },
+            ]
+        )
+
+
+@pytest.fixture
+def mock_get_auth_token():
+    with patch(
+        "crewai.cli.authentication.token.get_auth_token", return_value="test_token"
+    ):
+        yield
+
+
+@patch("crewai.cli.plus_api.PlusAPI.get_agent")
+def test_agent_from_repository(mock_get_agent, mock_get_auth_token):
+    from crewai_tools import SerperDevTool
+
+    mock_get_response = MagicMock()
+    mock_get_response.status_code = 200
+    mock_get_response.json.return_value = {
+        "role": "test role",
+        "goal": "test goal",
+        "backstory": "test backstory",
+        "tools": [{"name": "SerperDevTool"}],
+    }
+    mock_get_agent.return_value = mock_get_response
+    agent = Agent(from_repository="test_agent")
+
+    assert agent.role == "test role"
+    assert agent.goal == "test goal"
+    assert agent.backstory == "test backstory"
+    assert len(agent.tools) == 1
+    assert isinstance(agent.tools[0], SerperDevTool)
+
+
+@patch("crewai.cli.plus_api.PlusAPI.get_agent")
+def test_agent_from_repository_override_attributes(mock_get_agent, mock_get_auth_token):
+    from crewai_tools import SerperDevTool
+
+    mock_get_response = MagicMock()
+    mock_get_response.status_code = 200
+    mock_get_response.json.return_value = {
+        "role": "test role",
+        "goal": "test goal",
+        "backstory": "test backstory",
+        "tools": [{"name": "SerperDevTool"}],
+    }
+    mock_get_agent.return_value = mock_get_response
+    agent = Agent(from_repository="test_agent", role="Custom Role")
+
+    assert agent.role == "Custom Role"
+    assert agent.goal == "test goal"
+    assert agent.backstory == "test backstory"
+    assert len(agent.tools) == 1
+    assert isinstance(agent.tools[0], SerperDevTool)
+
+
+@patch("crewai.cli.plus_api.PlusAPI.get_agent")
+def test_agent_from_repository_with_invalid_tools(mock_get_agent, mock_get_auth_token):
+    mock_get_response = MagicMock()
+    mock_get_response.status_code = 200
+    mock_get_response.json.return_value = {
+        "role": "test role",
+        "goal": "test goal",
+        "backstory": "test backstory",
+        "tools": [{"name": "DoesNotExist"}],
+    }
+    mock_get_agent.return_value = mock_get_response
+    with pytest.raises(
+        AgentRepositoryError,
+        match="Tool DoesNotExist could not be loaded: module 'crewai_tools' has no attribute 'DoesNotExist'",
+    ):
+        Agent(from_repository="test_agent")
+
+
+@patch("crewai.cli.plus_api.PlusAPI.get_agent")
+def test_agent_from_repository_internal_error(mock_get_agent, mock_get_auth_token):
+    mock_get_response = MagicMock()
+    mock_get_response.status_code = 500
+    mock_get_response.text = "Internal server error"
+    mock_get_agent.return_value = mock_get_response
+    with pytest.raises(
+        AgentRepositoryError,
+        match="Agent test_agent could not be loaded: Internal server error",
+    ):
+        Agent(from_repository="test_agent")
+
+
+@patch("crewai.cli.plus_api.PlusAPI.get_agent")
+def test_agent_from_repository_agent_not_found(mock_get_agent, mock_get_auth_token):
+    mock_get_response = MagicMock()
+    mock_get_response.status_code = 404
+    mock_get_response.text = "Agent not found"
+    mock_get_agent.return_value = mock_get_response
+    with pytest.raises(
+        AgentRepositoryError,
+        match="Agent test_agent does not exist, make sure the name is correct or the agent is available on your organization",
+    ):
+        Agent(from_repository="test_agent")

tests/cassettes/test_agent_with_knowledge_sources_generate_search_query.yaml

@@ -0,0 +1,660 @@
+interactions:
+- request:
+    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
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '137'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SaWw+6SrPm799PsbJumTcCIt297hDkjDQnESeTCSAqB0VODfTO/u4T/O/smbkx
+        EYimm+qq5/dU/ce//vrr7zarinz8+5+//m7KYfz7f2zX7umY/v3PX//zX3/99ddf//H7/P+eLN5Z
+        cb+Xn+fv8d/N8nMvlr//+Yv97yv/96F//vpbqXVC1KY6Ai5tbEYUvL2Fz3d3UKbls2ooTr4sDq2d
+        H3I7zRfROAtPcpupB9i58SM02CpPTBYpFV92+RsAu3VxJt5ItRyJHKMCiSkJHii1FzN45mier6KL
+        Ip7L5nWpWVTu8pScO3MAizDvZ1Br3wLbot335HPPZbheQ8HlvOuQzV81D0SsxfIkjqoL9pgYb1Q+
+        zXbinHJXEY9NT+ix5hM+rQMCq7GWOepKI8RXuDL0vftIJ5iHrwKfMaParIgPOQwa5kEkgbyrZRSy
+        Dl6qJCJ3xdLCqeGqGYbZeYdlLiz71WQDBkXLyGPNY7yQ92PjDYVFvOOz4rfZHLYNj8YH5+AsdFSF
+        fF8vF7Xw8iU4PqFsoZFdI98/mwRfEMjoTvVb1JiOQwqjTKqJQ7WHOI5KRG0Ene4vpiGJX7vN8Xkl
+        n2r5vuUCBR9vj43K+tLZPXcWQJp6Jtfiydm0/ewk2JVWSHz18sqmmGQz9HHeupQ5JP3qJVwCucbm
+        iGw9cMhP6ZogL1sb4iS3WqFpw7qQaxpE5KvaKcNuKixoJM6daLe7aXMPwYzgmaQKCcX7XNHYeUkI
+        3JNpip3ZydagABq8jpk18R2gYNB6+IRDyi4kX4/Hig7rUUSxdohIKLtKSCMb8pBrPgjrRbAos0nL
+        CaR9qBOJHTjAy7H4hqOzRi4PdbPijmzII/C8f4hxEqRsXzq6AR7YWXG0OqeeawJpBgXKA+y7Ec0G
+        yecsxOQWcMNwfmSL03AMOF0ilahvBSjr4wZEqLCTiPX38gXLuQ069BIFndg8zik7v4QIqDBQiMIN
+        ZTWnp8uKVFNMiDXMLV1jtgnQddesOL60MFu68VSgM2Ft7KlVXu1fx8GCa3xrybkBLaDcNXmCZiCO
+        OwuvsmeVWx/BipUnbHweGJCBigm8na4m0YW7QOc3QKUo+H6ATQ4nlApvY4BqGj8JJk1CuYtleJCB
+        s+YKZyYKOc1yNdifqDLdWrkEs07uJQTkExPJnyV7r59DGRZItojy5EKFJlfBQaadJ9hMEbEpdzvK
+        SCmfAYn3rVfR7FNPgDGZkERrcQDklt1c+DK/Cw6ekq1weTMbSOdHmaQVNAE3io4FsehbOCbegY4S
+        JR3QQ1fGdx71/bK66wlcM7fEsqwn/eTHUg2Jfg6xw9d2tb/4bgTjA9GJbmpZv9zn0ICi/lRwiGXZ
+        5sGFuqg7qhJ2BWlP50fKWgjsYp8c+92x2gP+lSCr5B/u82GLyrzX0hm+zPOXON/sDRZfoDG6nahP
+        7Gs7KmsrVyX8NPVEgowXlEG87mb4PkdXUhjmMeQv7W2GU21kJG0zmfIN18/geHNaLH3yCcxKFrJI
+        oA5H/OzoKTT7DBM4KB3CEttQMJR1wKPxSe7YYaCc8aK7uOiaa+sE+fu3WlRt1KDb7CBxjVKoZsk7
+        dTCF9pUY6X1UZjm6sfDUpoiYVWcDrn0YOTQn1cBe2noKPw/XFAmlXWLF2i3Z2ATSCq5TmGJ8O3TK
+        nFthDm+nizm9u5GAxWkQhNE5bohmaM9wrYfFg8wOUyIfSNfPTEUt9CgJnRY347Kl4IYW+IF+cytO
+        1Ko12R8ZxIyPkKjgHlXf4yyyUHC7F972l850vUmQJdIJxy/4ohQAbYCN6ToTD/pXOKqKo4H9aGrY
+        Oi5l2LHU9OBvv9x3ZgH+g25QPCbr013aB7AXTX3OaOKpTbD08Kqp80gJOVlDWDITM+RZagZwMDWf
+        HIdxZ9PpMJ/Qh88ZfHycJLr/PJzytz5s+PRoc7obetAvXy8ixaGl7Et1idEnemXEOnZStoJb5ICv
+        c6qxP2Qm4J/pU0OGATrivBLeXlEmiBDYnUvkx/qmQ0NtCcq7oSDF/n7uB/dcWsjcGRnRy0ql2/4G
+        KLy5KZGOetS3wjlfoVUmV3K356PNFzc8HELz/iAyF8pVd13mHI3OHGHND/mMPnfgjWZmzon/gTOg
+        /TAniEFt/ItXezb46xNm7nVH9LPcZVOmlwOcqinE1wvR7dXRahcSo+qxqgth+Lrltxyk+qpjo5VT
+        ZQ8OhQuDg3LFUkpWe76hbICwrM8ktM9cSHfG2qH2Ox1ccZgNMKPMaKHlX0/YpUe1mv1kiX7xj939
+        /VyxBn8tYeKKDZafLlaWxVVFKJrqk1zh81vN4nW3AsZKMnxJkG5zyf0+Q9/Hpsva0dPeD1RMQWFf
+        B+LCfAdIabwN9OEP2sRF7UtZnM87h0LZdMQRD0vfy9A9QaL3GZYqSaP88hE1kfYf7U88sR/x4KCX
+        cbnhmyqAamFO3xSOj72Dj8H3ln0J48dI87DjHg6npqI73bJAaILPdOBiEXybJK6hUiUlya7t2eb3
+        uiIjqdHuxMHDR1kqK6hhHlaFy1OnrVa1PM5IOt0Dl6HGp1oPZ2OCvSAxOBsLF6zcLlrRNWs74iS2
+        ZK9z+awRx8XCFr8PZeaA8oSbnnKJ/wrDRegnD8wj2fTCaijzbioMML6akfjb+Zg7TSpQ3RoHXEA3
+        A7yNDi1sRjvCtpa8s4kpVwGhz7slcnaXwJ6RDAt8wlTDJmfEgGryLEPrBTE2VK0Oeb9wBTDxiz2l
+        zIXrF3GpGCSscYN//8+2SrUikgRvbI9DQOdmSZ/Q0ESV6HSw+lmOrRjy7ZtipVH2ShsUFg8eLyPG
+        j/h0zzhNmT10ip0LVncfPSPv6PsEXBQ2031NXxUhygThbJ9uGPtkHy5OZRqI9hYz7YvnRaHnT5r+
+        0Wd5/mntNRFLiLhafrrgSrBNdayUKEyfK5akg9cvhPEjdLrE6jQqSh1+F6sW/uRPk8MCnSykFvDA
+        i8Ikcne1X6y7ncPds7Cw+z5rYI5qo4StGJ+2fCWH/On90eBdvOduLfJzNaGGTICTd2di57qmjOsF
+        C3Bmogi7p4jtl/zzbKHH1AmJof6tRqn/RpB8LR6fI54LqXk5uvBqFjLGpS9R+nk4T/jwVGVi3u9C
+        mfmdN8HO33ku/JYtWJKHFkBivHoSbnqkzYwSok+0q9y9AYyQ/dUP4JziCSnKKVzrOQ2gY0YXcjvU
+        BZ0L72bA3VMIyFZPlZF/pDN0mIbDDm5Ue8bRYIBm8E940/M9T5dkhqfYvUyH4WrQ2j2XBhqM1iQP
+        QnM6+jCP4bb+ieu0HqyPxE4hcOCbeCzd04XLlhlpLz13m12f9PT8lUV0EvbqtLv0b3u10dL+7mOn
+        OZeAi+15Rf3hGpOTzH3CQe8EB92i04nku8utpy8NtX/0Xt48BGWkF1aDRP9m+KTosKcNTmQw38Oj
+        W08eBxY8JTG6vYOBuKfz2q+PGxXgquoe0Yn5rPaA+UzwOu6DjX9egACGDPAuHiOMy8eJssdLbIHF
+        Qyr25mIBmx57wpPAqcRTlSrjM72cwBolyh99Ph66F4O08zvDGlW1fv4wgQPK4qaTNDya9srLiIWH
+        xkqmw7Hb91TkkAuRhu7Tejyw/cZHBcqr6UVcZ+izrX5O8PR5jiTe9PS7bAcNTpwASJYdXnRZ/UmE
+        qv3gXHFgBtCCGOSAkysV//LLEp6sN6BomdzO+gbZ/PrgFhp6ExBv9kbavj56Czf9j1VQ8/0as6MH
+        Nr2Iz07YZySyTjF8rNIbXxS9CRfDZz1oiJbkvmrrYi/D4cpAekuK7Tx/MvLSuA7C41PE+aZ3VlTt
+        HKhwtkzcib6qpTicO/F8zp8kkjk95NXSnGGYnjribfVnYuoqhYyVZuQ+FSudplRMIAZ2OrHf0Qbv
+        3pFdpHCmPAHZr8NZXzQJTopuEOtwGKvlmjgepGA2sd/vjv0yUNlA+t623Pc0S9UsOdWmRzsLY8qP
+        1Rq9Xx6qL6WJpY9r0UGO5QiJRp9MjGG+wqki0wk0w+i4MzoN/bjxL/zwBYOlQf7S1QIRhM6QnbFu
+        nlG/nN+dAbnIbyakj3M2RbWwAl68hhPIP4+MllbcQYutd+QK1wLQ17G20OGkqxOzg+9s6tydBKaA
+        VdxdX8Rg73YggR0V6UQ3XprFGAcwc+J0klAw9xSiKkH3NmCx07xFe8js64o2fsPqrk+qVbnDGlJE
+        pz/nmwcX4ICqDNyJczJUrVv8omya1Gku+EiZp9QyoP9KHOJVN0aZn8XFgqrVNC58Wauy2vJVglxj
+        cuQX3+ve3LOwgYWOjSCF4aBWsgT6CxsTjXg3One6wECF9Vas+U6Utc8XY0G9PgXEn/cLndOdkMAU
+        SLLLrYPWc96yRCgPd+8fH1RrNXJv9LXdiEhVALf6Fxvgfmgcl9lxdTjeh9VAgsdZOHsugTLXpJRA
+        3VoH7BZKpLCdLkAYvNMP1vapUy23RCjgj88C5jRXy+KeRcjuxIiob39nf4l0FEXDeJRYMjumH6Iy
+        kVD/9gqcfB4ErMu3e4P2GyzY0s5dNqi1WIIfn2kv+AIU710Bph2/c9eM8Eqrj6MkNj0Pib1Qli7S
+        rLXgIl+PE++ra0jbwnChuasrnLqMEA43uQkgFklAsCA9+9lmFgHaQii7ezidq3nMtAJ+bSciGF60
+        aonPXw/8ePynlyZwyx3Yfr2FOJ6BQ37bP/jT6/r5Omft56hrsNwVqSseDud+MaMEwnE9cthUEzmk
+        XZdNMDs7HdGFoKnmaHB5yN7h4s6D/AX7C77w8NWNJ6zublVG+aqWwOngn0mkuEVFH3vzBOPY0bEj
+        rrginrBPYPKabvh8z2eFPsXyBJeXYZB7VEsKpwhfCT7f1uLujLkJF90SPbj5T64f7O9h5yiKA//s
+        78b/+8V4RtC+YoK3fE2XGg8ayIqXTI6sWFajuPQM7AXgEjs5cdk8Ph8MfKzymxzVyyucBcP2oGoW
+        HpYzEtu//At++coO06/dpscWgrRL9vj2WUYwXfnLyhXmion7jgw68YyXo90ztwje6h+9j2UCnzV/
+        c5d+96rmQzAF0AGDhM2Y2MqP58DmJ2DfPfvZaqxdDnNJmMi1nA7KpJbmCgv7Mkzr1RkUyl6eEnx4
+        u3Dal9x/8Q/c/C5sHrtrxelOuf7hA1P1n9kKi3GCadJe3Z1PrtmMo9pAoS7IRB5YE6zYk0WEk1NJ
+        /DY52N2l9VcgLMKdaJfjS6HD7KdwhxOeHDd+5ZB8GuAnQhU+4axUFsBKHbrmpeiiiQpgunRWAC9c
+        DYm5HCO6Hv3v6ceX5DwNPP2j/356wsxOvrJ22jxAdN2P02IKfTYLJpjB8rIMrH53JlhC5iChrT7h
+        k/ypwuWW+wWMD6OOpTPrZ5y3l3m45XtiBs5LebvOV4QqMkIcG2c5ZO/ObKA2SV+b3ooqXm2vNeS/
+        D2USiulF52c1dVDww8A9iWTqF0YWRKiE5weRysOJUoJ8Db3XiE7M7WbYvJz0GtwtUYqTjb/Hfr0z
+        P97A8jWd7T/rPV4Fj5wm7wKo1H1PUKq7CzHO+zUcL5YUQHQ1nljttJ7O1uGZon0+MdP7YigK5fJS
+        QhsfEXm5huC7b88BnHf3L9Hh7VMtC+YTSAy1wmbF7ezFygIG5U3IEDVqX/b8FvISPrzKJuebnWUT
+        LMYBPjwUYifnHJtIg1/D/BjzExivA31u8Sx+ai/GXhx2NmmCgwwqKeo3fXalXKl4b1TuhJKoIA76
+        Wx1xNfz5r9bjU4Hxk/crjGbjRh4G8822emUAqYEjMX88xcVtAFLDxUS5Uk8Z3EDPYXX8KsTO3VaZ
+        bZCIf/wGTEKlWh4iY0DjCxEpJnqsuFsyFz99g2/cPQeUK3csjHVaEyNQ44x7opQHWz7E+Kz22bc6
+        0zesr+rbfW56bHR6nMOOjYF7mMUAtEEexOgQspIL5UrOxn4UWiSmNwEf2+SmbPqLB/L5I2CjZzkw
+        DBfIwI+8Apcxrk1GY399QulyLbG2MnU1ie7BhfaHFbGCs1s4mkFbgO284eIUsdUW7xH45uVA1M1/
+        Xq/8fQbauodukxBFWa8HZv35f+6idnq4wENqgOf+bk5I6XbV5v92sP5435/fbv/hva1eu0ip7v2f
+        +GbdL7PpMTtcvetJhJorVS7Lp20186h1RW3lIHYYTgo5TX2ukBpPF99ccw6/12Bd0fZ98yMayglN
+        UsA3vkL3l2+IGSYTLKfNR+/BHvzqN6LwEROJgE81bHoSKsFyJdbP/9p4C6boQbCpLoeK6qYo/+Fv
+        W8731Xd7v+DsRrMr9OBK6fctDrBAkoXd27OzVzn03/DVeXBaH0i0l0mcYySUnw6rCa8qG6/F0HMO
+        Ila+j52yJNkYwNlqfXI9LVzVYR+kf/jJvd1aez44Sf5bDz7xrdPT9jFPEF258cf3IS8Y9PnLp0Q1
+        tGs/t0fqgahwOKy9/Q+YOEBXyDDXCp82/2GuSSf98atd6AKw6v2zgG3XmPhMjYISorwZQAy9mvpt
+        vfT7+joQOMwbH9tHpkwJ5xfwp0d+ft0Mb4kh/n5PPh6ifm1PuST+/F6FG+SKN8gxR+PZzSfOZkuF
+        +ntwAhwrzhufSP1Saoc3HIzOJPbX6+hbcKIS7dZu/cPzU3C33pAc1qPLQMuquJ1hJTCE0pkch0gH
+        K128GdZJxrh15HjZ5D/2KQg7RnRFxqX920sbAT5eVkzO3ouEgy11OdzqlVtt55lMsBaR9qAKdsR+
+        7B8PYXlD4VVcsBEfG+V9D87Dn3oqFb1EefSSU5jt6guWj9MroxfTkNEasTb2Y9G1xydKWbhIJw5f
+        9GoMp/HqJ5AmMMbFln/XsrFP8Mfv51uAsiZ7swXc/A13af29stVr56eP8HE4N4CeqyUFbJEciC5V
+        fkUVxNTQjXDu8lt94K7JKYDylGrToTVrSmhoR/DZeK8pQVJfzTeJnWHO3Y/kGHwP4Sycoxm2Wnvc
+        3iew6ZFzNHi14mCCTVTTdetvQTFhM4Jj+xG+7yHjAM2VK/fwEQhdRe81occq8vjXX6Dh7uuB9/Md
+        uqJVztlqQ9MQsRha5GzPR2UeC1JA1B4kcnbUTzgn/G0Amz9F7KV9/eFBmDxZ0+W2/txe2RENkG/N
+        EFm7wH6+yY0HeZVRsPOdB7A41dGCWz/mj5+4565eiZJX4E+7/sqCbz8KHXy8soz8/FOuOJxb2DD3
+        AXv+vrTpS8lbsPl7RNUFmq1iJE/QMePL5udcbfqOUxlozxS7C1qDat3rioRqlbpYL3MF0F//4sdf
+        kR1J9h4dTzlc6CpM4tOalGGvBTNaL7un+2GNlZLj0p/Eza+aIJBoP5472wA6x65Ewd97yIXSq/75
+        ycTb9MBry29IapjRre3oqczxHMmoo3I18ZeXGP78fuAM+wvZ+AysfuRp6HPZU+J8ZwewWz4Twdx2
+        5HGpa2V+lV0Mpkbup91Z7cPp5+/ibyLih8/fMmrFhwkeosEjOpzGfvj1UxrmWE/Lxpe8l6AEzsya
+        E5MzeDDNn7MgMqiLp2TwGJsCuHdAfYG++/O/53VSeCiFs4oTsxw2ntMDSHuDwa4xw359vcoTMgwl
+        ndYDmnpaykkEt/7rxFP13X8Lrm5h/IEfbB7sT7VawtNA1Dhp2DW+Yr+SF5vAzb8mliqcMv5UMzVc
+        SjnBqr3jsrn8DjEcX5+R2PUogc9LPRuwVi8a1s+yFU7raNdwPHc1sTmk99yw/xRw84snTrl8w7Uz
+        Xi4gh/mIzfil2/vpyOQwZ40vzvLcUXiTTSHMQz3++e+ApXP7hMZ1veCzvVfsrf/AgG19LsXmyZ61
+        dyWhsSjZaeWPO7DCnHPQ2+3IdKguKli2fjTc9Oq0p43Rc4dJZuBUWxl2vqVBOV+sWMQdW45oG9+z
+        boALKLykM85zONnfrR8CdUXa4bhUFEAjI2NhflwZojnfLltRNovItGoDu2Cl1Yxx0P76M79+Srgg
+        pmpRsJ92+LxzpYzOp9CAlpSzW/+rt5cY32aw9Yuwdqt7e3g1DwOKt6Da/KMadBaIGCAphojTMGTC
+        xRcrHm36kNypwdCxSfWTyIwgI9KnmsHIqM3w6zfhokxSZZG+M4+6Kmyxw8efihxGeYJYHANshcev
+        vb4eyxtZkgCx2Zo1WNdRecNxVbiffwXWmt3XcJIdYetHN/YQvCoWloQ8poO6u1e0LSQX/v2bCvjP
+        f/311//6TRi823vRbIMBY7GM//7vUYF/7/89vNOm+TOGMA3ps/j7n/+aQPj727fv7/i/x7YuPsPf
+        //zF8X9mDf4e2zFt/t/r/9r+6j//9X8AAAD//wMAEEMP2eAgAAA=
+    headers:
+      CF-RAY:
+      - 93bd468618792506-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 07 May 2025 02:26:58 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=b8RyPEId4yq9HJyuFnK7KNXV1hEa38vaf3KsPaYMi6U-1746584818-1.0.1.1-D2L05owANBA1NNJNxdD5avYizVIMB0Q9M_6PgN4YJzuXkQLOyORtRMDfNCF4SCptihGS_hISsNIh4LqfOcp9pQDRlLaFsYpAvHOaWt6teXk;
+        path=/; expires=Wed, 07-May-25 02:56:58 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=xH94XekAl_WXtZ8yJYk4wagWOpjufglIcgBHuIK4j5s-1746584818263-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '271'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-6fcbcbb5fd-rlx2b
+      x-envoy-upstream-service-time:
+      - '276'
+      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_dfb1b7e20cfae7dd4c21a591f5989210
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "Your goal is to rewrite the
+      user query so that it is optimized for retrieval from a vector database. Consider
+      how the query will be used to find relevant documents, and aim to make it more
+      specific and context-aware. \n\n Do not include any other text than the rewritten
+      query, especially any preamble or postamble and only add expected output format
+      if its relevant to the rewritten query. \n\n Focus on the key words of the intended
+      task and to retrieve the most relevant information. \n\n There will be some
+      extra context provided that might need to be removed such as expected_output
+      formats structured_outputs and other instructions."}, {"role": "user", "content":
+      "The original query is: What is Brandon''s favorite color?\n\nThis is the expected
+      criteria for your final answer: The answer to the question, in a format like
+      this: `{{name: str, favorite_color: str}}`\nyou MUST return the actual complete
+      content as the final answer, not a summary.."}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1054'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4xSsW7bMBTc9RXEW7pYhaw6leylQJClU4AGyRIEAkM+yUwoPoJ8MloE/veAkmMp
+        aQp04cB7d7w7vpdMCDAadgLUXrLqvc0vb697eroKNzdey/hLF9XzdXm4uLqTZfUTVolBj0+o+I31
+        VVHvLbIhN8EqoGRMqutq8/2i3tTregR60mgTrfOcbyjvjTN5WZSbvKjydX1i78kojLAT95kQQryM
+        Z/LpNP6GnShWbzc9xig7hN15SAgIZNMNyBhNZOkYVjOoyDG60fplkE6T+xJFKw8UDKNQZCn8WM4H
+        bIcok2c3WLsApHPEMmUenT6ckOPZm6XOB3qMH6jQGmfivgkoI7nkIzJ5GNFjJsTD2MHwLhb4QL3n
+        hukZx+fW23LSg7n6Ga1OGBNLuyRtV5/INRpZGhsXJYKSao96ps6Ny0EbWgDZIvTfZj7TnoIb1/2P
+        /AwohZ5RNz6gNup94HksYFrMf42dSx4NQ8RwMAobNhjSR2hs5WCndYH4JzL2TWtch8EHM+1M65vi
+        27asy7LYFpAds1cAAAD//wMA3xmId0EDAAA=
+    headers:
+      CF-RAY:
+      - 93bd468ac97dcedd-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 07 May 2025 02:26:58 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=RAnX9bxMu6FRFRvWLdkruoVeTpKeJSsewnbE5u1SKNc-1746584818-1.0.1.1-08O3HvJLNgXLW2GhIFer0bWIw7kc_bnco7201aq5kLNaI2.5R_LzcmmIHlEQmos6TsjWG..AYDzzeYQBts4AfDWCT__jWc1iMNREXvz_Bk4;
+        path=/; expires=Wed, 07-May-25 02:56:58 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=hVuA8E89306pCEvNIEtxK0bavBXUyyJLC45CNZ0NFcY-1746584818774-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '267'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '300'
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999769'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_9be67025184f64bbc77df86b89c5f894
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": ["Brandon''s favorite color?"], "model": "text-embedding-3-small",
+      "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '104'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=b8RyPEId4yq9HJyuFnK7KNXV1hEa38vaf3KsPaYMi6U-1746584818-1.0.1.1-D2L05owANBA1NNJNxdD5avYizVIMB0Q9M_6PgN4YJzuXkQLOyORtRMDfNCF4SCptihGS_hISsNIh4LqfOcp9pQDRlLaFsYpAvHOaWt6teXk;
+        _cfuvid=xH94XekAl_WXtZ8yJYk4wagWOpjufglIcgBHuIK4j5s-1746584818263-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R6SROyTLPl/vsVT7xb+oZMUsW3YxIRkEJBxI6ODlBkEpGhqqBu3P/eoU9HDxsX
+        QIAkmSfPOZn/+a8/f/7p86a4z//8+88/r3qa//lv32OPbM7++fef//6vP3/+/PnP3+//d2XR5cXj
+        Ub/L3+W/k/X7USz//PsP/3+O/N+L/v3nHy10PsRPcxuIYz6sIG03O6RXYmZOpt0pqpupCN1ta2+K
+        2T5U1Gg2d8TiXAzYNTdb1V+PVxL4y4exz8UvwQOkRxSSJ4tWZ2tkKpuTicTBlRsXtnHarSCuWzyr
+        8Xukk9e3ahtwIUF5NIA1fk8ZqD/yndw55DQYvzVRNRuDD/Jwh/O1q+ZYwffBJUfYrWDZhO2qCmzb
+        4QTlN7B8vB1VcQJa5DzSyqOKN1nwJKknZL74FSx8MrfwwkdHdAzUEqzqZ+tDDT0zooO9ZK6Orqwg
+        AmVAvE8yRvh1ppPagBvB8527NWyD7ETNW8fGwD6xCKcF5OCsG/sAOI+7t67vA/4br9M48GCun6da
+        fSsdR4xB2edrsb9RVQVaRyxn64IFtEuq0mU6kui6e0VLGm0n2LVGhA6R30UCfT4MYLEpRIaVUrYc
+        l2cB6+QCiN9yXrPcxmKAxZO+SCjT2Vv0MS1hpRUFySFXeVQ7nGVYB+cuKB/RPl/X4pRu7waTMTjg
+        1VwV99jD6+2iByUHhYYdz2kPa+0+EVQYMViot6/Vw7Zw8bIUCND94d7DPHy/CNo9p4adDpWv6p/u
+        HbB933hT7Wxt9TpoCJ0rvsqXOWl4NUFbg6T9E+a09NEAw3QwyYH7kIbGfG+oFPY8CmUjjeh4ag3o
+        hZNFTjuReYJX1zx4QfpGns3zDTUymMFFjUOyy9wLmDAeJpgnsYcuo1mNrJw6ET5AdkSaC9/N/Ny8
+        FFh212dwPTveNx6ZDCctGYnzOB4bCZ6UBPI62QWcHzgNW5owUU1NrJCOhiOTqtVp4ZGaJbHmuzi+
+        04vjqq/D1ibIPlYR3atSpjYFZ6Br/Nzn5HVOVjV0XQUd7feNSSF4WoBu6j3eEv+YSwsyeCilmwzL
+        NyPzhOwVBZBkRYSlQmzyCb5UGUqhYpPd8X0yv/Evf89HXnIS2Rw7eQ+54dIRywzNSIKnNYbf+KNg
+        N6WM3yw5B5zS8P/+XywQRYbPOyjxBgNtFDPABvh2spEYM28x5lVWqr6yNkbXi+GMVFhuCaSJfSX7
+        s+OZS9UfeHg5rw65Fk7QYAhOoqr49Qtdju/FZJ+LVapbRxVJoah3sKgbM4DZpSfol89DZA0h5Er7
+        iE58OkfUJ34N59sux8vWNjxh/xRsGMVhg5KLemjoR3NLyEwFEuNYJIBPyN6BJpsM9FSAZdKzJHbw
+        E2MPoYIeGsE+aYW6d7kr8atqYoT6F6iiTXAmaCx0wISsl+HeWc9ffHEBlbTAAEZOFWJvDb3heSle
+        VfvoBOQUG5to0Z4ght7n3gWC1Nk5aWRLho8T9yC7d44i8XC3Wugn7yrgztniMa24KzDE1ZlcrTjM
+        cZt/NGXoUIHs3ftp4t08JX/z86hx51HaZE2tajtfJ9dCbKJfvNXv/YgpbA5MDMGiwfi1iOSuWBeP
+        YfvWw2x73f6+hyfJykb7/T/0zJ1rJPDJq1Nr7xYhJxGXCBstcOHUEhMFxPEZ/w64EH7xErnKxhp/
+        9Q648/lMdro15ROQihKS8tqQo4iShu7VTQbrVrCIb7HFW5v50CuczBNitNrgkXP6EOFhe3fxBsJb
+        RLR1SIFd1W9k3ayK4Zjpraqn4Ib2KJibicXnXv3ia8AP9c1cEHYUqHBYxtDqH80SnkwLLpFcooP9
+        0UfpW1/wXDSYOA9Q52xfJL0an62JPIcvvjWiWCid29Yo2ZtOI9WHVweHRYjJbqqEkfFmV0M7pVYg
+        KaIb8VTzz5BGyMJL5+ueiI63CXzxnOziyTCla252Kt/tHmgHJ3+kurQGanHwHeJowyuX3uRRwM1o
+        GsSysJTTxLxjmHpNTHQeBM38q4+jNpXk3JGIsbHDBrRswuFyaDW2ZvtUUeNBCIgWH/VcFEBoQb2t
+        ECl6aOW8cMI9tPEYBQCfVDZdYiGGEGgpcu/CJl/1QexUd3tPyQ21sbdYV1NWK+1ekKc3XjzJsEyo
+        lpI2B3RoNSBs7gcOVJvlgfL7bgHk9OEK2HJcgQ79o2lGon7OimKzzbcfnpn4CF0bLsfYQDegvMal
+        3WkdFPyPgrdC8xnJ5sQC9W4sMnL85yWnwnKKVXsTV8Ra3q5Jedze1UKuHGJvgsFk2GxXOLbmGx36
+        c2hSKuUywDcqkdPqtw1VroczcMfhQdwdLke+/gQxuIz1QOwmaDwpvxwMsL3eN6TIDDOfe3iy1E8Z
+        60RTdNMUkQ5LOCVHhbgnbHkC3LNW/eIdbrK6NakzJSt875qUGFfhDMRL1UN1e6+vyFW3hrd21SuB
+        xzf0AmixxSSrWrvqvg5M5JXhLhK440YBuK4y4g78sWHsE/fwx29uFYgAf8g4F+rHqCHWM3Sj5UGX
+        Mzic/SfJb8mbzTFvW7AXGp64G0Xypq2zCQBnD3dk8dV7pMpz2/3wCcsvuuZTorSxOixSTJwnvEYS
+        K6cYyrdBxJBDfcNSbjfBMb0txOvuR8b83OFAROSUhJ/IBbz2KDM1CdsTikvM5WtIc1GJEUqRkxVm
+        s6Kt5UAhjSiyyu0CyBXhDJqCvP++7ytipk1FNRILEWlH8WVK+WMbw6tBWxL3Vestet37cLOtPbS/
+        mo/mh9dqe8UMrxpYvSWjcgqtoP+QxJlCb5X0ewG+/REdnsTz+lAZOnALMgFpppSMIu/LFDrD6YXX
+        O9iac3avZbjKJxsZhY88Atd9q2KPg2i/0DaafOUzwVTrZqzozWwOizwkcNdMBQkFkYxLUs936Nht
+        jpwPeAE6PvRAJZw4Eo0e+3ztZreEW0ZNlNunKF9wWKbQn+J9cDOJZeINUWvloeANCZZYGNngxz5c
+        RpUPBNddc9zNbg1fC68hC+QWE2tuOINtgO/IaAQxWty+C2Eevl7EnfFofutfg6vneIHs6XouRCeP
+        A6/y2ZKDTm85e5hlCnmZo+iLb9FyEVcI90l7JLYmad58Hu8yvIGKIsPwHZMeMtGBab1fgx9+0Zz/
+        UNiLR4Pku4Zrpv7hxODHt8zJQ6YgzSUPb8gyg0tYBQ29+UcFHvTqRFIo2EzafwAPOnyaSGQQhS3c
+        cSMDg2kdik930mDh7bZgErITCr71x1tC4AO0ZClxz6ddxHb6FcIMIp/YUTdH81wfDOgM0QsL9LAH
+        4tBGtvp8UkauerYyTM4sVkXU5HhrDQmgLD4P6o/f/fCe3zWvFl619olSpo+A//EDpaEnct29umiF
+        hO9VoxiOxJht6jFVbSlsm/iDLlb1jfdqBrCJpTPabThpXGitywrmDgi/tugImGGZnCqFsk2MvYDy
+        5X1cViXmww3J9aRkQhzJIuTmYItF+NRydtaorFrb9zPgL+/GFGh9kJVXmqFAufpXwMdqmijJuktI
+        npwSIOI2hyDbXrbIvHtjQ0/lbYB9bBDkjrWRT+Yhp2DsZIU8jpMLpNc5obBa+wV58k4GS9FrHBT4
+        lidewYNxiW7wDAnHjwRVw9tjgp1n21er7Uhehq98KfHxDGXPm0ngB864Zlt7hbdXX5Hd5516bC7r
+        DnZbUCOX9v3Irg9aqJJpewTxug1EfR7vMNyf3iRNImouKCh8GM9ThdeN8MjJgHRL/fIPdNzLBKyJ
+        Lp6VrbMRkQc53RT2T9WCZ/O9x9tvPq+Jzp0Be9YLcgO+a5ju8yGshNJCD1ZOIymnjodhlXUEzU/J
+        XBJsDEBlO0CCV7yaU2X7PiyeuyvJrMfQLHFERTWtdyu5e3Pw49cpTN98Sg5BxHmTkfGZim+rRAL5
+        1jWUjuIEv/gdwJKlJhnMRoaiEIboqqu8t2puFav34jZjNVkpY8X5osHayyMsa88T6G+BQiFejAYF
+        0bj3/urDbz4FlMRPRp/jmihavguRMfMtGILN/hvfbY3ubT7kL2WAPNyNbEX6V+/hWf4UIOHhB7lS
+        vQOL9rDvQCyMlljvPh/xLd2WQDc1l+QFn4+L+ZIG9boBBab02EfsroHyL58/AP2R85Ey3uG4Ge+Y
+        aXjH2E5/cnAjDjI6ikgc13TIHHh7DRXa11HtkbZrz+pciDq6bDipmQYpc2C8ja8ohEAbx+/3hXz2
+        eAdLS68Nc3zOgJzJDnjrnz8mcdLcB9ne64KtUWCTNbKvKLMZ+MiXOz2nnaYP0FFFmzieXuWMv0ID
+        DI8CBPAp76J1IasGw4x30F5xhBFf6aOD6T2okcl2fkTts89BHPDo10/ZKs2BDGXODNAxQL4nlWYV
+        qnPgMmQN9dac194O1MSgCTm665z3lZqL4NJ/rmR/ysR8Bu02hWnyhEiv9eO44tC+w6cejZh9+bRQ
+        4mMIX53vojztI3Oh9UGBFPNbdDFZ4rHc5jjIl0FAPFJHYG1S3oWBnzQBj10vYqp2mtRXmiJUfPn+
+        mnNlDUue71Fs1EGDNbdKgH48Nd/+swPzoyY+9NIlJZpMZ3Ot328F4mu3Ek+0zEZwPNIBUQsG4juc
+        Nf7w8McvUbB36og2IwjgpXltvv2g9OiY3WP4qtyVfOuRkVHtMwiTQcMrvtreeqWPFn7u7EkQvfHj
+        rLr9/ZefxMl1i0m/fPniAXH15mjS0t8PMMvwHgv3avVw+B5r0LVahAzVjppBF/MV5pZKvveLG1rZ
+        fgBj8WEhm5iRJ3RG3MHJqGkAo0s5rqJrUdgc0J1YidtGsxVfNSgYaYU0NthsbS08gIPenLCQyW4j
+        gauwQnWqHiRpFivi1fgSwmktOWIb8sVkNtmEAGBiB6FlDDl9ZCEPo7c6o+Ag+ZEoW3oMY/FpoeAV
+        n80v/8igAwY92IwRzrFyGURQiFeT+PVqAOGgBAosF/VC3MwW8l7Grxg+7PiNUC5OHjW6WweV7afE
+        KzvLY1/zTakmk2+jXOt9b8E7z4cI+RY5Z3o+kvowt1AY+RNyK6+LcETvGIRn8CDGp3gAelhoDd54
+        4+CJz48Md9WcQMm0PHRw7TJfLkYawPCoHUl4E51xfDTq8KsXTENjZsumVUJ4FKhNnvNT8uiLnzKl
+        3Moaun/10t/3cfvFRdZ8T8a14KpMFXeh8fMHwCLfNV/VNVciewn6jG4dKVA5YXMnpnASzOnLXxUh
+        DO4BhceR0clhGM7kIwciC7pmDQolAd2ucoN5K/WMBjHrIFdax4CFnuMxon5C+Mq6mPzw5qdPFeua
+        +8ES3K6MteTeQUEnEbK+/RPDtaqhI4D8y//EkYGrQGEGjz666GvlLQFvxSpI3Q+WLkbfsOG6zZTt
+        66xgSZY2I50Neob9wdr/xfvv+wVqXoUMXdRMj8SvH/jLZ+Qcj4PJnz46hEnYnb76rjaHiSEMwirt
+        8DY9T+MCbrEPJyE9kSh6MG8KynBV7cgsvvxWHZfzGCtwkV4D8tx7xyjGNVbdfbhDN0BWb0mCJ4T8
+        6AhY/NbD4vLmXX02Dw6rc2yZxJuqTj0RH6Nbut+a9Oz7LqTbpUIet0lMQT5yDpTeRYPpU3qM7Omf
+        OrhgYU+O1AzMJb5XjvrYjbcAPrbZSNORdmp43j4IGujRW5NUHqAwiifiUw552NEVCiHJaoIK+hlX
+        zx0hPNIJkwNRDHMdCA3lc22F6Kye3h7zKj+DrwOwv/6mFy2fgRYqKIGPtx+tBYv52vSKvgsQMjnl
+        nq/mXk3gvvbNQIXdyr71k0Bx5J9E/+q51XMbDrrociM/fCf5Rdf+6ttD/ekbxi7IBSeXT0j6SHVT
+        ZAIXAwf0OkkMWTAXttE66A+Oga7ffMLuXrIgbZQzOUZylPOXWEigtObe14+bGWvM2oHTh+bkHtzl
+        aN4/BUt17C4PODlgJuGbWwAbsmyJ230ykzm+qKnK0vroDtnGXDcgw6DxLYLulCMmbq2uh+9pL+DY
+        SQ6juH2bdxioQo98bC3jHJ5MWzVewYiM6qR5K+HmFdj7vP/y897sm8aQwY//m9GDmdQgugxfloSR
+        K/KLSd3Dowblsrng5C7tzeXnZx5Zp+MTRz7R6sxz8IsvKr78Y6WX3odffR5sHcHNhWiHKfzqE+Sm
+        uzKaVdZpCr3kB2R3ow6o+9ECWEn4gPbFiJi0XIG79VKWIstJDg3lFX1QfUO+In+Ueybwt3Px80sC
+        enMYWL79FTjPWCX3XfVi86fWHLVL/JQ83uXHXI3bBSo/f8wvmWziX79JumcZvKJQjn7nwVcfBuC2
+        PZh8rTkUBm/uRnan1WpEWZ4sSBpfJI7XGs1S0dWFP7/7UA4qYMGhT/7i+R6LNsPPIVeU6oa0QG7a
+        T7OYfVvDYm5LcqzisplyNbMh3u4lFNjZPNJt/5HBT997t2QP6PbhYyguMwnWr34Sja3Wg1+9G6eP
+        G61VXrp/+aHBe5W5+lZZq2jjn1F04EdAxf5jgJ8etV7WK18Eusm2pLMOyBss7dcvWvidL2Dl6kts
+        5dKwhcoms4NqHHg24dea/vX3dSI4Ed0sOYTn4dAGbbzF+eJCsEKgBgghC47RmoW6r6KSuFi5KlPD
+        vvobTIX7wuI6vnIGmoyDwYvG5Iqd1RyfGp+pNA3vJBtrI2KSf52UzvhIAfvmH8ty6w4F6b7Hy6vw
+        o/HupxP44gVeluieT1//AYjCOURaEojRfMNmCS6bI0/8XXLOmSL1dyC97w0yNsIjouTUKjC6XyRk
+        BL7XjPXFpdB2uUOw7R/myN7mqEEnThN0dNdjxIeLEoIvf/j5n953njCot8P1gQzl+mleX7yHXSUG
+        6MgHVUOJA1twuD/lQFzUcJzSkbZq7k4X4kikbGi4rCHMlvML2Xuzb5Yz1qkqBcYaiO10NdmqqKHy
+        9d/xOtuhyQcxaKEZV2PA2gay7/kz+PrLxDtsX82y3a+T6pi6ggL5ZjfrqQA+OAtLhoyrsIIpfXQ1
+        GFv9jX75OS2KtkLj1gmYa5xPRKIGGFAPxR0ySX9sVqG9TMpPDxyATxl9v+igroV0+enniLd8p4ej
+        UdfE//KlhTtKMrxKvEvyg0cZuU2zDcEx0DF3iEeTlObnDIRt7yMU3+ZxahpDgew+FgHzdjqQuos3
+        wFXIGQlwJnv05u8U0AYwRPHPX4Vho8B3xd+xuFvXhp2EfIB0/w7IcX/B4+IEcfHjr+TXn7/40MPH
+        HYlIjwQ9X79+CDhYaUscctuOS+rpmWL2to90Pj3ma+qSAkrFpAWc+9JN9p0/qD9+f/j2V5Z11QAZ
+        QxDZm2XM1932UIKPfhjIUZ/eEeWuhqNa5ytP9s6zYXOTVAG8hK1JDOV6GJfyKGtQrUOLxGgXRaIZ
+        ZSXUNw+R6JWomOTLLwDYRQk5oDY2KfWqQqXnSsQdWfZMCDafGih++SLhj2/8/OoPu6rE8np+XGeB
+        7/7iz1OhtMGkCGu1vVOP7MRLGC0342ZDbtR4lE0PwVx+84X2POa4t8UZUEsbC3hDtvmdL1SMSP5z
+        gsknZiRqmztbbtisFVUWK3QIouLrh8V3db7tc/ylGc0iH0UXuoY/I4eea3Ntkn0Ibkt4JfoSwZwW
+        p7JUlwrnxAtDnf2d511vVx3tjbFn82lTp5D4Q0qOcLEjfvLKVt341TZQ50M48j6xapgomo6877yU
+        uo/GgE+L91GcVtooTZddBre9eyS7Kzebf/X1N/7IvGOfsRBcLQjCIxeI1Xobhbx3bKjvfER2UZjm
+        tXgWbHh82XIgBJcd4GtNW0ElTQf0zCOXSfY6OTBlRYBM80FG2uDSUtu9+UK691RyvKSbAZ6Su4+8
+        O+uaQSCrrGp8o+OXqhrjb97306OBRGMF4CEVFODubI3YL/Xo8bJi1PAFd1+LKzQjPlTqVu3criaH
+        5LMzv/rxrOYL1NHztd+Bv3yzw9GEfv7PGrgTD1fP9TD39fuWi+fUwLymXMCxSIvEdf/U4JcPIRS8
+        1maRw0ZTv/WJfn71Ejw5HjavskTpV+9JR8601Wve2Mjn8yOg7akO1e/9kasJaU4HKXPl6L2ZkQ72
+        V5OKD1NU8bVdySnaT834Ohcr3PQeIYZ3xt5X7/pQ64GHAkPFjLlvJMIp50rkHF5XtoSvtIVK6ubI
+        knYqoCigrvrXP5OINi6Yqj3cR1hB+5sKPJY0TIbXIr2hvGeDtwhh7YCv3sbiWi5s2fZ7CP/5bQX8
+        17/+/Pkfvw2Drn8Ur+9iwFws83/8n1WB/5D+Y+qy1+vvGgKesrL459//ewPhn8/Yd5/5f859W7yn
+        f/79Z/t31eCfuZ+z1/9z+F/fB/3Xv/4XAAAA//8DAHXQUXneIAAA
+    headers:
+      CF-RAY:
+      - 93bd468e08302506-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 07 May 2025 02:26:59 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '140'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-678b766599-k7s96
+      x-envoy-upstream-service-time:
+      - '61'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999994'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_22e020337220a8384462c62d1e51bcc6
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Information Agent
+      with extensive role description that is longer than 80 characters. You have
+      access to specific knowledge sources.\nYour personal goal is: Provide information
+      based on knowledge sources\nTo give my best complete final answer to the task
+      respond using the exact following format:\n\nThought: I now can give a great
+      answer\nFinal Answer: Your final answer must be the great and the most complete
+      as possible, it must be outcome described.\n\nI MUST use these formats, my job
+      depends on it!"}, {"role": "user", "content": "\nCurrent Task: What is Brandon''s
+      favorite color?\n\nThis is the expected criteria for your final answer: The
+      answer to the question, in a format like this: `{{name: str, favorite_color:
+      str}}`\nyou MUST return the actual complete content as the final answer, 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:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1136'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=RAnX9bxMu6FRFRvWLdkruoVeTpKeJSsewnbE5u1SKNc-1746584818-1.0.1.1-08O3HvJLNgXLW2GhIFer0bWIw7kc_bnco7201aq5kLNaI2.5R_LzcmmIHlEQmos6TsjWG..AYDzzeYQBts4AfDWCT__jWc1iMNREXvz_Bk4;
+        _cfuvid=hVuA8E89306pCEvNIEtxK0bavBXUyyJLC45CNZ0NFcY-1746584818774-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jFNNb+IwEL3nV4x8JqsQYAu50UOl7mG/JE5LFU3tSXBxPJZt6K4Q/33l
+        QCHtdqVeInnevOf3ZpxDBiC0EhUIucEoO2fy29W3zq2+L2dmpb4sFj+2X5dm80Td9qe8j2KUGPz4
+        RDK+sD5J7pyhqNmeYOkJIyXV8c3082w+nY8XPdCxIpNorYv5lPNOW52XRTnNi5t8PD+zN6wlBVHB
+        rwwA4NB/k0+r6LeooBi9VDoKAVsS1aUJQHg2qSIwBB0i2pPnMyjZRrK99Xuw/AwSLbR6T4DQJtuA
+        NjyTB1jbO23RwLI/V3A4WOyogrW49WgV27UYQYN79jpSLdmwT6AntRbH4/BOT80uYMptd8YMALSW
+        I6a59Wkfzsjxks9w6zw/hjdU0Wirw6b2hIFtyhIiO9GjxwzgoZ/j7tVohPPcuVhH3lJ/XTmenPTE
+        dX0DdHYGI0c0g/pkPnpHr1YUUZsw2ISQKDekrtTr2nCnNA+AbJD6XzfvaZ+Sa9t+RP4KSEkukqqd
+        J6Xl68TXNk/pdf+v7TLl3rAI5PdaUh01+bQJRQ3uzPk/CX9CpK5utG3JO69PD69xdTFZlPOyLBaF
+        yI7ZXwAAAP//AwCISUFdhgMAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 93bd46929f55cedd-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 07 May 2025 02:27:00 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '394'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '399'
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999749'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_08f3bc0843f6a5d9afa8380d28251c47
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold.yaml

@@ -6,7 +6,7 @@ interactions:
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - gzip, deflate
       connection:
       - keep-alive
       content-length:
@@ -151,7 +151,7 @@ interactions:
         6NrP9D+nrsnf4z///rMV/t41+GfqpvT1/z7/1/dV//Wv/wUAAP//AwBcfFVx4CAAAA==
     headers:
       CF-RAY:
-      - 931fcf607c16eb34-SJC
+      - 93bd535cca31f973-SJC
       Connection:
       - keep-alive
       Content-Encoding:
@@ -159,14 +159,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 17 Apr 2025 23:47:53 GMT
+      - Wed, 07 May 2025 02:35:43 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=CncSMPCav.9EJL3emmM0sTqugx5GN6_Oy8JPFBssVho-1744933673-1.0.1.1-Q1XMvHbQdrfEWkkCYeeNHwFdZ1NpjAGJ_0jOUYIk_APelFe7nCanjW_xlOj12b3JQql9.iWQDiHvCeYJDTWkdxnNiMQOEiFMYHX5YZXUuJs;
-        path=/; expires=Fri, 18-Apr-25 00:17:53 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=FaqN2sfsTata5eZF3jpzsswr9Ry6.aLOWPP..HstyKk-1746585343-1.0.1.1-9IGOA.WxYd0mtZoXXs5PV_DSi6IzwCB.H8l4mQxLdl3V1cQ9rGr5FSQPLoDVJA5uPwxduxFEbLVxJobTW2J_P0iBVcEQSvxcMnsJ8Jtnsxk;
+        path=/; expires=Wed, 07-May-25 03:05:43 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=unfPTYCpF5COtm5PuZDuaJqlhefP0iibfjsXHc9lKq0-1744933673515-0.0.1.1-604800000;
+      - _cfuvid=SlYSO8wQlhrJsTTYoTXd7IBl_D9ZddMlIzW1PTFiZIE-1746585343627-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -185,15 +185,15 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '75'
+      - '38'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
       via:
-      - envoy-router-8687b6cbdb-4qpmr
+      - envoy-router-6fcbcbb5fd-pxw6t
       x-envoy-upstream-service-time:
-      - '46'
+      - '41'
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
@@ -207,32 +207,33 @@ interactions:
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_b8c884a7fe2bd4732903ecbdc632576d
+      - req_39d01dc72178a8952d00ba36c7512521
     status:
       code: 200
       message: OK
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are Information Agent.
-      You have access to specific knowledge sources.\nYour personal goal is: Provide
-      information based on knowledge sources\nTo give my best complete final answer
-      to the task respond using the exact following format:\n\nThought: I now can
-      give a great answer\nFinal Answer: Your final answer must be the great and the
-      most complete as possible, it must be outcome described.\n\nI MUST use these
-      formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task:
-      What is Brandon''s favorite color?\n\nThis is the expected criteria for your
-      final answer: Brandon''s favorite color.\nyou MUST return the actual complete
-      content as the final answer, not a summary.\n\nBegin! This is VERY important
-      to you, use the tools available and give your best Final Answer, your job depends
-      on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    body: '{"messages": [{"role": "system", "content": "Your goal is to rewrite the
+      user query so that it is optimized for retrieval from a vector database. Consider
+      how the query will be used to find relevant documents, and aim to make it more
+      specific and context-aware. \n\n Do not include any other text than the rewritten
+      query, especially any preamble or postamble and only add expected output format
+      if its relevant to the rewritten query. \n\n Focus on the key words of the intended
+      task and to retrieve the most relevant information. \n\n There will be some
+      extra context provided that might need to be removed such as expected_output
+      formats structured_outputs and other instructions."}, {"role": "user", "content":
+      "The original query is: What is Brandon''s favorite color?\n\nThis is the expected
+      criteria for your final answer: Brandon''s favorite color.\nyou MUST return
+      the actual complete content as the final answer, not a summary.."}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
     headers:
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - gzip, deflate
       connection:
       - keep-alive
       content-length:
-      - '926'
+      - '992'
       content-type:
       - application/json
       host:
@@ -264,18 +265,19 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAAwAAAP//jJNNi9swEIbv+RWDLr0ki/NBvm5NYUsplFK29NAuZiKNnWlkjVaSk02X
-        /PdiJxtn2y30YrCeecfvvCM/9QAUG7UEpTeYdOXtYPXp7vbLw7evm4ePmObvt/jrsVgVn9/5dbhj
-        1W8Usv5JOj2rbrRU3lJicSesA2GiputwNpksxuPpbNyCSgzZRlb6NJjIoGLHg1E2mgyy2WA4P6s3
-        wpqiWsL3HgDAU/tsfDpDj2oJWf/5pKIYsSS1vBQBqCC2OVEYI8eELql+B7W4RK61/gGc7EGjg5J3
-        BAhlYxvQxT0FgB/ulh1aeNu+L2EV0BlxbyIUuJPAiUCLlQAcwUkCX68ta3sAI7quyCUywA72bMge
-        AHfIFteWYOtkb8mUBFHqoCneXPsLVNQRm4xcbe0VQOckYZNxm8z9mRwvWVgpfZB1/EOqCnYcN3kg
-        jOKauWMSr1p67AHct5nXL2JUPkjlU55kS+3nhtP5qZ/qVt3R0fQMkyS0V6rFpP9Kv9xQQrbxamtK
-        o96Q6aTdirE2LFegdzX1325e632anF35P+07oDX5RCb3gQzrlxN3ZYGaP+FfZZeUW8MqUtixpjwx
-        hWYThgqs7el+qniIiaq8YFdS8IFPl7TweTZejOajUbbIVO/Y+w0AAP//AwA4a1/QsgMAAA==
+        H4sIAAAAAAAAAwAAAP//jFJNa9wwFLz7V4h36WVdvF5nv46BQEsPpYWeSjCK9GwrlfVU6XlpCfvf
+        i+zN2klT6EUHzZvRzOg9ZUKA0XAUoDrJqvc2v/32+fTh68e7bel/UtXFR6/vKv+FP6191cMqMejh
+        ERU/s94r6r1FNuQmWAWUjEl1vau2N/ubTbUZgZ402kRrPecV5b1xJi+LssqLXb7eX9gdGYURjuJ7
+        JoQQT+OZfDqNv+AoitXzTY8xyhbheB0SAgLZdAMyRhNZOobVDCpyjG60fhuk0+TeRdHIEwXDKBRZ
+        CsvxgM0QZbLsBmsXgHSOWKbIo9H7C3K+WrPU+kAP8RUVGuNM7OqAMpJLNiKThxE9Z0LcjxUML1KB
+        D9R7rpl+4PjcereZ9GBufka3F4yJpV2SDqs35GqNLI2Niw5BSdWhnqlz4XLQhhZAtgj9t5m3tKfg
+        xrX/Iz8DSqFn1LUPqI16GXgeC5j28l9j15JHwxAxnIzCmg2G9BEaGznYaVsg/o6Mfd0Y12LwwUwr
+        0/i62BzKfVkWhwKyc/YHAAD//wMAwl9O/EADAAA=
     headers:
+      CF-Cache-Status:
+      - DYNAMIC
       CF-RAY:
-      - 931fcf649bdbed40-SJC
+      - 93bd535e5f0b3ad4-SJC
       Connection:
       - keep-alive
       Content-Encoding:
@@ -283,14 +285,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 17 Apr 2025 23:47:54 GMT
+      - Wed, 07 May 2025 02:35:43 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=8vySwO0xqpm0u93_1_rXQwTeEIWa2ei3_CD5sAdoo3o-1744933674-1.0.1.1-iqZDpH5poOUp4Rcnhfrb0N2Z0c2662RBiPEcx_gefNW.m3tBA3qyFa8tmFv7PitH8u9vyYK7jxUwy4lPiSi830QWNbTMgCMTbrJ7iaUV7hY;
-        path=/; expires=Fri, 18-Apr-25 00:17:54 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=4ExRXOhgXGvPCnJZJFlvggG1kkRKGLpJmVtf53soQhg-1746585343-1.0.1.1-X3_EsGB.4aHojKVKihPI6WFlCtq43Qvk.iFgVlsU18nGDyeau8Mi0Y.LCQ8J8.g512gWoCQCEakoWWjNpR4G.sMDqDrKit3KUFaL71iPZXo;
+        path=/; expires=Wed, 07-May-25 03:05:43 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=IXAyT8eWpFERM53ngcYNmaqhocfGbOHWSoe7SFNdoGI-1744933674288-0.0.1.1-604800000;
+      - _cfuvid=vNgB2gnZiY_kSsrGNv.zug22PCkhqeyHmMQUQ5_FfM8-1746585343998-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -300,16 +302,133 @@ interactions:
       - X-Request-ID
       alt-svc:
       - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '167'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '174'
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999783'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_efb615e12a042605322c615ab896925c
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Information Agent.
+      You have access to specific knowledge sources.\nYour personal goal is: Provide
+      information based on knowledge sources\nTo give my best complete final answer
+      to the task respond using the exact following format:\n\nThought: I now can
+      give a great answer\nFinal Answer: Your final answer must be the great and the
+      most complete as possible, it must be outcome described.\n\nI MUST use these
+      formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task:
+      What is Brandon''s favorite color?\n\nThis is the expected criteria for your
+      final answer: Brandon''s favorite color.\nyou MUST return the actual complete
+      content as the final answer, not a summary.\n\nBegin! This is VERY important
+      to you, use the tools available and give your best Final Answer, your job depends
+      on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '926'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=4ExRXOhgXGvPCnJZJFlvggG1kkRKGLpJmVtf53soQhg-1746585343-1.0.1.1-X3_EsGB.4aHojKVKihPI6WFlCtq43Qvk.iFgVlsU18nGDyeau8Mi0Y.LCQ8J8.g512gWoCQCEakoWWjNpR4G.sMDqDrKit3KUFaL71iPZXo;
+        _cfuvid=vNgB2gnZiY_kSsrGNv.zug22PCkhqeyHmMQUQ5_FfM8-1746585343998-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4xTTU/bQBC951eM9tJLghITIORWVKFSDq0qoR5aZE12x/aW9Yy7O06IEP+9shPi
+        0FKpF0ueN+/tm6+nEYDxzizB2ArV1k2YXN19Xt/cVtnjh+2XbLH99W399a759HFzy8Xs0Yw7hqx+
+        ktUX1omVugmkXngH20io1KnOLubnZ4uz0/m8B2pxFDpa2ehkLpPas59k02w+mV5MZos9uxJvKZkl
+        fB8BADz1384nO3o0S5iOXyI1pYQlmeUhCcBECV3EYEo+KbKa8QBaYSXurd8AywYsMpR+TYBQdrYB
+        OW0oAvzga88Y4H3/v4SriOyE3yUocC3RK4GVIBF8AhaFpl0Fb8MWnNi2JlZy4Bms1LVw2AKu0Qdc
+        BYIHlk0gVxIkaaOldALXEgGtbSMqgedCYo1dP8fgFTbSBgcrghUlBRXA9PBiB5yPZDVsQSJY4dQG
+        hYZiks77Xh82FUUCrXw6Focat51sqjCSOzluU6SiTdiNitsQjgBkFu3Z/YDu98jzYSRByibKKv1B
+        NYVnn6o8Eibhrv1JpTE9+jwCuO9H376apmmi1I3mKg/UPzc7X+z0zLBxAzq/3IMqimGIZ7OL8Rt6
+        uSNFH9LR8hiLtiI3UIdNw9Z5OQJGR1X/7eYt7V3lnsv/kR8Aa6lRcnkTyXn7uuIhLVJ3kP9KO3S5
+        N2wSxbW3lKun2E3CUYFt2J2JSdukVOeF55JiE/3uVoomn55eZossm15Ozeh59BsAAP//AwAaTaZd
+        OQQAAA==
+    headers:
+      CF-RAY:
+      - 93bd53604e3f3ad4-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 07 May 2025 02:35:45 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
       cf-cache-status:
       - DYNAMIC
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '489'
+      - '933'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '936'
       x-ratelimit-limit-requests:
       - '30000'
       x-ratelimit-limit-tokens:
@@ -317,13 +436,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '29999'
       x-ratelimit-remaining-tokens:
-      - '149999801'
+      - '149999802'
       x-ratelimit-reset-requests:
       - 2ms
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_151f9d0b786f2022f249ee20ea108b43
+      - req_0001c38df543cc383617c370087f0ee3
     status:
       code: 200
       message: OK

tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default.yaml

@@ -6,7 +6,7 @@ interactions:
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - gzip, deflate
       connection:
       - keep-alive
       content-length:
@@ -150,8 +150,10 @@ interactions:
         Mj9mH/7zuxXwX//68+d//G4YtN0jf30vBkz5Mv3H/7kq8B/if4xt+nr9vYZAxrTI//n3/76B8M9n
         6NrP9D+nrsnf4z///rMV/t41+GfqpvT1/z7/1/dV//Wv/wUAAP//AwBcfFVx4CAAAA==
     headers:
+      CF-Cache-Status:
+      - DYNAMIC
       CF-RAY:
-      - 931fceef786ded38-SJC
+      - 93bd57189acf15be-SJC
       Connection:
       - keep-alive
       Content-Encoding:
@@ -159,14 +161,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 17 Apr 2025 23:47:35 GMT
+      - Wed, 07 May 2025 02:38:16 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=fj4RMXSXRDQjE2CFC6CGC3dVcJ8cl2Cbu8alijwMHA8-1744933655-1.0.1.1-M3c3AI4XQa.0GJoanNACuOm2aEL4xjqHR1grxIP3olFvq3e0eFHwQTvCF20YwR_OLiMJUH87eNUwgziawMccsxjR9OVZyDr5._5Wts6CrqA;
-        path=/; expires=Fri, 18-Apr-25 00:17:35 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=VGdrMAj2834vuX5RC6lPbHVNwWHXnBmqLb0kAhiGO4g-1746585496-1.0.1.1-kvgkEGO9fI9sasCfJjizGBG4k82_KhCRbH8CEyFrjJatzMoxhM0Z3suJO_hFFH13Wyi2wThiM9QSPvH3dddjfC7hC_tscxijZwiGqtCVnnE;
+        path=/; expires=Wed, 07-May-25 03:08:16 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=MSkpJsQZtdyIGvrl2mIwy0a_We8H6CIrS7etFgRBl2Y-1744933655703-0.0.1.1-604800000;
+      - _cfuvid=sAoMYVxAaEFBkQttcKO7GlBZ5NlUNUIaJomZ05pGlCs-1746585496569-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -178,22 +180,20 @@ interactions:
       - X-Request-ID
       alt-svc:
       - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
       openai-model:
       - text-embedding-3-small
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '140'
+      - '69'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
       via:
-      - envoy-router-84959bbcd5-rzqvq
+      - envoy-router-7d545f8f56-jx5wk
       x-envoy-upstream-service-time:
-      - '110'
+      - '52'
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
@@ -207,32 +207,33 @@ interactions:
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_dd3ef61c4765b46ed7db80ddfe261f41
+      - req_73f3f0d371e3c19b16c7a6d7cc45d3ee
     status:
       code: 200
       message: OK
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are Information Agent.
-      You have access to specific knowledge sources.\nYour personal goal is: Provide
-      information based on knowledge sources\nTo give my best complete final answer
-      to the task respond using the exact following format:\n\nThought: I now can
-      give a great answer\nFinal Answer: Your final answer must be the great and the
-      most complete as possible, it must be outcome described.\n\nI MUST use these
-      formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task:
-      What is Brandon''s favorite color?\n\nThis is the expected criteria for your
-      final answer: Brandon''s favorite color.\nyou MUST return the actual complete
-      content as the final answer, not a summary.\n\nBegin! This is VERY important
-      to you, use the tools available and give your best Final Answer, your job depends
-      on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    body: '{"messages": [{"role": "system", "content": "Your goal is to rewrite the
+      user query so that it is optimized for retrieval from a vector database. Consider
+      how the query will be used to find relevant documents, and aim to make it more
+      specific and context-aware. \n\n Do not include any other text than the rewritten
+      query, especially any preamble or postamble and only add expected output format
+      if its relevant to the rewritten query. \n\n Focus on the key words of the intended
+      task and to retrieve the most relevant information. \n\n There will be some
+      extra context provided that might need to be removed such as expected_output
+      formats structured_outputs and other instructions."}, {"role": "user", "content":
+      "The original query is: What is Brandon''s favorite color?\n\nThis is the expected
+      criteria for your final answer: Brandon''s favorite color.\nyou MUST return
+      the actual complete content as the final answer, not a summary.."}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
     headers:
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, zstd
+      - gzip, deflate
       connection:
       - keep-alive
       content-length:
-      - '926'
+      - '992'
       content-type:
       - application/json
       host:
@@ -264,20 +265,19 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAAwAAAP//jFLBbtswDL37KwhdeokLx0mbOLd2WIAC63YZdthWGIpMO9xkUZDkpEWR
-        fx/kpLG7dUAvBszHR733yOcEQFAlViDUVgbVWp3efv66LvKPRd7Q/f57vtaf7m6ePjze774sv23E
-        JDJ48wtVeGFdKm6txkBsjrByKAPGqdPFfF7MZtdXVz3QcoU60hob0jmnLRlK8yyfp9kinS5P7C2T
-        Qi9W8CMBAHjuv1GnqfBRrCCbvFRa9F42KFbnJgDhWMeKkN6TD9IEMRlAxSag6aXfgeE9KGmgoR2C
-        hCbKBmn8Hh3AT7MmIzXc9P8ruHXSVGwuPNRyx44CgmLNDsjDRnd4OX7GYd15Ga2aTusRII3hIGNU
-        vcGHE3I4W9LcWMcb/xdV1GTIb0uH0rOJ8n1gK3r0kAA89NF1r9IQ1nFrQxn4N/bPTa+Xx3li2NgI
-        LU5g4CD1qL5cTN6YV1YYJGk/Cl8oqbZYDdRhU7KriEdAMnL9r5q3Zh+dk2neM34AlEIbsCqtw4rU
-        a8dDm8N40P9rO6fcCxYe3Y4UloHQxU1UWMtOH89M+CcfsC1rMg066+h4a7Uts1mRL/M8KzKRHJI/
-        AAAA//8DALRhJdF5AwAA
+        H4sIAAAAAAAAA4xSy27bMBC86yuIvfRiFbKs+HVLUKBFL0YPRosWgcCQK5kNxSXItZEi8L8XlBxL
+        aVOgFx44O8OZ4T5nQoDRsBWgDpJV521+t989PX78tF/fnr5X+w/fdgv6WnxuWruzX25hlhj08BMV
+        v7DeK+q8RTbkBlgFlIxJdb6qljfrm2qz7IGONNpEaz3nFeWdcSYvi7LKi1U+X1/YBzIKI2zFj0wI
+        IZ77M/l0Gp9gK4rZy02HMcoWYXsdEgIC2XQDMkYTWTqG2Qgqcoyut34XpNPk3kXRyBMFwygUWQrT
+        8YDNMcpk2R2tnQDSOWKZIvdG7y/I+WrNUusDPcQ/qNAYZ+KhDigjuWQjMnno0XMmxH1fwfFVKvCB
+        Os810yP2z81Xi0EPxuZHdHnBmFjaKWkze0Ou1sjS2DjpEJRUB9QjdSxcHrWhCZBNQv9t5i3tIbhx
+        7f/Ij4BS6Bl17QNqo14HHscCpr3819i15N4wRAwno7BmgyF9hMZGHu2wLRB/RcauboxrMfhghpVp
+        fF0sNuW6LItNAdk5+w0AAP//AwDAmd1xQAMAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 931fcef51a67f947-SJC
+      - 93bd571a5a7267e2-SJC
       Connection:
       - keep-alive
       Content-Encoding:
@@ -285,14 +285,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 17 Apr 2025 23:47:36 GMT
+      - Wed, 07 May 2025 02:38:17 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=7agwu5JV1OJvEFNhvfvqdgWf.HoMyIni9D85soRl3WE-1744933656-1.0.1.1-dKUwAZnjjuuiswFKWGsxpwHNBJUpjhYlZvfZpyNQIejxEJrXMCppgPvtQ9wa4SKezLmKqftvn_H.bAx_AEFJD2EWm5V6R_uK8.odneErR6A;
-        path=/; expires=Fri, 18-Apr-25 00:17:36 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=62_LRbzx15KBnTorpnulb_ZMoUJCYXHWEnTXVApNOr4-1746585497-1.0.1.1-KqnrR_1Udr1SzCiZW4umsNj1gQgcKOjAPf24HsqotTebuxO48nvo8g_X5O7Mng9tGurC0otvvkjYjsSWuRaddXculJnfdeGq5W3hJhxI21k;
+        path=/; expires=Wed, 07-May-25 03:08:17 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=LdTrzwZYrB6ZyQLY7NdaaHVpDVFvIjYm3arSpNy87wU-1744933656504-0.0.1.1-604800000;
+      - _cfuvid=LPWfk79PGAoGrMHseblqRazN9H8qdBY0BP50Y1Bp5wI-1746585497006-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -305,11 +305,130 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '540'
+      - '183'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '187'
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999783'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_50fa35cb9ba592c55aacf7ddded877ac
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Information Agent.
+      You have access to specific knowledge sources.\nYour personal goal is: Provide
+      information based on knowledge sources\nTo give my best complete final answer
+      to the task respond using the exact following format:\n\nThought: I now can
+      give a great answer\nFinal Answer: Your final answer must be the great and the
+      most complete as possible, it must be outcome described.\n\nI MUST use these
+      formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task:
+      What is Brandon''s favorite color?\n\nThis is the expected criteria for your
+      final answer: Brandon''s favorite color.\nyou MUST return the actual complete
+      content as the final answer, not a summary.\n\nBegin! This is VERY important
+      to you, use the tools available and give your best Final Answer, your job depends
+      on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '926'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=62_LRbzx15KBnTorpnulb_ZMoUJCYXHWEnTXVApNOr4-1746585497-1.0.1.1-KqnrR_1Udr1SzCiZW4umsNj1gQgcKOjAPf24HsqotTebuxO48nvo8g_X5O7Mng9tGurC0otvvkjYjsSWuRaddXculJnfdeGq5W3hJhxI21k;
+        _cfuvid=LPWfk79PGAoGrMHseblqRazN9H8qdBY0BP50Y1Bp5wI-1746585497006-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jFNNb9swDL3nVxC67JIMSZo0aW4ttmI77bIO3UdhMBLtcJVJQZKTBkX/
+        +2CnrdOuA3YxYD4+8lGPvB8AGHZmBcZuMNs6+NHF1Zc7Xycnp/Rhdv3x2/fL82r+9Tr/uDrxn8yw
+        Zej6N9n8xHpvtQ6eMqscYBsJM7VVJ4vZ6Xw5n50tOqBWR76lVSGPZjqqWXg0HU9no/FiNFk+sjfK
+        lpJZwc8BAMB99211iqM7s4Lx8ClSU0pYkVk9JwGYqL6NGEyJU0bJZtiDViWTdNI/g+gOLApUvCVA
+        qFrZgJJ2FAF+ySULejjv/ldwEVGcyrsEJW41ciaw6jUCJxDNEJq1Z+v3cCu6E9AIuEX2uPYELGC1
+        rlU60JOrCJI20VIaAiYIFJO2zUKkkiKJpQSeb+lVrwQYCfI+sEXv9xAibzEToLhukC3GPezYkd8D
+        1ioVsDjesmvQJ9hx3mhzpDRtMJIDllJjja1/74/fKlLZJGz9ksb7IwBFNHf5nUs3j8jDsy9eqxB1
+        nV5RTcnCaVNEwqTSepCyBtOhDwOAm87/5oWlJkStQy6y3lLXbnK6PNQz/dr16GzxCGbN6Pv4dDIf
+        vlGvcJSRfTraIGPRbsj11H7dsHGsR8DgaOq/1bxV+zA5S/U/5XvAWgqZXBEiObYvJ+7TIrVX+a+0
+        51fuBJtEccuWiswUWyccldj4w62YtE+Z6qJkqSiGyIeDKUMxPjmbLqfT8dnYDB4GfwAAAP//AwA/
+        0jeHPgQAAA==
+    headers:
+      CF-RAY:
+      - 93bd571c9cf367e2-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 07 May 2025 02:38:18 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '785'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '931'
       x-ratelimit-limit-requests:
       - '30000'
       x-ratelimit-limit-tokens:
@@ -323,7 +442,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_8837be6510731522fd5ac4b75c11d486
+      - req_9bf7c8e011b2b1a8e8546b68c82384a7
     status:
       code: 200
       message: OK

tests/cassettes/test_get_knowledge_search_query.yaml

@@ -0,0 +1,333 @@
+interactions:
+- request:
+    body: '{"input": ["Capital of France"], "model": "text-embedding-3-small", "encoding_format":
+      "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '96'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R6Ww+yyrbl+/4VK+uV3pGLUFXrjbsISKEgYqfTAUEEBeRWQJ2c/97Br/t094uJ
+        WIZUzVljjjHm/I9//fXX321a5Y/x73/++vtTDuPf/217liVj8vc/f/33f/31119//cfv8/9bmddp
+        nmVlU/yW/34smyxf/v7nL/a/nvzfRf/89XfIFDaOu8OtX0ttiOESiQE+pXaRrnxot/BYFAy5kEUP
+        ONOCJaymU0mOVijT9bPeH/BZXg4kYptvv4S7/QQztojx/ay+Ul5kFR8F+9XEUeizziKFvQ+uIr4T
+        E107h77ZSw1r9zPiUCqSYL4SxUbv5usRy5ZLusgkecBnVXUYOzGbrs25voiDG1c4vEhCTxHz8GCW
+        BAdvL9+sngv6iwv3uxDj7HWgPUkXUIBvFy3YnkpJo7AQIvipwoIEgINatQMnCZbG54EP4NtQGgm1
+        j84HJBDbhxeNI+7DBsboBuS5G27VeLUbGV4TmSEyXDVNYO2qg963GbCJrrazpK3iIk9XzQn1/aGa
+        HvHpDatPvZDj9a5UvL67PpApmxGO6maite0dfTjujIfHLN4F0Dun8IiTkpSc0vyuLRl9hRAz+on4
+        10ruubG6mchYruLEKW2rfYOdyUKFSzKs4XeRsjXNYsmeAMVeXOk9n7hjDu9xnGNTZ57p3DVSDWr5
+        fMXpOdNo4zDGG1m7/QtHFVHoPOe4gw9gDliBlhTQ8z7hRY3aLjneZ4Uu8u3TAfe1ODjU9lrFPfww
+        hvez5uNTtZcBx1Zhglg5CrF231NAhv5ewND/BCQ5FX2/CJdjAW8sKYkyly7lHFe2AdR9HZ9Jc6EC
+        8O8qelzOmcdoegrac2xJ0KLvI8be8UXp28I+fJ/uiCQH4ews2KhKpFTMwxPPo5S+M+Oxh4esr7Hb
+        TDigi6VIaPf8aMS6GVol/PItMgbfA8z3HghaTguYSWJFrmr1AovFCxN6lWOCH8Zy0Cj3tG24rysZ
+        n9r61c8ncz9A32GbqY46xeETxDNIpUswCWHyqRbOfMVIaG0bG4uy9Et2iGSYhTeJqEEyARpwbgEt
+        fzpMxzJXU9bImBBMrPAicq0fwCyP9wiGaWsRR481jeNRCZHD8pG348i7IurdyaE9iRTHha1X0yeE
+        NbicCPCK19j063LnYvSxK5+oxyWshHE3y2h/CD/kfrjXdEaVFIL3y9fwbQWHgApiPMGnM2U4gotf
+        rZ/1nKNkskqcWfRTrXUytNBlfAWr5VD1rak4ETSWm4iVsLxt+8tVwDlaOfWqg7XlfHY6cDjfPGIy
+        4EFJveg+1JsHxmnzzgDl35IHDwafeKabnYLRmXoXamJ1m+ZoDTQara0OOTVZsHr21YoviMHCV9w2
+        Xhyo0Fma0VZh/dXfON9HRTV/7vMAFpFeJxbnZ20Rs28L+x0YiFcKNzDj21P95SexzvRYcVejYNHL
+        3p9w6l15ZzaGYQZWc7gQo/rMKQEr1P+s12KUOD+8gU/9ir193EcVh3mkwnF3eGDjcbS1LV9l8aiE
+        lbfU4hqMtzd6S8X3POFnBStnNPtbjcDbqLGm0n06n77BCkrCD948wBDMDjY8+L7vWRztmSPoLobs
+        /fCAaLN67eeMnxKYHFWJHOpFTvlQEfcwPpWLR7+T6nBPHQ9S9MI6ceprH0yrM/OI8IDBTs6jdNu/
+        DN9WTr3yzmgaX5ATD3fr0/R4tjlWbCmuMlpPOSTqnak0sgPGHo6vm7bhs619j3KhIsKLzDT/8EeV
+        1hpe4nkhF+HtaLPNtTnkXo2LtUA2KUfDD4SscAUY21nSc339iVEYXiSiAuAEfKu9BnSa9hl+HG4i
+        WMTs1aGT3p/w7z7wL7dc0RLgAeMrbKtB08gM7kdXw9nexVrfiZGOPs9uT3R6PmksFWUT1dXxhuWD
+        ++l7duVnMGVqiPVdGjpcC+YHhF+uw9bK7bWFrcIYct54xGcd2g6b9t7lT71zGdpRKl2frhTXkeJ9
+        TEnVKDafDxh0yteD3rOp1rgp3uiZ2Tnxjq2vsVdrlKRLvC5Y9vRLT+tFv6DrpZ+JWoHIWVRpfcMt
+        HsSNn2oq3OsgRiqlAbaSl+1wVXSckWv6N5I43Q3wrfdkwHzTHyRWXyxYSb/av/wg3m6t6cJPsJTU
+        lDFxoE2rs6T3ywxD+rxO+8ukpUIowTesh9kh0fhM6dqy1IXtM9OxfBtdwKUjTuA8ePrEcrmiCTwT
+        STCTvSvOZOPjbPjeIvdFHeKJitivfqDP6G7CjBzN/KSNuyV4w21/WAuA3As69GPIvT4uPsx2oq1R
+        zQ+wegGbGLWJtCH83k0QNKHhzVnUpHzifh4ofz1PHmdKpdOuB30AeUY/3jc+Tz2NKrH9xYPkr7Oh
+        Cca7f0PXOb2wdXocA5Zw7AOBV6wSP9bHtPM5wkrIHQdispqv0fNBidD3XJUT3zHYoW7nQyh809Hb
+        H42vI2QobaEa+0+c4XB11putTSA5yhLxrDFKZ41QHd4WDXit8S2rqTo+HvA1zphoPP4GRHncV4jl
+        YzR9g2oE81l+mGLTgpToVcqAWc7LPUpQhDzY2FfA8rkO4Wjw2OOy+FEtmjBc4GMML0S1StXhbOH1
+        RkrTavhxApPGqcevDleddYhy+egBOUmCj2q3GT3JSz/BELGi+wd/5LfHBvRY7WTYIQETXDSPlN3w
+        AgyJhXDEAEgH7RTLcOc5KjlcTueeFtkl+lMPsEISh33czh26z7gnp8K9g29/kic0WAMkh8WgQBh0
+        5gKKy74ix0vLassrjy5o6d4SkfkP0eawuEyQu5V3YufKBcyXbIboy6bvaTl1di+8IzRImSWY09kl
+        PhAI/A6QdbuBKLcG9QMPvrzQTt8nztr6VbHzwJhSFKcslmP9lAp5UXQIjFPiOUTrwWqpX+tP/mtc
+        iPvJCZZQcly+J9rXtirhtexZIJhVTzb8C9aIGy1YfS8x8T7tJ2gMl1/h/az4ntBbRb9AtS7gEoEA
+        O80bgd/9hnyvCuQQJp+eWnp5kXhcatOeQwZdNHy2YWsZPLbXz6tarvfrAz1hKGKv65j+veEV5BhT
+        nahzKpxZqqMVupNRYVvMvJ7/Sv0FbnhHrLpfHHrX5hB+PE8gWos9sAiP3Sy1RnzBxzQK+3l9v2oQ
+        0uyKQ3RuANH8kw6/kxzjbOOXQmSGK/RVTCdwMqtq3Yn6/MtPbL1fOhBOr0uNBll38F2LngHHFZ4O
+        F/4wEcv4qpUQa14Ob2eh8Fgdvx1ivKs3xPWww7kIg2BelEcLLr4tT8vjyqRrVS/RH34h2+2gLexq
+        s7DjvHxipUJK6cangcZxM06uwSWgOHcvcMoDwXvkDy7o+ciZ4XqpP8RRHezwQ/JiID/bxSS6vaJ9
+        X/arQyKBPTGGbglG4SGscPceBhzQQ9ovtzf3hvU1QRPParO27KWwg/zJ2OHj1B6D9ZuZMVQiV8VB
+        9DgFg8a8CpAnB8YTZlvSfvkNtXlf4xv4HgArpW0BNzwm6l37BlRT8g4wnxudqslQg8mLAhOZgoG8
+        9cdHEsRDIKwumnapmPbzQJMJHoKaxcrGX3/4iMDpBYnmfc1KcLsYwvq4PxLtNA2UCF3ng+h10qdd
+        nRFap50aojJPeqx+TnPaSb26R8wcf7G/C0j1zbuOgXs3IB6bjExA90dBB32sF95Mj1YvbN/Rxk9I
+        Yow64HOQFKChzJngJv72q6r2rOSwbIQV5VgFg4dWH5k3scTu+q0Ambs3A1fR8vBt/I7BPBwOCdyJ
+        fEiMV6pro+d9JVCY94FYXzcDvaWXPkpFGeN4qY2eqyJlRnBfH7yPfmTpwOc6I92mMMJX5MQVbYyO
+        lcbbxd/yray2/V/g5/o2cZ7qi7a691eC1FoVf3yhmp+q+YbvCjUkQ/lXowa9qHA9PSBR7WFK5/KR
+        WX/qXYfYCfQ5m13gGLy/2FuPQz/o+rlD6mwM5NZbcs9zXlLD4/1IyHH+wIrGZ1aCA7l88AlWJFjk
+        OjQRMydfD5qDDFojYyL44+PO+lyDRa1OM7zlzh5rytugQh2QGEz6ycAGcvbV+sZ6iXKDuU/rwW/o
+        d+MbwJyHFWdfjnVmfgAJ+O4PDnHzB5cSK/AHwJeJOQmrPFakbNccJRwi2OqRo/G96Tykl1buvPHw
+        clK2ZVAJxITTSJ4chWAKqBPDTb8RV3zNdEnvyQq9em9h88GE/WrRtQU/fXXAg06Xj36SITeKb2Ie
+        P0Ww6GaygmOUO8RwzmUwd/xLRdM9GsnJrJd+0x8h2PALO1nTASp/Yhvm/JvDxySVwAgnkUcbvyWG
+        SC4O6198HlbOtcAGhiCYHkzBI2ZiGqw97RP9jNXThGlkn7APhKPDO8ESAeMqGMTK0Fwt+nOXgy6S
+        NSID4aiRXVyyUGVYi4RZ7lA+oE4CZRrJRNvPvEM13zChJr5u3szEVzoPV8SDa6Iy+CSpaiXgQZog
+        aOgJK2fz7FBWGX3QS7DE2vHm9iy+3VT49mJ54saPowmPq1xA4SSJZLu/gGbJ/EblmwrePn1UYCK7
+        eoYnK2KJ9uNb2KgKVLZZThyLVMEsj+fwd37TaxrELV8T9Yd3WJ51tV+b8+RDJN/DTZ/LgQAPlxYq
+        OU+J+Rk4rVX2hxruibNMHGNeAqGLqIys0rLIvTqCYH6xCgPZ83rFch+9wNAyXAmsTH16/J75gtWF
+        7gPmXmOTw+GLUrryJxPeB93A12BXgpmmvQtxpcX48OHNfnnqeIK/88eTH/XLcjR4KJbu5efngHm3
+        93kwOe+AeJirwLpOwR5BE7XE84vM4YmX+fAwV19vJ5lvSpMskyHoZIpl6B37ae/DCGqWBIjiiZlG
+        iywJYQpG6rH53ajmvBRXsHfPBGNmycDS5EHNFfYhmCStmOliGZMLW2Xq8UkJb9Wq3ezo5/8Qyw7T
+        fmzBPof5x2L/3C9CSz9H3rMQt/yWA77eKwWsDl+RHGuurKZz0/vQct45OZiaXa0JtSZo4zEmj/Rt
+        pbN/vOSIUZ8L0eXqQckS7UNkZfKThPdD3xP541uIpHebeIOwVpueV9FTv2FsVB8/ZfscenCPUYST
+        p2AGwtwNDEj1ycWHwOpTOuj8Bb7qu4LtyXsFlG2tEpYscyVHxaXOUvrnAaaXR01wRnC62rtklTa+
+        hR1hGdI581Ifci2TTNLkKcH8uJ1bBKvHk+SPqA8oLeMc6L6h4OTerRUlju8iIn0+5KkQyVm3+waR
+        LVv48PMn9kfNhsGS7DF2A+/P+6Dn6fuJ9xqxmupvasKyKsNpOZtnjQaXVw43vj7B6kaccfN34GGI
+        NXw5LmxFJLDm6E7BBePzxwros/Yn1LRiSix/jyk7MRIPzVGzscmVWspl+6aAnkk6rL9V2elEET+A
+        wWkFUTAbAbI2UQdTLmwnfsOrmR9oAn5+1MZXNYrIZwbnqSqwBaq4GqD8SX7xxNiBI/3hF6yk4U4y
+        G52BUAdNjN479eEtHybu1+SdXODiFxYxjF2bzk3UxaAy44hc47HqOU6Q9rC7hA/y03NLt+/sP3h0
+        P9xNSoB/lmHER8MEnsvNmdeDPv38S2IEO5XysGFruOHHJLEO2087f+mQJl9sfCx0Lp2E9mVLDfz8
+        H3z9+Y+92T5J0N1TjRejdwKb2e+wB0eZCoo+MPBz3j9JnD4qOvO2HyI218epZ773dGaZvSVKTvbE
+        zmRdnMU2YxNsfi22FokJ6DU/1jDx4yOJDFF0Vv0hJbBdbwdyXIoo5cluWiHiISLKs/s4czHd9/B0
+        OjPeromPlaDloICptzJTtfEvfqsvUHbCK85pvNPWTI8hXKAMiBJBvRLq3TpA53jUsXWm34rW5ZWF
+        9sFsiCwUFqDrTsvBhic/Pzcgh1PRIl5/etNSlhdnLcx1QMHBabB5CWQgiPpeguvudfeks9CDGV01
+        CRJhrxDsxGGwgK8yo9N95TwmONvpli8xOuFBxUotrikVTkYsbviDbZsw2urm5A0vjnojxqbvOYja
+        C9TOk7Pxt5VOh+fDhrITXYlyMPlgIl52gT7lLwTv/XMw9zl0oV0HKsafMtJ6rRH3YNPHHkpz0SEO
+        c6rBFl8PHm4inU971UM/v3njc/1YKr0PkuQBMN78ofVjehbIh0KdOss79/RCwgeaUWdgIypwRa/D
+        Xv35H8T/HCetu+elBze/yqNB+OxX7aaG6B4OAlZrq3MWOC0s2vQrPi4Fn071/ljCULAhdkKxC4Tj
+        3Vp//yd4ifV0OUlaKL5cZ/akMI77OWsECAfxGk/DdQrB/LAqV9rwHpt6V1fLK899wIZPcfps/IGA
+        t9FC/eN+SSSKVT/sv6MJvOvjgI/bfRluJcx/+OsJwuVQkW1/8OcnRZ/hqpEhGAawOMmTyGe3SJfY
+        st9wjdGM5UEBThMOng02PMHpeIrTdZ1SCT7vuYCtpf5Um1/jwWU3lfiw3yf9eH5KJuSr73d68c8d
+        HZ5CfIGJ2EdeluC6H+7+bpB0r9thNb9qwdLg0Yab3+S9SLMC2j3F5Fff8LFdOUCYizTDyzv4bHpP
+        6ac6eXfwgFh92vCkWhRNVCWPNyti2/rH+cMHNj1JsNoFlHuN7gB/eu6w6c25a9Y3PPUePzEgrau5
+        H8sWfs+vkiiS0zgr2U3zD3+J+wVawLMiq4p5qitb/jt0nC+6h+BYnT1287/G5XhioWDjCza+Xgfo
+        O+ImOEGXkOweukDoxFwH0XNRsU+Pbb/A8wMC9TsU5K64VBuDR79CY/QCchIPLaBRtbTIL+Mz9oJz
+        l87v0OrgtH9Zf/g0a+CDBJ4NPhNN2ec9laPXgPKhVLE5JdeKX0x5RUNfM8S5srrDea1Xw+FCCXFD
+        CrRe5NUYNpa/89Ys+VYziBMXuJ5oEWVcdsEqioccNP1RmVB9P1V00BkfIvKZsDKadUA2fQ/XhcrE
+        PJNDwNvzOwTIJQO2ETvR9YVYH8nXu0WwA0+UZRIA4bQcpenr9i9tuJvHHAYnk8XWk+oOnYzWRvVR
+        OmI1HL7OWl4SHsTCqnprBXhtBfPK/PETVLK8gxXoTQt/9ce1rUOwvtxuhTrfdjgUOSXd+jUR4n1o
+        kNvVYPqhOQAIG9ioRFWYkfbV1JVQNdl8i9/ozBoBJpS6XvLKPnlr9BBHe9hO/dMT/UNTzbS7t+Cn
+        f8yBVakwn+UL0voZYVUyBNpMT52Hm77CrtAjbfzohiotXS0RXSqkYNz8Ydg4TE0co7lWa/SwHrAX
+        fEDOF8WmA2aphGqp/GAVnYyK/eknTG4zdrf+Bx837RvWt64izidZKpKhtIOWjn1vTU9cvw4OKP74
+        G27y9SqujqvyT3ycnM+C+aenLkXDTEAzW0B//mckqQGxxPuQbniXw7NPD9P+ZlT93BwoA5Rl4rFN
+        Mgp+fgtqC2AS75kuwXjlpQhKB7qfaIwkrb37wgCUnKWbuXTUtn5OCX563rt7WbVemb6Al0cee4Ji
+        zXRuojL+g/+O63zBuvVv4MjnPTGKwk6XJCgH4BhZNoHhwlS02KEYZucu8sQDklN+5y8t2urptLjE
+        p+MLExaQUztjL3T1YN09CxMpjOYRZ/emv35E9/N7sBeNM/0mQTdB8WR+seXga7pgoy/h7/w3Pkzn
+        PNQiKO/PNn7gRAl+/BSuzXTC0fgEdG57aw+as4mx7J/NXiidaw09XTbxTx99Gc/rwOPb9eTg3phf
+        P6aFy90WPenD3qtl67cARTR1bJH7uZ/rZ7GiD7u+iMWhD5imW9BB/l7zxFJq4AxN1CVQi/rrNOtp
+        nC7P1/AGSuFzePOHqzk9f99w81vxIXqfKf1IdvvTo+QEKxyspfSB0OpmER8SsDrLvm5l2Do0m3a+
+        eXXW2pxldLw7hDjbeQ9bPwKW7TPHbrC8Kirydgw7WUqJcUw9IJCR+n/8Gquw39Xy45PdyaNbf0yv
+        eNeWINSDucUGIUK6/PrV/bd4TWCrH6yUFgXqtM8O6+cdAtMtsHW4a5OAWN6t0pYqPUAoNUzk9bJS
+        /vRVDiRDD6dff41w4/wGh3Z4ELvwTMpLvSr9/GmibPySpgstkYZcxoNKYlLaRUCFW78HywNk6fLh
+        8lL6Puob1hP1E7TNATDQGTST2JE3ONRIPy6MmF3mwQ0vh7h9F1B+zBGJk5et8Y3bmpDgffTzryjX
+        vp0WTiz3msRVJ2CuVWcPHGXhyeH2dCrOlDwVdIXJEwdNu75Tzxcf7YziTDJ2bqu1Fx4Q/v2bCvjP
+        f/311//4TRjUbZZ/tsGAMV/Gf//XqMC/hX8PdfL5/BlDmIakyP/+539PIPz97dv6O/7PsX3nzfD3
+        P38Jf0YN/h7bMfn8P4//tb3oP//1vwAAAP//AwDPjjDU3iAAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 93c2407849cb943e-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 07 May 2025 16:56:39 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=iRcThWdZ.NO0HPhZg.pUV1AiG0u.0Dkd58N9HGucKdQ-1746636999-1.0.1.1-Cswtia9bUNC0npExHV2GcZLT2MVo6tEQbFU_dsKpjNN5R3s37B6JGWTE1IIZV9V0UGLhiy04og474anpJW4c6yLw0.9q5F4MPcxtAOjwBvo;
+        path=/; expires=Wed, 07-May-25 17:26:39 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=rvDDZbBWaissP0luvtyuyyAWcPx3AiaoZS9LkAuK4sM-1746636999152-0.0.1.1-604800000;
+        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:
+      - '116'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-6b78fbf94c-z6prb
+      x-envoy-upstream-service-time:
+      - '123'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999996'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_3f67e7a1b90d845c25e9cef31147aba0
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Information Agent.
+      I have access to knowledge sources\nYour personal goal is: Provide information
+      based on knowledge sources\nTo give my best complete final answer to the task
+      respond using the exact following format:\n\nThought: I now can give a great
+      answer\nFinal Answer: Your final answer must be the great and the most complete
+      as possible, it must be outcome described.\n\nI MUST use these formats, my job
+      depends on it!"}, {"role": "user", "content": "\nCurrent Task: What is the capital
+      of France?\n\nThis is the expected criteria for your final answer: The capital
+      of France is Paris.\nyou MUST return the actual complete content as the final
+      answer, not a summary.\n\nBegin! This is VERY important to you, use the tools
+      available and give your best Final Answer, your job depends on it!\n\nThought:"}],
+      "model": "gpt-4", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '911'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4xSwW7bMAy9+ysIXXpJgmbN0iW3DEPQAtswDBt2WAuDlWhbjSxpEt00KPLvg+Uk
+        drYeetGBj3x6fHwvGYDQSixByApZ1t6MP/6UX75vV82n7Yf17uvKX4dVuXn/Sxc3n2+uxKidcA+P
+        JPk4NZGu9oZYO9vBMhAytazT69l8fjVfLBYJqJ0i046Vnsez8eV8eiCUldOSoljC7wwA4CW9rTar
+        6Fks4XJ0rNQUI5YklqcmABGcaSsCY9SR0bIY9aB0lskmubcg0VrH4IN70ooA7Q4cVxRA28KFGtst
+        ACNwRcAYNyANYTA7iIxMXZ2ePUkmBYW2aABt3FIAtAqUo2gvGAL9aXQgQKV0y4hmyD+BW4iVa4w6
+        6ehoUfKR7cCgJnf2zq7TP6uELOFHRSDRa0YDroB1QCsJdIRvGHScDFcPVDQRW8ttY8wASC4kMcn0
+        +wOyP9lsXOmDe4j/jIpCWx2rPBBGZ1tLIzsvErrPAO7TOZuzCwkfXO05Z7eh9N10vuj4RJ+cHp1N
+        DyA7RtPX300PITjnyxUxahMHgRASZUWqH+3Tg43SbgBkg63/V/Mad7e5tuVb6HtASvJMKveBlJbn
+        G/dtgR5Tsl5vO7mcBItI4UlLyllTaC+hqMDGdNEXcReZ6rzQtqTgg075by+Z7bO/AAAA//8DAI9H
+        rN32AwAA
+    headers:
+      CF-RAY:
+      - 93c2407d5cfaface-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 07 May 2025 16:56:41 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=g.ZMxB8fB7ZSkwD6w5ws93pGGw6nEi3uFVh.JDp2OOU-1746637001-1.0.1.1-59mPPW0bDWyD6ngFx6m9LdHurrdN9Kaem.eFcKAwWp_H_4kabp2CzCRiEaW2QhRYYPWE6fZPgqWU8amQtZqpRZHtEjTyoL8t6UtyzyTCoAQ;
+        path=/; expires=Wed, 07-May-25 17:26:41 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=WOtfHIloFTPkupN1gC2z.3cExzObgfz.p4fXYpCK0aI-1746637001631-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '2084'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '2086'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '1000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '999805'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 11ms
+      x-request-id:
+      - req_1ff0f0c079f8e7f5feb17fe762b5e40a
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_lite_agent_structured_output.yaml

@@ -16,7 +16,7 @@ interactions:
       answer MUST contain all the information requested in the following format: {\n  \"summary\":
       str,\n  \"confidence\": int\n}\n\nIMPORTANT: Ensure the final output does not
       include any code block markers like ```json or ```python."}, {"role": "user",
-      "content": "What is the population of Tokyo? Return your strucutred output in
+      "content": "What is the population of Tokyo? Return your structured output in
       JSON format with the following fields: summary, confidence"}], "model": "gpt-4o-mini",
       "stop": []}'
     headers:

tests/cassettes/test_task_interpolation_with_hyphens.yaml

@@ -0,0 +1,121 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
+      an expert researcher, specialized in technology, software engineering, AI and
+      startups. You work as a freelancer and is now working on doing research and
+      analysis for a new customer.\nYour personal goal is: be an assistant that responds
+      with say hello world\nTo give my best complete final answer to the task respond
+      using the exact following format:\n\nThought: I now can give a great answer\nFinal
+      Answer: Your final answer must be the great and the most complete as possible,
+      it must be outcome described.\n\nI MUST use these formats, my job depends on
+      it!"}, {"role": "user", "content": "\nCurrent Task: be an assistant that responds
+      with say hello world\n\nThis is the expected criteria for your final answer:
+      The response should be addressing: say hello world\nyou MUST return the actual
+      complete content as the final answer, not a summary.\n\nBegin! This is VERY
+      important to you, use the tools available and give your best Final Answer, your
+      job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1108'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4xSTW/UMBC951cMPicoScMu3RuIooUDcOOrVeS1J4mp4zG2sy2q9r9XTrqbtBSJ
+        iyX7zXt+b2buEgCmJNsAEx0Porc6e/vt4nf3xVxweVZ+3v/Q17fF9+pjs92+O//0iqWRQbtfKMKR
+        9VJQbzUGRWaChUMeMKoW62pdropVfjYCPUnUkdbakFWU9cqorMzLKsvXWfH6gd2REujZBn4mAAB3
+        4xl9Gom3bAN5enzp0XveItucigCYIx1fGPde+cBNYOkMCjIBzWj9Axi6AcENtGqPwKGNtoEbf4MO
+        4NK8V4ZreDPeN7BFrSmFr+S0fLGUdNgMnsdYZtB6AXBjKPDYljHM1QNyONnX1FpHO/+EyhpllO9q
+        h9yTiVZ9IMtG9JAAXI1tGh4lZ9ZRb0Md6BrH78p8NemxeTozWhzBQIHrBass02f0aomBK+0XjWaC
+        iw7lTJ2nwgepaAEki9R/u3lOe0quTPs/8jMgBNqAsrYOpRKPE89lDuPy/qvs1OXRMPPo9kpgHRS6
+        OAmJDR/0tFLM//EB+7pRpkVnnZr2qrH1utjl5bo6bzhLDsk9AAAA//8DAAxaM/dlAwAA
+    headers:
+      CF-RAY:
+      - 93fdd19cdbfb6428-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 14 May 2025 22:26:43 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=eCtOgOCsKt_ybdNPdtFAocCmuQbNltR52chaHVe7Y_Q-1747261603-1.0.1.1-827eoA7wHS5SOkTsTqoMq6OSioi0VznQBVjvmabNSVX1bf5PpWZvblw58iggZ_wyKDB0EuVoeLKFspgBJa0kuQYR17hu43Y2C14sgdvOXIE;
+        path=/; expires=Wed, 14-May-25 22:56:43 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=QUa5MnypdaVxO826bwdQaN4G6CBEV8HYVV.7OLF.qvQ-1747261603742-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '307'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '309'
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999757'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_61d9066e0258b7095517f9f9c01d38e9
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cli/cli_test.py

@@ -18,6 +18,7 @@ from crewai.cli.cli import (
     train,
     version,
 )
+from crewai.crew import Crew
 
 
 @pytest.fixture
@@ -55,81 +56,143 @@ def test_train_invalid_string_iterations(train_crew, runner):
     )
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_all_memories(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+@pytest.fixture
+def mock_crew():
+    _mock = mock.Mock(spec=Crew, name="test_crew")
+    _mock.name = "test_crew"
+    return _mock
+
+
+@pytest.fixture
+def mock_get_crews(mock_crew):
+    with mock.patch(
+        "crewai.cli.reset_memories_command.get_crews", return_value=[mock_crew]
+    ) as mock_get_crew:
+        yield mock_get_crew
+
+
+def test_reset_all_memories(mock_get_crews, runner):
     result = runner.invoke(reset_memories, ["-a"])
 
-    mock_crew.reset_memories.assert_called_once_with(command_type="all")
-    assert result.output == "All memories have been reset.\n"
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_called_once_with(command_type="all")
+        assert (
+            f"[Crew ({crew.name})] Reset memories command has been completed."
+            in result.output
+        )
+        call_count += 1
+
+    assert call_count == 1, "reset_memories should have been called once"
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_short_term_memories(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+def test_reset_short_term_memories(mock_get_crews, runner):
     result = runner.invoke(reset_memories, ["-s"])
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_called_once_with(command_type="short")
+        assert (
+            f"[Crew ({crew.name})] Short term memory has been reset." in result.output
+        )
+        call_count += 1
 
-    mock_crew.reset_memories.assert_called_once_with(command_type="short")
-    assert result.output == "Short term memory has been reset.\n"
+    assert call_count == 1, "reset_memories should have been called once"
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_entity_memories(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+def test_reset_entity_memories(mock_get_crews, runner):
     result = runner.invoke(reset_memories, ["-e"])
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_called_once_with(command_type="entity")
+        assert f"[Crew ({crew.name})] Entity memory has been reset." in result.output
+        call_count += 1
 
-    mock_crew.reset_memories.assert_called_once_with(command_type="entity")
-    assert result.output == "Entity memory has been reset.\n"
+    assert call_count == 1, "reset_memories should have been called once"
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_long_term_memories(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+def test_reset_long_term_memories(mock_get_crews, runner):
     result = runner.invoke(reset_memories, ["-l"])
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_called_once_with(command_type="long")
+        assert f"[Crew ({crew.name})] Long term memory has been reset." in result.output
+        call_count += 1
 
-    mock_crew.reset_memories.assert_called_once_with(command_type="long")
-    assert result.output == "Long term memory has been reset.\n"
+    assert call_count == 1, "reset_memories should have been called once"
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_kickoff_outputs(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+def test_reset_kickoff_outputs(mock_get_crews, runner):
     result = runner.invoke(reset_memories, ["-k"])
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_called_once_with(command_type="kickoff_outputs")
+        assert (
+            f"[Crew ({crew.name})] Latest Kickoff outputs stored has been reset."
+            in result.output
+        )
+        call_count += 1
 
-    mock_crew.reset_memories.assert_called_once_with(command_type="kickoff_outputs")
-    assert result.output == "Latest Kickoff outputs stored has been reset.\n"
+    assert call_count == 1, "reset_memories should have been called once"
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_multiple_memory_flags(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+def test_reset_multiple_memory_flags(mock_get_crews, runner):
     result = runner.invoke(reset_memories, ["-s", "-l"])
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_has_calls(
+            [mock.call(command_type="long"), mock.call(command_type="short")]
+        )
+        assert (
+            f"[Crew ({crew.name})] Long term memory has been reset.\n"
+            f"[Crew ({crew.name})] Short term memory has been reset.\n" in result.output
+        )
+        call_count += 1
 
-    # Check that reset_memories was called twice with the correct arguments
-    assert mock_crew.reset_memories.call_count == 2
-    mock_crew.reset_memories.assert_has_calls(
-        [mock.call(command_type="long"), mock.call(command_type="short")]
-    )
-    assert (
-        result.output
-        == "Long term memory has been reset.\nShort term memory has been reset.\n"
-    )
+    assert call_count == 1, "reset_memories should have been called once"
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_knowledge(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+def test_reset_knowledge(mock_get_crews, runner):
+    result = runner.invoke(reset_memories, ["--knowledge"])
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_called_once_with(command_type="knowledge")
+        assert f"[Crew ({crew.name})] Knowledge has been reset." in result.output
+        call_count += 1
+
+    assert call_count == 1, "reset_memories should have been called once"
+
+
+def test_reset_agent_knowledge(mock_get_crews, runner):
+    result = runner.invoke(reset_memories, ["--agent-knowledge"])
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_called_once_with(command_type="agent_knowledge")
+        assert f"[Crew ({crew.name})] Agents knowledge has been reset." in result.output
+        call_count += 1
+
+    assert call_count == 1, "reset_memories should have been called once"
+
+
+def test_reset_memory_from_many_crews(mock_get_crews, runner):
+    crews = []
+    for crew_id in ["id-1234", "id-5678"]:
+        mock_crew = mock.Mock(spec=Crew)
+        mock_crew.name = None
+        mock_crew.id = crew_id
+        crews.append(mock_crew)
+
+    mock_get_crews.return_value = crews
+
+    # Run the command
     result = runner.invoke(reset_memories, ["--knowledge"])
 
-    mock_crew.reset_memories.assert_called_once_with(command_type="knowledge")
-    assert result.output == "Knowledge has been reset.\n"
+    call_count = 0
+    for crew in crews:
+        call_count += 1
+        crew.reset_memories.assert_called_once_with(command_type="knowledge")
+        assert f"[Crew ({crew.id})] Knowledge has been reset." in result.output
+
+    assert call_count == 2, "reset_memories should have been called twice"
 
 
 def test_reset_no_memory_flags(runner):

tests/cli/tools/test_main.py

@@ -3,12 +3,13 @@ import tempfile
 import unittest
 import unittest.mock
 from contextlib import contextmanager
-from io import StringIO
 from unittest import mock
 from unittest.mock import MagicMock, patch
 
+import pytest
 from pytest import raises
 
+from crewai.cli.authentication.utils import TokenManager
 from crewai.cli.tools.main import ToolCommand
 
 
@@ -23,17 +24,20 @@ def in_temp_dir():
             os.chdir(original_dir)
 
 
-@patch("crewai.cli.tools.main.subprocess.run")
-def test_create_success(mock_subprocess):
-    with in_temp_dir():
-        tool_command = ToolCommand()
+@pytest.fixture
+def tool_command():
+    TokenManager().save_tokens("test-token", 36000)
+    tool_command = ToolCommand()
+    with patch.object(tool_command, "login"):
+        yield tool_command
 
-        with (
-            patch.object(tool_command, "login") as mock_login,
-            patch("sys.stdout", new=StringIO()) as fake_out,
-        ):
-            tool_command.create("test-tool")
-            output = fake_out.getvalue()
+
+@patch("crewai.cli.tools.main.subprocess.run")
+def test_create_success(mock_subprocess, capsys, tool_command):
+    with in_temp_dir():
+        tool_command.create("test-tool")
+        output = capsys.readouterr().out
+        assert "Creating custom tool test_tool..." in output
 
         assert os.path.isdir("test_tool")
         assert os.path.isfile(os.path.join("test_tool", "README.md"))
@@ -47,15 +51,12 @@ def test_create_success(mock_subprocess):
             content = f.read()
             assert "class TestTool" in content
 
-        mock_login.assert_called_once()
         mock_subprocess.assert_called_once_with(["git", "init"], check=True)
 
-        assert "Creating custom tool test_tool..." in output
-
 
 @patch("crewai.cli.tools.main.subprocess.run")
 @patch("crewai.cli.plus_api.PlusAPI.get_tool")
-def test_install_success(mock_get, mock_subprocess_run):
+def test_install_success(mock_get, mock_subprocess_run, capsys, tool_command):
     mock_get_response = MagicMock()
     mock_get_response.status_code = 200
     mock_get_response.json.return_value = {
@@ -65,11 +66,9 @@ def test_install_success(mock_get, mock_subprocess_run):
     mock_get.return_value = mock_get_response
     mock_subprocess_run.return_value = MagicMock(stderr=None)
 
-    tool_command = ToolCommand()
-
-    with patch("sys.stdout", new=StringIO()) as fake_out:
-        tool_command.install("sample-tool")
-        output = fake_out.getvalue()
+    tool_command.install("sample-tool")
+    output = capsys.readouterr().out
+    assert "Successfully installed sample-tool" in output
 
     mock_get.assert_has_calls([mock.call("sample-tool"), mock.call().json()])
     mock_subprocess_run.assert_any_call(
@@ -86,54 +85,42 @@ def test_install_success(mock_get, mock_subprocess_run):
         env=unittest.mock.ANY,
     )
 
-    assert "Successfully installed sample-tool" in output
-
 
 @patch("crewai.cli.plus_api.PlusAPI.get_tool")
-def test_install_tool_not_found(mock_get):
+def test_install_tool_not_found(mock_get, capsys, tool_command):
     mock_get_response = MagicMock()
     mock_get_response.status_code = 404
     mock_get.return_value = mock_get_response
 
-    tool_command = ToolCommand()
-
-    with patch("sys.stdout", new=StringIO()) as fake_out:
-        try:
-            tool_command.install("non-existent-tool")
-        except SystemExit:
-            pass
-        output = fake_out.getvalue()
+    with raises(SystemExit):
+        tool_command.install("non-existent-tool")
+    output = capsys.readouterr().out
+    assert "No tool found with this name" in output
 
     mock_get.assert_called_once_with("non-existent-tool")
-    assert "No tool found with this name" in output
 
 
 @patch("crewai.cli.plus_api.PlusAPI.get_tool")
-def test_install_api_error(mock_get):
+def test_install_api_error(mock_get, capsys, tool_command):
     mock_get_response = MagicMock()
     mock_get_response.status_code = 500
     mock_get.return_value = mock_get_response
 
-    tool_command = ToolCommand()
-
-    with patch("sys.stdout", new=StringIO()) as fake_out:
-        try:
-            tool_command.install("error-tool")
-        except SystemExit:
-            pass
-        output = fake_out.getvalue()
+    with raises(SystemExit):
+        tool_command.install("error-tool")
+    output = capsys.readouterr().out
+    assert "Failed to get tool details" in output
 
     mock_get.assert_called_once_with("error-tool")
-    assert "Failed to get tool details" in output
 
 
 @patch("crewai.cli.tools.main.git.Repository.is_synced", return_value=False)
-def test_publish_when_not_in_sync(mock_is_synced):
-    with patch("sys.stdout", new=StringIO()) as fake_out, raises(SystemExit):
-        tool_command = ToolCommand()
+def test_publish_when_not_in_sync(mock_is_synced, capsys, tool_command):
+    with raises(SystemExit):
         tool_command.publish(is_public=True)
 
-    assert "Local changes need to be resolved before publishing" in fake_out.getvalue()
+    output = capsys.readouterr().out
+    assert "Local changes need to be resolved before publishing" in output
 
 
 @patch("crewai.cli.tools.main.get_project_name", return_value="sample-tool")
@@ -157,13 +144,13 @@ def test_publish_when_not_in_sync_and_force(
     mock_get_project_description,
     mock_get_project_version,
     mock_get_project_name,
+    tool_command,
 ):
     mock_publish_response = MagicMock()
     mock_publish_response.status_code = 200
     mock_publish_response.json.return_value = {"handle": "sample-tool"}
     mock_publish.return_value = mock_publish_response
 
-    tool_command = ToolCommand()
     tool_command.publish(is_public=True, force=True)
 
     mock_get_project_name.assert_called_with(require=True)
@@ -205,13 +192,13 @@ def test_publish_success(
     mock_get_project_description,
     mock_get_project_version,
     mock_get_project_name,
+    tool_command,
 ):
     mock_publish_response = MagicMock()
     mock_publish_response.status_code = 200
     mock_publish_response.json.return_value = {"handle": "sample-tool"}
     mock_publish.return_value = mock_publish_response
 
-    tool_command = ToolCommand()
     tool_command.publish(is_public=True)
 
     mock_get_project_name.assert_called_with(require=True)
@@ -251,25 +238,22 @@ def test_publish_failure(
     mock_get_project_description,
     mock_get_project_version,
     mock_get_project_name,
+    capsys,
+    tool_command,
 ):
     mock_publish_response = MagicMock()
     mock_publish_response.status_code = 422
     mock_publish_response.json.return_value = {"name": ["is already taken"]}
     mock_publish.return_value = mock_publish_response
 
-    tool_command = ToolCommand()
-
-    with patch("sys.stdout", new=StringIO()) as fake_out:
-        try:
-            tool_command.publish(is_public=True)
-        except SystemExit:
-            pass
-        output = fake_out.getvalue()
-
-    mock_publish.assert_called_once()
+    with raises(SystemExit):
+        tool_command.publish(is_public=True)
+    output = capsys.readouterr().out
     assert "Failed to complete operation" in output
     assert "Name is already taken" in output
 
+    mock_publish.assert_called_once()
+
 
 @patch("crewai.cli.tools.main.get_project_name", return_value="sample-tool")
 @patch("crewai.cli.tools.main.get_project_version", return_value="1.0.0")
@@ -290,6 +274,8 @@ def test_publish_api_error(
     mock_get_project_description,
     mock_get_project_version,
     mock_get_project_name,
+    capsys,
+    tool_command,
 ):
     mock_response = MagicMock()
     mock_response.status_code = 500
@@ -297,14 +283,9 @@ def test_publish_api_error(
     mock_response.ok = False
     mock_publish.return_value = mock_response
 
-    tool_command = ToolCommand()
-
-    with patch("sys.stdout", new=StringIO()) as fake_out:
-        try:
-            tool_command.publish(is_public=True)
-        except SystemExit:
-            pass
-        output = fake_out.getvalue()
+    with raises(SystemExit):
+        tool_command.publish(is_public=True)
+    output = capsys.readouterr().out
+    assert "Request to Enterprise API failed" in output
 
     mock_publish.assert_called_once()
-    assert "Request to Enterprise API failed" in output

tests/crew_test.py

@@ -2,21 +2,19 @@
 
 import hashlib
 import json
-import os
-import tempfile
 from concurrent.futures import Future
 from unittest import mock
-from unittest.mock import MagicMock, patch
+from unittest.mock import ANY, MagicMock, patch
 
 import pydantic_core
 import pytest
 
 from crewai.agent import Agent
 from crewai.agents import CacheHandler
-from crewai.agents.cache import CacheHandler
-from crewai.agents.crew_agent_executor import CrewAgentExecutor
 from crewai.crew import Crew
 from crewai.crews.crew_output import CrewOutput
+from crewai.flow import Flow, start
+from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.llm import LLM
 from crewai.memory.contextual.contextual_memory import ContextualMemory
@@ -42,29 +40,38 @@ from crewai.utilities.events.event_listener import EventListener
 from crewai.utilities.rpm_controller import RPMController
 from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
 
-ceo = Agent(
-    role="CEO",
-    goal="Make sure the writers in your company produce amazing content.",
-    backstory="You're an long time CEO of a content creation agency with a Senior Writer on the team. You're now working on a new project and want to make sure the content produced is amazing.",
-    allow_delegation=True,
-)
 
-researcher = Agent(
-    role="Researcher",
-    goal="Make the best research and analysis on content about AI and AI agents",
-    backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
-    allow_delegation=False,
-)
-
-writer = Agent(
-    role="Senior Writer",
-    goal="Write the best content about AI and AI agents.",
-    backstory="You're a senior writer, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer.",
-    allow_delegation=False,
-)
+@pytest.fixture
+def ceo():
+    return Agent(
+        role="CEO",
+        goal="Make sure the writers in your company produce amazing content.",
+        backstory="You're an long time CEO of a content creation agency with a Senior Writer on the team. You're now working on a new project and want to make sure the content produced is amazing.",
+        allow_delegation=True,
+    )
 
 
-def test_crew_with_only_conditional_tasks_raises_error():
+@pytest.fixture
+def researcher():
+    return Agent(
+        role="Researcher",
+        goal="Make the best research and analysis on content about AI and AI agents",
+        backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
+        allow_delegation=False,
+    )
+
+
+@pytest.fixture
+def writer():
+    return Agent(
+        role="Senior Writer",
+        goal="Write the best content about AI and AI agents.",
+        backstory="You're a senior writer, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer.",
+        allow_delegation=False,
+    )
+
+
+def test_crew_with_only_conditional_tasks_raises_error(researcher):
     """Test that creating a crew with only conditional tasks raises an error."""
 
     def condition_func(task_output: TaskOutput) -> bool:
@@ -146,7 +153,9 @@ def test_crew_config_conditional_requirement():
     ]
 
 
-def test_async_task_cannot_include_sequential_async_tasks_in_context():
+def test_async_task_cannot_include_sequential_async_tasks_in_context(
+    researcher, writer
+):
     task1 = Task(
         description="Task 1",
         async_execution=True,
@@ -194,7 +203,7 @@ def test_async_task_cannot_include_sequential_async_tasks_in_context():
         pytest.fail("Unexpected ValidationError raised")
 
 
-def test_context_no_future_tasks():
+def test_context_no_future_tasks(researcher, writer):
     task2 = Task(
         description="Task 2",
         expected_output="output",
@@ -258,7 +267,7 @@ def test_crew_config_with_wrong_keys():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_creation():
+def test_crew_creation(researcher, writer):
     tasks = [
         Task(
             description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
@@ -290,7 +299,7 @@ def test_crew_creation():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_sync_task_execution():
+def test_sync_task_execution(researcher, writer):
     from unittest.mock import patch
 
     tasks = [
@@ -331,7 +340,7 @@ def test_sync_task_execution():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_hierarchical_process():
+def test_hierarchical_process(researcher, writer):
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -352,7 +361,7 @@ def test_hierarchical_process():
     )
 
 
-def test_manager_llm_requirement_for_hierarchical_process():
+def test_manager_llm_requirement_for_hierarchical_process(researcher, writer):
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -367,7 +376,7 @@ def test_manager_llm_requirement_for_hierarchical_process():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_manager_agent_delegating_to_assigned_task_agent():
+def test_manager_agent_delegating_to_assigned_task_agent(researcher, writer):
     """
     Test that the manager agent delegates to the assigned task agent.
     """
@@ -419,7 +428,7 @@ def test_manager_agent_delegating_to_assigned_task_agent():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_manager_agent_delegating_to_all_agents():
+def test_manager_agent_delegating_to_all_agents(researcher, writer):
     """
     Test that the manager agent delegates to all agents when none are specified.
     """
@@ -529,7 +538,7 @@ def test_manager_agent_delegates_with_varied_role_cases():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_with_delegating_agents():
+def test_crew_with_delegating_agents(ceo, writer):
     tasks = [
         Task(
             description="Produce and amazing 1 paragraph draft of an article about AI Agents.",
@@ -553,7 +562,7 @@ def test_crew_with_delegating_agents():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_with_delegating_agents_should_not_override_task_tools():
+def test_crew_with_delegating_agents_should_not_override_task_tools(ceo, writer):
     from typing import Type
 
     from pydantic import BaseModel, Field
@@ -615,7 +624,7 @@ def test_crew_with_delegating_agents_should_not_override_task_tools():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_with_delegating_agents_should_not_override_agent_tools():
+def test_crew_with_delegating_agents_should_not_override_agent_tools(ceo, writer):
     from typing import Type
 
     from pydantic import BaseModel, Field
@@ -679,7 +688,7 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_task_tools_override_agent_tools():
+def test_task_tools_override_agent_tools(researcher):
     from typing import Type
 
     from pydantic import BaseModel, Field
@@ -734,7 +743,7 @@ def test_task_tools_override_agent_tools():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_task_tools_override_agent_tools_with_allow_delegation():
+def test_task_tools_override_agent_tools_with_allow_delegation(researcher, writer):
     """
     Test that task tools override agent tools while preserving delegation tools when allow_delegation=True
     """
@@ -817,7 +826,7 @@ def test_task_tools_override_agent_tools_with_allow_delegation():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_verbose_output(capsys):
+def test_crew_verbose_output(researcher, writer, capsys):
     tasks = [
         Task(
             description="Research AI advancements.",
@@ -877,7 +886,7 @@ def test_crew_verbose_output(capsys):
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_cache_hitting_between_agents():
+def test_cache_hitting_between_agents(researcher, writer, ceo):
     from unittest.mock import call, patch
 
     from crewai.tools import tool
@@ -1050,7 +1059,7 @@ def test_agents_rpm_is_never_set_if_crew_max_RPM_is_not_set():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_sequential_async_task_execution_completion():
+def test_sequential_async_task_execution_completion(researcher, writer):
     list_ideas = Task(
         description="Give me a list of 5 interesting ideas to explore for an article, what makes them unique and interesting.",
         expected_output="Bullet point list of 5 important events.",
@@ -1204,7 +1213,7 @@ async def test_crew_async_kickoff():
 
 @pytest.mark.asyncio
 @pytest.mark.vcr(filter_headers=["authorization"])
-async def test_async_task_execution_call_count():
+async def test_async_task_execution_call_count(researcher, writer):
     from unittest.mock import MagicMock, patch
 
     list_ideas = Task(
@@ -1707,7 +1716,7 @@ def test_agents_do_not_get_delegation_tools_with_there_is_only_one_agent():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_sequential_crew_creation_tasks_without_agents():
+def test_sequential_crew_creation_tasks_without_agents(researcher):
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -1757,7 +1766,7 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_hierarchical_crew_creation_tasks_with_agents():
+def test_hierarchical_crew_creation_tasks_with_agents(researcher, writer):
     """
     Agents are not required for tasks in a hierarchical process but sometimes they are still added
     This test makes sure that the manager still delegates the task to the agent even if the agent is passed in the task
@@ -1810,7 +1819,7 @@ def test_hierarchical_crew_creation_tasks_with_agents():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_hierarchical_crew_creation_tasks_with_async_execution():
+def test_hierarchical_crew_creation_tasks_with_async_execution(researcher, writer, ceo):
     """
     Tests that async tasks in hierarchical crews are handled correctly with proper delegation tools
     """
@@ -1867,7 +1876,7 @@ def test_hierarchical_crew_creation_tasks_with_async_execution():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_hierarchical_crew_creation_tasks_with_sync_last():
+def test_hierarchical_crew_creation_tasks_with_sync_last(researcher, writer, ceo):
     """
     Agents are not required for tasks in a hierarchical process but sometimes they are still added
     This test makes sure that the manager still delegates the task to the agent even if the agent is passed in the task
@@ -2153,7 +2162,6 @@ def test_tools_with_custom_caching():
     with patch.object(
         CacheHandler, "add", wraps=crew._cache_handler.add
     ) as add_to_cache:
-
         result = crew.kickoff()
 
         # Check that add_to_cache was called exactly twice
@@ -2170,7 +2178,7 @@ def test_tools_with_custom_caching():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_conditional_task_uses_last_output():
+def test_conditional_task_uses_last_output(researcher, writer):
     """Test that conditional tasks use the last task output for condition evaluation."""
     task1 = Task(
         description="First task",
@@ -2244,7 +2252,7 @@ def test_conditional_task_uses_last_output():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_conditional_tasks_result_collection():
+def test_conditional_tasks_result_collection(researcher, writer):
     """Test that task outputs are properly collected based on execution status."""
     task1 = Task(
         description="Normal task that always executes",
@@ -2325,7 +2333,7 @@ def test_conditional_tasks_result_collection():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_multiple_conditional_tasks():
+def test_multiple_conditional_tasks(researcher, writer):
     """Test that having multiple conditional tasks in sequence works correctly."""
     task1 = Task(
         description="Initial research task",
@@ -2560,7 +2568,7 @@ def test_disabled_memory_using_contextual_memory():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_log_file_output(tmp_path):
+def test_crew_log_file_output(tmp_path, researcher):
     test_file = tmp_path / "logs.txt"
     tasks = [
         Task(
@@ -2658,7 +2666,7 @@ def test_crew_output_file_validation_failures():
         Crew(agents=[agent], tasks=[task]).kickoff()
 
 
-def test_manager_agent():
+def test_manager_agent(researcher, writer):
     from unittest.mock import patch
 
     task = Task(
@@ -2696,7 +2704,7 @@ def test_manager_agent():
         mock_execute_sync.assert_called()
 
 
-def test_manager_agent_in_agents_raises_exception():
+def test_manager_agent_in_agents_raises_exception(researcher, writer):
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -2718,7 +2726,7 @@ def test_manager_agent_in_agents_raises_exception():
         )
 
 
-def test_manager_agent_with_tools_raises_exception():
+def test_manager_agent_with_tools_raises_exception(researcher, writer):
     from crewai.tools import tool
 
     @tool
@@ -2755,7 +2763,7 @@ def test_manager_agent_with_tools_raises_exception():
 @patch("crewai.crew.TaskEvaluator")
 @patch("crewai.crew.Crew.copy")
 def test_crew_train_success(
-    copy_mock, task_evaluator, crew_training_handler, kickoff_mock
+    copy_mock, task_evaluator, crew_training_handler, kickoff_mock, researcher, writer
 ):
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
@@ -2831,7 +2839,7 @@ def test_crew_train_success(
     assert isinstance(received_events[1], CrewTrainCompletedEvent)
 
 
-def test_crew_train_error():
+def test_crew_train_error(researcher, writer):
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -2850,7 +2858,7 @@ def test_crew_train_error():
         )
 
 
-def test__setup_for_training():
+def test__setup_for_training(researcher, writer):
     researcher.allow_delegation = True
     writer.allow_delegation = True
     agents = [researcher, writer]
@@ -2881,7 +2889,7 @@ def test__setup_for_training():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_replay_feature():
+def test_replay_feature(researcher, writer):
     list_ideas = Task(
         description="Generate a list of 5 interesting ideas to explore for an article, where each bulletpoint is under 15 words.",
         expected_output="Bullet point list of 5 important events. No additional commentary.",
@@ -2918,7 +2926,7 @@ def test_replay_feature():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_replay_error():
+def test_crew_replay_error(researcher, writer):
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -3130,6 +3138,30 @@ def test_replay_with_context():
         assert crew.tasks[1].context[0].output.raw == "context raw output"
 
 
+def test_replay_with_context_set_to_nullable():
+    agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
+    task1 = Task(
+        description="Context Task", expected_output="Say Task Output", agent=agent
+    )
+    task2 = Task(
+        description="Test Task", expected_output="Say Hi", agent=agent, context=[]
+    )
+    task3 = Task(
+        description="Test Task 3", expected_output="Say Hi", agent=agent, context=None
+    )
+
+    crew = Crew(agents=[agent], tasks=[task1, task2, task3], process=Process.sequential)
+    with patch("crewai.task.Task.execute_sync") as mock_execute_task:
+        mock_execute_task.return_value = TaskOutput(
+            description="Test Task Output",
+            raw="test raw output",
+            agent="test_agent",
+        )
+        crew.kickoff()
+
+    mock_execute_task.assert_called_with(agent=ANY, context="", tools=ANY)
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_replay_with_invalid_task_id():
     agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
@@ -3314,7 +3346,7 @@ def test_replay_setup_context():
         assert crew.tasks[1].prompt_context == "context raw output"
 
 
-def test_key():
+def test_key(researcher, writer):
     tasks = [
         Task(
             description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
@@ -3383,7 +3415,9 @@ def test_key_with_interpolated_inputs():
     assert crew.key == curr_key
 
 
-def test_conditional_task_requirement_breaks_when_singular_conditional_task():
+def test_conditional_task_requirement_breaks_when_singular_conditional_task(
+    researcher, writer
+):
     def condition_fn(output) -> bool:
         return output.raw.startswith("Andrew Ng has!!")
 
@@ -3401,7 +3435,7 @@ def test_conditional_task_requirement_breaks_when_singular_conditional_task():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_conditional_task_last_task_when_conditional_is_true():
+def test_conditional_task_last_task_when_conditional_is_true(researcher, writer):
     def condition_fn(output) -> bool:
         return True
 
@@ -3428,7 +3462,7 @@ def test_conditional_task_last_task_when_conditional_is_true():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_conditional_task_last_task_when_conditional_is_false():
+def test_conditional_task_last_task_when_conditional_is_false(researcher, writer):
     def condition_fn(output) -> bool:
         return False
 
@@ -3452,7 +3486,7 @@ def test_conditional_task_last_task_when_conditional_is_false():
     assert result.raw == "Hi"
 
 
-def test_conditional_task_requirement_breaks_when_task_async():
+def test_conditional_task_requirement_breaks_when_task_async(researcher, writer):
     def my_condition(context):
         return context.get("some_value") > 10
 
@@ -3477,7 +3511,7 @@ def test_conditional_task_requirement_breaks_when_task_async():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_conditional_should_skip():
+def test_conditional_should_skip(researcher, writer):
     task1 = Task(description="Return hello", expected_output="say hi", agent=researcher)
 
     condition_mock = MagicMock(return_value=False)
@@ -3509,7 +3543,7 @@ def test_conditional_should_skip():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_conditional_should_execute():
+def test_conditional_should_execute(researcher, writer):
     task1 = Task(description="Return hello", expected_output="say hi", agent=researcher)
 
     condition_mock = MagicMock(
@@ -3542,7 +3576,7 @@ def test_conditional_should_execute():
 @mock.patch("crewai.crew.CrewEvaluator")
 @mock.patch("crewai.crew.Crew.copy")
 @mock.patch("crewai.crew.Crew.kickoff")
-def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
+def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator, researcher):
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -3592,7 +3626,7 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_hierarchical_verbose_manager_agent():
+def test_hierarchical_verbose_manager_agent(researcher, writer):
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -3613,7 +3647,7 @@ def test_hierarchical_verbose_manager_agent():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_hierarchical_verbose_false_manager_agent():
+def test_hierarchical_verbose_false_manager_agent(researcher, writer):
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -4186,7 +4220,7 @@ def test_before_kickoff_without_inputs():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_with_knowledge_sources_works_with_copy():
+def test_crew_with_knowledge_sources_works_with_copy(researcher, writer):
     content = "Brandon's favorite color is red and he likes Mexican food."
     string_source = StringKnowledgeSource(content=content)
 
@@ -4195,7 +4229,6 @@ def test_crew_with_knowledge_sources_works_with_copy():
         tasks=[Task(description="test", expected_output="test", agent=researcher)],
         knowledge_sources=[string_source],
     )
-
     crew_copy = crew.copy()
 
     assert crew_copy.knowledge_sources == crew.knowledge_sources
@@ -4339,3 +4372,197 @@ def test_crew_copy_with_memory():
             raise e  # Re-raise other validation errors
     except Exception as e:
         pytest.fail(f"Copying crew raised an unexpected exception: {e}")
+
+
+def test_sets_parent_flow_when_outside_flow(researcher, writer):
+    crew = Crew(
+        agents=[researcher, writer],
+        process=Process.sequential,
+        tasks=[
+            Task(description="Task 1", expected_output="output", agent=researcher),
+            Task(description="Task 2", expected_output="output", agent=writer),
+        ],
+    )
+    assert crew.parent_flow is None
+
+
+def test_sets_parent_flow_when_inside_flow(researcher, writer):
+    class MyFlow(Flow):
+        @start()
+        def start(self):
+            return Crew(
+                agents=[researcher, writer],
+                process=Process.sequential,
+                tasks=[
+                    Task(
+                        description="Task 1", expected_output="output", agent=researcher
+                    ),
+                    Task(description="Task 2", expected_output="output", agent=writer),
+                ],
+            )
+
+    flow = MyFlow()
+    result = flow.kickoff()
+    assert result.parent_flow is flow
+
+
+def test_reset_knowledge_with_no_crew_knowledge(researcher,writer):
+    crew = Crew(
+        agents=[researcher, writer],
+        process=Process.sequential,
+        tasks=[
+            Task(description="Task 1", expected_output="output", agent=researcher),
+            Task(description="Task 2", expected_output="output", agent=writer),
+        ]
+    )
+
+    with pytest.raises(RuntimeError) as excinfo:
+        crew.reset_memories(command_type='knowledge')
+        
+        # Optionally, you can also check the error message
+    assert "Crew Knowledge and Agent Knowledge memory system is not initialized" in str(excinfo.value)  # Replace with the expected message
+
+
+def test_reset_knowledge_with_only_crew_knowledge(researcher,writer):
+    mock_ks = MagicMock(spec=Knowledge)
+
+    with patch.object(Crew,'reset_knowledge') as mock_reset_agent_knowledge:
+        crew = Crew(
+            agents=[researcher, writer],
+            process=Process.sequential,
+            tasks=[
+                Task(description="Task 1", expected_output="output", agent=researcher),
+                Task(description="Task 2", expected_output="output", agent=writer),
+            ],
+            knowledge=mock_ks
+        )
+
+        crew.reset_memories(command_type='knowledge')
+        mock_reset_agent_knowledge.assert_called_once_with([mock_ks])
+
+
+def test_reset_knowledge_with_crew_and_agent_knowledge(researcher,writer):
+    mock_ks_crew = MagicMock(spec=Knowledge)
+    mock_ks_research = MagicMock(spec=Knowledge)
+    mock_ks_writer = MagicMock(spec=Knowledge)
+
+    researcher.knowledge = mock_ks_research
+    writer.knowledge = mock_ks_writer
+
+    with patch.object(Crew,'reset_knowledge') as mock_reset_agent_knowledge:
+        crew = Crew(
+            agents=[researcher, writer],
+            process=Process.sequential,
+            tasks=[
+                Task(description="Task 1", expected_output="output", agent=researcher),
+                Task(description="Task 2", expected_output="output", agent=writer),
+            ],
+            knowledge=mock_ks_crew
+        )
+
+        crew.reset_memories(command_type='knowledge')
+        mock_reset_agent_knowledge.assert_called_once_with([mock_ks_crew,mock_ks_research,mock_ks_writer])
+
+
+def test_reset_knowledge_with_only_agent_knowledge(researcher,writer):
+    mock_ks_research = MagicMock(spec=Knowledge)
+    mock_ks_writer = MagicMock(spec=Knowledge)
+
+    researcher.knowledge = mock_ks_research
+    writer.knowledge = mock_ks_writer
+
+    with patch.object(Crew,'reset_knowledge') as mock_reset_agent_knowledge:
+        crew = Crew(
+            agents=[researcher, writer],
+            process=Process.sequential,
+            tasks=[
+                Task(description="Task 1", expected_output="output", agent=researcher),
+                Task(description="Task 2", expected_output="output", agent=writer),
+            ],
+        )
+
+        crew.reset_memories(command_type='knowledge')
+        mock_reset_agent_knowledge.assert_called_once_with([mock_ks_research,mock_ks_writer])
+
+
+def test_reset_agent_knowledge_with_no_agent_knowledge(researcher,writer):
+    crew = Crew(
+        agents=[researcher, writer],
+        process=Process.sequential,
+        tasks=[
+            Task(description="Task 1", expected_output="output", agent=researcher),
+            Task(description="Task 2", expected_output="output", agent=writer),
+        ],
+    )
+
+    with pytest.raises(RuntimeError) as excinfo:
+        crew.reset_memories(command_type='agent_knowledge')
+    
+    # Optionally, you can also check the error message
+    assert "Agent Knowledge memory system is not initialized" in str(excinfo.value)  # Replace with the expected message
+
+
+def test_reset_agent_knowledge_with_only_crew_knowledge(researcher,writer):
+    mock_ks = MagicMock(spec=Knowledge)
+
+    crew = Crew(
+        agents=[researcher, writer],
+        process=Process.sequential,
+        tasks=[
+            Task(description="Task 1", expected_output="output", agent=researcher),
+            Task(description="Task 2", expected_output="output", agent=writer),
+        ],
+        knowledge=mock_ks
+    )
+
+    with pytest.raises(RuntimeError) as excinfo:
+        crew.reset_memories(command_type='agent_knowledge')
+    
+    # Optionally, you can also check the error message
+    assert "Agent Knowledge memory system is not initialized" in str(excinfo.value)  # Replace with the expected message
+
+
+def test_reset_agent_knowledge_with_crew_and_agent_knowledge(researcher,writer):
+    mock_ks_crew = MagicMock(spec=Knowledge)
+    mock_ks_research = MagicMock(spec=Knowledge)
+    mock_ks_writer = MagicMock(spec=Knowledge)
+
+    researcher.knowledge = mock_ks_research
+    writer.knowledge = mock_ks_writer
+
+    with patch.object(Crew,'reset_knowledge') as mock_reset_agent_knowledge:
+        crew = Crew(
+            agents=[researcher, writer],
+            process=Process.sequential,
+            tasks=[
+                Task(description="Task 1", expected_output="output", agent=researcher),
+                Task(description="Task 2", expected_output="output", agent=writer),
+            ],
+            knowledge=mock_ks_crew
+        )
+
+        crew.reset_memories(command_type='agent_knowledge')
+        mock_reset_agent_knowledge.assert_called_once_with([mock_ks_research,mock_ks_writer])
+
+
+def test_reset_agent_knowledge_with_only_agent_knowledge(researcher,writer):
+    mock_ks_research = MagicMock(spec=Knowledge)
+    mock_ks_writer = MagicMock(spec=Knowledge)
+
+    researcher.knowledge = mock_ks_research
+    writer.knowledge = mock_ks_writer
+
+    with patch.object(Crew,'reset_knowledge') as mock_reset_agent_knowledge:
+        crew = Crew(
+            agents=[researcher, writer],
+            process=Process.sequential,
+            tasks=[
+                Task(description="Task 1", expected_output="output", agent=researcher),
+                Task(description="Task 2", expected_output="output", agent=writer),
+            ],
+        )
+
+        crew.reset_memories(command_type='agent_knowledge')
+        mock_reset_agent_knowledge.assert_called_once_with([mock_ks_research,mock_ks_writer])
+
+

tests/knowledge/knowledge_test.py

@@ -547,6 +547,7 @@ def test_excel_knowledge_source(mock_vector_db, tmpdir):
     mock_vector_db.query.assert_called_once()
 
 
+@pytest.mark.vcr
 def test_docling_source(mock_vector_db):
     docling_source = CrewDoclingSource(
         file_paths=[
@@ -567,6 +568,7 @@ def test_docling_source(mock_vector_db):
     mock_vector_db.query.assert_called_once()
 
 
+@pytest.mark.vcr
 def test_multiple_docling_sources():
     urls: List[Union[Path, str]] = [
         "https://lilianweng.github.io/posts/2024-11-28-reward-hacking/",

tests/task_test.py

@@ -837,9 +837,6 @@ def test_interpolate_inputs():
 
 def test_interpolate_only():
     """Test the interpolate_only method for various scenarios including JSON structure preservation."""
-    task = Task(
-        description="Unused in this test", expected_output="Unused in this test"
-    )
 
     # Test JSON structure preservation
     json_string = '{"info": "Look at {placeholder}", "nested": {"val": "{nestedVal}"}}'
@@ -871,10 +868,6 @@ def test_interpolate_only():
 
 def test_interpolate_only_with_dict_inside_expected_output():
     """Test the interpolate_only method for various scenarios including JSON structure preservation."""
-    task = Task(
-        description="Unused in this test",
-        expected_output="Unused in this test: {questions}",
-    )
 
     json_string = '{"questions": {"main_question": "What is the user\'s name?", "secondary_question": "What is the user\'s age?"}}'
     result = interpolate_only(
@@ -1094,11 +1087,6 @@ def test_task_execution_times():
 
 
 def test_interpolate_with_list_of_strings():
-    task = Task(
-        description="Test list interpolation",
-        expected_output="List: {items}",
-    )
-
     # Test simple list of strings
     input_str = "Available items: {items}"
     inputs = {"items": ["apple", "banana", "cherry"]}
@@ -1112,11 +1100,6 @@ def test_interpolate_with_list_of_strings():
 
 
 def test_interpolate_with_list_of_dicts():
-    task = Task(
-        description="Test list of dicts interpolation",
-        expected_output="People: {people}",
-    )
-
     input_data = {
         "people": [
             {"name": "Alice", "age": 30, "skills": ["Python", "AI"]},
@@ -1137,11 +1120,6 @@ def test_interpolate_with_list_of_dicts():
 
 
 def test_interpolate_with_nested_structures():
-    task = Task(
-        description="Test nested structures",
-        expected_output="Company: {company}",
-    )
-
     input_data = {
         "company": {
             "name": "TechCorp",
@@ -1165,11 +1143,6 @@ def test_interpolate_with_nested_structures():
 
 
 def test_interpolate_with_special_characters():
-    task = Task(
-        description="Test special characters in dicts",
-        expected_output="Data: {special_data}",
-    )
-
     input_data = {
         "special_data": {
             "quotes": """This has "double" and 'single' quotes""",
@@ -1188,11 +1161,6 @@ def test_interpolate_with_special_characters():
 
 
 def test_interpolate_mixed_types():
-    task = Task(
-        description="Test mixed type interpolation",
-        expected_output="Mixed: {data}",
-    )
-
     input_data = {
         "data": {
             "name": "Test Dataset",
@@ -1214,11 +1182,6 @@ def test_interpolate_mixed_types():
 
 
 def test_interpolate_complex_combination():
-    task = Task(
-        description="Test complex combination",
-        expected_output="Report: {report}",
-    )
-
     input_data = {
         "report": [
             {
@@ -1243,11 +1206,6 @@ def test_interpolate_complex_combination():
 
 
 def test_interpolate_invalid_type_validation():
-    task = Task(
-        description="Test invalid type validation",
-        expected_output="Should never reach here",
-    )
-
     # Test with invalid top-level type
     with pytest.raises(ValueError) as excinfo:
         interpolate_only("{data}", {"data": set()})  # type: ignore we are purposely testing this failure
@@ -1268,11 +1226,6 @@ def test_interpolate_invalid_type_validation():
 
 
 def test_interpolate_custom_object_validation():
-    task = Task(
-        description="Test custom object rejection",
-        expected_output="Should never reach here",
-    )
-
     class CustomObject:
         def __init__(self, value):
             self.value = value
@@ -1304,11 +1257,6 @@ def test_interpolate_custom_object_validation():
 
 
 def test_interpolate_valid_complex_types():
-    task = Task(
-        description="Test valid complex types",
-        expected_output="Validation should pass",
-    )
-
     # Valid complex structure
     valid_data = {
         "name": "Valid Dataset",
@@ -1328,11 +1276,6 @@ def test_interpolate_valid_complex_types():
 
 
 def test_interpolate_edge_cases():
-    task = Task(
-        description="Test edge cases",
-        expected_output="Edge case handling",
-    )
-
     # Test empty dict and list
     assert interpolate_only("{}", {"data": {}}) == "{}"
     assert interpolate_only("[]", {"data": []}) == "[]"
@@ -1347,11 +1290,6 @@ def test_interpolate_edge_cases():
 
 
 def test_interpolate_valid_types():
-    task = Task(
-        description="Test valid types including null and boolean",
-        expected_output="Should pass validation",
-    )
-
     # Test with boolean and null values (valid JSON types)
     valid_data = {
         "name": "Test",
@@ -1373,11 +1311,11 @@ def test_interpolate_valid_types():
 
 def test_task_with_no_max_execution_time():
     researcher = Agent(
-    role="Researcher",
-    goal="Make the best research and analysis on content about AI and AI agents",
-    backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
-    allow_delegation=False,
-    max_execution_time=None
+        role="Researcher",
+        goal="Make the best research and analysis on content about AI and AI agents",
+        backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
+        allow_delegation=False,
+        max_execution_time=None,
     )
 
     task = Task(
@@ -1386,7 +1324,7 @@ def test_task_with_no_max_execution_time():
         agent=researcher,
     )
 
-    with patch.object(Agent, "_execute_without_timeout", return_value = "ok") as execute:
+    with patch.object(Agent, "_execute_without_timeout", return_value="ok") as execute:
         result = task.execute_sync(agent=researcher)
         assert result.raw == "ok"
         execute.assert_called_once()
@@ -1395,6 +1333,7 @@ def test_task_with_no_max_execution_time():
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_task_with_max_execution_time():
     from crewai.tools import tool
+
     """Test that execution raises TimeoutError when max_execution_time is exceeded."""
 
     @tool("what amazing tool", result_as_answer=True)
@@ -1412,7 +1351,7 @@ def test_task_with_max_execution_time():
         ),
         allow_delegation=False,
         tools=[my_tool],
-        max_execution_time=4
+        max_execution_time=4,
     )
 
     task = Task(
@@ -1428,6 +1367,7 @@ def test_task_with_max_execution_time():
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_task_with_max_execution_time_exceeded():
     from crewai.tools import tool
+
     """Test that execution raises TimeoutError when max_execution_time is exceeded."""
 
     @tool("what amazing tool", result_as_answer=True)
@@ -1445,7 +1385,7 @@ def test_task_with_max_execution_time_exceeded():
         ),
         allow_delegation=False,
         tools=[my_tool],
-        max_execution_time=1
+        max_execution_time=1,
     )
 
     task = Task(
@@ -1455,4 +1395,28 @@ def test_task_with_max_execution_time_exceeded():
     )
 
     with pytest.raises(TimeoutError):
-        task.execute_sync(agent=researcher)
+        task.execute_sync(agent=researcher)
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_task_interpolation_with_hyphens():
+    agent = Agent(
+        role="Researcher",
+        goal="be an assistant that responds with {interpolation-with-hyphens}",
+        backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
+        allow_delegation=False,
+    )
+    task = Task(
+        description="be an assistant that responds with {interpolation-with-hyphens}",
+        expected_output="The response should be addressing: {interpolation-with-hyphens}",
+        agent=agent,
+    )
+    crew = Crew(
+        agents=[agent],
+        tasks=[task],
+        verbose=True,
+    )
+    result = crew.kickoff(inputs={"interpolation-with-hyphens": "say hello world"})
+    assert "say hello world" in task.prompt()
+
+    assert result.raw == "Hello, World!"

tests/telemetry/test_telemetry.py

@@ -0,0 +1,69 @@
+import os
+from unittest.mock import patch
+
+import pytest
+
+from crewai import Agent, Crew, Task
+from crewai.telemetry import Telemetry
+
+
+@pytest.mark.parametrize(
+    "env_var,value,expected_ready",
+    [
+        ("OTEL_SDK_DISABLED", "true", False),
+        ("OTEL_SDK_DISABLED", "TRUE", False),
+        ("CREWAI_DISABLE_TELEMETRY", "true", False),
+        ("CREWAI_DISABLE_TELEMETRY", "TRUE", False),
+        ("OTEL_SDK_DISABLED", "false", True),
+        ("CREWAI_DISABLE_TELEMETRY", "false", True),
+    ],
+)
+def test_telemetry_environment_variables(env_var, value, expected_ready):
+    """Test telemetry state with different environment variable configurations."""
+    with patch.dict(os.environ, {env_var: value}):
+        with patch("crewai.telemetry.telemetry.TracerProvider"):
+            telemetry = Telemetry()
+            assert telemetry.ready is expected_ready
+
+
+def test_telemetry_enabled_by_default():
+    """Test that telemetry is enabled by default."""
+    with patch.dict(os.environ, {}, clear=True):
+        with patch("crewai.telemetry.telemetry.TracerProvider"):
+            telemetry = Telemetry()
+            assert telemetry.ready is True
+
+
+from opentelemetry import trace
+
+
+@patch("crewai.telemetry.telemetry.logger.error")
+@patch(
+    "opentelemetry.exporter.otlp.proto.http.trace_exporter.OTLPSpanExporter.export",
+    side_effect=Exception("Test exception"),
+)
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_telemetry_fails_due_connect_timeout(export_mock, logger_mock):
+    error = Exception("Test exception")
+    export_mock.side_effect = error
+
+    tracer = trace.get_tracer(__name__)
+    with tracer.start_as_current_span("test-span"):
+        agent = Agent(
+            role="agent",
+            llm="gpt-4o-mini",
+            goal="Just say hi",
+            backstory="You are a helpful assistant that just says hi",
+        )
+        task = Task(
+            description="Just say hi",
+            expected_output="hi",
+            agent=agent,
+        )
+        crew = Crew(agents=[agent], tasks=[task], name="TestCrew")
+        crew.kickoff()
+
+    trace.get_tracer_provider().force_flush()
+
+    export_mock.assert_called_once()
+    logger_mock.assert_called_once_with(error)

tests/test_lite_agent.py

@@ -1,13 +1,16 @@
 import asyncio
 from typing import cast
+from unittest.mock import Mock
 
 import pytest
 from pydantic import BaseModel, Field
 
 from crewai import LLM, Agent
+from crewai.flow import Flow, start
 from crewai.lite_agent import LiteAgent, LiteAgentOutput
 from crewai.tools import BaseTool
 from crewai.utilities.events import crewai_event_bus
+from crewai.utilities.events.agent_events import LiteAgentExecutionStartedEvent
 from crewai.utilities.events.tool_usage_events import ToolUsageStartedEvent
 
 
@@ -255,3 +258,60 @@ async def test_lite_agent_returns_usage_metrics_async():
     assert "21 million" in result.raw or "37 million" in result.raw
     assert result.usage_metrics is not None
     assert result.usage_metrics["total_tokens"] > 0
+
+
+class TestFlow(Flow):
+    """A test flow that creates and runs an agent."""
+
+    def __init__(self, llm, tools):
+        self.llm = llm
+        self.tools = tools
+        super().__init__()
+
+    @start()
+    def start(self):
+        agent = Agent(
+            role="Test Agent",
+            goal="Test Goal",
+            backstory="Test Backstory",
+            llm=self.llm,
+            tools=self.tools,
+        )
+        return agent.kickoff("Test query")
+
+
+def verify_agent_parent_flow(result, agent, flow):
+    """Verify that both the result and agent have the correct parent flow."""
+    assert result.parent_flow is flow
+    assert agent is not None
+    assert agent.parent_flow is flow
+
+
+def test_sets_parent_flow_when_inside_flow():
+    captured_agent = None
+
+    mock_llm = Mock(spec=LLM)
+    mock_llm.call.return_value = "Test response"
+
+    class MyFlow(Flow):
+        @start()
+        def start(self):
+            agent = Agent(
+                role="Test Agent",
+                goal="Test Goal",
+                backstory="Test Backstory",
+                llm=mock_llm,
+                tools=[WebSearchTool()],
+            )
+            return agent.kickoff("Test query")
+
+    flow = MyFlow()
+    with crewai_event_bus.scoped_handlers():
+
+        @crewai_event_bus.on(LiteAgentExecutionStartedEvent)
+        def capture_agent(source, event):
+            nonlocal captured_agent
+            captured_agent = source
+
+        result = flow.kickoff()
+        assert captured_agent.parent_flow is flow

tests/test_markdown_task.py

@@ -0,0 +1,96 @@
+"""Test the markdown attribute in Task class."""
+
+import pytest
+from pydantic import BaseModel
+
+from crewai import Agent, Task
+
+
+@pytest.mark.parametrize(
+    "markdown_enabled,should_contain_instructions",
+    [
+        (True, True),
+        (False, False),
+    ],
+)
+def test_markdown_option_in_task_prompt(markdown_enabled, should_contain_instructions):
+    """Test that markdown flag correctly controls the inclusion of markdown formatting instructions."""
+    
+    researcher = Agent(
+        role="Researcher",
+        goal="Research a topic",
+        backstory="You're a researcher specialized in providing well-formatted content.",
+        allow_delegation=False,
+    )
+
+    task = Task(
+        description="Research advances in AI in 2023",
+        expected_output="A summary of key AI advances in 2023",
+        markdown=markdown_enabled,
+        agent=researcher,
+    )
+
+    prompt = task.prompt()
+    
+    assert "Research advances in AI in 2023" in prompt
+    assert "A summary of key AI advances in 2023" in prompt
+    
+    if should_contain_instructions:
+        assert "Your final answer MUST be formatted in Markdown syntax." in prompt
+        assert "Use # for headers" in prompt
+        assert "Use ** for bold text" in prompt
+    else:
+        assert "Your final answer MUST be formatted in Markdown syntax." not in prompt
+
+
+def test_markdown_with_empty_description():
+    """Test markdown formatting with empty description."""
+    
+    researcher = Agent(
+        role="Researcher",
+        goal="Research a topic",
+        backstory="You're a researcher.",
+        allow_delegation=False,
+    )
+
+    task = Task(
+        description="",
+        expected_output="A summary",
+        markdown=True,
+        agent=researcher,
+    )
+
+    prompt = task.prompt()
+    
+    assert prompt.strip() != ""
+    assert "A summary" in prompt
+    assert "Your final answer MUST be formatted in Markdown syntax." in prompt
+
+
+def test_markdown_with_complex_output_format():
+    """Test markdown with JSON output format to ensure compatibility."""
+    
+    class ResearchOutput(BaseModel):
+        title: str
+        findings: list[str]
+    
+    researcher = Agent(
+        role="Researcher",
+        goal="Research a topic",
+        backstory="You're a researcher.",
+        allow_delegation=False,
+    )
+
+    task = Task(
+        description="Research topic",
+        expected_output="Research results",
+        markdown=True,
+        output_json=ResearchOutput,
+        agent=researcher,
+    )
+
+    prompt = task.prompt()
+    
+    assert "Your final answer MUST be formatted in Markdown syntax." in prompt
+    assert "Research topic" in prompt
+    assert "Research results" in prompt

tests/utilities/cassettes/test_converter_with_llama3_2_model.yaml

@@ -1,9 +1,10 @@
 interactions:
 - request:
-    body: '{"model": "llama3.2:3b", "prompt": "### System:\nPlease convert the following
-      text into valid JSON.\n\nOutput ONLY the valid JSON and nothing else.\n\nThe
-      JSON must follow this format exactly:\n{\n  \"name\": str,\n  \"age\": int\n}\n\n###
-      User:\nName: Alice Llama, Age: 30\n\n", "options": {"stop": []}, "stream": false}'
+    body: '{"model": "meta-llama/llama-3.2-3b-instruct", "messages": [{"role": "system",
+      "content": "Please convert the following text into valid JSON.\n\nOutput ONLY
+      the valid JSON and nothing else.\n\nThe JSON must follow this format exactly:\n{\n  \"name\":
+      str,\n  \"age\": int\n}"}, {"role": "user", "content": "Name: Alice Llama, Age:
+      30"}], "stream": false, "stop": []}'
     headers:
       accept:
       - '*/*'
@@ -12,853 +13,55 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '321'
-      host:
-      - localhost:11434
-      user-agent:
-      - litellm/1.60.2
-    method: POST
-    uri: http://localhost:11434/api/generate
-  response:
-    content: '{"model":"llama3.2:3b","created_at":"2025-02-21T02:57:55.059392Z","response":"{\"name\":
-      \"Alice Llama\", \"age\": 30}","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,744,512,5618,5625,279,2768,1495,1139,2764,4823,382,5207,27785,279,2764,4823,323,4400,775,382,791,4823,2011,1833,420,3645,7041,512,517,220,330,609,794,610,345,220,330,425,794,528,198,633,14711,2724,512,678,25,30505,445,81101,11,13381,25,220,966,271,128009,128006,78191,128007,271,5018,609,794,330,62786,445,81101,498,330,425,794,220,966,92],"total_duration":4675906000,"load_duration":836091458,"prompt_eval_count":82,"prompt_eval_duration":3561000000,"eval_count":15,"eval_duration":275000000}'
-    headers:
-      Content-Length:
-      - '761'
-      Content-Type:
-      - application/json; charset=utf-8
-      Date:
-      - Fri, 21 Feb 2025 02:57:55 GMT
-    http_version: HTTP/1.1
-    status_code: 200
-- request:
-    body: '{"name": "llama3.2:3b"}'
-    headers:
-      accept:
-      - '*/*'
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '23'
+      - '365'
       content-type:
       - application/json
       host:
-      - localhost:11434
+      - openrouter.ai
+      http-referer:
+      - https://litellm.ai
       user-agent:
-      - litellm/1.60.2
+      - litellm/1.68.0
+      x-title:
+      - liteLLM
     method: POST
-    uri: http://localhost:11434/api/show
+    uri: https://openrouter.ai/api/v1/chat/completions
   response:
-    content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
-      Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
-      and conditions for use, reproduction, distribution \\nand modification of the
-      Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
-      manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
-      or \u201Cyou\u201D means you, or your employer or any other person or entity
-      (if you are \\nentering into this Agreement on such person or entity\u2019s
-      behalf), of the age required under\\napplicable laws, rules or regulations to
-      provide legal consent and that has legal authority\\nto bind your employer or
-      such other person or entity if you are entering in this Agreement\\non their
-      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
-      and software and algorithms, including\\nmachine-learning model code, trained
-      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
-      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
-      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
-      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
-      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
-      or, \\nif you are an entity, your principal place of business is in the EEA
-      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
-      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
-      or distributing any portion or element of the Llama Materials,\\nyou agree to
-      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
-      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
-      and royalty-free limited license under Meta\u2019s intellectual property or
-      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
-      distribute, copy, create derivative works \\nof, and make modifications to the
-      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
-      you distribute or make available the Llama Materials (or any derivative works
-      thereof), \\nor a product or service (including another AI model) that contains
-      any of them, you shall (A) provide\\na copy of this Agreement with any such
-      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
-      a related website, user interface, blogpost, about page, or product documentation.
-      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
-      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
-      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
-      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
-      or any derivative works thereof, from a Licensee as part\\nof an integrated
-      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
-      \       iii. You must retain in all copies of the Llama Materials that you distribute
-      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
-      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
-      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
-      \       iv. Your use of the Llama Materials must comply with applicable laws
-      and regulations\\n(including trade compliance laws and regulations) and adhere
-      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
-      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
-      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
-      monthly active users\\nof the products or services made available by or for
-      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
-      active users in the preceding calendar month, you must request \\na license
-      from Meta, which Meta may grant to you in its sole discretion, and you are not
-      authorized to\\nexercise any of the rights under this Agreement unless or until
-      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
-      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
-      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
-      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
-      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
-      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
-      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
-      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
-      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
-      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
-      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
-      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
-      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
-      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
-      \   a. No trademark licenses are granted under this Agreement, and in connection
-      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
-      owned by or associated with the other or any of its affiliates, \\nexcept as
-      required for reasonable and customary use in describing and redistributing the
-      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
-      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
-      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
-      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
-      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
-      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
-      derivatives made by or for Meta, with respect to any\\n    derivative works
-      and modifications of the Llama Materials that are made by you, as between you
-      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
-      \   c. If you institute litigation or other proceedings against Meta or any
-      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
-      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
-      \   of any of the foregoing, constitutes infringement of intellectual property
-      or other rights owned or licensable\\n    by you, then any licenses granted
-      to you under this Agreement shall terminate as of the date such litigation or\\n
-      \   claim is filed or instituted. You will indemnify and hold harmless Meta
-      from and against any claim by any third\\n    party arising out of or related
-      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
-      The term of this Agreement will commence upon your acceptance of this Agreement
-      or access\\nto the Llama Materials and will continue in full force and effect
-      until terminated in accordance with the terms\\nand conditions herein. Meta
-      may terminate this Agreement if you are in breach of any term or condition of
-      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
-      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
-      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
-      be governed and construed under the laws of the State of \\nCalifornia without
-      regard to choice of law principles, and the UN Convention on Contracts for the
-      International\\nSale of Goods does not apply to this Agreement. The courts of
-      California shall have exclusive jurisdiction of\\nany dispute arising out of
-      this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
-      to promoting safe and fair use of its tools and features, including Llama 3.2.
-      If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
-      The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
-      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
-      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
-      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
-      contribute to, encourage, plan, incite, or further illegal or unlawful activity
-      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
-      or harm to children, including the solicitation, creation, acquisition, or dissemination
-      of child exploitative content or failure to report Child Sexual Abuse Material\\n
-      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
-      The illegal distribution of information or materials to minors, including obscene
-      materials, or failure to employ legally required age-gating in connection with
-      such information or materials.\\n        5. Sexual solicitation\\n        6.
-      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
-      the harassment, abuse, threatening, or bullying of individuals or groups of
-      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
-      or other unlawful or harmful conduct in the provision of employment, employment
-      benefits, credit, housing, other economic benefits, or other essential goods
-      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
-      profession including, but not limited to, financial, legal, medical/health,
-      or related professional practices\\n    4. Collect, process, disclose, generate,
-      or infer private or sensitive information about individuals, including information
-      about individuals\u2019 identity, health, or demographic information, unless
-      you have obtained the right to do so in accordance with applicable law\\n    5.
-      Engage in or facilitate any action or generate any content that infringes, misappropriates,
-      or otherwise violates any third-party rights, including the outputs or results
-      of any products or services using the Llama Materials\\n    6. Create, generate,
-      or facilitate the creation of malicious code, malware, computer viruses or do
-      anything else that could disable, overburden, interfere with or impair the proper
-      working, integrity, operation or appearance of a website or computer system\\n
-      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
-      or remove usage restrictions or other safety measures, or to enable functionality
-      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
-      planning or development of activities that present a risk of death or bodily
-      harm to individuals, including use of Llama 3.2 related to the following:\\n
-      \   8. Military, warfare, nuclear industries or applications, espionage, use
-      for materials or activities that are subject to the International Traffic Arms
-      Regulations (ITAR) maintained by the United States Department of State or to
-      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
-      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
-      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
-      \   11. Operation of critical infrastructure, transportation technologies, or
-      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
-      and eating disorders\\n    13. Any content intended to incite or promote violence,
-      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
-      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
-      \   14. Generating, promoting, or furthering fraud or the creation or promotion
-      of disinformation\\n    15. Generating, promoting, or furthering defamatory
-      content, including the creation of defamatory statements, images, or other content\\n
-      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
-      another individual without consent, authorization, or legal right\\n    18.
-      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
-      Generating or facilitating false online engagement, including fake reviews and
-      other means of fake online engagement\\n4. Fail to appropriately disclose to
-      end users any known dangers of your AI system\\n5. Interact with third party
-      tools, models, or software designed to generate unlawful content or engage in
-      unlawful or harmful conduct and/or represent that the outputs of such tools,
-      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
-      to any multimodal models included in Llama 3.2, the rights granted under Section
-      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
-      if you are an individual domiciled in, or a company with a principal place of
-      business in, the European Union. This restriction does not apply to end users
-      of a product or service that incorporates any such multimodal models.\\n\\nPlease
-      report any violation of this Policy, software \u201Cbug,\u201D or other problems
-      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
-      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
-      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
-      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
-      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
-      3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
-      show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
-      FROM llama3.2:3b\\n\\nFROM /Users/joaomoura/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
-      \\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
-      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
-      if .Tools }}When you receive a tool call response, use the output to format
-      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
-      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
-      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
-      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
-      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
-      a JSON for a function call with its proper arguments that best answers the given
-      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
-      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
-      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
-      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
-      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
-      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
-      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
-      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
-      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
-      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
-      end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
-      stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
-      \\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
-      September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
-      for use, reproduction, distribution \\nand modification of the Llama Materials
-      set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
-      and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
-      or \u201Cyou\u201D means you, or your employer or any other person or entity
-      (if you are \\nentering into this Agreement on such person or entity\u2019s
-      behalf), of the age required under\\napplicable laws, rules or regulations to
-      provide legal consent and that has legal authority\\nto bind your employer or
-      such other person or entity if you are entering in this Agreement\\non their
-      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
-      and software and algorithms, including\\nmachine-learning model code, trained
-      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
-      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
-      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
-      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
-      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
-      or, \\nif you are an entity, your principal place of business is in the EEA
-      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
-      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
-      or distributing any portion or element of the Llama Materials,\\nyou agree to
-      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
-      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
-      and royalty-free limited license under Meta\u2019s intellectual property or
-      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
-      distribute, copy, create derivative works \\nof, and make modifications to the
-      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
-      you distribute or make available the Llama Materials (or any derivative works
-      thereof), \\nor a product or service (including another AI model) that contains
-      any of them, you shall (A) provide\\na copy of this Agreement with any such
-      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
-      a related website, user interface, blogpost, about page, or product documentation.
-      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
-      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
-      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
-      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
-      or any derivative works thereof, from a Licensee as part\\nof an integrated
-      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
-      \       iii. You must retain in all copies of the Llama Materials that you distribute
-      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
-      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
-      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
-      \       iv. Your use of the Llama Materials must comply with applicable laws
-      and regulations\\n(including trade compliance laws and regulations) and adhere
-      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
-      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
-      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
-      monthly active users\\nof the products or services made available by or for
-      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
-      active users in the preceding calendar month, you must request \\na license
-      from Meta, which Meta may grant to you in its sole discretion, and you are not
-      authorized to\\nexercise any of the rights under this Agreement unless or until
-      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
-      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
-      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
-      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
-      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
-      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
-      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
-      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
-      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
-      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
-      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
-      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
-      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
-      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
-      \   a. No trademark licenses are granted under this Agreement, and in connection
-      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
-      owned by or associated with the other or any of its affiliates, \\nexcept as
-      required for reasonable and customary use in describing and redistributing the
-      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
-      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
-      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
-      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
-      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
-      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
-      derivatives made by or for Meta, with respect to any\\n    derivative works
-      and modifications of the Llama Materials that are made by you, as between you
-      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
-      \   c. If you institute litigation or other proceedings against Meta or any
-      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
-      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
-      \   of any of the foregoing, constitutes infringement of intellectual property
-      or other rights owned or licensable\\n    by you, then any licenses granted
-      to you under this Agreement shall terminate as of the date such litigation or\\n
-      \   claim is filed or instituted. You will indemnify and hold harmless Meta
-      from and against any claim by any third\\n    party arising out of or related
-      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
-      The term of this Agreement will commence upon your acceptance of this Agreement
-      or access\\nto the Llama Materials and will continue in full force and effect
-      until terminated in accordance with the terms\\nand conditions herein. Meta
-      may terminate this Agreement if you are in breach of any term or condition of
-      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
-      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
-      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
-      be governed and construed under the laws of the State of \\nCalifornia without
-      regard to choice of law principles, and the UN Convention on Contracts for the
-      International\\nSale of Goods does not apply to this Agreement. The courts of
-      California shall have exclusive jurisdiction of\\nany dispute arising out of
-      this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
-      is committed to promoting safe and fair use of its tools and features, including
-      Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
-      Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
-      found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
-      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
-      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
-      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
-      contribute to, encourage, plan, incite, or further illegal or unlawful activity
-      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
-      or harm to children, including the solicitation, creation, acquisition, or dissemination
-      of child exploitative content or failure to report Child Sexual Abuse Material\\n
-      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
-      The illegal distribution of information or materials to minors, including obscene
-      materials, or failure to employ legally required age-gating in connection with
-      such information or materials.\\n        5. Sexual solicitation\\n        6.
-      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
-      the harassment, abuse, threatening, or bullying of individuals or groups of
-      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
-      or other unlawful or harmful conduct in the provision of employment, employment
-      benefits, credit, housing, other economic benefits, or other essential goods
-      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
-      profession including, but not limited to, financial, legal, medical/health,
-      or related professional practices\\n    4. Collect, process, disclose, generate,
-      or infer private or sensitive information about individuals, including information
-      about individuals\u2019 identity, health, or demographic information, unless
-      you have obtained the right to do so in accordance with applicable law\\n    5.
-      Engage in or facilitate any action or generate any content that infringes, misappropriates,
-      or otherwise violates any third-party rights, including the outputs or results
-      of any products or services using the Llama Materials\\n    6. Create, generate,
-      or facilitate the creation of malicious code, malware, computer viruses or do
-      anything else that could disable, overburden, interfere with or impair the proper
-      working, integrity, operation or appearance of a website or computer system\\n
-      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
-      or remove usage restrictions or other safety measures, or to enable functionality
-      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
-      planning or development of activities that present a risk of death or bodily
-      harm to individuals, including use of Llama 3.2 related to the following:\\n
-      \   8. Military, warfare, nuclear industries or applications, espionage, use
-      for materials or activities that are subject to the International Traffic Arms
-      Regulations (ITAR) maintained by the United States Department of State or to
-      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
-      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
-      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
-      \   11. Operation of critical infrastructure, transportation technologies, or
-      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
-      and eating disorders\\n    13. Any content intended to incite or promote violence,
-      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
-      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
-      \   14. Generating, promoting, or furthering fraud or the creation or promotion
-      of disinformation\\n    15. Generating, promoting, or furthering defamatory
-      content, including the creation of defamatory statements, images, or other content\\n
-      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
-      another individual without consent, authorization, or legal right\\n    18.
-      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
-      Generating or facilitating false online engagement, including fake reviews and
-      other means of fake online engagement\\n4. Fail to appropriately disclose to
-      end users any known dangers of your AI system\\n5. Interact with third party
-      tools, models, or software designed to generate unlawful content or engage in
-      unlawful or harmful conduct and/or represent that the outputs of such tools,
-      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
-      to any multimodal models included in Llama 3.2, the rights granted under Section
-      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
-      if you are an individual domiciled in, or a company with a principal place of
-      business in, the European Union. This restriction does not apply to end users
-      of a product or service that incorporates any such multimodal models.\\n\\nPlease
-      report any violation of this Policy, software \u201Cbug,\u201D or other problems
-      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
-      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
-      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
-      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
-      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
-      3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop                           \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
-      \                          \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop                           \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
-      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
-      if .Tools }}When you receive a tool call response, use the output to format
-      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
-      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
-      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
-      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
-      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
-      a JSON for a function call with its proper arguments that best answers the given
-      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
-      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
-      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
-      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
-      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
-      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
-      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
-      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
-      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
-      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
-      end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2025-02-20T18:55:09.150577031-08:00\"}"
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//dJDBTsMwEER/pZqzU1ICKfKNMwgQEieCKsfZJgbHG9mbghTl31FatZy4
+        7GHm8N7OBNdAo6WQbbY327zMi81t9vwizVv5sB9f22/DdOg730FhiHxwDUVoPFHtxgSFnhvy0OhJ
+        TOa96c3V8WbF+jor6syFJHG0AgWuP8kKNGxnZG25HzyJ4wAFG8kINdB/Egq2Y2cpQb9P8NwOkesE
+        HUbvFfYuuNTtIpnEARpJeIBCMOIOtPundaGhH+hcoaeUTEvQEyJ7goZJySUxYRG1HITCYjpVCKan
+        CnpV4d47S6vH5bsKalXBtMemyGcoRNqPyfiz4IntQnsK5vlDYTwzh8j9IDvhLwoJuiwX5nmOS7xs
+        ICzGX5K7zTz/AgAA//8DAIXfumyyAQAA
     headers:
-      Content-Type:
-      - application/json; charset=utf-8
-      Date:
-      - Fri, 21 Feb 2025 02:57:55 GMT
-      Transfer-Encoding:
-      - chunked
-    http_version: HTTP/1.1
-    status_code: 200
-- request:
-    body: '{"name": "llama3.2:3b"}'
-    headers:
-      accept:
-      - '*/*'
-      accept-encoding:
-      - gzip, deflate
-      connection:
+      Access-Control-Allow-Origin:
+      - '*'
+      CF-RAY:
+      - 93ea9f59596559fa-DEL
+      Connection:
       - keep-alive
-      content-length:
-      - '23'
-      content-type:
-      - application/json
-      host:
-      - localhost:11434
-      user-agent:
-      - litellm/1.60.2
-    method: POST
-    uri: http://localhost:11434/api/show
-  response:
-    content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
-      Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
-      and conditions for use, reproduction, distribution \\nand modification of the
-      Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
-      manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
-      or \u201Cyou\u201D means you, or your employer or any other person or entity
-      (if you are \\nentering into this Agreement on such person or entity\u2019s
-      behalf), of the age required under\\napplicable laws, rules or regulations to
-      provide legal consent and that has legal authority\\nto bind your employer or
-      such other person or entity if you are entering in this Agreement\\non their
-      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
-      and software and algorithms, including\\nmachine-learning model code, trained
-      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
-      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
-      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
-      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
-      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
-      or, \\nif you are an entity, your principal place of business is in the EEA
-      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
-      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
-      or distributing any portion or element of the Llama Materials,\\nyou agree to
-      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
-      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
-      and royalty-free limited license under Meta\u2019s intellectual property or
-      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
-      distribute, copy, create derivative works \\nof, and make modifications to the
-      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
-      you distribute or make available the Llama Materials (or any derivative works
-      thereof), \\nor a product or service (including another AI model) that contains
-      any of them, you shall (A) provide\\na copy of this Agreement with any such
-      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
-      a related website, user interface, blogpost, about page, or product documentation.
-      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
-      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
-      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
-      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
-      or any derivative works thereof, from a Licensee as part\\nof an integrated
-      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
-      \       iii. You must retain in all copies of the Llama Materials that you distribute
-      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
-      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
-      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
-      \       iv. Your use of the Llama Materials must comply with applicable laws
-      and regulations\\n(including trade compliance laws and regulations) and adhere
-      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
-      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
-      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
-      monthly active users\\nof the products or services made available by or for
-      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
-      active users in the preceding calendar month, you must request \\na license
-      from Meta, which Meta may grant to you in its sole discretion, and you are not
-      authorized to\\nexercise any of the rights under this Agreement unless or until
-      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
-      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
-      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
-      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
-      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
-      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
-      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
-      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
-      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
-      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
-      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
-      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
-      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
-      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
-      \   a. No trademark licenses are granted under this Agreement, and in connection
-      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
-      owned by or associated with the other or any of its affiliates, \\nexcept as
-      required for reasonable and customary use in describing and redistributing the
-      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
-      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
-      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
-      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
-      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
-      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
-      derivatives made by or for Meta, with respect to any\\n    derivative works
-      and modifications of the Llama Materials that are made by you, as between you
-      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
-      \   c. If you institute litigation or other proceedings against Meta or any
-      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
-      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
-      \   of any of the foregoing, constitutes infringement of intellectual property
-      or other rights owned or licensable\\n    by you, then any licenses granted
-      to you under this Agreement shall terminate as of the date such litigation or\\n
-      \   claim is filed or instituted. You will indemnify and hold harmless Meta
-      from and against any claim by any third\\n    party arising out of or related
-      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
-      The term of this Agreement will commence upon your acceptance of this Agreement
-      or access\\nto the Llama Materials and will continue in full force and effect
-      until terminated in accordance with the terms\\nand conditions herein. Meta
-      may terminate this Agreement if you are in breach of any term or condition of
-      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
-      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
-      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
-      be governed and construed under the laws of the State of \\nCalifornia without
-      regard to choice of law principles, and the UN Convention on Contracts for the
-      International\\nSale of Goods does not apply to this Agreement. The courts of
-      California shall have exclusive jurisdiction of\\nany dispute arising out of
-      this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
-      to promoting safe and fair use of its tools and features, including Llama 3.2.
-      If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
-      The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
-      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
-      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
-      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
-      contribute to, encourage, plan, incite, or further illegal or unlawful activity
-      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
-      or harm to children, including the solicitation, creation, acquisition, or dissemination
-      of child exploitative content or failure to report Child Sexual Abuse Material\\n
-      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
-      The illegal distribution of information or materials to minors, including obscene
-      materials, or failure to employ legally required age-gating in connection with
-      such information or materials.\\n        5. Sexual solicitation\\n        6.
-      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
-      the harassment, abuse, threatening, or bullying of individuals or groups of
-      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
-      or other unlawful or harmful conduct in the provision of employment, employment
-      benefits, credit, housing, other economic benefits, or other essential goods
-      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
-      profession including, but not limited to, financial, legal, medical/health,
-      or related professional practices\\n    4. Collect, process, disclose, generate,
-      or infer private or sensitive information about individuals, including information
-      about individuals\u2019 identity, health, or demographic information, unless
-      you have obtained the right to do so in accordance with applicable law\\n    5.
-      Engage in or facilitate any action or generate any content that infringes, misappropriates,
-      or otherwise violates any third-party rights, including the outputs or results
-      of any products or services using the Llama Materials\\n    6. Create, generate,
-      or facilitate the creation of malicious code, malware, computer viruses or do
-      anything else that could disable, overburden, interfere with or impair the proper
-      working, integrity, operation or appearance of a website or computer system\\n
-      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
-      or remove usage restrictions or other safety measures, or to enable functionality
-      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
-      planning or development of activities that present a risk of death or bodily
-      harm to individuals, including use of Llama 3.2 related to the following:\\n
-      \   8. Military, warfare, nuclear industries or applications, espionage, use
-      for materials or activities that are subject to the International Traffic Arms
-      Regulations (ITAR) maintained by the United States Department of State or to
-      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
-      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
-      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
-      \   11. Operation of critical infrastructure, transportation technologies, or
-      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
-      and eating disorders\\n    13. Any content intended to incite or promote violence,
-      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
-      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
-      \   14. Generating, promoting, or furthering fraud or the creation or promotion
-      of disinformation\\n    15. Generating, promoting, or furthering defamatory
-      content, including the creation of defamatory statements, images, or other content\\n
-      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
-      another individual without consent, authorization, or legal right\\n    18.
-      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
-      Generating or facilitating false online engagement, including fake reviews and
-      other means of fake online engagement\\n4. Fail to appropriately disclose to
-      end users any known dangers of your AI system\\n5. Interact with third party
-      tools, models, or software designed to generate unlawful content or engage in
-      unlawful or harmful conduct and/or represent that the outputs of such tools,
-      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
-      to any multimodal models included in Llama 3.2, the rights granted under Section
-      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
-      if you are an individual domiciled in, or a company with a principal place of
-      business in, the European Union. This restriction does not apply to end users
-      of a product or service that incorporates any such multimodal models.\\n\\nPlease
-      report any violation of this Policy, software \u201Cbug,\u201D or other problems
-      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
-      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
-      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
-      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
-      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
-      3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
-      show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
-      FROM llama3.2:3b\\n\\nFROM /Users/joaomoura/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
-      \\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
-      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
-      if .Tools }}When you receive a tool call response, use the output to format
-      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
-      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
-      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
-      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
-      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
-      a JSON for a function call with its proper arguments that best answers the given
-      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
-      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
-      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
-      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
-      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
-      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
-      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
-      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
-      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
-      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
-      end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
-      stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
-      \\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
-      September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
-      for use, reproduction, distribution \\nand modification of the Llama Materials
-      set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
-      and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
-      or \u201Cyou\u201D means you, or your employer or any other person or entity
-      (if you are \\nentering into this Agreement on such person or entity\u2019s
-      behalf), of the age required under\\napplicable laws, rules or regulations to
-      provide legal consent and that has legal authority\\nto bind your employer or
-      such other person or entity if you are entering in this Agreement\\non their
-      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
-      and software and algorithms, including\\nmachine-learning model code, trained
-      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
-      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
-      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
-      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
-      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
-      or, \\nif you are an entity, your principal place of business is in the EEA
-      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
-      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
-      or distributing any portion or element of the Llama Materials,\\nyou agree to
-      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
-      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
-      and royalty-free limited license under Meta\u2019s intellectual property or
-      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
-      distribute, copy, create derivative works \\nof, and make modifications to the
-      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
-      you distribute or make available the Llama Materials (or any derivative works
-      thereof), \\nor a product or service (including another AI model) that contains
-      any of them, you shall (A) provide\\na copy of this Agreement with any such
-      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
-      a related website, user interface, blogpost, about page, or product documentation.
-      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
-      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
-      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
-      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
-      or any derivative works thereof, from a Licensee as part\\nof an integrated
-      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
-      \       iii. You must retain in all copies of the Llama Materials that you distribute
-      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
-      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
-      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
-      \       iv. Your use of the Llama Materials must comply with applicable laws
-      and regulations\\n(including trade compliance laws and regulations) and adhere
-      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
-      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
-      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
-      monthly active users\\nof the products or services made available by or for
-      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
-      active users in the preceding calendar month, you must request \\na license
-      from Meta, which Meta may grant to you in its sole discretion, and you are not
-      authorized to\\nexercise any of the rights under this Agreement unless or until
-      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
-      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
-      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
-      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
-      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
-      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
-      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
-      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
-      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
-      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
-      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
-      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
-      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
-      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
-      \   a. No trademark licenses are granted under this Agreement, and in connection
-      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
-      owned by or associated with the other or any of its affiliates, \\nexcept as
-      required for reasonable and customary use in describing and redistributing the
-      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
-      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
-      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
-      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
-      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
-      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
-      derivatives made by or for Meta, with respect to any\\n    derivative works
-      and modifications of the Llama Materials that are made by you, as between you
-      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
-      \   c. If you institute litigation or other proceedings against Meta or any
-      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
-      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
-      \   of any of the foregoing, constitutes infringement of intellectual property
-      or other rights owned or licensable\\n    by you, then any licenses granted
-      to you under this Agreement shall terminate as of the date such litigation or\\n
-      \   claim is filed or instituted. You will indemnify and hold harmless Meta
-      from and against any claim by any third\\n    party arising out of or related
-      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
-      The term of this Agreement will commence upon your acceptance of this Agreement
-      or access\\nto the Llama Materials and will continue in full force and effect
-      until terminated in accordance with the terms\\nand conditions herein. Meta
-      may terminate this Agreement if you are in breach of any term or condition of
-      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
-      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
-      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
-      be governed and construed under the laws of the State of \\nCalifornia without
-      regard to choice of law principles, and the UN Convention on Contracts for the
-      International\\nSale of Goods does not apply to this Agreement. The courts of
-      California shall have exclusive jurisdiction of\\nany dispute arising out of
-      this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
-      is committed to promoting safe and fair use of its tools and features, including
-      Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
-      Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
-      found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
-      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
-      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
-      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
-      contribute to, encourage, plan, incite, or further illegal or unlawful activity
-      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
-      or harm to children, including the solicitation, creation, acquisition, or dissemination
-      of child exploitative content or failure to report Child Sexual Abuse Material\\n
-      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
-      The illegal distribution of information or materials to minors, including obscene
-      materials, or failure to employ legally required age-gating in connection with
-      such information or materials.\\n        5. Sexual solicitation\\n        6.
-      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
-      the harassment, abuse, threatening, or bullying of individuals or groups of
-      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
-      or other unlawful or harmful conduct in the provision of employment, employment
-      benefits, credit, housing, other economic benefits, or other essential goods
-      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
-      profession including, but not limited to, financial, legal, medical/health,
-      or related professional practices\\n    4. Collect, process, disclose, generate,
-      or infer private or sensitive information about individuals, including information
-      about individuals\u2019 identity, health, or demographic information, unless
-      you have obtained the right to do so in accordance with applicable law\\n    5.
-      Engage in or facilitate any action or generate any content that infringes, misappropriates,
-      or otherwise violates any third-party rights, including the outputs or results
-      of any products or services using the Llama Materials\\n    6. Create, generate,
-      or facilitate the creation of malicious code, malware, computer viruses or do
-      anything else that could disable, overburden, interfere with or impair the proper
-      working, integrity, operation or appearance of a website or computer system\\n
-      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
-      or remove usage restrictions or other safety measures, or to enable functionality
-      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
-      planning or development of activities that present a risk of death or bodily
-      harm to individuals, including use of Llama 3.2 related to the following:\\n
-      \   8. Military, warfare, nuclear industries or applications, espionage, use
-      for materials or activities that are subject to the International Traffic Arms
-      Regulations (ITAR) maintained by the United States Department of State or to
-      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
-      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
-      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
-      \   11. Operation of critical infrastructure, transportation technologies, or
-      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
-      and eating disorders\\n    13. Any content intended to incite or promote violence,
-      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
-      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
-      \   14. Generating, promoting, or furthering fraud or the creation or promotion
-      of disinformation\\n    15. Generating, promoting, or furthering defamatory
-      content, including the creation of defamatory statements, images, or other content\\n
-      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
-      another individual without consent, authorization, or legal right\\n    18.
-      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
-      Generating or facilitating false online engagement, including fake reviews and
-      other means of fake online engagement\\n4. Fail to appropriately disclose to
-      end users any known dangers of your AI system\\n5. Interact with third party
-      tools, models, or software designed to generate unlawful content or engage in
-      unlawful or harmful conduct and/or represent that the outputs of such tools,
-      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
-      to any multimodal models included in Llama 3.2, the rights granted under Section
-      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
-      if you are an individual domiciled in, or a company with a principal place of
-      business in, the European Union. This restriction does not apply to end users
-      of a product or service that incorporates any such multimodal models.\\n\\nPlease
-      report any violation of this Policy, software \u201Cbug,\u201D or other problems
-      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
-      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
-      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
-      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
-      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
-      3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop                           \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
-      \                          \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop                           \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
-      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
-      if .Tools }}When you receive a tool call response, use the output to format
-      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
-      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
-      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
-      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
-      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
-      a JSON for a function call with its proper arguments that best answers the given
-      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
-      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
-      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
-      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
-      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
-      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
-      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
-      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
-      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
-      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
-      end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2025-02-20T18:55:09.150577031-08:00\"}"
-    headers:
+      Content-Encoding:
+      - gzip
       Content-Type:
-      - application/json; charset=utf-8
+      - application/json
       Date:
-      - Fri, 21 Feb 2025 02:57:55 GMT
+      - Mon, 12 May 2025 14:31:55 GMT
+      Server:
+      - cloudflare
       Transfer-Encoding:
       - chunked
-    http_version: HTTP/1.1
-    status_code: 200
+      Vary:
+      - Accept-Encoding
+      x-clerk-auth-message:
+      - Invalid JWT form. A JWT consists of three parts separated by dots. (reason=token-invalid,
+        token-carrier=header)
+      x-clerk-auth-reason:
+      - token-invalid
+      x-clerk-auth-status:
+      - signed-out
+    status:
+      code: 200
+      message: OK
 version: 1

tests/utilities/events/test_crewai_event_bus.py

@@ -32,3 +32,16 @@ def test_wildcard_event_handler():
     crewai_event_bus.emit("source_object", event)
 
     mock_handler.assert_called_once_with("source_object", event)
+
+
+def test_event_bus_error_handling(capfd):
+    @crewai_event_bus.on(BaseEvent)
+    def broken_handler(source, event):
+        raise ValueError("Simulated handler failure")
+
+    event = TestEvent(type="test_event")
+    crewai_event_bus.emit("source_object", event)
+
+    out, err = capfd.readouterr()
+    assert "Simulated handler failure" in out
+    assert "Handler 'broken_handler' failed" in out

tests/utilities/test_converter.py

@@ -1,5 +1,4 @@
 import json
-import os
 from typing import Dict, List, Optional
 from unittest.mock import MagicMock, Mock, patch
 
@@ -19,6 +18,8 @@ from crewai.utilities.converter import (
     validate_model,
 )
 from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
+# Tests for enums
+from enum import Enum
 
 
 @pytest.fixture(scope="module")
@@ -357,16 +358,9 @@ def test_convert_with_instructions():
     assert output.age == 30
 
 
-# Skip tests that call external APIs when running in CI/CD
-skip_external_api = pytest.mark.skipif(
-    os.getenv("CI") is not None, reason="Skipping tests that call external API in CI/CD"
-)
-
-
-@skip_external_api
-@pytest.mark.vcr(filter_headers=["authorization"], record_mode="once")
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_converter_with_llama3_2_model():
-    llm = LLM(model="ollama/llama3.2:3b", base_url="http://localhost:11434")
+    llm = LLM(model="openrouter/meta-llama/llama-3.2-3b-instruct")
     sample_text = "Name: Alice Llama, Age: 30"
     instructions = get_conversion_instructions(SimpleModel, llm)
     converter = Converter(
@@ -381,8 +375,7 @@ def test_converter_with_llama3_2_model():
     assert output.age == 30
 
 
-@skip_external_api
-@pytest.mark.vcr(filter_headers=["authorization"], record_mode="once")
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_converter_with_llama3_1_model():
     llm = LLM(model="ollama/llama3.1", base_url="http://localhost:11434")
     sample_text = "Name: Alice Llama, Age: 30"
@@ -399,13 +392,6 @@ def test_converter_with_llama3_1_model():
     assert output.age == 30
 
 
-# Skip tests that call external APIs when running in CI/CD
-skip_external_api = pytest.mark.skipif(
-    os.getenv("CI") is not None, reason="Skipping tests that call external API in CI/CD"
-)
-
-
-@skip_external_api
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_converter_with_nested_model():
     llm = LLM(model="gpt-4o-mini")
@@ -446,7 +432,7 @@ def test_converter_error_handling():
     )
 
     with pytest.raises(ConverterError) as exc_info:
-        output = converter.to_pydantic()
+        converter.to_pydantic()
 
     assert "Failed to convert text into a Pydantic model" in str(exc_info.value)
 
@@ -530,10 +516,6 @@ def test_converter_with_list_field():
     assert output.items == [1, 2, 3]
 
 
-# Tests for enums
-from enum import Enum
-
-
 def test_converter_with_enum():
     class Color(Enum):
         RED = "red"
@@ -580,7 +562,7 @@ def test_converter_with_ambiguous_input():
     )
 
     with pytest.raises(ConverterError) as exc_info:
-        output = converter.to_pydantic()
+        converter.to_pydantic()
 
     assert "failed to convert text into a pydantic model" in str(exc_info.value).lower()
 

uv.lock

@@ -738,7 +738,7 @@ wheels = [
 
 [[package]]
 name = "crewai"
-version = "0.118.0"
+version = "0.120.1"
 source = { editable = "." }
 dependencies = [
     { name = "appdirs" },
@@ -811,8 +811,10 @@ dev = [
     { name = "pre-commit" },
     { name = "pytest" },
     { name = "pytest-asyncio" },
+    { name = "pytest-randomly" },
     { name = "pytest-recording" },
     { name = "pytest-subprocess" },
+    { name = "pytest-timeout" },
     { name = "python-dotenv" },
     { name = "ruff" },
 ]
@@ -826,14 +828,14 @@ requires-dist = [
     { name = "blinker", specifier = ">=1.9.0" },
     { name = "chromadb", specifier = ">=0.5.23" },
     { name = "click", specifier = ">=8.1.7" },
-    { name = "crewai-tools", marker = "extra == 'tools'", specifier = "~=0.42.2" },
+    { name = "crewai-tools", marker = "extra == 'tools'", specifier = "~=0.45.0" },
     { name = "docling", marker = "extra == 'docling'", specifier = ">=2.12.0" },
     { name = "fastembed", marker = "extra == 'fastembed'", specifier = ">=0.4.1" },
     { name = "instructor", specifier = ">=1.3.3" },
     { name = "json-repair", specifier = ">=0.25.2" },
     { name = "json5", specifier = ">=0.10.0" },
     { name = "jsonref", specifier = ">=1.1.0" },
-    { name = "litellm", specifier = "==1.67.1" },
+    { name = "litellm", specifier = "==1.68.0" },
     { name = "mem0ai", marker = "extra == 'mem0'", specifier = ">=0.1.94" },
     { name = "openai", specifier = ">=1.13.3" },
     { name = "openpyxl", specifier = ">=3.1.5" },
@@ -867,15 +869,17 @@ dev = [
     { name = "pre-commit", specifier = ">=3.6.0" },
     { name = "pytest", specifier = ">=8.0.0" },
     { name = "pytest-asyncio", specifier = ">=0.23.7" },
+    { name = "pytest-randomly", specifier = ">=3.16.0" },
     { name = "pytest-recording", specifier = ">=0.13.2" },
     { name = "pytest-subprocess", specifier = ">=1.5.2" },
+    { name = "pytest-timeout", specifier = ">=2.3.1" },
     { name = "python-dotenv", specifier = ">=1.0.0" },
     { name = "ruff", specifier = ">=0.8.2" },
 ]
 
 [[package]]
 name = "crewai-tools"
-version = "0.42.2"
+version = "0.45.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "chromadb" },
@@ -890,9 +894,9 @@ dependencies = [
     { name = "pytube" },
     { name = "requests" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/17/34/9e63e2db53d8f5c30353f271a3240687a48e55204bbd176a057c0b7658c8/crewai_tools-0.42.2.tar.gz", hash = "sha256:69365ffb168cccfea970e09b308905aa5007cfec60024d731ffac1362a0153c0", size = 754967 }
+sdist = { url = "https://files.pythonhosted.org/packages/e9/3a/7070dcacef56702c5d83ad1a87021b1666ff1850ff80b3aa7540892406e7/crewai_tools-0.45.0.tar.gz", hash = "sha256:1b2e4eff3f928ce5fac308d6e648719a0e4718a1228ae98980aa0d74fc16bfc7", size = 909723 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/4e/43/0f70b95350084e5cb1e1d74e9acb9e18a89ba675b1d579c787c2662baba7/crewai_tools-0.42.2-py3-none-any.whl", hash = "sha256:13727fb68f0efefd21edeb281be3d66ff2f5a3b5029d4e6adef388b11fd5846a", size = 583933 },
+    { url = "https://files.pythonhosted.org/packages/6e/72/db45626973027c992df75cbc7ef391f18393d631be3bceb6388c1b9f01e1/crewai_tools-0.45.0-py3-none-any.whl", hash = "sha256:9dd34e4792c075ee7a72134aedaab268e78d0e350114fd7fe2426e691c5f52a3", size = 602659 },
 ]
 
 [[package]]
@@ -2383,7 +2387,7 @@ wheels = [
 
 [[package]]
 name = "litellm"
-version = "1.67.1"
+version = "1.68.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aiohttp" },
@@ -2398,9 +2402,9 @@ dependencies = [
     { name = "tiktoken" },
     { name = "tokenizers" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/54/a4/bb3e9ae59e5a9857443448de7c04752630dc84cddcbd8cee037c0976f44f/litellm-1.67.1.tar.gz", hash = "sha256:78eab1bd3d759ec13aa4a05864356a4a4725634e78501db609d451bf72150ee7", size = 7242044 }
+sdist = { url = "https://files.pythonhosted.org/packages/ba/22/138545b646303ca3f4841b69613c697b9d696322a1386083bb70bcbba60b/litellm-1.68.0.tar.gz", hash = "sha256:9fb24643db84dfda339b64bafca505a2eef857477afbc6e98fb56512c24dbbfa", size = 7314051 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/88/86/c14d3c24ae13c08296d068e6f79fd4bd17a0a07bddbda94990b87c35d20e/litellm-1.67.1-py3-none-any.whl", hash = "sha256:8fff5b2a16b63bb594b94d6c071ad0f27d3d8cd4348bd5acea2fd40c8e0c11e8", size = 7607266 },
+    { url = "https://files.pythonhosted.org/packages/10/af/1e344bc8aee41445272e677d802b774b1f8b34bdc3bb5697ba30f0fb5d52/litellm-1.68.0-py3-none-any.whl", hash = "sha256:3bca38848b1a5236b11aa6b70afa4393b60880198c939e582273f51a542d4759", size = 7684460 },
 ]
 
 [[package]]
@@ -4228,6 +4232,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/96/31/6607dab48616902f76885dfcf62c08d929796fc3b2d2318faf9fd54dbed9/pytest_asyncio-0.24.0-py3-none-any.whl", hash = "sha256:a811296ed596b69bf0b6f3dc40f83bcaf341b155a269052d82efa2b25ac7037b", size = 18024 },
 ]
 
+[[package]]
+name = "pytest-randomly"
+version = "3.16.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pytest" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c0/68/d221ed7f4a2a49a664da721b8e87b52af6dd317af2a6cb51549cf17ac4b8/pytest_randomly-3.16.0.tar.gz", hash = "sha256:11bf4d23a26484de7860d82f726c0629837cf4064b79157bd18ec9d41d7feb26", size = 13367 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/22/70/b31577d7c46d8e2f9baccfed5067dd8475262a2331ffb0bfdf19361c9bde/pytest_randomly-3.16.0-py3-none-any.whl", hash = "sha256:8633d332635a1a0983d3bba19342196807f6afb17c3eef78e02c2f85dade45d6", size = 8396 },
+]
+
 [[package]]
 name = "pytest-recording"
 version = "0.13.2"
@@ -4254,6 +4270,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/10/77/a80e8f9126b95ffd5ad4d04bd14005c68dcbf0d88f53b2b14893f6cc7232/pytest_subprocess-1.5.2-py3-none-any.whl", hash = "sha256:23ac7732aa8bd45f1757265b1316eb72a7f55b41fb21e2ca22e149ba3629fa46", size = 20886 },
 ]
 
+[[package]]
+name = "pytest-timeout"
+version = "2.3.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pytest" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/93/0d/04719abc7a4bdb3a7a1f968f24b0f5253d698c9cc94975330e9d3145befb/pytest-timeout-2.3.1.tar.gz", hash = "sha256:12397729125c6ecbdaca01035b9e5239d4db97352320af155b3f5de1ba5165d9", size = 17697 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/03/27/14af9ef8321f5edc7527e47def2a21d8118c6f329a9342cc61387a0c0599/pytest_timeout-2.3.1-py3-none-any.whl", hash = "sha256:68188cb703edfc6a18fad98dc25a3c61e9f24d644b0b70f33af545219fc7813e", size = 14148 },
+]
+
 [[package]]
 name = "python-bidi"
 version = "0.6.3"