Fix import formatting in crew.py

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

.github/security.md

@@ -1,27 +1,19 @@
-## CrewAI Security Vulnerability Reporting Policy
+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 prioritizes the security of our software products, services, and GitHub repositories. To promptly address vulnerabilities, follow these steps for reporting security issues:
+ ## 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
 
-### Reporting Process
-Do **not** report vulnerabilities via public GitHub 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
 
-Email all vulnerability reports directly to:  
-**security@crewai.com**
+ 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.
 
-### 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.
+ At this time, we are not offering a bug bounty program. Any rewards will be at our discretion.

.github/workflows/linter.yml

@@ -5,29 +5,12 @@ 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: Fetch Target Branch
-        run: git fetch origin $TARGET_BRANCH --depth=1
-
-      - name: Install Ruff
-        run: pip install ruff
-
-      - name: Get Changed Python Files
-        id: changed-files
+      - name: Install Requirements
         run: |
-          merge_base=$(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
+          pip install ruff
 
-      - 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 "{}"
+      - name: Run Ruff Linter
+        run: ruff check

.ruff.toml

@@ -2,3 +2,8 @@ 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 your 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 you agents' connections to models.
 
 ## How CrewAI Compares
 

docs/concepts/cli.mdx

@@ -110,8 +110,6 @@ 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. Defaults 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. Defautls 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.                                                     |
@@ -246,7 +246,7 @@ 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(Boolean)` or `None`, the logs will not be populated.
+In case of `output_log_file` is set as `False(Booelan)` or `None`, the logs will not be populated.
 
 ```python Code
 # Save crew logs

docs/concepts/flows.mdx

@@ -75,12 +75,11 @@ 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.
@@ -147,7 +146,6 @@ class OutputExampleFlow(Flow):
 
 
 flow = OutputExampleFlow()
-flow.plot("my_flow_plot")
 final_output = flow.kickoff()
 
 print("---- Final Output ----")
@@ -160,10 +158,9 @@ 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 `plot()` method will generate the HTML file, which will help you understand the flow.
+The `kickoff()` method will return the final output, which is then printed to the console.
 
 #### Accessing and Updating State
 
@@ -195,7 +192,6 @@ 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:")
@@ -210,8 +206,6 @@ 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.
 
@@ -255,12 +249,9 @@ 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:**
@@ -311,8 +302,6 @@ 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.
@@ -447,7 +436,6 @@ class OrExampleFlow(Flow):
 
 
 flow = OrExampleFlow()
-flow.plot("my_flow_plot")
 flow.kickoff()
 ```
 
@@ -458,8 +446,6 @@ 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.
 
@@ -488,7 +474,6 @@ class AndExampleFlow(Flow):
         print(self.state)
 
 flow = AndExampleFlow()
-flow.plot()
 flow.kickoff()
 ```
 
@@ -499,8 +484,6 @@ 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.
 
@@ -544,7 +527,6 @@ class RouterFlow(Flow[ExampleState]):
 
 
 flow = RouterFlow()
-flow.plot("my_flow_plot")
 flow.kickoff()
 ```
 
@@ -556,8 +538,6 @@ 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"`.
@@ -661,7 +641,6 @@ 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
 
@@ -671,8 +650,6 @@ 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.
@@ -769,16 +746,13 @@ def kickoff():
 
 def plot():
     poem_flow = PoemFlow()
-    poem_flow.plot("PoemFlowPlot")
+    poem_flow.plot()
 
 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. The PoemFlowPlot will be generated by `plot()` method.
-
-![Flow Visual image](/images/crewai-flow-8.png)
+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.
 
 ### Running the Flow
 

docs/concepts/knowledge.mdx

@@ -397,53 +397,6 @@ 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.
@@ -497,13 +450,6 @@ 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>
@@ -707,11 +653,4 @@ 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

@@ -27,19 +27,23 @@ Large Language Models (LLMs) are the core intelligence behind CrewAI agents. The
   </Card>
 </CardGroup>
 
-## Setting up your LLM
+## Setting Up Your LLM
 
-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.
+There are three ways to configure LLMs in CrewAI. Choose the method that best fits your workflow:
 
 <Tabs>
   <Tab title="1. Environment Variables">
-    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.
+    The simplest way to get started. Set these variables in your environment:
 
-    ```bash .env
-    MODEL=model-id  # e.g. gpt-4o, gemini-2.0-flash, claude-3-sonnet-...
+    ```bash
+    # Required: Your API key for authentication
+    OPENAI_API_KEY=<your-api-key>
 
-    # Be sure to set your API keys here too. See the Provider
-    # section below.
+    # 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>
     ```
 
     <Warning>
@@ -49,13 +53,13 @@ There are different places in CrewAI code where you can specify the model to use
   <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 agents.yaml {6}
+    ```yaml
     researcher:
         role: Research Specialist
         goal: Conduct comprehensive research and analysis
         backstory: A dedicated research professional with years of experience
         verbose: true
-        llm: provider/model-id  # e.g. openai/gpt-4o, google/gemini-2.0-flash, anthropic/claude...
+        llm: openai/gpt-4o-mini # your model here
         # (see provider configuration examples below for more)
     ```
 
@@ -70,23 +74,23 @@ There are different places in CrewAI code where you can specify the model to use
   <Tab title="3. Direct Code">
     For maximum flexibility, configure LLMs directly in your Python code:
 
-    ```python {4,8}
+    ```python
     from crewai import LLM
 
     # Basic configuration
-    llm = LLM(model="model-id-here")  # gpt-4o, gemini-2.0-flash, anthropic/claude...
+    llm = LLM(model="gpt-4")
 
     # Advanced configuration with detailed parameters
     llm = LLM(
-        model="model-id-here",  # gpt-4o, gemini-2.0-flash, anthropic/claude...
+        model="gpt-4o-mini",
         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
     )
     ```
 
@@ -106,6 +110,7 @@ There are different places in CrewAI code where you can specify the model to use
 
 ## 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.
 
@@ -169,55 +174,19 @@ In this section, you'll find detailed examples that help you select, configure,
     ```
   </Accordion>
 
-  <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).
+  <Accordion title="Google">
+    Set the following environment variables in your `.env` file:
 
-    ```toml .env
+    ```toml Code
+    # Option 1: Gemini accessed with an API key.
     # https://ai.google.dev/gemini-api/docs/api-key
     GEMINI_API_KEY=<your-api-key>
+
+    # Option 2: Vertex AI IAM credentials for Gemini, Anthropic, and Model Garden.
+    # https://cloud.google.com/vertex-ai/generative-ai/docs/overview
     ```
 
-    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:
+    Get credentials from your Google Cloud Console and save it to a JSON file with the following code:
     ```python Code
     import json
 
@@ -241,18 +210,14 @@ 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-2.5-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 |
+    | 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 |
   </Accordion>
 
   <Accordion title="Azure">
@@ -418,7 +383,7 @@ 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 architecture to deliver compute efficient content generation |
+    | microsoft/phi-3.5-moe-instruct                                      | 128K tokens    | Advanced LLM based on Mixture of Experts architecure to deliver compute efficient content generation |
     | microsoft/kosmos-2                                                  | 1,024 tokens   | Groundbreaking multimodal model designed to understand and reason about visual elements in images. |
     | microsoft/phi-3-vision-128k-instruct                               | 128k tokens    | Cutting-edge open multimodal model exceling in high-quality reasoning from images. |
     | microsoft/phi-3.5-vision-instruct                                  | 128k tokens    | Cutting-edge open multimodal model exceling in high-quality reasoning from images. |
@@ -442,19 +407,19 @@ 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
 
@@ -476,7 +441,7 @@ 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>
@@ -672,19 +637,19 @@ 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())
@@ -820,7 +785,7 @@ 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

@@ -679,7 +679,6 @@ 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.
@@ -717,11 +716,9 @@ 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/guides/crews/first-crew.mdx

@@ -35,8 +35,7 @@ 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 LLM API key in your environment, following the [LLM setup
-   guide](/concepts/llms#setting-up-your-llm)
+2. Set up your OpenAI API key in your environment variables
 3. Basic understanding of Python
 
 ## Step 1: Create a New CrewAI Project
@@ -93,8 +92,7 @@ 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. Be sure
-to set `llm` to the provider you are using.
+Let's modify the `agents.yaml` file to define these specialized agents:
 
 ```yaml
 # src/research_crew/config/agents.yaml
@@ -109,7 +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: provider/model-id  # e.g. openai/gpt-4o, google/gemini-2.0-flash, anthropic/claude...
+  llm: openai/gpt-4o-mini
 
 analyst:
   role: >
@@ -122,7 +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: provider/model-id  # e.g. openai/gpt-4o, google/gemini-2.0-flash, anthropic/claude...
+  llm: openai/gpt-4o-mini
 ```
 
 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.
@@ -284,12 +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:
 
-```sh
+```
+OPENAI_API_KEY=your_openai_api_key
 SERPER_API_KEY=your_serper_api_key
-# Add your provider's API key here too.
 ```
 
-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/).
+You can get a Serper API key from [Serper.dev](https://serper.dev/).
 
 ## Step 8: Install Dependencies
 

docs/guides/flows/first-flow.mdx

@@ -45,8 +45,7 @@ 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 LLM API key in your environment, following the [LLM setup
-   guide](/concepts/llms#setting-up-your-llm)
+2. Set up your OpenAI API key in your environment variables
 3. Basic understanding of Python
 
 ## Step 1: Create a New CrewAI Flow Project
@@ -108,8 +107,6 @@ 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:
@@ -122,7 +119,7 @@ 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: provider/model-id  # e.g. openai/gpt-4o, google/gemini-2.0-flash, anthropic/claude...
+  llm: openai/gpt-4o-mini
 
 content_reviewer:
   role: >
@@ -135,7 +132,7 @@ 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: provider/model-id  # e.g. openai/gpt-4o, google/gemini-2.0-flash, anthropic/claude...
+  llm: openai/gpt-4o-mini
 ```
 
 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.
@@ -444,15 +441,10 @@ 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. See the [LLM setup
-guide](/concepts/llms#setting-up-your-llm) for details on configuring a provider.
+Create a `.env` file in your project root with your API keys:
 
-```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
@@ -555,10 +547,7 @@ 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="model-id-here",  # gpt-4o, gemini-2.0-flash, anthropic/claude...
-    response_format=GuideOutline
-)
+llm = LLM(model="openai/gpt-4o-mini", response_format=GuideOutline)
 response = llm.call(messages=messages)
 ```
 

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

@@ -68,13 +68,7 @@ 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

@@ -71,10 +71,6 @@ 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

@@ -180,9 +180,8 @@ 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:
@@ -318,7 +317,7 @@ email_summarizer:
       Summarize emails into a concise and clear summary
     backstory: >
       You will create a 5 bullet point summary of the report
-    llm: provider/model-id  # Add your choice of model here
+    llm: openai/gpt-4o
 ```
 
 <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
-uv pip install docx2txt 'crewai[tools]'
+pip install '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 passed 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 passsed 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 provides the ability for the Agent to update the database based on its goal.
+Along with that proivdes 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

@@ -143,30 +143,12 @@ 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)
 ```
 
-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.

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.119.0"
+version = "0.118.0"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
@@ -45,7 +45,7 @@ Documentation = "https://docs.crewai.com"
 Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
-tools = ["crewai-tools~=0.44.0"]
+tools = ["crewai-tools~=0.42.2"]
 embeddings = [
     "tiktoken~=0.7.0"
 ]

src/crewai/__init__.py

@@ -17,7 +17,7 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.119.0"
+__version__ = "0.118.0"
 __all__ = [
     "Agent",
     "Crew",

src/crewai/agent.py

@@ -20,7 +20,6 @@ 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,
 )
@@ -32,14 +31,6 @@ 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
@@ -131,20 +122,6 @@ 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):
@@ -208,7 +185,7 @@ 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.
 
@@ -268,65 +245,27 @@ class Agent(BaseAgent):
         knowledge_config = (
             self.knowledge_config.model_dump() if self.knowledge_config else {}
         )
-
         if self.knowledge:
-            crewai_event_bus.emit(
-                self,
-                event=KnowledgeRetrievalStartedEvent(
-                    agent=self,
-                ),
+            agent_knowledge_snippets = self.knowledge.query(
+                [task.prompt()], **knowledge_config
             )
-            try:
-                self.knowledge_search_query = self._get_knowledge_search_query(
-                    task_prompt
+            if agent_knowledge_snippets:
+                self.agent_knowledge_context = extract_knowledge_context(
+                    agent_knowledge_snippets
                 )
-                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
+                if self.agent_knowledge_context:
+                    task_prompt += self.agent_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_snippets = self.crew.query_knowledge(
+                [task.prompt()], **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
 
         tools = tools or self.tools or []
         self.create_agent_executor(tools=tools, task=task)
@@ -349,19 +288,12 @@ 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(
@@ -413,46 +345,54 @@ 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.
         """
@@ -620,61 +560,6 @@ 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("No token found, make sure you are logged in")
+        raise Exception()
     return access_token

src/crewai/cli/cli.py

@@ -1,5 +1,6 @@
+import os
 from importlib.metadata import version as get_version
-from typing import Optional
+from typing import Optional, Tuple
 
 import click
 
@@ -137,8 +138,12 @@ 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("-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(
+    "-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,
@@ -146,20 +151,18 @@ 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, knowledge, agent_knowledge). This will delete all the data saved.
+    Reset the crew memories (long, short, entity, latest_crew_kickoff_ouputs). This will delete all the data saved.
     """
     try:
-        memory_types = [long, short, entities, knowledge, agent_knowledge, kickoff_outputs, all]
-        if not any(memory_types):
+        if not all and not (long or short or entities or knowledge or kickoff_outputs):
             click.echo(
                 "Please specify at least one memory type to reset using the appropriate flags."
             )
             return
-        reset_memories_command(long, short, entities, knowledge, agent_knowledge, kickoff_outputs, all)
+        reset_memories_command(long, short, entities, knowledge, kickoff_outputs, all)
     except Exception as e:
         click.echo(f"An error occurred while resetting memories: {e}", err=True)
 
@@ -198,9 +201,22 @@ def install(context):
 
 
 @crewai.command()
-def run():
+@click.option(
+    "--record",
+    is_flag=True,
+    help="Record LLM responses for later replay",
+)
+@click.option(
+    "--replay",
+    is_flag=True,
+    help="Replay from recorded LLM responses without making network calls",
+)
+def run(record: bool = False, replay: bool = False):
     """Run the Crew."""
-    run_crew()
+    if record and replay:
+        raise click.UsageError("Cannot use --record and --replay simultaneously")
+    click.echo("Running the Crew")
+    run_crew(record=record, replay=replay)
 
 
 @crewai.command()

src/crewai/cli/constants.py

@@ -13,7 +13,7 @@ ENV_VARS = {
     ],
     "gemini": [
         {
-            "prompt": "Enter your GEMINI API key from https://ai.dev/apikey (press Enter to skip)",
+            "prompt": "Enter your GEMINI API key (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 environments we don't use this command but instead uv sync directly
+# on some enviorments we don't use this command but instead uv sync directly
 # so if you expect this to support more things you will need to replicate it there
 # ask @joaomdmoura if you are unsure
 def install_crew(proxy_options: list[str]) -> None:

src/crewai/cli/plus_api.py

@@ -14,7 +14,6 @@ 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
@@ -38,9 +37,6 @@ 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

@@ -10,7 +10,6 @@ def reset_memories_command(
     short,
     entity,
     knowledge,
-    agent_knowledge,
     kickoff_outputs,
     all,
 ) -> None:
@@ -24,11 +23,10 @@ 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:
-        if not any([long, short, entity, kickoff_outputs, knowledge, agent_knowledge, all]):
+        if not any([long, short, entity, kickoff_outputs, knowledge, all]):
             click.echo(
                 "No memory type specified. Please specify at least one type to reset."
             )
@@ -69,11 +67,6 @@ def reset_memories_command(
                 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/run_crew.py

@@ -14,13 +14,17 @@ class CrewType(Enum):
     FLOW = "flow"
 
 
-def run_crew() -> None:
+def run_crew(record: bool = False, replay: bool = False) -> None:
     """
     Run the crew or flow by running a command in the UV environment.
 
     Starting from version 0.103.0, this command can be used to run both
     standard crews and flows. For flows, it detects the type from pyproject.toml
     and automatically runs the appropriate command.
+    
+    Args:
+        record (bool, optional): Whether to record LLM responses. Defaults to False.
+        replay (bool, optional): Whether to replay from recorded LLM responses. Defaults to False.
     """
     crewai_version = get_crewai_version()
     min_required_version = "0.71.0"
@@ -44,17 +48,24 @@ def run_crew() -> None:
     click.echo(f"Running the {'Flow' if is_flow else 'Crew'}")
 
     # Execute the appropriate command
-    execute_command(crew_type)
+    execute_command(crew_type, record, replay)
 
 
-def execute_command(crew_type: CrewType) -> None:
+def execute_command(crew_type: CrewType, record: bool = False, replay: bool = False) -> None:
     """
     Execute the appropriate command based on crew type.
 
     Args:
         crew_type: The type of crew to run
+        record: Whether to record LLM responses
+        replay: Whether to replay from recorded LLM responses
     """
     command = ["uv", "run", "kickoff" if crew_type == CrewType.FLOW else "run_crew"]
+    
+    if record:
+        command.append("--record")
+    if replay:
+        command.append("--replay")
 
     try:
         subprocess.run(command, capture_output=False, text=True, check=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]>=0.119.0,<1.0.0"
+    "crewai[tools]>=0.118.0,<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]>=0.119.0,<1.0.0",
+    "crewai[tools]>=0.118.0,<1.0.0",
 ]
 
 [project.scripts]

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

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.119.0"
+    "crewai[tools]>=0.118.0"
 ]
 
 [tool.crewai]

src/crewai/crew.py

@@ -52,7 +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 NOT_SPECIFIED, TRAINING_DATA_FILE
+from crewai.utilities.constants import 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 (
@@ -244,6 +244,15 @@ class Crew(FlowTrackable, BaseModel):
         default_factory=SecurityConfig,
         description="Security configuration for the crew, including fingerprinting.",
     )
+    record_mode: bool = Field(
+        default=False,
+        description="Whether to record LLM responses for later replay.",
+    )
+    replay_mode: bool = Field(
+        default=False,
+        description="Whether to replay from recorded LLM responses without making network calls.",
+    )
+    _llm_response_cache_handler: Optional[Any] = PrivateAttr(default=None)
 
     @field_validator("id", mode="before")
     @classmethod
@@ -478,7 +487,7 @@ class Crew(FlowTrackable, BaseModel):
         separated by a synchronous task.
         """
         for i, task in enumerate(self.tasks):
-            if task.async_execution and isinstance(task.context, list):
+            if task.async_execution and task.context:
                 for context_task in task.context:
                     if context_task.async_execution:
                         for j in range(i - 1, -1, -1):
@@ -496,7 +505,7 @@ class Crew(FlowTrackable, BaseModel):
         task_indices = {id(task): i for i, task in enumerate(self.tasks)}
 
         for task in self.tasks:
-            if isinstance(task.context, list):
+            if task.context:
                 for context_task in task.context:
                     if id(context_task) not in task_indices:
                         continue  # Skip context tasks not in the main tasks list
@@ -633,6 +642,19 @@ class Crew(FlowTrackable, BaseModel):
             self._task_output_handler.reset()
             self._logging_color = "bold_purple"
 
+            if self.record_mode and self.replay_mode:
+                raise ValueError("Cannot use both record_mode and replay_mode at the same time")
+                
+            if self.record_mode or self.replay_mode:
+                from crewai.utilities.llm_response_cache_handler import (
+                    LLMResponseCacheHandler,
+                )
+                self._llm_response_cache_handler = LLMResponseCacheHandler()
+                if self.record_mode:
+                    self._llm_response_cache_handler.start_recording()
+                elif self.replay_mode:
+                    self._llm_response_cache_handler.start_replaying()
+
             if inputs is not None:
                 self._inputs = inputs
                 self._interpolate_inputs(inputs)
@@ -651,6 +673,12 @@ class Crew(FlowTrackable, BaseModel):
 
                 if not agent.step_callback:  # type: ignore # "BaseAgent" has no attribute "step_callback"
                     agent.step_callback = self.step_callback  # type: ignore # "BaseAgent" has no attribute "step_callback"
+                    
+                if self._llm_response_cache_handler:
+                    if hasattr(agent, "llm") and agent.llm:
+                        agent.llm.set_response_cache_handler(self._llm_response_cache_handler)
+                    if hasattr(agent, "function_calling_llm") and agent.function_calling_llm:
+                        agent.function_calling_llm.set_response_cache_handler(self._llm_response_cache_handler)
 
                 agent.create_agent_executor()
 
@@ -1034,14 +1062,11 @@ class Crew(FlowTrackable, BaseModel):
                 )
         return cast(List[BaseTool], tools)
 
-    def _get_context(self, task: Task, task_outputs: List[TaskOutput]) -> str:
-        if not task.context:
-            return ""
-
+    def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
         context = (
-            aggregate_raw_outputs_from_task_outputs(task_outputs)
-            if task.context is NOT_SPECIFIED
-            else aggregate_raw_outputs_from_tasks(task.context)
+            aggregate_raw_outputs_from_tasks(task.context)
+            if task.context
+            else aggregate_raw_outputs_from_task_outputs(task_outputs)
         )
         return context
 
@@ -1229,7 +1254,7 @@ class Crew(FlowTrackable, BaseModel):
             task_mapping[task.key] = cloned_task
 
         for cloned_task, original_task in zip(cloned_tasks, self.tasks):
-            if isinstance(original_task.context, list):
+            if original_task.context:
                 cloned_context = [
                     task_mapping[context_task.key]
                     for context_task in original_task.context
@@ -1290,6 +1315,9 @@ class Crew(FlowTrackable, BaseModel):
     def _finish_execution(self, final_string_output: str) -> None:
         if self.max_rpm:
             self._rpm_controller.stop_rpm_counter()
+            
+        if self._llm_response_cache_handler:
+            self._llm_response_cache_handler.stop()
 
     def calculate_usage_metrics(self) -> UsageMetrics:
         """Calculates and returns the usage metrics."""
@@ -1356,7 +1384,7 @@ class Crew(FlowTrackable, BaseModel):
 
         Args:
             command_type: Type of memory to reset.
-                Valid options: 'long', 'short', 'entity', 'knowledge', 'agent_knowledge'
+                Valid options: 'long', 'short', 'entity', 'knowledge',
                 'kickoff_outputs', or 'all'
 
         Raises:
@@ -1369,7 +1397,6 @@ class Crew(FlowTrackable, BaseModel):
                 "short",
                 "entity",
                 "knowledge",
-                "agent_knowledge",
                 "kickoff_outputs",
                 "all",
                 "external",
@@ -1394,14 +1421,19 @@ class Crew(FlowTrackable, BaseModel):
 
     def _reset_all_memories(self) -> None:
         """Reset all available memory systems."""
-        memory_systems = self._get_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)),
+        ]
 
-        for memory_type, config in memory_systems.items():
-            if (system := config.get('system')) is not None:
-                name = config.get('name')
+        for name, system in memory_systems:
+            if system is not None:
                 try:
-                    reset_fn: Callable = cast(Callable, config.get('reset'))
-                    reset_fn(system)
+                    system.reset()
                     self._logger.log(
                         "info",
                         f"[Crew ({self.name if self.name else self.id})] {name} memory has been reset",
@@ -1420,17 +1452,24 @@ class Crew(FlowTrackable, BaseModel):
         Raises:
             RuntimeError: If the specified memory system fails to reset
         """
-        memory_systems = self._get_memory_systems()
-        config = memory_systems[memory_type]
-        system = config.get('system')
-        name = config.get('name')
+        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"),
+        }
 
-        if system is None:
+        memory_system, name = reset_functions[memory_type]
+        if memory_system is None:
             raise RuntimeError(f"{name} memory system is not initialized")
-        
+
         try:
-            reset_fn: Callable = cast(Callable, config.get('reset'))
-            reset_fn(system)
+            memory_system.reset()
             self._logger.log(
                 "info",
                 f"[Crew ({self.name if self.name else self.id})] {name} memory has been reset",
@@ -1439,64 +1478,3 @@ class Crew(FlowTrackable, BaseModel):
             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'
-            }
-        }
-
-    def reset_knowledge(self, knowledges: List[Knowledge]) -> None:
-        """Reset crew and agent knowledge storage."""
-        for ks in knowledges:
-            ks.reset()

src/crewai/knowledge/embedder/chromadb/__init__.py

@@ -1,3 +0,0 @@
-from .utils.embedding_functions import VoyageAIEmbeddingFunction
-
-__all__ = ["VoyageAIEmbeddingFunction"]

src/crewai/knowledge/embedder/chromadb/utils/__init__.py

@@ -1,3 +0,0 @@
-from . import embedding_functions
-
-__all__ = ["embedding_functions"]

src/crewai/knowledge/embedder/chromadb/utils/embedding_functions/__init__.py

@@ -1,3 +0,0 @@
-from .voyageai_embedding_function import VoyageAIEmbeddingFunction
-
-__all__ = ["VoyageAIEmbeddingFunction"]

src/crewai/knowledge/embedder/chromadb/utils/embedding_functions/voyageai_embedding_function.py

@@ -1,91 +0,0 @@
-import logging
-from typing import List, Union
-
-from chromadb.api.types import Documents, EmbeddingFunction
-
-logger = logging.getLogger(__name__)
-
-
-class VoyageAIEmbeddingFunction(EmbeddingFunction[Documents]):
-    """
-    VoyageAI embedding function for ChromaDB.
-    
-    This class provides integration with VoyageAI's embedding models for use with ChromaDB.
-    It supports various VoyageAI models including voyage-3, voyage-3.5, and voyage-3.5-lite.
-    
-    Attributes:
-        _api_key (str): The API key for VoyageAI.
-        _model_name (str): The name of the VoyageAI model to use.
-    """
-
-    def __init__(self, api_key: str, model_name: str = "voyage-3"):
-        """
-        Initialize the VoyageAI embedding function.
-        
-        Args:
-            api_key (str): The API key for VoyageAI.
-            model_name (str, optional): The name of the VoyageAI model to use. 
-                Defaults to "voyage-3".
-        
-        Raises:
-            ValueError: If the voyageai package is not installed or if the API key is empty.
-        """
-        self._ensure_voyageai_installed()
-        
-        if not api_key:
-            raise ValueError("API key is required for VoyageAI embeddings")
-        
-        self._api_key = api_key
-        self._model_name = model_name
-
-    def _ensure_voyageai_installed(self):
-        """
-        Ensure that the voyageai package is installed.
-        
-        Raises:
-            ValueError: If the voyageai package is not installed.
-        """
-        try:
-            import voyageai  # noqa: F401
-        except ImportError:
-            raise ValueError(
-                "The voyageai python package is not installed. Please install it with `pip install voyageai`"
-            )
-
-    def __call__(self, input: Union[str, List[str]]) -> List[List[float]]:
-        """
-        Generate embeddings for the input text(s).
-        
-        Args:
-            input (Union[str, List[str]]): The text or list of texts to generate embeddings for.
-        
-        Returns:
-            List[List[float]]: A list of embeddings, where each embedding is a list of floats.
-        
-        Raises:
-            ValueError: If the input is not a string or list of strings.
-            voyageai.VoyageError: If there is an error with the VoyageAI API.
-        """
-        self._ensure_voyageai_installed()
-        import voyageai
-
-        if not input:
-            return []
-
-        if not isinstance(input, (str, list)):
-            raise ValueError("Input must be a string or a list of strings")
-
-        if isinstance(input, str):
-            input = [input]
-
-        try:
-            embeddings = voyageai.get_embeddings(
-                input, model=self._model_name, api_key=self._api_key
-            )
-            return embeddings
-        except voyageai.VoyageError as e:
-            logger.error(f"VoyageAI API error: {e}")
-            raise
-        except Exception as e:
-            logger.error(f"Unexpected error during VoyageAI embedding: {e}")
-            raise

src/crewai/llm.py

@@ -5,7 +5,8 @@ import sys
 import threading
 import warnings
 from collections import defaultdict
-from contextlib import contextmanager, redirect_stderr, redirect_stdout
+from contextlib import contextmanager
+from types import SimpleNamespace
 from typing import (
     Any,
     DefaultDict,
@@ -30,6 +31,7 @@ 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)
@@ -43,9 +45,6 @@ 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 (
@@ -55,17 +54,12 @@ from crewai.utilities.exceptions.context_window_exceeding_exception import (
 load_dotenv()
 
 
-class FilteredStream(io.TextIOBase):
-    _lock = None
-
-    def __init__(self, original_stream: TextIO):
+class FilteredStream:
+    def __init__(self, original_stream):
         self._original_stream = original_stream
         self._lock = threading.Lock()
 
-    def write(self, s: str) -> int:
-        if not self._lock:
-            self._lock = threading.Lock()
-
+    def write(self, s) -> int:
         with self._lock:
             # Filter out extraneous messages from LiteLLM
             if (
@@ -220,11 +214,15 @@ def suppress_warnings():
         )
 
         # Redirect stdout and stderr
-        with (
-            redirect_stdout(FilteredStream(sys.stdout)),
-            redirect_stderr(FilteredStream(sys.stderr)),
-        ):
+        old_stdout = sys.stdout
+        old_stderr = sys.stderr
+        sys.stdout = FilteredStream(old_stdout)
+        sys.stderr = FilteredStream(old_stderr)
+        try:
             yield
+        finally:
+            sys.stdout = old_stdout
+            sys.stderr = old_stderr
 
 
 class Delta(TypedDict):
@@ -298,6 +296,7 @@ class LLM(BaseLLM):
         self.additional_params = kwargs
         self.is_anthropic = self._is_anthropic_model(model)
         self.stream = stream
+        self._response_cache_handler = None
 
         litellm.drop_params = True
 
@@ -871,25 +870,43 @@ class LLM(BaseLLM):
             for message in messages:
                 if message.get("role") == "system":
                     message["role"] = "assistant"
+                    
+        if self._response_cache_handler and self._response_cache_handler.is_replaying():
+            cached_response = self._response_cache_handler.get_cached_response(
+                self.model, messages
+            )
+            if cached_response:
+                # Emit completion event for the cached response
+                self._handle_emit_call_events(cached_response, LLMCallType.LLM_CALL)
+                return cached_response
 
-        # --- 5) Set up callbacks if provided
+        # --- 6) Set up callbacks if provided
         with suppress_warnings():
             if callbacks and len(callbacks) > 0:
                 self.set_callbacks(callbacks)
 
             try:
-                # --- 6) Prepare parameters for the completion call
+                # --- 7) Prepare parameters for the completion call
                 params = self._prepare_completion_params(messages, tools)
 
-                # --- 7) Make the completion call and handle response
+                # --- 8) Make the completion call and handle response
                 if self.stream:
-                    return self._handle_streaming_response(
+                    response = self._handle_streaming_response(
                         params, callbacks, available_functions
                     )
                 else:
-                    return self._handle_non_streaming_response(
+                    response = self._handle_non_streaming_response(
                         params, callbacks, available_functions
                     )
+                    
+                if (self._response_cache_handler and 
+                    self._response_cache_handler.is_recording() and 
+                    isinstance(response, str)):
+                    self._response_cache_handler.cache_response(
+                        self.model, messages, response
+                    )
+                    
+                return response
 
             except LLMContextLengthExceededException:
                 # Re-raise LLMContextLengthExceededException as it should be handled
@@ -1109,3 +1126,18 @@ class LLM(BaseLLM):
 
                 litellm.success_callback = success_callbacks
                 litellm.failure_callback = failure_callbacks
+                
+    def set_response_cache_handler(self, handler):
+        """
+        Sets the response cache handler for record/replay functionality.
+        
+        Args:
+            handler: An instance of LLMResponseCacheHandler.
+        """
+        self._response_cache_handler = handler
+        
+    def clear_response_cache_handler(self):
+        """
+        Clears the response cache handler.
+        """
+        self._response_cache_handler = None

src/crewai/memory/storage/llm_response_cache_storage.py

@@ -0,0 +1,296 @@
+import hashlib
+import json
+import logging
+import sqlite3
+import threading
+from typing import Any, Dict, List, Optional
+
+from crewai.utilities import Printer
+from crewai.utilities.crew_json_encoder import CrewJSONEncoder
+from crewai.utilities.paths import db_storage_path
+
+logger = logging.getLogger(__name__)
+
+
+class LLMResponseCacheStorage:
+    """
+    SQLite storage for caching LLM responses.
+    Used for offline record/replay functionality.
+    """
+
+    def __init__(
+        self, db_path: str = f"{db_storage_path()}/llm_response_cache.db"
+    ) -> None:
+        self.db_path = db_path
+        self._printer: Printer = Printer()
+        self._connection_pool = {}
+        self._initialize_db()
+
+    def _get_connection(self) -> sqlite3.Connection:
+        """
+        Gets a connection from the connection pool or creates a new one.
+        Uses thread-local storage to ensure thread safety.
+        """
+        thread_id = threading.get_ident()
+        if thread_id not in self._connection_pool:
+            try:
+                conn = sqlite3.connect(self.db_path)
+                conn.execute("PRAGMA foreign_keys = ON")
+                conn.execute("PRAGMA journal_mode = WAL")
+                self._connection_pool[thread_id] = conn
+            except sqlite3.Error as e:
+                error_msg = f"Failed to create SQLite connection: {e}"
+                self._printer.print(
+                    content=f"LLM RESPONSE CACHE ERROR: {error_msg}",
+                    color="red",
+                )
+                logger.error(error_msg)
+                raise
+        return self._connection_pool[thread_id]
+
+    def _close_connections(self) -> None:
+        """
+        Closes all connections in the connection pool.
+        """
+        for thread_id, conn in list(self._connection_pool.items()):
+            try:
+                conn.close()
+                del self._connection_pool[thread_id]
+            except sqlite3.Error as e:
+                error_msg = f"Failed to close SQLite connection: {e}"
+                self._printer.print(
+                    content=f"LLM RESPONSE CACHE ERROR: {error_msg}",
+                    color="red",
+                )
+                logger.error(error_msg)
+
+    def _initialize_db(self) -> None:
+        """
+        Initializes the SQLite database and creates the llm_response_cache table
+        """
+        try:
+            conn = self._get_connection()
+            cursor = conn.cursor()
+            cursor.execute(
+                """
+                CREATE TABLE IF NOT EXISTS llm_response_cache (
+                    request_hash TEXT PRIMARY KEY,
+                    model TEXT,
+                    messages TEXT,
+                    response TEXT,
+                    timestamp DATETIME DEFAULT CURRENT_TIMESTAMP
+                )
+                """
+            )
+            conn.commit()
+        except sqlite3.Error as e:
+            error_msg = f"Failed to initialize database: {e}"
+            self._printer.print(
+                content=f"LLM RESPONSE CACHE ERROR: {error_msg}",
+                color="red",
+            )
+            logger.error(error_msg)
+            raise
+
+    def _compute_request_hash(self, model: str, messages: List[Dict[str, str]]) -> str:
+        """
+        Computes a hash for the request based on the model and messages.
+        This hash is used as the key for caching.
+        
+        Sensitive information like API keys should not be included in the hash.
+        """
+        try:
+            message_str = json.dumps(messages, sort_keys=True)
+            request_hash = hashlib.sha256(f"{model}:{message_str}".encode()).hexdigest()
+            return request_hash
+        except Exception as e:
+            error_msg = f"Failed to compute request hash: {e}"
+            self._printer.print(
+                content=f"LLM RESPONSE CACHE ERROR: {error_msg}",
+                color="red",
+            )
+            logger.error(error_msg)
+            raise
+
+    def add(self, model: str, messages: List[Dict[str, str]], response: str) -> None:
+        """
+        Adds a response to the cache.
+        """
+        try:
+            request_hash = self._compute_request_hash(model, messages)
+            messages_json = json.dumps(messages, cls=CrewJSONEncoder)
+            
+            conn = self._get_connection()
+            cursor = conn.cursor()
+            cursor.execute(
+                """
+                INSERT OR REPLACE INTO llm_response_cache
+                (request_hash, model, messages, response)
+                VALUES (?, ?, ?, ?)
+                """,
+                (
+                    request_hash,
+                    model,
+                    messages_json,
+                    response,
+                ),
+            )
+            conn.commit()
+        except sqlite3.Error as e:
+            error_msg = f"Failed to add response to cache: {e}"
+            self._printer.print(
+                content=f"LLM RESPONSE CACHE ERROR: {error_msg}",
+                color="red",
+            )
+            logger.error(error_msg)
+            raise
+        except Exception as e:
+            error_msg = f"Unexpected error when adding response: {e}"
+            self._printer.print(
+                content=f"LLM RESPONSE CACHE ERROR: {error_msg}",
+                color="red",
+            )
+            logger.error(error_msg)
+            raise
+
+    def get(self, model: str, messages: List[Dict[str, str]]) -> Optional[str]:
+        """
+        Retrieves a response from the cache based on the model and messages.
+        Returns None if not found.
+        """
+        try:
+            request_hash = self._compute_request_hash(model, messages)
+            
+            conn = self._get_connection()
+            cursor = conn.cursor()
+            cursor.execute(
+                """
+                SELECT response
+                FROM llm_response_cache
+                WHERE request_hash = ?
+                """,
+                (request_hash,),
+            )
+            
+            result = cursor.fetchone()
+            return result[0] if result else None
+                
+        except sqlite3.Error as e:
+            error_msg = f"Failed to retrieve response from cache: {e}"
+            self._printer.print(
+                content=f"LLM RESPONSE CACHE ERROR: {error_msg}",
+                color="red",
+            )
+            logger.error(error_msg)
+            return None
+        except Exception as e:
+            error_msg = f"Unexpected error when retrieving response: {e}"
+            self._printer.print(
+                content=f"LLM RESPONSE CACHE ERROR: {error_msg}",
+                color="red",
+            )
+            logger.error(error_msg)
+            return None
+
+    def delete_all(self) -> None:
+        """
+        Deletes all records from the llm_response_cache table.
+        """
+        try:
+            conn = self._get_connection()
+            cursor = conn.cursor()
+            cursor.execute("DELETE FROM llm_response_cache")
+            conn.commit()
+        except sqlite3.Error as e:
+            error_msg = f"Failed to clear cache: {e}"
+            self._printer.print(
+                content=f"LLM RESPONSE CACHE ERROR: {error_msg}",
+                color="red",
+            )
+            logger.error(error_msg)
+            raise
+
+    def cleanup_expired_cache(self, max_age_days: int = 7) -> None:
+        """
+        Removes cache entries older than the specified number of days.
+        
+        Args:
+            max_age_days: Maximum age of cache entries in days. Defaults to 7.
+                          If set to 0, all entries will be deleted.
+        """
+        try:
+            conn = self._get_connection()
+            cursor = conn.cursor()
+            
+            if max_age_days <= 0:
+                cursor.execute("DELETE FROM llm_response_cache")
+                deleted_count = cursor.rowcount
+                logger.info("Deleting all cache entries (max_age_days <= 0)")
+            else:
+                cursor.execute(
+                    f"""
+                    DELETE FROM llm_response_cache
+                    WHERE timestamp < datetime('now', '-{max_age_days} days')
+                    """
+                )
+                deleted_count = cursor.rowcount
+                
+            conn.commit()
+            
+            if deleted_count > 0:
+                self._printer.print(
+                    content=f"LLM RESPONSE CACHE: Removed {deleted_count} expired cache entries",
+                    color="green",
+                )
+                logger.info(f"Removed {deleted_count} expired cache entries")
+                
+        except sqlite3.Error as e:
+            error_msg = f"Failed to cleanup expired cache: {e}"
+            self._printer.print(
+                content=f"LLM RESPONSE CACHE ERROR: {error_msg}",
+                color="red",
+            )
+            logger.error(error_msg)
+            raise
+
+    def get_cache_stats(self) -> Dict[str, Any]:
+        """
+        Returns statistics about the cache.
+        
+        Returns:
+            A dictionary containing cache statistics.
+        """
+        try:
+            conn = self._get_connection()
+            cursor = conn.cursor()
+            
+            cursor.execute("SELECT COUNT(*) FROM llm_response_cache")
+            total_count = cursor.fetchone()[0]
+            
+            cursor.execute("SELECT model, COUNT(*) FROM llm_response_cache GROUP BY model")
+            model_counts = {model: count for model, count in cursor.fetchall()}
+            
+            cursor.execute("SELECT MIN(timestamp), MAX(timestamp) FROM llm_response_cache")
+            oldest, newest = cursor.fetchone()
+            
+            return {
+                "total_entries": total_count,
+                "entries_by_model": model_counts,
+                "oldest_entry": oldest,
+                "newest_entry": newest,
+            }
+            
+        except sqlite3.Error as e:
+            error_msg = f"Failed to get cache stats: {e}"
+            self._printer.print(
+                content=f"LLM RESPONSE CACHE ERROR: {error_msg}",
+                color="red",
+            )
+            logger.error(error_msg)
+            return {"error": str(e)}
+
+    def __del__(self) -> None:
+        """
+        Closes all connections when the object is garbage collected.
+        """
+        self._close_connections()

src/crewai/task.py

@@ -2,6 +2,7 @@ import datetime
 import inspect
 import json
 import logging
+import re
 import threading
 import uuid
 from concurrent.futures import Future
@@ -40,7 +41,6 @@ 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=NOT_SPECIFIED,
+        default=None,
     )
     async_execution: Optional[bool] = Field(
         description="Whether the task should be executed asynchronously or not.",
@@ -643,7 +643,7 @@ class Task(BaseModel):
 
         cloned_context = (
             [task_mapping[context_task.key] for context_task in self.context]
-            if isinstance(self.context, list)
+            if self.context
             else None
         )
 

src/crewai/telemetry/telemetry.py

@@ -10,18 +10,6 @@ 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,
@@ -37,6 +25,18 @@ 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 (  # noqa: E402
+    BatchSpanProcessor,
+    SpanExportResult,
+)
+from opentelemetry.trace import Span, Status, StatusCode  # noqa: E402
+
 if TYPE_CHECKING:
     from crewai.crew import Crew
     from crewai.task import Task
@@ -232,7 +232,7 @@ class Telemetry:
                                 "agent_key": task.agent.key if task.agent else None,
                                 "context": (
                                     [task.description for task in task.context]
-                                    if isinstance(task.context, list)
+                                    if task.context
                                     else None
                                 ),
                                 "tools_names": [
@@ -748,7 +748,7 @@ class Telemetry:
                             "agent_key": task.agent.key if task.agent else None,
                             "context": (
                                 [task.description for task in task.context]
-                                if isinstance(task.context, list)
+                                if task.context
                                 else None
                             ),
                             "tools_names": [

src/crewai/translations/en.json

@@ -27,9 +27,7 @@
     "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.",
-    "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."
+    "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."
   },
   "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

@@ -16,7 +16,6 @@ from crewai.tools.base_tool import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.tools.tool_types import ToolResult
 from crewai.utilities import I18N, Printer
-from crewai.utilities.errors import AgentRepositoryError
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
 )
@@ -429,41 +428,3 @@ 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

@@ -5,14 +5,3 @@ 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/embedding_configurator.py

@@ -140,7 +140,7 @@ class EmbeddingConfigurator:
 
     @staticmethod
     def _configure_voyageai(config, model_name):
-        from crewai.knowledge.embedder.chromadb.utils.embedding_functions.voyageai_embedding_function import (
+        from chromadb.utils.embedding_functions.voyageai_embedding_function import (
             VoyageAIEmbeddingFunction,
         )
 

src/crewai/utilities/errors.py

@@ -1,5 +1,4 @@
 """Error message definitions for CrewAI database operations."""
-
 from typing import Optional
 
 
@@ -38,9 +37,3 @@ 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/event_listener.py

@@ -8,14 +8,6 @@ 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,
@@ -65,8 +57,6 @@ 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:
@@ -352,59 +342,5 @@ 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

@@ -1,56 +0,0 @@
-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

@@ -783,202 +783,3 @@ 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
@@ -17,11 +17,6 @@ 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]
-        if isinstance(tasks, list)
-        else []
-    )
+    task_outputs = [task.output for task in tasks if task.output is not None]
 
     return aggregate_raw_outputs_from_task_outputs(task_outputs)

src/crewai/utilities/llm_response_cache_handler.py

@@ -0,0 +1,156 @@
+import logging
+from typing import Any, Dict, List, Optional
+
+from crewai.memory.storage.llm_response_cache_storage import LLMResponseCacheStorage
+
+logger = logging.getLogger(__name__)
+
+
+class LLMResponseCacheHandler:
+    """
+    Handler for the LLM response cache storage.
+    Used for record/replay functionality.
+    """
+
+    def __init__(self, max_cache_age_days: int = 7) -> None:
+        """
+        Initializes the LLM response cache handler.
+        
+        Args:
+            max_cache_age_days: Maximum age of cache entries in days. Defaults to 7.
+        """
+        self.storage = LLMResponseCacheStorage()
+        self._recording = False
+        self._replaying = False
+        self.max_cache_age_days = max_cache_age_days
+        
+        try:
+            self.storage.cleanup_expired_cache(self.max_cache_age_days)
+        except Exception as e:
+            logger.warning(f"Failed to cleanup expired cache on initialization: {e}")
+
+    def start_recording(self) -> None:
+        """
+        Starts recording LLM responses.
+        """
+        self._recording = True
+        self._replaying = False
+        logger.info("Started recording LLM responses")
+
+    def start_replaying(self) -> None:
+        """
+        Starts replaying LLM responses from the cache.
+        """
+        self._recording = False
+        self._replaying = True
+        logger.info("Started replaying LLM responses from cache")
+        
+        try:
+            stats = self.storage.get_cache_stats()
+            logger.info(f"Cache statistics: {stats}")
+        except Exception as e:
+            logger.warning(f"Failed to get cache statistics: {e}")
+
+    def stop(self) -> None:
+        """
+        Stops recording or replaying.
+        """
+        was_recording = self._recording
+        was_replaying = self._replaying
+        
+        self._recording = False
+        self._replaying = False
+        
+        if was_recording:
+            logger.info("Stopped recording LLM responses")
+        if was_replaying:
+            logger.info("Stopped replaying LLM responses")
+
+    def is_recording(self) -> bool:
+        """
+        Returns whether recording is active.
+        """
+        return self._recording
+
+    def is_replaying(self) -> bool:
+        """
+        Returns whether replaying is active.
+        """
+        return self._replaying
+
+    def cache_response(self, model: str, messages: List[Dict[str, str]], response: str) -> None:
+        """
+        Caches an LLM response if recording is active.
+        
+        Args:
+            model: The model used for the LLM call.
+            messages: The messages sent to the LLM.
+            response: The response from the LLM.
+        """
+        if not self._recording:
+            return
+            
+        try:
+            self.storage.add(model, messages, response)
+            logger.debug(f"Cached response for model {model}")
+        except Exception as e:
+            logger.error(f"Failed to cache response: {e}")
+
+    def get_cached_response(self, model: str, messages: List[Dict[str, str]]) -> Optional[str]:
+        """
+        Retrieves a cached LLM response if replaying is active.
+        Returns None if not found or if replaying is not active.
+        
+        Args:
+            model: The model used for the LLM call.
+            messages: The messages sent to the LLM.
+            
+        Returns:
+            The cached response, or None if not found or if replaying is not active.
+        """
+        if not self._replaying:
+            return None
+            
+        try:
+            response = self.storage.get(model, messages)
+            if response:
+                logger.debug(f"Retrieved cached response for model {model}")
+            else:
+                logger.debug(f"No cached response found for model {model}")
+            return response
+        except Exception as e:
+            logger.error(f"Failed to retrieve cached response: {e}")
+            return None
+
+    def clear_cache(self) -> None:
+        """
+        Clears the LLM response cache.
+        """
+        try:
+            self.storage.delete_all()
+            logger.info("Cleared LLM response cache")
+        except Exception as e:
+            logger.error(f"Failed to clear cache: {e}")
+            
+    def cleanup_expired_cache(self) -> None:
+        """
+        Removes cache entries older than the maximum age.
+        """
+        try:
+            self.storage.cleanup_expired_cache(self.max_cache_age_days)
+            logger.info(f"Cleaned up expired cache entries (older than {self.max_cache_age_days} days)")
+        except Exception as e:
+            logger.error(f"Failed to cleanup expired cache: {e}")
+            
+    def get_cache_stats(self) -> Dict[str, Any]:
+        """
+        Returns statistics about the cache.
+        
+        Returns:
+            A dictionary containing cache statistics.
+        """
+        try:
+            return self.storage.get_cache_stats()
+        except Exception as e:
+            logger.error(f"Failed to get cache stats: {e}")
+            return {"error": str(e)}

tests/agent_test.py

@@ -2,13 +2,14 @@
 
 import os
 from unittest import mock
-from unittest.mock import MagicMock, patch
+from unittest.mock import 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
@@ -18,7 +19,6 @@ 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
 
@@ -73,7 +73,6 @@ 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(
@@ -89,7 +88,6 @@ 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(
@@ -121,8 +119,7 @@ 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"
@@ -309,7 +306,9 @@ 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.",
@@ -1039,7 +1038,7 @@ 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)
@@ -1631,10 +1630,13 @@ 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") as MockKnowledge:
+
+    with patch(
+        "crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"
+    ) as MockKnowledge:
         mock_knowledge_instance = MockKnowledge.return_value
         mock_knowledge_instance.sources = [string_source]
-        mock_knowledge_instance.search.return_value = [{"content": content}]
+        mock_knowledge_instance.query.return_value = [{"content": content}]
 
         agent = Agent(
             role="Information Agent",
@@ -1688,7 +1690,7 @@ 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(
-                ["Brandon's favorite color"],
+                [task.prompt()],
                 **knowledge_config.model_dump(),
             )
 
@@ -1725,7 +1727,7 @@ 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(
-                ["Brandon's favorite color"],
+                [task.prompt()],
                 **knowledge_config.model_dump(),
             )
 
@@ -1735,7 +1737,9 @@ 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") as MockKnowledge:
+    with patch(
+        "crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"
+    ) as MockKnowledge:
         mock_knowledge_instance = MockKnowledge.return_value
         mock_knowledge_instance.sources = [string_source]
         mock_knowledge_instance.query.return_value = [{"content": content}]
@@ -1799,40 +1803,6 @@ 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."""
@@ -1970,153 +1940,3 @@ 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

@@ -1,660 +0,0 @@
-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
+      - gzip, deflate, zstd
       connection:
       - keep-alive
       content-length:
@@ -151,7 +151,7 @@ interactions:
         6NrP9D+nrsnf4z///rMV/t41+GfqpvT1/z7/1/dV//Wv/wUAAP//AwBcfFVx4CAAAA==
     headers:
       CF-RAY:
-      - 93bd535cca31f973-SJC
+      - 931fcf607c16eb34-SJC
       Connection:
       - keep-alive
       Content-Encoding:
@@ -159,14 +159,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 07 May 2025 02:35:43 GMT
+      - Thu, 17 Apr 2025 23:47:53 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __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;
+      - __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;
         Secure; SameSite=None
-      - _cfuvid=SlYSO8wQlhrJsTTYoTXd7IBl_D9ZddMlIzW1PTFiZIE-1746585343627-0.0.1.1-604800000;
+      - _cfuvid=unfPTYCpF5COtm5PuZDuaJqlhefP0iibfjsXHc9lKq0-1744933673515-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -185,15 +185,15 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '38'
+      - '75'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
       via:
-      - envoy-router-6fcbcbb5fd-pxw6t
+      - envoy-router-8687b6cbdb-4qpmr
       x-envoy-upstream-service-time:
-      - '41'
+      - '46'
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
@@ -207,125 +207,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_39d01dc72178a8952d00ba36c7512521
-    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: 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
-      connection:
-      - keep-alive
-      content-length:
-      - '992'
-      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 |
-        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:
-      - 93bd535e5f0b3ad4-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 07 May 2025 02:35:43 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __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=vNgB2gnZiY_kSsrGNv.zug22PCkhqeyHmMQUQ5_FfM8-1746585343998-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '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
+      - req_b8c884a7fe2bd4732903ecbdc632576d
     status:
       code: 200
       message: OK
@@ -346,16 +228,13 @@ interactions:
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate
+      - gzip, deflate, zstd
       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:
@@ -385,20 +264,18 @@ interactions:
   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==
+        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==
     headers:
       CF-RAY:
-      - 93bd53604e3f3ad4-SJC
+      - 931fcf649bdbed40-SJC
       Connection:
       - keep-alive
       Content-Encoding:
@@ -406,9 +283,15 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 07 May 2025 02:35:45 GMT
+      - Thu, 17 Apr 2025 23:47:54 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;
+        Secure; SameSite=None
+      - _cfuvid=IXAyT8eWpFERM53ngcYNmaqhocfGbOHWSoe7SFNdoGI-1744933674288-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
@@ -422,13 +305,11 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '933'
+      - '489'
       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:
@@ -436,13 +317,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '29999'
       x-ratelimit-remaining-tokens:
-      - '149999802'
+      - '149999801'
       x-ratelimit-reset-requests:
       - 2ms
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_0001c38df543cc383617c370087f0ee3
+      - req_151f9d0b786f2022f249ee20ea108b43
     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
+      - gzip, deflate, zstd
       connection:
       - keep-alive
       content-length:
@@ -150,10 +150,8 @@ 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:
-      - 93bd57189acf15be-SJC
+      - 931fceef786ded38-SJC
       Connection:
       - keep-alive
       Content-Encoding:
@@ -161,14 +159,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 07 May 2025 02:38:16 GMT
+      - Thu, 17 Apr 2025 23:47:35 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __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;
+      - __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;
         Secure; SameSite=None
-      - _cfuvid=sAoMYVxAaEFBkQttcKO7GlBZ5NlUNUIaJomZ05pGlCs-1746585496569-0.0.1.1-604800000;
+      - _cfuvid=MSkpJsQZtdyIGvrl2mIwy0a_We8H6CIrS7etFgRBl2Y-1744933655703-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -180,20 +178,22 @@ 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:
-      - '69'
+      - '140'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
       via:
-      - envoy-router-7d545f8f56-jx5wk
+      - envoy-router-84959bbcd5-rzqvq
       x-envoy-upstream-service-time:
-      - '52'
+      - '110'
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
@@ -207,125 +207,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_73f3f0d371e3c19b16c7a6d7cc45d3ee
-    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: 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
-      connection:
-      - keep-alive
-      content-length:
-      - '992'
-      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 |
-        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:
-      - 93bd571a5a7267e2-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 07 May 2025 02:38:17 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __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=LPWfk79PGAoGrMHseblqRazN9H8qdBY0BP50Y1Bp5wI-1746585497006-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '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
+      - req_dd3ef61c4765b46ed7db80ddfe261f41
     status:
       code: 200
       message: OK
@@ -346,16 +228,13 @@ interactions:
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate
+      - gzip, deflate, zstd
       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:
@@ -385,20 +264,20 @@ interactions:
   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==
+        H4sIAAAAAAAAAwAAAP//jFLBbtswDL37KwhdeokLx0mbOLd2WIAC63YZdthWGIpMO9xkUZDkpEWR
+        fx/kpLG7dUAvBszHR733yOcEQFAlViDUVgbVWp3efv66LvKPRd7Q/f57vtaf7m6ePjze774sv23E
+        JDJ48wtVeGFdKm6txkBsjrByKAPGqdPFfF7MZtdXVz3QcoU60hob0jmnLRlK8yyfp9kinS5P7C2T
+        Qi9W8CMBAHjuv1GnqfBRrCCbvFRa9F42KFbnJgDhWMeKkN6TD9IEMRlAxSag6aXfgeE9KGmgoR2C
+        hCbKBmn8Hh3AT7MmIzXc9P8ruHXSVGwuPNRyx44CgmLNDsjDRnd4OX7GYd15Ga2aTusRII3hIGNU
+        vcGHE3I4W9LcWMcb/xdV1GTIb0uH0rOJ8n1gK3r0kAA89NF1r9IQ1nFrQxn4N/bPTa+Xx3li2NgI
+        LU5g4CD1qL5cTN6YV1YYJGk/Cl8oqbZYDdRhU7KriEdAMnL9r5q3Zh+dk2neM34AlEIbsCqtw4rU
+        a8dDm8N40P9rO6fcCxYe3Y4UloHQxU1UWMtOH89M+CcfsC1rMg066+h4a7Uts1mRL/M8KzKRHJI/
+        AAAA//8DALRhJdF5AwAA
     headers:
+      CF-Cache-Status:
+      - DYNAMIC
       CF-RAY:
-      - 93bd571c9cf367e2-SJC
+      - 931fcef51a67f947-SJC
       Connection:
       - keep-alive
       Content-Encoding:
@@ -406,9 +285,15 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 07 May 2025 02:38:18 GMT
+      - Thu, 17 Apr 2025 23:47:36 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;
+        Secure; SameSite=None
+      - _cfuvid=LdTrzwZYrB6ZyQLY7NdaaHVpDVFvIjYm3arSpNy87wU-1744933656504-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
@@ -417,18 +302,14 @@ interactions:
       - X-Request-ID
       alt-svc:
       - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '785'
+      - '540'
       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:
@@ -442,7 +323,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_9bf7c8e011b2b1a8e8546b68c82384a7
+      - req_8837be6510731522fd5ac4b75c11d486
     status:
       code: 200
       message: OK

tests/cassettes/test_get_knowledge_search_query.yaml

@@ -1,333 +0,0 @@
-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 structured output in
+      "content": "What is the population of Tokyo? Return your strucutred output in
       JSON format with the following fields: summary, confidence"}], "model": "gpt-4o-mini",
       "stop": []}'
     headers:

tests/cli/cli_test.py

@@ -162,18 +162,8 @@ def test_reset_knowledge(mock_get_crews, runner):
     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)

tests/crew_test.py

@@ -2,19 +2,22 @@
 
 import hashlib
 import json
+import os
+import tempfile
 from concurrent.futures import Future
 from unittest import mock
-from unittest.mock import ANY, MagicMock, patch
+from unittest.mock import 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.flow import Flow, listen, start
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.llm import LLM
 from crewai.memory.contextual.contextual_memory import ContextualMemory
@@ -3138,30 +3141,6 @@ 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")
@@ -4404,165 +4383,3 @@ def test_sets_parent_flow_when_inside_flow(researcher, 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/llm_response_cache_test.py

@@ -0,0 +1,155 @@
+import sqlite3
+import threading
+from concurrent.futures import ThreadPoolExecutor
+from types import SimpleNamespace
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from crewai.llm import LLM
+from crewai.memory.storage.llm_response_cache_storage import LLMResponseCacheStorage
+from crewai.utilities.llm_response_cache_handler import LLMResponseCacheHandler
+
+
+@pytest.fixture
+def handler():
+    handler = LLMResponseCacheHandler()
+    handler.storage.add = MagicMock()
+    handler.storage.get = MagicMock()
+    return handler
+
+
+def create_mock_response(content):
+    """Create a properly structured mock response object for litellm.completion"""
+    message = SimpleNamespace(content=content)
+    choice = SimpleNamespace(message=message)
+    response = SimpleNamespace(choices=[choice])
+    return response
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_llm_recording(handler):
+    handler.start_recording()
+    
+    llm = LLM(model="gpt-4o-mini")
+    llm.set_response_cache_handler(handler)
+    
+    messages = [{"role": "user", "content": "Hello, world!"}]
+    
+    with patch('litellm.completion') as mock_completion:
+        mock_completion.return_value = create_mock_response("Hello, human!")
+        
+        response = llm.call(messages)
+        
+        assert response == "Hello, human!"
+        
+        handler.storage.add.assert_called_once_with(
+            "gpt-4o-mini", messages, "Hello, human!"
+        )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_llm_replaying(handler):
+    handler.start_replaying()
+    handler.storage.get.return_value = "Cached response"
+    
+    llm = LLM(model="gpt-4o-mini")
+    llm.set_response_cache_handler(handler)
+    
+    messages = [{"role": "user", "content": "Hello, world!"}]
+    
+    with patch('litellm.completion') as mock_completion:
+        response = llm.call(messages)
+        
+        assert response == "Cached response"
+        
+        mock_completion.assert_not_called()
+        
+        handler.storage.get.assert_called_once_with("gpt-4o-mini", messages)
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_llm_replay_fallback(handler):
+    handler.start_replaying()
+    handler.storage.get.return_value = None
+    
+    llm = LLM(model="gpt-4o-mini")
+    llm.set_response_cache_handler(handler)
+    
+    messages = [{"role": "user", "content": "Hello, world!"}]
+    
+    with patch('litellm.completion') as mock_completion:
+        mock_completion.return_value = create_mock_response("Hello, human!")
+        
+        response = llm.call(messages)
+        
+        assert response == "Hello, human!"
+        
+        mock_completion.assert_called_once()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_cache_error_handling():
+    """Test that errors during cache operations are handled gracefully."""
+    handler = LLMResponseCacheHandler()
+    
+    handler.storage.add = MagicMock(side_effect=sqlite3.Error("Mock DB error"))
+    handler.storage.get = MagicMock(side_effect=sqlite3.Error("Mock DB error"))
+    
+    handler.start_recording()
+    
+    handler.cache_response("model", [{"role": "user", "content": "test"}], "response")
+    
+    handler.start_replaying()
+    
+    assert handler.get_cached_response("model", [{"role": "user", "content": "test"}]) is None
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_cache_expiration():
+    """Test that cache expiration works correctly."""
+    import sqlite3
+    
+    conn = sqlite3.connect(":memory:")
+    cursor = conn.cursor()
+    cursor.execute(
+        """
+        CREATE TABLE IF NOT EXISTS llm_response_cache (
+            request_hash TEXT PRIMARY KEY,
+            model TEXT,
+            messages TEXT,
+            response TEXT,
+            timestamp DATETIME DEFAULT CURRENT_TIMESTAMP
+        )
+        """
+    )
+    conn.commit()
+    
+    storage = LLMResponseCacheStorage(":memory:")
+    
+    original_get_connection = storage._get_connection
+    storage._get_connection = lambda: conn
+    
+    try:
+        model = "test-model"
+        messages = [{"role": "user", "content": "test"}]
+        response = "test response"
+        storage.add(model, messages, response)
+        
+        assert storage.get(model, messages) == response
+        
+        storage.cleanup_expired_cache(max_age_days=0)
+        
+        assert storage.get(model, messages) is None
+    finally:
+        storage._get_connection = original_get_connection
+        conn.close()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_concurrent_cache_access():
+    """Test that concurrent cache access works correctly."""
+    pytest.skip("SQLite in-memory databases are not shared between threads")
+    
+    
+    # storage = LLMResponseCacheStorage(temp_db.name)

tests/record_replay_test.py

@@ -0,0 +1,93 @@
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from crewai.agent import Agent
+from crewai.crew import Crew
+from crewai.process import Process
+from crewai.task import Task
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_recording_mode():
+    agent = Agent(
+        role="Test Agent",
+        goal="Test the recording functionality",
+        backstory="A test agent for recording LLM responses",
+    )
+    
+    task = Task(
+        description="Return a simple response",
+        expected_output="A simple response",
+        agent=agent,
+    )
+    
+    crew = Crew(
+        agents=[agent],
+        tasks=[task],
+        process=Process.sequential,
+        record_mode=True,
+    )
+    
+    mock_handler = MagicMock()
+    crew._llm_response_cache_handler = mock_handler
+    
+    mock_llm = MagicMock()
+    agent.llm = mock_llm
+    
+    with patch('crewai.agent.Agent.execute_task', return_value="Test response"):
+        with patch('crewai.utilities.llm_response_cache_handler.LLMResponseCacheHandler', return_value=mock_handler):
+            crew.kickoff()
+    
+    mock_handler.start_recording.assert_called_once()
+    
+    mock_llm.set_response_cache_handler.assert_called_once_with(mock_handler)
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_replay_mode():
+    agent = Agent(
+        role="Test Agent",
+        goal="Test the replay functionality",
+        backstory="A test agent for replaying LLM responses",
+    )
+    
+    task = Task(
+        description="Return a simple response",
+        expected_output="A simple response",
+        agent=agent,
+    )
+    
+    crew = Crew(
+        agents=[agent],
+        tasks=[task],
+        process=Process.sequential,
+        replay_mode=True,
+    )
+    
+    mock_handler = MagicMock()
+    crew._llm_response_cache_handler = mock_handler
+    
+    mock_llm = MagicMock()
+    agent.llm = mock_llm
+    
+    with patch('crewai.agent.Agent.execute_task', return_value="Test response"):
+        with patch('crewai.utilities.llm_response_cache_handler.LLMResponseCacheHandler', return_value=mock_handler):
+            crew.kickoff()
+    
+    mock_handler.start_replaying.assert_called_once()
+    
+    mock_llm.set_response_cache_handler.assert_called_once_with(mock_handler)
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_record_replay_flags_conflict():
+    with pytest.raises(ValueError):
+        crew = Crew(
+            agents=[],
+            tasks=[],
+            process=Process.sequential,
+            record_mode=True,
+            replay_mode=True,
+        )
+        crew.kickoff()

tests/utilities/test_converter.py

@@ -357,7 +357,14 @@ def test_convert_with_instructions():
     assert output.age == 30
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+# 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")
 def test_converter_with_llama3_2_model():
     llm = LLM(model="ollama/llama3.2:3b", base_url="http://localhost:11434")
     sample_text = "Name: Alice Llama, Age: 30"
@@ -374,7 +381,8 @@ def test_converter_with_llama3_2_model():
     assert output.age == 30
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@skip_external_api
+@pytest.mark.vcr(filter_headers=["authorization"], record_mode="once")
 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"
@@ -391,6 +399,13 @@ 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")

tests/utilities/test_embedding_configurator.py

@@ -1,80 +0,0 @@
-import pytest
-from unittest.mock import patch, MagicMock
-
-from crewai.utilities.embedding_configurator import EmbeddingConfigurator
-
-
-class TestEmbeddingConfigurator:
-    def test_configure_voyageai_embedder(self):
-        """Test that the VoyageAI embedder is configured correctly."""
-        with patch(
-            "crewai.utilities.embedding_configurator.VoyageAIEmbeddingFunction"
-        ) as mock_voyageai:
-            mock_instance = MagicMock()
-            mock_voyageai.return_value = mock_instance
-
-            config = {"api_key": "test-key"}
-            model_name = "voyage-3"
-
-            configurator = EmbeddingConfigurator()
-            embedder = configurator._configure_voyageai(config, model_name)
-
-            mock_voyageai.assert_called_once_with(
-                model_name=model_name, api_key="test-key"
-            )
-            assert embedder == mock_instance
-
-    def test_configure_embedder_with_voyageai(self):
-        """Test that the embedder configurator correctly handles VoyageAI provider."""
-        with patch(
-            "crewai.utilities.embedding_configurator.VoyageAIEmbeddingFunction"
-        ) as mock_voyageai:
-            mock_instance = MagicMock()
-            mock_voyageai.return_value = mock_instance
-
-            embedder_config = {
-                "provider": "voyageai",
-                "config": {"api_key": "test-key", "model": "voyage-3"},
-            }
-
-            configurator = EmbeddingConfigurator()
-            embedder = configurator.configure_embedder(embedder_config)
-
-            mock_voyageai.assert_called_once_with(
-                model_name="voyage-3", api_key="test-key"
-            )
-            assert embedder == mock_instance
-            
-    def test_configure_voyageai_embedder_missing_api_key(self):
-        """Test that the VoyageAI embedder raises an error when API key is missing."""
-        with patch(
-            "crewai.utilities.embedding_configurator.VoyageAIEmbeddingFunction"
-        ) as mock_voyageai:
-            mock_voyageai.side_effect = ValueError("API key is required for VoyageAI embeddings")
-
-            config = {}  # Empty config without API key
-            model_name = "voyage-3"
-
-            configurator = EmbeddingConfigurator()
-            
-            with pytest.raises(ValueError, match="API key is required"):
-                configurator._configure_voyageai(config, model_name)
-                
-    def test_configure_voyageai_embedder_custom_model(self):
-        """Test that the VoyageAI embedder works with different model names."""
-        with patch(
-            "crewai.utilities.embedding_configurator.VoyageAIEmbeddingFunction"
-        ) as mock_voyageai:
-            mock_instance = MagicMock()
-            mock_voyageai.return_value = mock_instance
-
-            config = {"api_key": "test-key"}
-            model_name = "voyage-3.5-lite"  # Using a different model
-
-            configurator = EmbeddingConfigurator()
-            embedder = configurator._configure_voyageai(config, model_name)
-
-            mock_voyageai.assert_called_once_with(
-                model_name=model_name, api_key="test-key"
-            )
-            assert embedder == mock_instance

uv.lock

@@ -738,7 +738,7 @@ wheels = [
 
 [[package]]
 name = "crewai"
-version = "0.119.0"
+version = "0.118.0"
 source = { editable = "." }
 dependencies = [
     { name = "appdirs" },
@@ -828,7 +828,7 @@ requires-dist = [
     { name = "blinker", specifier = ">=1.9.0" },
     { name = "chromadb", specifier = ">=0.5.23" },
     { name = "click", specifier = ">=8.1.7" },
-    { name = "crewai-tools", marker = "extra == 'tools'", specifier = "~=0.44.0" },
+    { name = "crewai-tools", marker = "extra == 'tools'", specifier = "~=0.42.2" },
     { name = "docling", marker = "extra == 'docling'", specifier = ">=2.12.0" },
     { name = "fastembed", marker = "extra == 'fastembed'", specifier = ">=0.4.1" },
     { name = "instructor", specifier = ">=1.3.3" },
@@ -879,7 +879,7 @@ dev = [
 
 [[package]]
 name = "crewai-tools"
-version = "0.44.0"
+version = "0.42.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "chromadb" },
@@ -894,9 +894,9 @@ dependencies = [
     { name = "pytube" },
     { name = "requests" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/b8/1f/2977dc72628c1225bf5788ae22a65e5a53df384d19b197646d2c4760684e/crewai_tools-0.44.0.tar.gz", hash = "sha256:44e0c26079396503a326efdd9ff34bf369d410cbf95c362cc523db65b18f3c3a", size = 892004 }
+sdist = { url = "https://files.pythonhosted.org/packages/17/34/9e63e2db53d8f5c30353f271a3240687a48e55204bbd176a057c0b7658c8/crewai_tools-0.42.2.tar.gz", hash = "sha256:69365ffb168cccfea970e09b308905aa5007cfec60024d731ffac1362a0153c0", size = 754967 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ba/80/b91aa837d06edbb472445ea3c92d7619518894fd3049d480e5fffbf0c21b/crewai_tools-0.44.0-py3-none-any.whl", hash = "sha256:119e2365fe66ee16e18a5e8e222994b19f76bafcc8c1bb87f61609c1e39b2463", size = 583462 },
+    { url = "https://files.pythonhosted.org/packages/4e/43/0f70b95350084e5cb1e1d74e9acb9e18a89ba675b1d579c787c2662baba7/crewai_tools-0.42.2-py3-none-any.whl", hash = "sha256:13727fb68f0efefd21edeb281be3d66ff2f5a3b5029d4e6adef388b11fd5846a", size = 583933 },
 ]
 
 [[package]]