Fix type error and test issues

Co-Authored-By: Joe Moura <joao@crewai.com>
Fix import sorting with ruff
2026-01-05 22:28:29 +00:00 · 2025-04-25 21:03:36 +00:00 · 2025-04-25 20:58:24 +00:00 · 2025-04-25 20:56:22 +00:00 · 2025-04-25 20:51:36 +00:00 · 2025-04-25 09:34:00 -04:00
44 changed files with 2236 additions and 273 deletions
--- a/docs/changelog.mdx
+++ b/docs/changelog.mdx
@@ -4,6 +4,36 @@ description: View the latest updates and changes to CrewAI
 icon: timeline
 ---

+<Update label="2025-04-07" description="v0.114.0">
+  ## Release Highlights
+  <Frame>
+    <img src="/images/v01140.png" />
+  </Frame>
+
+  **New Features & Enhancements**
+  - Agents as an atomic unit. (`Agent(...).kickoff()`)
+  - Support for [Custom LLM implementations](https://docs.crewai.com/guides/advanced/custom-llm).
+  - Integrated External Memory and [Opik observability](https://docs.crewai.com/how-to/opik-observability).
+  - Enhanced YAML extraction.
+  - Multimodal agent validation.
+  - Added Secure fingerprints for agents and crews.
+
+  **Core Improvements & Fixes**
+  - Improved serialization, agent copying, and Python compatibility.
+  - Added wildcard support to `emit()`
+  - Added support for additional router calls and context window adjustments.
+  - Fixed typing issues, validation, and import statements.
+  - Improved method performance.
+  - Enhanced agent task handling, event emissions, and memory management.
+  - Fixed CLI issues, conditional tasks, cloning behavior, and tool outputs.
+
+  **Documentation & Guides**
+  - Improved documentation structure, theme, and organization.
+  - Added guides for Local NVIDIA NIM with WSL2, W&B Weave, and Arize Phoenix.
+  - Updated tool configuration examples, prompts, and observability docs.
+  - Guide on using singular agents within Flows.
+</Update>
+
 <Update label="2025-03-17" description="v0.108.0">
  **Features**
  - Converted tabs to spaces in `crew.py` template
--- a/docs/concepts/cli.mdx
+++ b/docs/concepts/cli.mdx
@@ -179,7 +179,78 @@ def crew(self) -> Crew:
 ```
 </Note>

-### 10. API Keys
+### 10. Deploy
+
+Deploy the crew or flow to [CrewAI Enterprise](https://app.crewai.com).
+
+- **Authentication**: You need to be authenticated to deploy to CrewAI Enterprise.
+    ```shell Terminal
+    crewai signup
+    ```
+    If you already have an account, you can login with:
+    ```shell Terminal
+    crewai login
+    ```
+
+- **Create a deployment**: Once you are authenticated, you can create a deployment for your crew or flow from the root of your localproject.
+    ```shell Terminal
+    crewai deploy create
+    ```
+    - Reads your local project configuration.
+    - Prompts you to confirm the environment variables (like `OPENAI_API_KEY`, `SERPER_API_KEY`) found locally. These will be securely stored with the deployment on the Enterprise platform. Ensure your sensitive keys are correctly configured locally (e.g., in a `.env` file) before running this.
+    - Links the deployment to the corresponding remote GitHub repository (it usually detects this automatically).
+
+- **Deploy the Crew**: Once you are authenticated, you can deploy your crew or flow to CrewAI Enterprise.
+    ```shell Terminal
+    crewai deploy push
+    ``` 
+    - Initiates the deployment process on the CrewAI Enterprise platform.
+    - Upon successful initiation, it will output the Deployment created successfully! message along with the Deployment Name and a unique Deployment ID (UUID).
+
+- **Deployment Status**: You can check the status of your deployment with:
+    ```shell Terminal
+    crewai deploy status
+    ```
+    This fetches the latest deployment status of your most recent deployment attempt (e.g., `Building Images for Crew`, `Deploy Enqueued`, `Online`).
+
+- **Deployment Logs**: You can check the logs of your deployment with:
+    ```shell Terminal
+    crewai deploy logs
+    ```
+    This streams the deployment logs to your terminal.
+
+- **List deployments**: You can list all your deployments with:
+    ```shell Terminal
+    crewai deploy list
+    ```
+    This lists all your deployments.
+
+- **Delete a deployment**: You can delete a deployment with:
+    ```shell Terminal
+    crewai deploy remove
+    ```
+    This deletes the deployment from the CrewAI Enterprise platform.
+
+- **Help Command**: You can get help with the CLI with:
+    ```shell Terminal
+    crewai deploy --help
+    ```
+    This shows the help message for the CrewAI Deploy CLI.
+
+Watch this video tutorial for a step-by-step demonstration of deploying your crew to [CrewAI Enterprise](http://app.crewai.com) using the CLI.
+
+<iframe
+  width="100%"
+  height="400"
+  src="https://www.youtube.com/embed/3EqSV-CYDZA"
+  title="CrewAI Deployment Guide"
+  frameborder="0"
+  style={{ borderRadius: '10px' }}
+  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
+  allowfullscreen
+></iframe>
+
+### 11. API Keys

 When running ```crewai create crew``` command, the CLI will first show you the top 5 most common LLM providers and ask you to select one.

--- a/docs/concepts/knowledge.mdx
+++ b/docs/concepts/knowledge.mdx
@@ -42,6 +42,16 @@ CrewAI supports various types of knowledge sources out of the box:
 | `collection_name`          | **str**                              | No       | Name of the collection where the knowledge will be stored. Used to identify different sets of knowledge. Defaults to "knowledge" if not provided.     |
 | `storage`                  | **Optional[KnowledgeStorage]**       | No       | Custom storage configuration for managing how the knowledge is stored and retrieved. If not provided, a default storage will be created.              |

+
+<Tip>
+Unlike retrieval from a vector database using a tool, agents preloaded with knowledge will not need a retrieval persona or task.
+Simply add the relevant knowledge sources your agent or crew needs to function.
+
+Knowledge sources can be added at the agent or crew level.
+Crew level knowledge sources will be used by **all agents** in the crew.
+Agent level knowledge sources will be used by the **specific agent** that is preloaded with the knowledge.
+</Tip>
+
 ## Quickstart Example

 <Tip>
@@ -146,6 +156,26 @@ result = crew.kickoff(
 )
 ```

+## Knowledge Configuration
+
+You can configure the knowledge configuration for the crew or agent.
+
+```python Code
+from crewai.knowledge.knowledge_config import KnowledgeConfig
+
+knowledge_config = KnowledgeConfig(results_limit=10, score_threshold=0.5)
+
+agent = Agent(
+    ...
+    knowledge_config=knowledge_config
+)
+```
+
+<Tip>
+  `results_limit`: is the number of relevant documents to return. Default is 3.
+  `score_threshold`: is the minimum score for a document to be considered relevant. Default is 0.35.
+</Tip>
+
 ## More Examples

 Here are examples of how to use different types of knowledge sources:
--- a/docs/concepts/llamaindex-tools.mdx
+++ b/docs/concepts/llamaindex-tools.mdx
@@ -1,71 +0,0 @@
---
-title: Using LlamaIndex Tools
-description: Learn how to integrate LlamaIndex tools with CrewAI agents to enhance search-based queries and more.
-icon: toolbox
---
-
-## Using LlamaIndex Tools
-
-<Info>
-    CrewAI seamlessly integrates with LlamaIndex’s comprehensive toolkit for RAG (Retrieval-Augmented Generation) and agentic pipelines, enabling advanced search-based queries and more. 
-</Info>
-
-Here are the available built-in tools offered by LlamaIndex.
-
-```python Code
-from crewai import Agent
-from crewai_tools import LlamaIndexTool
-
-# Example 1: Initialize from FunctionTool
-from llama_index.core.tools import FunctionTool
-
-your_python_function = lambda ...: ...
-og_tool = FunctionTool.from_defaults(
-    your_python_function, 
-    name="<name>", 
-    description='<description>'
-)
-tool = LlamaIndexTool.from_tool(og_tool)
-
-# Example 2: Initialize from LlamaHub Tools
-from llama_index.tools.wolfram_alpha import WolframAlphaToolSpec
-wolfram_spec = WolframAlphaToolSpec(app_id="<app_id>")
-wolfram_tools = wolfram_spec.to_tool_list()
-tools = [LlamaIndexTool.from_tool(t) for t in wolfram_tools]
-
-# Example 3: Initialize Tool from a LlamaIndex Query Engine
-query_engine = index.as_query_engine()
-query_tool = LlamaIndexTool.from_query_engine(
-    query_engine,
-    name="Uber 2019 10K Query Tool",
-    description="Use this tool to lookup the 2019 Uber 10K Annual Report"
-)
-
-# Create and assign the tools to an agent
-agent = Agent(
-    role='Research Analyst',
-    goal='Provide up-to-date market analysis',
-    backstory='An expert analyst with a keen eye for market trends.',
-    tools=[tool, *tools, query_tool]
-)
-
-# rest of the code ...
-```
-
-## Steps to Get Started
-
-To effectively use the LlamaIndexTool, follow these steps:
-
-<Steps>
-    <Step title="Package Installation">
-    Make sure that `crewai[tools]` package is installed in your Python environment:
-    <CodeGroup>
-        ```shell Terminal
-        pip install 'crewai[tools]'
-        ```
-    </CodeGroup>
-    </Step>
-    <Step title="Install and Use LlamaIndex">
-    Follow the LlamaIndex documentation [LlamaIndex Documentation](https://docs.llamaindex.ai/) to set up a RAG/agent pipeline.
-    </Step>
-</Steps>
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -8,25 +8,27 @@
    "dark": "#C94C3C"
  },
  "favicon": "favicon.svg",
+  "contextual": {
+    "options": ["copy", "view", "chatgpt", "claude"]
+  },
  "navigation": {
    "tabs": [
      {
-        "tab": "Get Started",
+        "tab": "Documentation",
        "groups": [
          {
            "group": "Get Started",
            "pages": [
              "introduction",
              "installation",
-              "quickstart",
-              "changelog"
+              "quickstart"
            ]
          },
          {
            "group": "Guides",
            "pages": [
              {
-                "group": "Concepts",
+                "group": "Strategy",
                "pages": [
                  "guides/concepts/evaluating-use-cases"
                ]
@@ -79,41 +81,6 @@
              "concepts/event-listener"
            ]
          },
-          {
-            "group": "How to Guides",
-            "pages": [
-              "how-to/create-custom-tools",
-              "how-to/sequential-process",
-              "how-to/hierarchical-process",
-              "how-to/custom-manager-agent",
-              "how-to/llm-connections",
-              "how-to/customizing-agents",
-              "how-to/multimodal-agents",
-              "how-to/coding-agents",
-              "how-to/force-tool-output-as-result",
-              "how-to/human-input-on-execution",
-              "how-to/kickoff-async",
-              "how-to/kickoff-for-each",
-              "how-to/replay-tasks-from-latest-crew-kickoff",
-              "how-to/conditional-tasks",
-              "how-to/langchain-tools",
-              "how-to/llamaindex-tools"
-            ]
-          },
-          {
-            "group": "Agent Monitoring & Observability",
-            "pages": [
-              "how-to/agentops-observability",
-              "how-to/arize-phoenix-observability",
-              "how-to/langfuse-observability",
-              "how-to/langtrace-observability",
-              "how-to/mlflow-observability",
-              "how-to/openlit-observability",
-              "how-to/opik-observability",
-              "how-to/portkey-observability",
-              "how-to/weave-integration"
-            ]
-          },
          {
            "group": "Tools",
            "pages": [
@@ -141,6 +108,7 @@
              "tools/hyperbrowserloadtool",
              "tools/linkupsearchtool",
              "tools/llamaindextool",
+              "tools/langchaintool",
              "tools/serperdevtool",
              "tools/s3readertool",
              "tools/s3writertool",
@@ -170,6 +138,40 @@
              "tools/youtubevideosearchtool"
            ]
          },
+          {
+            "group": "Agent Monitoring & Observability",
+            "pages": [
+              "how-to/agentops-observability",
+              "how-to/arize-phoenix-observability",
+              "how-to/langfuse-observability",
+              "how-to/langtrace-observability",
+              "how-to/mlflow-observability",
+              "how-to/openlit-observability",
+              "how-to/opik-observability",
+              "how-to/portkey-observability",
+              "how-to/weave-integration"
+            ]
+          },
+          {
+            "group": "Learn",
+            "pages": [
+              "how-to/conditional-tasks",
+              "how-to/coding-agents",
+              "how-to/create-custom-tools",
+              "how-to/custom-llm",
+              "how-to/custom-manager-agent",
+              "how-to/customizing-agents",
+              "how-to/force-tool-output-as-result",
+              "how-to/hierarchical-process",
+              "how-to/human-input-on-execution",
+              "how-to/kickoff-async",
+              "how-to/kickoff-for-each",
+              "how-to/llm-connections",
+              "how-to/multimodal-agents",
+              "how-to/replay-tasks-from-latest-crew-kickoff",
+              "how-to/sequential-process"
+            ]
+          },
          {
            "group": "Telemetry",
            "pages": [
@@ -188,19 +190,35 @@
            ]
          }
        ]
+      },
+      {
+        "tab": "Releases",
+        "groups": [
+          {
+            "group": "Releases",
+            "pages": [
+              "changelog"
+            ]
+          }
+        ]
      }
    ],
    "global": {
      "anchors": [
        {
-          "anchor": "Community",
+          "anchor": "Website",
+          "href": "https://crewai.com",
+          "icon": "globe"
+        },
+        {
+          "anchor": "Forum",
          "href": "https://community.crewai.com",
          "icon": "discourse"
        },
        {
-          "anchor": "Tutorials",
-          "href": "https://www.youtube.com/@crewAIInc",
-          "icon": "youtube"
+          "anchor": "Get Help",
+          "href": "mailto:support@crewai.com",
+          "icon": "headset"
        }
      ]
    }
@@ -214,6 +232,12 @@
    "strict": false
  },
  "navbar": {
+    "links": [
+      {
+        "label": "Start Free Trial",
+        "href": "https://app.crewai.com"
+      }
+    ],
    "primary": {
      "type": "github",
      "href": "https://github.com/crewAIInc/crewAI"
@@ -223,7 +247,12 @@
    "prompt": "Search CrewAI docs"
  },
  "seo": {
-    "indexing": "navigable"
+    "indexing": "all"
+  },
+  "errors": {
+    "404": {
+      "redirect": true
+    }
  },
  "footer": {
    "socials": {
--- a/docs/how-to/custom-llm.mdx
+++ b/docs/how-to/custom-llm.mdx
@@ -1,9 +1,13 @@
-# Custom LLM Implementations
+---
+title: Custom LLM Implementation
+description: Learn how to create custom LLM implementations in CrewAI.
+icon: code
+---
+
+## Custom LLM Implementations

 CrewAI now supports custom LLM implementations through the `BaseLLM` abstract base class. This allows you to create your own LLM implementations that don't rely on litellm's authentication mechanism.

-## Using Custom LLM Implementations
-
 To create a custom LLM implementation, you need to:

 1. Inherit from the `BaseLLM` abstract base class
--- a/docs/how-to/custom-manager-agent.mdx
+++ b/docs/how-to/custom-manager-agent.mdx
@@ -1,5 +1,5 @@
 ---
-title: Create Your Own Manager Agent
+title: Custom Manager Agent
 description: Learn how to set a custom agent as the manager in CrewAI, providing more control over task management and coordination.
 icon: user-shield
 ---
--- a/docs/how-to/replay-tasks-from-latest-crew-kickoff.mdx
+++ b/docs/how-to/replay-tasks-from-latest-crew-kickoff.mdx
@@ -20,10 +20,8 @@ Here's an example of how to replay from a task:
 To use the replay feature, follow these steps:

 <Steps>
-   <Step title="Open your terminal or command prompt.">
-   </Step>
-   <Step title="Navigate to the directory where your CrewAI project is located.">
-   </Step>
+   <Step title="Open your terminal or command prompt."></Step>
+   <Step title="Navigate to the directory where your CrewAI project is located."></Step>
   <Step title="Run the following commands:">
      To view the latest kickoff task_ids use:

--- a/docs/images/v01140.png
+++ b/docs/images/v01140.png
--- a/docs/quickstart.mdx
+++ b/docs/quickstart.mdx
@@ -336,9 +336,22 @@ email_summarizer_task:
      - research_task
 ```

-## Deploying Your Project
+## Deploying Your Crew

-The easiest way to deploy your crew is through [CrewAI Enterprise](http://app.crewai.com), where you can deploy your crew in a few clicks.
+The easiest way to deploy your crew to production is through [CrewAI Enterprise](http://app.crewai.com).
+
+Watch this video tutorial for a step-by-step demonstration of deploying your crew to [CrewAI Enterprise](http://app.crewai.com) using the CLI.
+
+<iframe
+  width="100%"
+  height="400"
+  src="https://www.youtube.com/embed/3EqSV-CYDZA"
+  title="CrewAI Deployment Guide"
+  frameborder="0"
+  style={{ borderRadius: '10px' }}
+  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
+  allowfullscreen
+></iframe>

 <CardGroup cols={2}>
  <Card
--- a/docs/tools/codeinterpretertool.mdx
+++ b/docs/tools/codeinterpretertool.mdx
@@ -8,11 +8,29 @@ icon: code-simple

 ## Description

-The `CodeInterpreterTool` enables CrewAI agents to execute Python 3 code that they generate autonomously. The code is run in a secure, isolated Docker container, ensuring safety regardless of the content. This functionality is particularly valuable as it allows agents to create code, execute it, obtain the results, and utilize that information to inform subsequent decisions and actions.
+The `CodeInterpreterTool` enables CrewAI agents to execute Python 3 code that they generate autonomously. This functionality is particularly valuable as it allows agents to create code, execute it, obtain the results, and utilize that information to inform subsequent decisions and actions.

-## Requirements
+There are several ways to use this tool:
+
+### Docker Container (Recommended)
+
+This is the primary option. The code runs in a secure, isolated Docker container, ensuring safety regardless of its content.
+Make sure Docker is installed and running on your system. If you don’t have it, you can install it from [here](https://docs.docker.com/get-docker/).
+
+### Sandbox environment
+
+If Docker is unavailable — either not installed or not accessible for any reason — the code will be executed in a restricted Python environment - called sandbox.
+This environment is very limited, with strict restrictions on many modules and built-in functions.
+
+### Unsafe Execution
+
+**NOT RECOMMENDED FOR PRODUCTION** 
+This mode allows execution of any Python code, including dangerous calls to `sys, os..` and similar modules. [Check out](/tools/codeinterpretertool#enabling-unsafe-mode) how to enable this mode
+
+## Logging
+
+The `CodeInterpreterTool` logs the selected execution strategy to STDOUT

- Docker must be installed and running on your system. If you don't have it, you can install it from [here](https://docs.docker.com/get-docker/).

 ## Installation

@@ -74,18 +92,32 @@ programmer_agent = Agent(
 )
 ```

+### Enabling `unsafe_mode`
+
+```python Code
+from crewai_tools import CodeInterpreterTool
+
+code = """
+import os
+os.system("ls -la")
+"""
+
+CodeInterpreterTool(unsafe_mode=True).run(code=code)
+```
+
 ## Parameters

 The `CodeInterpreterTool` accepts the following parameters during initialization:

 - **user_dockerfile_path**: Optional. Path to a custom Dockerfile to use for the code interpreter container.
 - **user_docker_base_url**: Optional. URL to the Docker daemon to use for running the container.
- **unsafe_mode**: Optional. Whether to run code directly on the host machine instead of in a Docker container. Default is `False`. Use with caution!
+- **unsafe_mode**: Optional. Whether to run code directly on the host machine instead of in a Docker container or sandbox. Default is `False`. Use with caution!
+- **default_image_tag**: Optional. Default Docker image tag. Default is `code-interpreter:latest`

 When using the tool with an agent, the agent will need to provide:

 - **code**: Required. The Python 3 code to execute.
- **libraries_used**: Required. A list of libraries used in the code that need to be installed.
+- **libraries_used**: Optional. A list of libraries used in the code that need to be installed. Default is `[]`

 ## Agent Integration Example

@@ -152,7 +184,7 @@ class CodeInterpreterTool(BaseTool):
        if self.unsafe_mode:
            return self.run_code_unsafe(code, libraries_used)
        else:
-            return self.run_code_in_docker(code, libraries_used)
+            return self.run_code_safety(code, libraries_used)
 ```

 The tool performs the following steps:
@@ -168,8 +200,9 @@ The tool performs the following steps:
 By default, the `CodeInterpreterTool` runs code in an isolated Docker container, which provides a layer of security. However, there are still some security considerations to keep in mind:

 1. The Docker container has access to the current working directory, so sensitive files could potentially be accessed.
-2. The `unsafe_mode` parameter allows code to be executed directly on the host machine, which should only be used in trusted environments.
-3. Be cautious when allowing agents to install arbitrary libraries, as they could potentially include malicious code.
+2. If the Docker container is unavailable and the code needs to run safely, it will be executed in a sandbox environment. For security reasons, installing arbitrary libraries is not allowed
+3. The `unsafe_mode` parameter allows code to be executed directly on the host machine, which should only be used in trusted environments.
+4. Be cautious when allowing agents to install arbitrary libraries, as they could potentially include malicious code.

 ## Conclusion

--- a/docs/concepts/langchain-tools.mdx
+++ b/docs/concepts/langchain-tools.mdx
@@ -1,10 +1,10 @@
 ---
-title: Using LangChain Tools
-description: Learn how to integrate LangChain tools with CrewAI agents to enhance search-based queries and more.
+title: LangChain Tool
+description: The `LangChainTool` is a wrapper for LangChain tools and query engines.
 icon: link
 ---

-## Using LangChain Tools
+## `LangChainTool`

 <Info>
    CrewAI seamlessly integrates with LangChain's comprehensive [list of tools](https://python.langchain.com/docs/integrations/tools/), all of which can be used with CrewAI.
--- a/src/crewai/agent.py
+++ b/src/crewai/agent.py
@@ -114,6 +114,14 @@ class Agent(BaseAgent):
        default=None,
        description="Embedder configuration for the agent.",
    )
+    agent_knowledge_context: Optional[str] = Field(
+        default=None,
+        description="Knowledge context for the agent.",
+    )
+    crew_knowledge_context: Optional[str] = Field(
+        default=None,
+        description="Knowledge context for the crew.",
+    )

    @model_validator(mode="after")
    def post_init_setup(self):
@@ -234,22 +242,30 @@ class Agent(BaseAgent):
            memory = contextual_memory.build_context_for_task(task, context)
            if memory.strip() != "":
                task_prompt += self.i18n.slice("memory").format(memory=memory)
-
+        knowledge_config = (
+            self.knowledge_config.model_dump() if self.knowledge_config else {}
+        )
        if self.knowledge:
-            agent_knowledge_snippets = self.knowledge.query([task.prompt()])
+            agent_knowledge_snippets = self.knowledge.query(
+                [task.prompt()], **knowledge_config
+            )
            if agent_knowledge_snippets:
-                agent_knowledge_context = extract_knowledge_context(
+                self.agent_knowledge_context = extract_knowledge_context(
                    agent_knowledge_snippets
                )
-                if agent_knowledge_context:
-                    task_prompt += agent_knowledge_context
+                if self.agent_knowledge_context:
+                    task_prompt += self.agent_knowledge_context

        if self.crew:
-            knowledge_snippets = self.crew.query_knowledge([task.prompt()])
+            knowledge_snippets = self.crew.query_knowledge(
+                [task.prompt()], **knowledge_config
+            )
            if knowledge_snippets:
-                crew_knowledge_context = extract_knowledge_context(knowledge_snippets)
-                if crew_knowledge_context:
-                    task_prompt += crew_knowledge_context
+                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)
--- a/src/crewai/agents/agent_builder/base_agent.py
+++ b/src/crewai/agents/agent_builder/base_agent.py
@@ -19,6 +19,7 @@ from crewai.agents.agent_builder.utilities.base_token_process import TokenProces
 from crewai.agents.cache.cache_handler import CacheHandler
 from crewai.agents.tools_handler import ToolsHandler
 from crewai.knowledge.knowledge import Knowledge
+from crewai.knowledge.knowledge_config import KnowledgeConfig
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.security.security_config import SecurityConfig
 from crewai.tools.base_tool import BaseTool, Tool
@@ -155,6 +156,10 @@ class BaseAgent(ABC, BaseModel):
    adapted_agent: bool = Field(
        default=False, description="Whether the agent is adapted"
    )
+    knowledge_config: Optional[KnowledgeConfig] = Field(
+        default=None,
+        description="Knowledge configuration for the agent such as limits and threshold",
+    )

    @model_validator(mode="before")
    @classmethod
--- a/src/crewai/cli/constants.py
+++ b/src/crewai/cli/constants.py
@@ -122,7 +122,16 @@ PROVIDERS = [
 ]

 MODELS = {
-    "openai": ["gpt-4", "gpt-4o", "gpt-4o-mini", "o1-mini", "o1-preview"],
+    "openai": [
+        "gpt-4",
+        "gpt-4.1",
+        "gpt-4.1-mini-2025-04-14",
+        "gpt-4.1-nano-2025-04-14",
+        "gpt-4o",
+        "gpt-4o-mini",
+        "o1-mini",
+        "o1-preview",
+    ],
    "anthropic": [
        "claude-3-5-sonnet-20240620",
        "claude-3-sonnet-20240229",
@@ -132,8 +141,17 @@ MODELS = {
    "gemini": [
        "gemini/gemini-1.5-flash",
        "gemini/gemini-1.5-pro",
+        "gemini/gemini-2.0-flash-lite-001",
+        "gemini/gemini-2.0-flash-001",
+        "gemini/gemini-2.0-flash-thinking-exp-01-21",
+        "gemini/gemini-2.5-flash-preview-04-17",
+        "gemini/gemini-2.5-pro-exp-03-25",
        "gemini/gemini-gemma-2-9b-it",
        "gemini/gemini-gemma-2-27b-it",
+        "gemini/gemma-3-1b-it",
+        "gemini/gemma-3-4b-it",
+        "gemini/gemma-3-12b-it",
+        "gemini/gemma-3-27b-it",
    ],
    "nvidia_nim": [
        "nvidia_nim/nvidia/mistral-nemo-minitron-8b-8k-instruct",
--- a/src/crewai/cli/plot_flow.py
+++ b/src/crewai/cli/plot_flow.py
@@ -1,32 +1,23 @@
-import importlib.util
-import os
-import sys
+import subprocess

 import click


 def plot_flow() -> None:
    """
-    Plot the flow by finding and importing the plot function from the project's main.py file.
+    Plot the flow by running a command in the UV environment.
    """
-    main_file_path = os.path.join(os.getcwd(), "main.py")
-    
+    command = ["uv", "run", "plot"]
+
    try:
-        if os.path.exists(main_file_path):
-            spec = importlib.util.spec_from_file_location("main", main_file_path)
-            if spec is not None and spec.loader is not None:
-                main = importlib.util.module_from_spec(spec)
-                sys.modules["main"] = main
-                spec.loader.exec_module(main)
-                
-                if hasattr(main, "plot"):
-                    main.plot()
-                else:
-                    click.echo("Error: No plot function found in main.py", err=True)
-            else:
-                click.echo("Error: Could not load main.py module", err=True)
-        else:
-            click.echo("Error: Could not find main.py in the current directory", err=True)
-            
-    except Exception as e:
+        result = subprocess.run(command, capture_output=False, text=True, check=True)
+
+        if result.stderr:
+            click.echo(result.stderr, err=True)
+
+    except subprocess.CalledProcessError as e:
        click.echo(f"An error occurred while plotting the flow: {e}", err=True)
+        click.echo(e.output, err=True)
+
+    except Exception as e:
+        click.echo(f"An unexpected error occurred: {e}", err=True)
--- a/src/crewai/cli/tools/main.py
+++ b/src/crewai/cli/tools/main.py
@@ -117,7 +117,9 @@ class ToolCommand(BaseCommand, PlusAPIMixin):

        published_handle = publish_response.json()["handle"]
        console.print(
-            f"Successfully published {published_handle} ({project_version}).\nInstall it in other projects with crewai tool install {published_handle}",
+            f"Successfully published `{published_handle}` ({project_version}).\n\n"
+            + "⚠️ Security checks are running in the background. Your tool will be available once these are complete.\n"
+            + f"You can monitor the status or access your tool here:\nhttps://app.crewai.com/crewai_plus/tools/{published_handle}",
            style="bold green",
        )

@@ -153,8 +155,12 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
        login_response_json = login_response.json()

        settings = Settings()
-        settings.tool_repository_username = login_response_json["credential"]["username"]
-        settings.tool_repository_password = login_response_json["credential"]["password"]
+        settings.tool_repository_username = login_response_json["credential"][
+            "username"
+        ]
+        settings.tool_repository_password = login_response_json["credential"][
+            "password"
+        ]
        settings.dump()

        console.print(
@@ -179,7 +185,7 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
            capture_output=False,
            env=self._build_env_with_credentials(repository_handle),
            text=True,
-            check=True
+            check=True,
        )

        if add_package_result.stderr:
@@ -204,7 +210,11 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
        settings = Settings()

        env = os.environ.copy()
-        env[f"UV_INDEX_{repository_handle}_USERNAME"] = str(settings.tool_repository_username or "")
-        env[f"UV_INDEX_{repository_handle}_PASSWORD"] = str(settings.tool_repository_password or "")
+        env[f"UV_INDEX_{repository_handle}_USERNAME"] = str(
+            settings.tool_repository_username or ""
+        )
+        env[f"UV_INDEX_{repository_handle}_PASSWORD"] = str(
+            settings.tool_repository_password or ""
+        )

        return env
--- a/src/crewai/crew.py
+++ b/src/crewai/crew.py
@@ -304,9 +304,7 @@ class Crew(BaseModel):
        """Initialize private memory attributes."""
        self._external_memory = (
            # External memory doesn’t support a default value since it was designed to be managed entirely externally
-            self.external_memory.set_crew(self)
-            if self.external_memory
-            else None
+            self.external_memory.set_crew(self) if self.external_memory else None
        )

        self._long_term_memory = self.long_term_memory
@@ -1136,9 +1134,13 @@ class Crew(BaseModel):
        result = self._execute_tasks(self.tasks, start_index, True)
        return result

-    def query_knowledge(self, query: List[str]) -> Union[List[Dict[str, Any]], None]:
+    def query_knowledge(
+        self, query: List[str], results_limit: int = 3, score_threshold: float = 0.35
+    ) -> Union[List[Dict[str, Any]], None]:
        if self.knowledge:
-            return self.knowledge.query(query)
+            return self.knowledge.query(
+                query, results_limit=results_limit, score_threshold=score_threshold
+            )
        return None

    def fetch_inputs(self) -> Set[str]:
@@ -1220,9 +1222,13 @@ class Crew(BaseModel):
        copied_data = self.model_dump(exclude=exclude)
        copied_data = {k: v for k, v in copied_data.items() if v is not None}
        if self.short_term_memory:
-            copied_data["short_term_memory"] = self.short_term_memory.model_copy(deep=True)
+            copied_data["short_term_memory"] = self.short_term_memory.model_copy(
+                deep=True
+            )
        if self.long_term_memory:
-            copied_data["long_term_memory"] = self.long_term_memory.model_copy(deep=True)
+            copied_data["long_term_memory"] = self.long_term_memory.model_copy(
+                deep=True
+            )
        if self.entity_memory:
            copied_data["entity_memory"] = self.entity_memory.model_copy(deep=True)
        if self.external_memory:
@@ -1230,7 +1236,6 @@ class Crew(BaseModel):
        if self.user_memory:
            copied_data["user_memory"] = self.user_memory.model_copy(deep=True)

-
        copied_data.pop("agents", None)
        copied_data.pop("tasks", None)

@@ -1328,19 +1333,6 @@ class Crew(BaseModel):

    def __repr__(self):
        return f"Crew(id={self.id}, process={self.process}, number_of_agents={len(self.agents)}, number_of_tasks={len(self.tasks)})"
-        
-    def plot(self, filename: str = "crewai_crew") -> None:
-        """
-        This method is not implemented for Crew objects.
-        Plot functionality is available only for Flow objects.
-        
-        To visualize a Flow, use flow_instance.plot() instead.
-        """
-        raise NotImplementedError(
-            "The plot method is not available for Crew objects. "
-            "Plot functionality is only available for Flow objects. "
-            "Please use flow_instance.plot() instead."
-        )

    def reset_memories(self, command_type: str) -> None:
        """Reset specific or all memories for the crew.
@@ -1416,7 +1408,10 @@ class Crew(BaseModel):
            "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"),
+            "kickoff_outputs": (
+                getattr(self, "_task_output_handler", None),
+                "task output",
+            ),
            "external": (getattr(self, "_external_memory", None), "external"),
        }

--- a/src/crewai/knowledge/knowledge.py
+++ b/src/crewai/knowledge/knowledge.py
@@ -43,7 +43,9 @@ class Knowledge(BaseModel):
        self.storage.initialize_knowledge_storage()
        self._add_sources()

-    def query(self, query: List[str], limit: int = 3) -> List[Dict[str, Any]]:
+    def query(
+        self, query: List[str], results_limit: int = 3, score_threshold: float = 0.35
+    ) -> List[Dict[str, Any]]:
        """
        Query across all knowledge sources to find the most relevant information.
        Returns the top_k most relevant chunks.
@@ -56,7 +58,8 @@ class Knowledge(BaseModel):

        results = self.storage.search(
            query,
-            limit,
+            limit=results_limit,
+            score_threshold=score_threshold,
        )
        return results

--- a/src/crewai/knowledge/knowledge_config.py
+++ b/src/crewai/knowledge/knowledge_config.py
@@ -0,0 +1,16 @@
+from pydantic import BaseModel, Field
+
+
+class KnowledgeConfig(BaseModel):
+    """Configuration for knowledge retrieval.
+
+    Args:
+        results_limit (int): The number of relevant documents to return.
+        score_threshold (float): The minimum score for a document to be considered relevant.
+    """
+
+    results_limit: int = Field(default=3, description="The number of results to return")
+    score_threshold: float = Field(
+        default=0.35,
+        description="The minimum score for a result to be considered relevant",
+    )
--- a/src/crewai/knowledge/storage/knowledge_storage.py
+++ b/src/crewai/knowledge/storage/knowledge_storage.py
@@ -4,7 +4,7 @@ import io
 import logging
 import os
 import shutil
-from typing import Any, Dict, List, Optional, Union, cast
+from typing import Any, Dict, List, Optional, Union

 import chromadb
 import chromadb.errors
--- a/src/crewai/llm.py
+++ b/src/crewai/llm.py
@@ -37,6 +37,7 @@ with warnings.catch_warnings():
    warnings.simplefilter("ignore", UserWarning)
    import litellm
    from litellm import Choices
+    from litellm.exceptions import ContextWindowExceededError
    from litellm.litellm_core_utils.get_supported_openai_params import (
        get_supported_openai_params,
    )
@@ -81,14 +82,26 @@ LLM_CONTEXT_WINDOW_SIZES = {
    "gpt-4o": 128000,
    "gpt-4o-mini": 128000,
    "gpt-4-turbo": 128000,
+    "gpt-4.1": 1047576,  # Based on official docs
+    "gpt-4.1-mini-2025-04-14": 1047576,
+    "gpt-4.1-nano-2025-04-14": 1047576,
    "o1-preview": 128000,
    "o1-mini": 128000,
    "o3-mini": 200000,  # Based on official o3-mini specifications
    # gemini
    "gemini-2.0-flash": 1048576,
+    "gemini-2.0-flash-thinking-exp-01-21": 32768,
+    "gemini-2.0-flash-lite-001": 1048576,
+    "gemini-2.0-flash-001": 1048576,
+    "gemini-2.5-flash-preview-04-17": 1048576,
+    "gemini-2.5-pro-exp-03-25": 1048576,
    "gemini-1.5-pro": 2097152,
    "gemini-1.5-flash": 1048576,
    "gemini-1.5-flash-8b": 1048576,
+    "gemini/gemma-3-1b-it": 32000,
+    "gemini/gemma-3-4b-it": 128000,
+    "gemini/gemma-3-12b-it": 128000,
+    "gemini/gemma-3-27b-it": 128000,
    # deepseek
    "deepseek-chat": 128000,
    # groq
@@ -585,6 +598,11 @@ class LLM(BaseLLM):
            self._handle_emit_call_events(full_response, LLMCallType.LLM_CALL)
            return full_response

+        except ContextWindowExceededError as e:
+            # Catch context window errors from litellm and convert them to our own exception type.
+            # This exception is handled by CrewAgentExecutor._invoke_loop() which can then
+            # decide whether to summarize the content or abort based on the respect_context_window flag.
+            raise LLMContextLengthExceededException(str(e))
        except Exception as e:
            logging.error(f"Error in streaming response: {str(e)}")
            if full_response.strip():
@@ -699,7 +717,16 @@ class LLM(BaseLLM):
            str: The response text
        """
        # --- 1) Make the completion call
-        response = litellm.completion(**params)
+        try:
+            # Attempt to make the completion call, but catch context window errors
+            # and convert them to our own exception type for consistent handling
+            # across the codebase. This allows CrewAgentExecutor to handle context
+            # length issues appropriately.
+            response = litellm.completion(**params)
+        except ContextWindowExceededError as e:
+            # Convert litellm's context window error to our own exception type
+            # for consistent handling in the rest of the codebase
+            raise LLMContextLengthExceededException(str(e))

        # --- 2) Extract response message and content
        response_message = cast(Choices, cast(ModelResponse, response).choices)[
@@ -858,15 +885,17 @@ class LLM(BaseLLM):
                        params, callbacks, available_functions
                    )

+            except LLMContextLengthExceededException:
+                # Re-raise LLMContextLengthExceededException as it should be handled
+                # by the CrewAgentExecutor._invoke_loop method, which can then decide
+                # whether to summarize the content or abort based on the respect_context_window flag
+                raise
            except Exception as e:
                crewai_event_bus.emit(
                    self,
                    event=LLMCallFailedEvent(error=str(e)),
                )
-                if not LLMContextLengthExceededException(
-                    str(e)
-                )._is_context_limit_error(str(e)):
-                    logging.error(f"LiteLLM call failed: {str(e)}")
+                logging.error(f"LiteLLM call failed: {str(e)}")
                raise

    def _handle_emit_call_events(self, response: Any, call_type: LLMCallType):
--- a/src/crewai/utilities/embedding_configurator.py
+++ b/src/crewai/utilities/embedding_configurator.py
@@ -104,16 +104,25 @@ class EmbeddingConfigurator:

    @staticmethod
    def _configure_vertexai(config, model_name):
-        from chromadb.utils.embedding_functions.google_embedding_function import (
-            GoogleVertexEmbeddingFunction,
-        )
+        try:
+            from chromadb.utils.embedding_functions.google_embedding_function import (
+                GoogleVertexEmbeddingFunction,
+            )

-        return GoogleVertexEmbeddingFunction(
-            model_name=model_name,
-            api_key=config.get("api_key"),
-            project_id=config.get("project_id"),
-            region=config.get("region"),
-        )
+            from crewai.utilities.embedding_functions import (
+                FixedGoogleVertexEmbeddingFunction,
+            )
+            
+            return FixedGoogleVertexEmbeddingFunction(
+                model_name=model_name,
+                api_key=config.get("api_key"),
+                project_id=config.get("project_id"),
+                region=config.get("region"),
+            )
+        except ImportError as e:
+            raise ImportError(
+                "Google Vertex dependencies are not installed. Please install them to use Vertex embedding."
+            ) from e

    @staticmethod
    def _configure_google(config, model_name):
--- a/src/crewai/utilities/embedding_functions.py
+++ b/src/crewai/utilities/embedding_functions.py
@@ -0,0 +1,40 @@
+from typing import Any, List, Optional
+from urllib.parse import parse_qs, urlencode, urlparse, urlunparse
+
+import requests
+from chromadb import Documents, Embeddings
+from chromadb.utils.embedding_functions.google_embedding_function import (
+    GoogleVertexEmbeddingFunction,
+)
+
+
+class FixedGoogleVertexEmbeddingFunction(GoogleVertexEmbeddingFunction):
+    """
+    A wrapper around ChromaDB's GoogleVertexEmbeddingFunction that fixes the URL typo
+    where 'publishers/goole' is incorrectly used instead of 'publishers/google'.
+    
+    Issue reference: https://github.com/crewaiinc/crewai/issues/2690
+    """
+    
+    def __init__(self, 
+                model_name: str = "textembedding-gecko", 
+                api_key: Optional[str] = None,
+                **kwargs: Any):
+        api_key_str = "" if api_key is None else api_key
+        super().__init__(model_name=model_name, api_key=api_key_str, **kwargs)
+        
+        self._original_post = requests.post
+        requests.post = self._patched_post
+    
+    def __del__(self):
+        if hasattr(self, '_original_post'):
+            requests.post = self._original_post
+    
+    def _patched_post(self, url, *args, **kwargs):
+        if 'publishers/goole' in url:
+            url = url.replace('publishers/goole', 'publishers/google')
+        
+        return self._original_post(url, *args, **kwargs)
+    
+    def __call__(self, input: Documents) -> Embeddings:
+        return super().__call__(input)
--- a/tests/agent_test.py
+++ b/tests/agent_test.py
@@ -10,6 +10,8 @@ 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
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.llm import LLM
@@ -259,7 +261,9 @@ 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.",
@@ -1611,6 +1615,78 @@ def test_agent_with_knowledge_sources():
        assert "red" in result.raw.lower()


+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_with_knowledge_sources_with_query_limit_and_score_threshold():
+    content = "Brandon's favorite color is red and he likes Mexican food."
+    string_source = StringKnowledgeSource(content=content)
+    knowledge_config = KnowledgeConfig(results_limit=10, score_threshold=0.5)
+    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}]
+        with patch.object(Knowledge, "query") as mock_knowledge_query:
+            agent = Agent(
+                role="Information Agent",
+                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],
+                knowledge_config=knowledge_config,
+            )
+            task = Task(
+                description="What is Brandon's favorite color?",
+                expected_output="Brandon's favorite color.",
+                agent=agent,
+            )
+            crew = Crew(agents=[agent], tasks=[task])
+            crew.kickoff()
+
+            assert agent.knowledge is not None
+            mock_knowledge_query.assert_called_once_with(
+                [task.prompt()],
+                **knowledge_config.model_dump(),
+            )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default():
+    content = "Brandon's favorite color is red and he likes Mexican food."
+    string_source = StringKnowledgeSource(content=content)
+    knowledge_config = KnowledgeConfig()
+    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}]
+        with patch.object(Knowledge, "query") as mock_knowledge_query:
+            string_source = StringKnowledgeSource(content=content)
+            knowledge_config = KnowledgeConfig()
+            agent = Agent(
+                role="Information Agent",
+                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],
+                knowledge_config=knowledge_config,
+            )
+            task = Task(
+                description="What is Brandon's favorite color?",
+                expected_output="Brandon's favorite color.",
+                agent=agent,
+            )
+            crew = Crew(agents=[agent], tasks=[task])
+            crew.kickoff()
+
+            assert agent.knowledge is not None
+            mock_knowledge_query.assert_called_once_with(
+                [task.prompt()],
+                **knowledge_config.model_dump(),
+            )
+
+
@pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_with_knowledge_sources_extensive_role():
    content = "Brandon's favorite color is red and he likes Mexican food."
--- a/tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold.yaml
+++ b/tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold.yaml
@@ -0,0 +1,330 @@
+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, zstd
+      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+yPtfmz59Pced/yrwR2bV9zhAQ2UkRFHEymYAiOxHZtEDfvN99ovdkNicm
+        YiNpu1bXdf1W//Nff/7802V1fp/++feff17VOP3z377PHumU/vPvP//9X3/+/Pnzn7/P/29k3mb5
+        41G9i9/w34/V+5Ev//z7D/9/nvzfQf/+889JZZQeb+UOCJHjaQqtRQfv1mXUaf0OTfTuHjx+CvAU
+        CWC/KEik3pNeZScAwr5Zzkgne4Gqd6jX2+oDW3BxGx8nMkfrxaq0GM2PNaV5G6QZM0P1joRJl32W
+        BVuXtTPPo02jZhRX8gjWdj7MgDz2D+wRexhoUHsaTN9P0RfLw5itFrmbCgzCHVFOdx/wQte1qJvK
+        FxH556YeT0pqoJ0RTNhqPwiskhTe0T7qIpzrwS4arGS24D4uc6y90d4VpMq+wy7hntS8mG297p2B
+        QNrwZ5pV1p4RZ6vPEHEPDtuWVA0L/w451CylgPUZBhFvXaQWWqXwwKobdNmavrcCyvDk4aRDezby
+        2c5Hym33obtXgLKlioYGKUfZovrOBtkSu6cOQbHw6POcJoyE+vmMxtegUst+HNh2ZImhpFTNsJ4V
+        73p1XlWO8NsSscGvH7asThqCqtoe6anKt+6SsI0K91Ef0UtGS5dIB8DD3QV2vtwaybB8lksCj5K7
+        pTjWccSrU5igG+hfVOuSRl+4sPGhtJ4Qtfr4w4g0EQcaRfCgnrKxXVFD8hnSZ6jTk5PN9ax4JxU5
+        T/5MsnTwskU6ARNOHnCJYHpsoPbgFfDzsRYaLe9dPbfLoiDTls800h+6vjruXYDSGiGs3fJFXw5Z
+        2APLfh+ok3y2YDvrfQvLm3/x5fPervlV0QUUF5c33aFAzQRua0JwHeCKb5/FGITQVzsgc1KIg6vA
+        Mmo+Xg5CiY/80LSf2UqSFwdOKDHoMVyBvk6jq0DzTRTs1uUHLFui9ciAyYGq8fHOhDqzzoCpgkE9
+        Ta/q9aW/VnRO/IR6zaVjs8DvQ9Q/byvOji+YzUV7ztGHji4+b4t7LZqHuwO9+NRR9aZ0YFFWKQF8
+        oXu+5D2rgfee2RlmG3/CO+mFXbq0SgJ35cGm+JxKjEnnY6vsjlOI9+aSsPUqdSNMj3FBD3qdMHHA
+        UgCXpjj46xaeI6GBnAZtrfZJOLMKLKg6VrDCz5jaF6K6/LjWGpwt36FHS430JTwlHtrvYIL3q03d
+        JUkWDWVaEtKLvglq9sj4HiRDHtFo3yjuyGe2D/nPY8ER4xwmtq/AQtvoptF7rdiAX9jdgRtn7+Bn
+        tJEZJc2GgD4yNZz3YBjWu3ziAaFrhXenYwImk8wNpOrj/M13t+Y7wz/D3/57Lz0b2K1kHixsVceP
+        ztUy8VYyH90e/AbvXU+sGZ8aDnKhc6LWu9nVPJp3CYqztfBbYCn6DDf9CG16+VBf9VswK6seI7h7
+        nqirt5POrDOr4LC/ExoMssgmx6EzlCfv+s2fnS5e3vIM9VeX0YDfaUxs04EHhXb/4KPzJoC1ac2j
+        jeltac5xgc5gd++B3PYI22Bmw1g9KgFZx+cdGynQMv7ilz7yDuFKkP351LMfTiYsJQCpLhIpWguN
+        76FsiVd6cLRJX4LU5qEFOUQdt3OBGCfJHX7PD/x7H+9L1xThHJQYF+HiUrWYe6DvogzvTlKvM6OP
+        EijuT5i01wcF7Pg6QvgK4pZ6vlzo82dzCmBAD4zuU7MfFvypHbRLREZku91ma5+PBfjGjz8e7mbN
+        sFByKDkcInrs5Iv+oVDhoTppJTYI17LVHD4qvBBo4NB9lmyRDuYMt0bqkQWbJZteYsaBUpZNvFf7
+        Su+cVQ5gr6YI+7u3A0Sev83KJowLXyzuwGV7N5jR68Zc6iWPoB71O63gwiqEtU9sR3wq2yG0nPZE
+        ja7fuKuzmQ10PnUctriPysROHCtogQ3D+JPs3O1a1AGULo+SauHJ0XlpX8ZI350yeqCtmjFn4T0w
+        SHyDz/xqg+2xnU3UZWJP7VURXHaDlgBHg8P00NhvfTy2rgqPRM1pvKIjmPwodNDU8neq2ydTZ2O7
+        C1F5qFKKX8PFHRZvXGFV81eaBMou4wcOjzLwbk/qpxe1/uyMoEAmCc4Yl4GQrZzstsgq+Qe9D4cZ
+        LFkbJCg6NjG9Wy8pWzj/3cBY7VSaymuf0eK2jnBXmRE+bZkJlqdp+NAf6gFbh9saPQ/d7Q6siTtg
+        HG1ubDtLnA8/1fuK/TpfXVbO7gijGR7pQ3e2EVPA2qJ170v+FosWWEPf6iBRgI6dku7Z0ianM2Jl
+        scWq4R/Z9qkd2l98YU3isD7z7UuBtw4V9Hbef+pZu2wEEE/3DCdFdXDF6j7NMOmftg99uXDFME1T
+        MCX6SA/OvAGTcm4tlJ1uFoHzsdQZvxHu8BQ+eurtkiXrcuobMLzW2Tf+TCZka+8or+FpYqypDhBU
+        5eahY3a54ftLBzULDTuF0f3t4X2N7+4QGrsUifHG8We0fdXzbCoOQHjzJlwbKFk/umYDMQsqmunt
+        0RUDj2ko+/QP6ofSW19xoDVQUHHuw289YJf3MiM+vwQ+f5Xf9Xw3OwIT3eNwcu59sDruWUBjOQ/f
+        /FPd+V0FDZKlWPrG71Nf1UJvYOyh2R+rUxQxL88D0KnUoeq8sfTV3+cBME6Pid5uPnDXZBOk6Fyf
+        ZRxe02wQd6LdweOknzHu4zYj42WV0P5QddSbjzv3qydMEMutia3sHgOmk0CDnZ5gjO1HEwm9kUsg
+        7R47cu6j7bBWwVlDfsy9sNHXls5jXV+R6sYt3hdSyJZQdAo4dvGeWtHJGeYUpzEUkpzhg3UT6l5c
+        +hVAw4rxJeUfmejpQYAe7+6CdUM4ZGPt2wW4RvRBTtK2rCdD9yE8lUGK3fdJjNa++ljoKDsbsnkN
+        F53pZyeF72U806h3OnfVpwqiOx8+fbEH2F1lv65QNhUrPp6FYGChsUuQ44QG+XyWpu72qOHhmi4W
+        tqSLrI8lfOXwu/4EWcF+WPwK3OHNF2y8++UP90gq6LuCgdXyqkXisl5N+DS3D38cDjOb2LrpQYap
+        R+1XvGckOz8lKB7gGVtNyA9MLeYO1uSe/I1/sm/kM4Q0FPAh4LfR3JwXH+7ulYbNfa6yZdqPBZyK
+        k0b4Q5zrM4hUAscBB/7mUXRgtsU2hJvLcaDhV691b0uDCJ2G2lcS2YqEX/1Q93NMFi0wIuZTJYQf
+        73yhd1Tm7Lee8Fffn2G0YyR5OTMEiiz81cNzNXkWKOjJwLio9IHXmm6Gh06JCVceLPbyo9BCttTY
+        9EGHhz562zGGhnn1iOQLA1jj65BCw5NaelNnkTGzLGcknMDNp+c0ASztKgWN+mZPeLtvXbYTdx0q
+        J5Zh4/OqgNhc5xWl92tMHca9I4L7xEPcqzDopdvfwGLnxxGQ15nhOMWSPj60xoROc8uwNRhwWC9Z
+        pwFXwzufhMctYKdJilFrhyN1JbQOS+ExCV5KMaA4JUUtkkYkcHekId1J23KYPlc8Q6F+nbHpiAYT
+        /H0cgqbY7nF2/SzDeidTAcXus6exvKsznvVVBWzcaVitLu+azP2OQ3nQ3vFR35rDSuswAN/zi6bc
+        0XZnTnvwEOXrlSyXThyW4v7wIS5eDwJvAj98/VGOXpVWUvVkDBnLrZhAr4MTTQ63NXv1JTThZz8D
+        ejZOlc7sgFNgs9SCr4xwBMOK3AQw8bDHTnhQ3fmcOxVQRVvyW+cdZrNw23RQTsuQXvdvEnXCTezg
+        V/9jXyyFYU7eUwC+649x0A/Z2F6bEH52UovvrviKmGQ0AZQjJPn0W8+WROs0eNPGJ/7uV0ZO4baH
+        7MnLOEorLZtruvGgbGw0uie3sl5W89Er6fFc0KvCDpHYEHuGj6zoaWC/FzDSOMqha60ZvcX3ldEw
+        TRN48Z83ImSSP7ztfeijDzftyLwXm2hpa0GFtVFb1Lrtp3q2XC+AN5+38a1Gu2HN1spCfpC5fu1F
+        Klubq05A9zIdvFPfE2P35xIgpQptvAOew8b+Up1RoEUJWVq31L/+xwKdOjk+SIcxG7/+BT6FmMM7
+        3f/UyzbaqlAe8RG7toOG1RtTC87BpyXKc5gzej51K5DTOiTrz3+MrtlC7Xzf0MygOViFneEgTWMG
+        EU/PdqDQxyr4xruvnP2rK1YCSGDPVkbk1dOjNS83IXynuUV2TjYPrBJYgooP4b/1XAbjwB0IspIX
+        wvjrJxfjcW+g/RjI3/zeEsG1ABUqTNAeopppx5CgQx2bRA53Z33xo9SCX/9CQ6fh9NkQtg5U+qnx
+        pcVadfbYvVV4lOwtdV3dHOayuvLwr5442DAah3uoAilsYuqm2Y0xv0g4aDTWilWeXob+5yerbRHS
+        3OMXtvRjl8DoNu588P0/oVlOZyTprMWHT5jUc1xsW8QB80z3NYb6Kk2tBQzz4vmgrZuaeGNooe/+
+        4Hs7hvo69zsICkuT8eGCz7qwSS0Ic1F442P08CIWJ0n+mx/OT3iumXB8KNAk4Zna25HLuqYJKyV/
+        uRXWb29uIHxnqYg7jDmOv/p5xYHTgs/HWbB52PYubV2nAr1xCjEOoxIsFSYQds1B9cEwCvqH65Cn
+        tLkAqblbeMZW2ZxBe3R3hKvzVV/VxvLh6SjVON9fpYg8thcffuOF7le+yJazUUL4He+DMDjWq9AK
+        Ofz6bep/kBmtgfoJwM+P//QSAcPowcpUF2oNZ6zz2+nSwmePI+p847G/eKIJvzzG59zsOKzFsYOQ
+        K7dbrOW2Fq3skRH48rueujh/RYufcwJMQ2nxV0n9AJ7TLgI8vh8G9oZr/eUxZwOs9v74t77MQWMb
+        cFrhAf/4AlnDdwJrkifY9rpZnwu1smBwMix6KRxVF+JFVmFgCasv3MpXtBYPJ4Bf/uR/84P1nlZ7
+        sDrZIba//n972BYB7ByXYrtGZT13ecYB4zNp1N33VT3xaOBgkjCf2l//skRPysHPTmmpcxzLaN4e
+        hgA+5DjA9qrE7rLDyAdAgwrWpdsH9N94Adc0EPGVxRMYXwKRBN1PMVXdwIrGSpzv6PIIbGorh4e+
+        3MP1DrlPevOVIi7ZOp24EH6su4rdp+nqc7o1eoBs74AzdXPK1s/q3OGzmAm9G45c08tbXuGrkUey
+        kblRX81LoMIg2kRkMa4gm8N+nuFq+hrWw/RabzNPWxEHjDPeqWKRfeshgXypxv6WB9eMNRFvIWJ0
+        2pff2GB94EpBT7uoaGRvJDAE6NSDn5/An6TUZ/JZUmgZqkj9n59Mt0YHvTeqMW5QFTFOnnv0KE3g
+        S9JFdsku6EOIL3dINet4ZswwPsbPj1Kz6gX2V/898tsWm5F20lnwVjsISTQS5uAh+/kLkBi+hfeL
+        a4P1Jdkqsh8f8ounaO2yJYeeax+wh5ZTti2ESoDILDVqA61gLdjLCrw/1AjnXaNFQmqqFpJkofzq
+        rXMtPLJDAwf7qpNNGJVs1Squh0shSr5eTWRgnZYoP/5Hf/V9eegnBzk93JJlSSx3+3EH86/+TJxs
+        0sePw2k/v4F97TW7rDrZBuTX8UT98HgBf+P9wlcXapy2a0Q9PQhhnM0FtnxhYKstqykiUS8RepR0
+        ff6ej+jnv9WrEGWdwB9D+OODNnu9o+X1MM8wf9kVVu3rJluaUuNQuz1wVP2spfv14xU0p8ih2lfv
+        j/1pGuH7cYmw7WIXTOZ+10FWVlsif/VmZa3JqHz1IE6Q2mdTzXcK+PmPmzpfmdjbaovW07mmh1sf
+        slwB+wKi+pLjQ35p3JHgYYXvQr3R5+x8shliwwBBWkzU6U6gZkpshYB1Jv7LE8lbEO+wjo869SWv
+        05dVkRQYO+aLajei12xrEg+ixEM07tddLcZJkENjy084v6V3MJfVk4dKTxu6S/U4E19GKoDlnYXY
+        GODodibRq59/95tOWQZi9887hMcW+BsBnrKuv1Qxep42nE8bpGX0OSUdsvqT9NX7N3196dMK3jGT
+        8Y8v0vvF4+DcKcDnC/rK2NVYC9gmUYXNuW3qsTnLPuT4QvnL36gZWjkgVnHF8VDw0ZJ06Rn89OXh
+        y5/nYotm8KwH2R+Ss66z80hWeLZvnb9aj0O09pJigVbYW2TzfG/qL//t4fvVfDCWudFlfc8F4Fuv
+        /RmUj+FvfP/48zGTXH3eo0aA3SFofHFNunruPlao6PcbwCY7qpFgrQGBJ0f18cXakujzOy/uZPTp
+        MVVeTOQbKf/xJh8Yu1GfnFtC/uphR65EMCpVpaLwg2O6D8I3G7n7cIfh5xhT9cu/tk2pwb/n704o
+        5ZrlUOb++m9POIvscxpzD/C6N/scM69s9kdlhPFbcrGfjL07J+uphfkwQiIAS3HZrAQxOoXPHtuq
+        ttdZ6ZxS2NCtgs3XfaOz1H+EEE/jiUZZsNX71wOkcHFaAWP+1X39b5LA5elCbHCtNyyf10xgfUQT
+        tsL2FgkuYHf441Xu+3TNVuUSeSDMjS3+zg9M9ypa4Tk71PjohoW7dNtUhd4hWKm1nwFgr7zI4U9f
+        eN/6Roqu5cBV0yvy+vLHJXx/PAhvpMV6L6VsNHZlBcUYOfiIPM9d3pakKi+xWagfd+eBedIgKXUV
+        E+zue60WY1LeUX1fH4Trmiqa72OmAtDGM7WGjZqtvixX8DQQ++cHojZLzhWyLmSlh52oAvLVI1Ai
+        RPXnznZqwQTOGZJBOn737wAYy9UZXomI/K6Sg4wqh2sMPvsV+Eyyxay5pHsJSmEb00MPqD5yZnqH
+        h13n+gVYAp0gq+GQ8nzr2KrkOXsqr7KFocZdsEfXSm+8/XGEsekH2NIClQnNoUrhV/9hz8nL7Dt/
+        Dfn87OIo0P1sCuaUh6Of8Pi51FM04scpgYdOinE4LZa7ts1gQOsyrth5C3B4r9E5h29gyT48qaK+
+        wh0KfvoIm6P7AsupWCowjKNMjU451bM1cw388lYfda4W8T//8tO3qL40NZ3C4QzltkMkXa5DvV7e
+        xgjD7WVHrbCVo/Vz5Xl4dYMdPnz546/fBNVrfiLsNDZsLTTY/+XBzlu418365DyABK32pQDPOuOC
+        HUGPdRWwffOBvn75E7D3fuRvP2TOft+V3/ltPOOdvrinZw7H10elKh7e+qwr8vyXJ+jLuxx+fAea
+        B9X20bc/Jy7r0wT1W+KoSUI4rHC3DWBQrTr2PmQEM51LE3KPgFDHPmn1ll7VCpW9EhDu64f7Je16
+        CPJDSv/y09/+QXIa8U14V+53fh3gdq5B/Uxn2boeNPJ3v3+8aL7HjgbsVvH9zVqGNVPNWkWFC3yM
+        maeDWZ3SBB57y8YPN1RdsT4ad3iuY5kweZ3YlHnajMjj8PDrxlwZKVgWKN/8JLydsmGcH64FvvyG
+        2l7yqIXJPDXw16+5uJ445C03E7Sl1egPYVHojNJGQy3sK7LVYkVfvL0yg/FWX+h+cT9gDo6z+ePZ
+        1PsQD/A7fbgrWtH09FLWjT7LmRKD24frCT9fB33clpICnVug4PjC37J5rG0Cw3MXUHVBU0buZKqg
+        9pAbIn/95dZpUAKNIvz2x6gwEJl/8Art04akzwyB1VkOFij8JvKRKZbRXDMmwFLv9vj2kMdo2Vyu
+        IXwKZw5rEoEDO5eage7lOyVojsmwGn53/ulzwmXRC3Q/fbbi7o3d8fqu57MUWCiWGxMb57cyrPHE
+        J3Cjdi+q7kUjEz+N3/x4Az7qzjZjiHox9Iz3RL/nq1v20tGAuXUx8SGWnJpwsttA8VE1VK0uh0E0
+        9WsFke0fiJArn+jbLwgB7qwdVvFwcLfpLr//rV93NfV0QZ96CF3zEGMHZCoQxtkq4MtZL1g7GLo7
+        f/UUcJos80EkGy7jnrWKmizkCbt4G7AU94uHCpBSAvNyD2axGTiYB82dgAFag6iatQY3jZZh/Cgs
+        9u0H8gicu+2X56g1PxmbHF6r4ogvQjOBbhaDFZqmusEnutHB+uuH3o2Vo4ar9+58wKqCEsOzsMtX
+        jM03q+pQrfYMHxVniZaW0zuknfPNr75m7CxGBrSLM4+vn2pwl3Qrj8BiRYKdahrc6ZhgCwqaUmNL
+        /zRg+PYf//qLxxBw0fzrXzqiUdCQShyjXz+tpM6QUe/L9+kkXToI1nuGL1qc6uu9VgVk1G6HHRO/
+        f/mz/vgNdpX247L+eWrR1WogVpOyAV9+3EKBozw2/L0BmKy+O0iiTsJJHL0yui0YD6XLsyTAdh71
+        Mj9mH/7zuxXwX//68+d//G4YtN0jf30vBkz5Mv3H/7kq8B/if4xt+nr9vYZAxrTI//n3/76B8M9n
+        6NrP9D+nrsnf4z///rMV/t41+GfqpvT1/z7/1/dV//Wv/wUAAP//AwBcfFVx4CAAAA==
+    headers:
+      CF-RAY:
+      - 931fcf607c16eb34-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 17 Apr 2025 23:47:53 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=CncSMPCav.9EJL3emmM0sTqugx5GN6_Oy8JPFBssVho-1744933673-1.0.1.1-Q1XMvHbQdrfEWkkCYeeNHwFdZ1NpjAGJ_0jOUYIk_APelFe7nCanjW_xlOj12b3JQql9.iWQDiHvCeYJDTWkdxnNiMQOEiFMYHX5YZXUuJs;
+        path=/; expires=Fri, 18-Apr-25 00:17:53 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=unfPTYCpF5COtm5PuZDuaJqlhefP0iibfjsXHc9lKq0-1744933673515-0.0.1.1-604800000;
+        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:
+      - '75'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-8687b6cbdb-4qpmr
+      x-envoy-upstream-service-time:
+      - '46'
+      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_b8c884a7fe2bd4732903ecbdc632576d
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Information Agent.
+      You have access to specific knowledge sources.\nYour personal goal is: Provide
+      information based on knowledge sources\nTo give my best complete final answer
+      to the task respond using the exact following format:\n\nThought: I now can
+      give a great answer\nFinal Answer: Your final answer must be the great and the
+      most complete as possible, it must be outcome described.\n\nI MUST use these
+      formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task:
+      What is Brandon''s favorite color?\n\nThis is the expected criteria for your
+      final answer: Brandon''s favorite color.\nyou MUST return the actual complete
+      content as the final answer, not a summary.\n\nBegin! This is VERY important
+      to you, use the tools available and give your best Final Answer, your job depends
+      on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '926'
+      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//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:
+      - 931fcf649bdbed40-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - 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:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '489'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999801'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_151f9d0b786f2022f249ee20ea108b43
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default.yaml
+++ b/tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default.yaml
@@ -0,0 +1,330 @@
+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, zstd
+      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+yPtfmz59Pced/yrwR2bV9zhAQ2UkRFHEymYAiOxHZtEDfvN99ovdkNicm
+        YiNpu1bXdf1W//Nff/7802V1fp/++feff17VOP3z377PHumU/vPvP//9X3/+/Pnzn7/P/29k3mb5
+        41G9i9/w34/V+5Ev//z7D/9/nvzfQf/+889JZZQeb+UOCJHjaQqtRQfv1mXUaf0OTfTuHjx+CvAU
+        CWC/KEik3pNeZScAwr5Zzkgne4Gqd6jX2+oDW3BxGx8nMkfrxaq0GM2PNaV5G6QZM0P1joRJl32W
+        BVuXtTPPo02jZhRX8gjWdj7MgDz2D+wRexhoUHsaTN9P0RfLw5itFrmbCgzCHVFOdx/wQte1qJvK
+        FxH556YeT0pqoJ0RTNhqPwiskhTe0T7qIpzrwS4arGS24D4uc6y90d4VpMq+wy7hntS8mG297p2B
+        QNrwZ5pV1p4RZ6vPEHEPDtuWVA0L/w451CylgPUZBhFvXaQWWqXwwKobdNmavrcCyvDk4aRDezby
+        2c5Hym33obtXgLKlioYGKUfZovrOBtkSu6cOQbHw6POcJoyE+vmMxtegUst+HNh2ZImhpFTNsJ4V
+        73p1XlWO8NsSscGvH7asThqCqtoe6anKt+6SsI0K91Ef0UtGS5dIB8DD3QV2vtwaybB8lksCj5K7
+        pTjWccSrU5igG+hfVOuSRl+4sPGhtJ4Qtfr4w4g0EQcaRfCgnrKxXVFD8hnSZ6jTk5PN9ax4JxU5
+        T/5MsnTwskU6ARNOHnCJYHpsoPbgFfDzsRYaLe9dPbfLoiDTls800h+6vjruXYDSGiGs3fJFXw5Z
+        2APLfh+ok3y2YDvrfQvLm3/x5fPervlV0QUUF5c33aFAzQRua0JwHeCKb5/FGITQVzsgc1KIg6vA
+        Mmo+Xg5CiY/80LSf2UqSFwdOKDHoMVyBvk6jq0DzTRTs1uUHLFui9ciAyYGq8fHOhDqzzoCpgkE9
+        Ta/q9aW/VnRO/IR6zaVjs8DvQ9Q/byvOji+YzUV7ztGHji4+b4t7LZqHuwO9+NRR9aZ0YFFWKQF8
+        oXu+5D2rgfee2RlmG3/CO+mFXbq0SgJ35cGm+JxKjEnnY6vsjlOI9+aSsPUqdSNMj3FBD3qdMHHA
+        UgCXpjj46xaeI6GBnAZtrfZJOLMKLKg6VrDCz5jaF6K6/LjWGpwt36FHS430JTwlHtrvYIL3q03d
+        JUkWDWVaEtKLvglq9sj4HiRDHtFo3yjuyGe2D/nPY8ER4xwmtq/AQtvoptF7rdiAX9jdgRtn7+Bn
+        tJEZJc2GgD4yNZz3YBjWu3ziAaFrhXenYwImk8wNpOrj/M13t+Y7wz/D3/57Lz0b2K1kHixsVceP
+        ztUy8VYyH90e/AbvXU+sGZ8aDnKhc6LWu9nVPJp3CYqztfBbYCn6DDf9CG16+VBf9VswK6seI7h7
+        nqirt5POrDOr4LC/ExoMssgmx6EzlCfv+s2fnS5e3vIM9VeX0YDfaUxs04EHhXb/4KPzJoC1ac2j
+        jeltac5xgc5gd++B3PYI22Bmw1g9KgFZx+cdGynQMv7ilz7yDuFKkP351LMfTiYsJQCpLhIpWguN
+        76FsiVd6cLRJX4LU5qEFOUQdt3OBGCfJHX7PD/x7H+9L1xThHJQYF+HiUrWYe6DvogzvTlKvM6OP
+        EijuT5i01wcF7Pg6QvgK4pZ6vlzo82dzCmBAD4zuU7MfFvypHbRLREZku91ma5+PBfjGjz8e7mbN
+        sFByKDkcInrs5Iv+oVDhoTppJTYI17LVHD4qvBBo4NB9lmyRDuYMt0bqkQWbJZteYsaBUpZNvFf7
+        Su+cVQ5gr6YI+7u3A0Sev83KJowLXyzuwGV7N5jR68Zc6iWPoB71O63gwiqEtU9sR3wq2yG0nPZE
+        ja7fuKuzmQ10PnUctriPysROHCtogQ3D+JPs3O1a1AGULo+SauHJ0XlpX8ZI350yeqCtmjFn4T0w
+        SHyDz/xqg+2xnU3UZWJP7VURXHaDlgBHg8P00NhvfTy2rgqPRM1pvKIjmPwodNDU8neq2ydTZ2O7
+        C1F5qFKKX8PFHRZvXGFV81eaBMou4wcOjzLwbk/qpxe1/uyMoEAmCc4Yl4GQrZzstsgq+Qe9D4cZ
+        LFkbJCg6NjG9Wy8pWzj/3cBY7VSaymuf0eK2jnBXmRE+bZkJlqdp+NAf6gFbh9saPQ/d7Q6siTtg
+        HG1ubDtLnA8/1fuK/TpfXVbO7gijGR7pQ3e2EVPA2qJ170v+FosWWEPf6iBRgI6dku7Z0ianM2Jl
+        scWq4R/Z9qkd2l98YU3isD7z7UuBtw4V9Hbef+pZu2wEEE/3DCdFdXDF6j7NMOmftg99uXDFME1T
+        MCX6SA/OvAGTcm4tlJ1uFoHzsdQZvxHu8BQ+eurtkiXrcuobMLzW2Tf+TCZka+8or+FpYqypDhBU
+        5eahY3a54ftLBzULDTuF0f3t4X2N7+4QGrsUifHG8We0fdXzbCoOQHjzJlwbKFk/umYDMQsqmunt
+        0RUDj2ko+/QP6ofSW19xoDVQUHHuw289YJf3MiM+vwQ+f5Xf9Xw3OwIT3eNwcu59sDruWUBjOQ/f
+        /FPd+V0FDZKlWPrG71Nf1UJvYOyh2R+rUxQxL88D0KnUoeq8sfTV3+cBME6Pid5uPnDXZBOk6Fyf
+        ZRxe02wQd6LdweOknzHu4zYj42WV0P5QddSbjzv3qydMEMutia3sHgOmk0CDnZ5gjO1HEwm9kUsg
+        7R47cu6j7bBWwVlDfsy9sNHXls5jXV+R6sYt3hdSyJZQdAo4dvGeWtHJGeYUpzEUkpzhg3UT6l5c
+        +hVAw4rxJeUfmejpQYAe7+6CdUM4ZGPt2wW4RvRBTtK2rCdD9yE8lUGK3fdJjNa++ljoKDsbsnkN
+        F53pZyeF72U806h3OnfVpwqiOx8+fbEH2F1lv65QNhUrPp6FYGChsUuQ44QG+XyWpu72qOHhmi4W
+        tqSLrI8lfOXwu/4EWcF+WPwK3OHNF2y8++UP90gq6LuCgdXyqkXisl5N+DS3D38cDjOb2LrpQYap
+        R+1XvGckOz8lKB7gGVtNyA9MLeYO1uSe/I1/sm/kM4Q0FPAh4LfR3JwXH+7ulYbNfa6yZdqPBZyK
+        k0b4Q5zrM4hUAscBB/7mUXRgtsU2hJvLcaDhV691b0uDCJ2G2lcS2YqEX/1Q93NMFi0wIuZTJYQf
+        73yhd1Tm7Lee8Fffn2G0YyR5OTMEiiz81cNzNXkWKOjJwLio9IHXmm6Gh06JCVceLPbyo9BCttTY
+        9EGHhz562zGGhnn1iOQLA1jj65BCw5NaelNnkTGzLGcknMDNp+c0ASztKgWN+mZPeLtvXbYTdx0q
+        J5Zh4/OqgNhc5xWl92tMHca9I4L7xEPcqzDopdvfwGLnxxGQ15nhOMWSPj60xoROc8uwNRhwWC9Z
+        pwFXwzufhMctYKdJilFrhyN1JbQOS+ExCV5KMaA4JUUtkkYkcHekId1J23KYPlc8Q6F+nbHpiAYT
+        /H0cgqbY7nF2/SzDeidTAcXus6exvKsznvVVBWzcaVitLu+azP2OQ3nQ3vFR35rDSuswAN/zi6bc
+        0XZnTnvwEOXrlSyXThyW4v7wIS5eDwJvAj98/VGOXpVWUvVkDBnLrZhAr4MTTQ63NXv1JTThZz8D
+        ejZOlc7sgFNgs9SCr4xwBMOK3AQw8bDHTnhQ3fmcOxVQRVvyW+cdZrNw23RQTsuQXvdvEnXCTezg
+        V/9jXyyFYU7eUwC+649x0A/Z2F6bEH52UovvrviKmGQ0AZQjJPn0W8+WROs0eNPGJ/7uV0ZO4baH
+        7MnLOEorLZtruvGgbGw0uie3sl5W89Er6fFc0KvCDpHYEHuGj6zoaWC/FzDSOMqha60ZvcX3ldEw
+        TRN48Z83ImSSP7ztfeijDzftyLwXm2hpa0GFtVFb1Lrtp3q2XC+AN5+38a1Gu2HN1spCfpC5fu1F
+        Klubq05A9zIdvFPfE2P35xIgpQptvAOew8b+Up1RoEUJWVq31L/+xwKdOjk+SIcxG7/+BT6FmMM7
+        3f/UyzbaqlAe8RG7toOG1RtTC87BpyXKc5gzej51K5DTOiTrz3+MrtlC7Xzf0MygOViFneEgTWMG
+        EU/PdqDQxyr4xruvnP2rK1YCSGDPVkbk1dOjNS83IXynuUV2TjYPrBJYgooP4b/1XAbjwB0IspIX
+        wvjrJxfjcW+g/RjI3/zeEsG1ABUqTNAeopppx5CgQx2bRA53Z33xo9SCX/9CQ6fh9NkQtg5U+qnx
+        pcVadfbYvVV4lOwtdV3dHOayuvLwr5442DAah3uoAilsYuqm2Y0xv0g4aDTWilWeXob+5yerbRHS
+        3OMXtvRjl8DoNu588P0/oVlOZyTprMWHT5jUc1xsW8QB80z3NYb6Kk2tBQzz4vmgrZuaeGNooe/+
+        4Hs7hvo69zsICkuT8eGCz7qwSS0Ic1F442P08CIWJ0n+mx/OT3iumXB8KNAk4Zna25HLuqYJKyV/
+        uRXWb29uIHxnqYg7jDmOv/p5xYHTgs/HWbB52PYubV2nAr1xCjEOoxIsFSYQds1B9cEwCvqH65Cn
+        tLkAqblbeMZW2ZxBe3R3hKvzVV/VxvLh6SjVON9fpYg8thcffuOF7le+yJazUUL4He+DMDjWq9AK
+        Ofz6bep/kBmtgfoJwM+P//QSAcPowcpUF2oNZ6zz2+nSwmePI+p847G/eKIJvzzG59zsOKzFsYOQ
+        K7dbrOW2Fq3skRH48rueujh/RYufcwJMQ2nxV0n9AJ7TLgI8vh8G9oZr/eUxZwOs9v74t77MQWMb
+        cFrhAf/4AlnDdwJrkifY9rpZnwu1smBwMix6KRxVF+JFVmFgCasv3MpXtBYPJ4Bf/uR/84P1nlZ7
+        sDrZIba//n972BYB7ByXYrtGZT13ecYB4zNp1N33VT3xaOBgkjCf2l//skRPysHPTmmpcxzLaN4e
+        hgA+5DjA9qrE7rLDyAdAgwrWpdsH9N94Adc0EPGVxRMYXwKRBN1PMVXdwIrGSpzv6PIIbGorh4e+
+        3MP1DrlPevOVIi7ZOp24EH6su4rdp+nqc7o1eoBs74AzdXPK1s/q3OGzmAm9G45c08tbXuGrkUey
+        kblRX81LoMIg2kRkMa4gm8N+nuFq+hrWw/RabzNPWxEHjDPeqWKRfeshgXypxv6WB9eMNRFvIWJ0
+        2pff2GB94EpBT7uoaGRvJDAE6NSDn5/An6TUZ/JZUmgZqkj9n59Mt0YHvTeqMW5QFTFOnnv0KE3g
+        S9JFdsku6EOIL3dINet4ZswwPsbPj1Kz6gX2V/898tsWm5F20lnwVjsISTQS5uAh+/kLkBi+hfeL
+        a4P1Jdkqsh8f8ounaO2yJYeeax+wh5ZTti2ESoDILDVqA61gLdjLCrw/1AjnXaNFQmqqFpJkofzq
+        rXMtPLJDAwf7qpNNGJVs1Squh0shSr5eTWRgnZYoP/5Hf/V9eegnBzk93JJlSSx3+3EH86/+TJxs
+        0sePw2k/v4F97TW7rDrZBuTX8UT98HgBf+P9wlcXapy2a0Q9PQhhnM0FtnxhYKstqykiUS8RepR0
+        ff6ej+jnv9WrEGWdwB9D+OODNnu9o+X1MM8wf9kVVu3rJluaUuNQuz1wVP2spfv14xU0p8ih2lfv
+        j/1pGuH7cYmw7WIXTOZ+10FWVlsif/VmZa3JqHz1IE6Q2mdTzXcK+PmPmzpfmdjbaovW07mmh1sf
+        slwB+wKi+pLjQ35p3JHgYYXvQr3R5+x8shliwwBBWkzU6U6gZkpshYB1Jv7LE8lbEO+wjo869SWv
+        05dVkRQYO+aLajei12xrEg+ixEM07tddLcZJkENjy084v6V3MJfVk4dKTxu6S/U4E19GKoDlnYXY
+        GODodibRq59/95tOWQZi9887hMcW+BsBnrKuv1Qxep42nE8bpGX0OSUdsvqT9NX7N3196dMK3jGT
+        8Y8v0vvF4+DcKcDnC/rK2NVYC9gmUYXNuW3qsTnLPuT4QvnL36gZWjkgVnHF8VDw0ZJ06Rn89OXh
+        y5/nYotm8KwH2R+Ss66z80hWeLZvnb9aj0O09pJigVbYW2TzfG/qL//t4fvVfDCWudFlfc8F4Fuv
+        /RmUj+FvfP/48zGTXH3eo0aA3SFofHFNunruPlao6PcbwCY7qpFgrQGBJ0f18cXakujzOy/uZPTp
+        MVVeTOQbKf/xJh8Yu1GfnFtC/uphR65EMCpVpaLwg2O6D8I3G7n7cIfh5xhT9cu/tk2pwb/n704o
+        5ZrlUOb++m9POIvscxpzD/C6N/scM69s9kdlhPFbcrGfjL07J+uphfkwQiIAS3HZrAQxOoXPHtuq
+        ttdZ6ZxS2NCtgs3XfaOz1H+EEE/jiUZZsNX71wOkcHFaAWP+1X39b5LA5elCbHCtNyyf10xgfUQT
+        tsL2FgkuYHf441Xu+3TNVuUSeSDMjS3+zg9M9ypa4Tk71PjohoW7dNtUhd4hWKm1nwFgr7zI4U9f
+        eN/6Roqu5cBV0yvy+vLHJXx/PAhvpMV6L6VsNHZlBcUYOfiIPM9d3pakKi+xWagfd+eBedIgKXUV
+        E+zue60WY1LeUX1fH4Trmiqa72OmAtDGM7WGjZqtvixX8DQQ++cHojZLzhWyLmSlh52oAvLVI1Ai
+        RPXnznZqwQTOGZJBOn737wAYy9UZXomI/K6Sg4wqh2sMPvsV+Eyyxay5pHsJSmEb00MPqD5yZnqH
+        h13n+gVYAp0gq+GQ8nzr2KrkOXsqr7KFocZdsEfXSm+8/XGEsekH2NIClQnNoUrhV/9hz8nL7Dt/
+        Dfn87OIo0P1sCuaUh6Of8Pi51FM04scpgYdOinE4LZa7ts1gQOsyrth5C3B4r9E5h29gyT48qaK+
+        wh0KfvoIm6P7AsupWCowjKNMjU451bM1cw388lYfda4W8T//8tO3qL40NZ3C4QzltkMkXa5DvV7e
+        xgjD7WVHrbCVo/Vz5Xl4dYMdPnz546/fBNVrfiLsNDZsLTTY/+XBzlu418365DyABK32pQDPOuOC
+        HUGPdRWwffOBvn75E7D3fuRvP2TOft+V3/ltPOOdvrinZw7H10elKh7e+qwr8vyXJ+jLuxx+fAea
+        B9X20bc/Jy7r0wT1W+KoSUI4rHC3DWBQrTr2PmQEM51LE3KPgFDHPmn1ll7VCpW9EhDu64f7Je16
+        CPJDSv/y09/+QXIa8U14V+53fh3gdq5B/Uxn2boeNPJ3v3+8aL7HjgbsVvH9zVqGNVPNWkWFC3yM
+        maeDWZ3SBB57y8YPN1RdsT4ad3iuY5kweZ3YlHnajMjj8PDrxlwZKVgWKN/8JLydsmGcH64FvvyG
+        2l7yqIXJPDXw16+5uJ445C03E7Sl1egPYVHojNJGQy3sK7LVYkVfvL0yg/FWX+h+cT9gDo6z+ePZ
+        1PsQD/A7fbgrWtH09FLWjT7LmRKD24frCT9fB33clpICnVug4PjC37J5rG0Cw3MXUHVBU0buZKqg
+        9pAbIn/95dZpUAKNIvz2x6gwEJl/8Art04akzwyB1VkOFij8JvKRKZbRXDMmwFLv9vj2kMdo2Vyu
+        IXwKZw5rEoEDO5eage7lOyVojsmwGn53/ulzwmXRC3Q/fbbi7o3d8fqu57MUWCiWGxMb57cyrPHE
+        J3Cjdi+q7kUjEz+N3/x4Az7qzjZjiHox9Iz3RL/nq1v20tGAuXUx8SGWnJpwsttA8VE1VK0uh0E0
+        9WsFke0fiJArn+jbLwgB7qwdVvFwcLfpLr//rV93NfV0QZ96CF3zEGMHZCoQxtkq4MtZL1g7GLo7
+        f/UUcJos80EkGy7jnrWKmizkCbt4G7AU94uHCpBSAvNyD2axGTiYB82dgAFag6iatQY3jZZh/Cgs
+        9u0H8gicu+2X56g1PxmbHF6r4ogvQjOBbhaDFZqmusEnutHB+uuH3o2Vo4ar9+58wKqCEsOzsMtX
+        jM03q+pQrfYMHxVniZaW0zuknfPNr75m7CxGBrSLM4+vn2pwl3Qrj8BiRYKdahrc6ZhgCwqaUmNL
+        /zRg+PYf//qLxxBw0fzrXzqiUdCQShyjXz+tpM6QUe/L9+kkXToI1nuGL1qc6uu9VgVk1G6HHRO/
+        f/mz/vgNdpX247L+eWrR1WogVpOyAV9+3EKBozw2/L0BmKy+O0iiTsJJHL0yui0YD6XLsyTAdh71
+        Mj9mH/7zuxXwX//68+d//G4YtN0jf30vBkz5Mv3H/7kq8B/if4xt+nr9vYZAxrTI//n3/76B8M9n
+        6NrP9D+nrsnf4z///rMV/t41+GfqpvT1/z7/1/dV//Wv/wUAAP//AwBcfFVx4CAAAA==
+    headers:
+      CF-RAY:
+      - 931fceef786ded38-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 17 Apr 2025 23:47:35 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=fj4RMXSXRDQjE2CFC6CGC3dVcJ8cl2Cbu8alijwMHA8-1744933655-1.0.1.1-M3c3AI4XQa.0GJoanNACuOm2aEL4xjqHR1grxIP3olFvq3e0eFHwQTvCF20YwR_OLiMJUH87eNUwgziawMccsxjR9OVZyDr5._5Wts6CrqA;
+        path=/; expires=Fri, 18-Apr-25 00:17:35 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=MSkpJsQZtdyIGvrl2mIwy0a_We8H6CIrS7etFgRBl2Y-1744933655703-0.0.1.1-604800000;
+        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:
+      - '140'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-84959bbcd5-rzqvq
+      x-envoy-upstream-service-time:
+      - '110'
+      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_dd3ef61c4765b46ed7db80ddfe261f41
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Information Agent.
+      You have access to specific knowledge sources.\nYour personal goal is: Provide
+      information based on knowledge sources\nTo give my best complete final answer
+      to the task respond using the exact following format:\n\nThought: I now can
+      give a great answer\nFinal Answer: Your final answer must be the great and the
+      most complete as possible, it must be outcome described.\n\nI MUST use these
+      formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task:
+      What is Brandon''s favorite color?\n\nThis is the expected criteria for your
+      final answer: Brandon''s favorite color.\nyou MUST return the actual complete
+      content as the final answer, not a summary.\n\nBegin! This is VERY important
+      to you, use the tools available and give your best Final Answer, your job depends
+      on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '926'
+      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//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:
+      - 931fcef51a67f947-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - 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:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '540'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999802'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_8837be6510731522fd5ac4b75c11d486
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_gemini_models[gemini-gemini-2.0-flash-001].yaml
+++ b/tests/cassettes/test_gemini_models[gemini-gemini-2.0-flash-001].yaml
@@ -0,0 +1,59 @@
+interactions:
+- request:
+    body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
+      of France?"}]}], "generationConfig": {"stop_sequences": []}}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '131'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      user-agent:
+      - litellm/1.60.2
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-001:generateContent
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAC/62RTU+EMBCG7/0VTY9kIQUT1vXqx0njRokxUQ8jDNAILaFdoyH8dwssbNGrTdo0
+        807nnT7TEUpZCjITGRjU7IK+2Ail3XgOmpIGpbHCHLLBBlpzyp1W59xtisGv4RFLSqQpNMJARVVO
+        b1qQKVKhqeftoRXa84JXyZy3/XJ/25wcW1XhUK5WGVZzej8nsFxIocsHBK3kkPaY3O/ZosJncauK
+        plXvQ9M+D3gUxiE/tzs6i+JtyHdkth5N2UFDgXdowFKB5e/Mlqgbk6gPlJfqMFLZTi4Ow5W8O8pG
+        WQArJYw3f4rqK2spKhetQ93+HSphvkes188Jc/iYVU8zH+Jg/N3hP3nt1l7kOJVpUE/YajFNpMDa
+        zsiPAu7nFejS5zxkpCc/6so6tIECAAA=
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 22 Apr 2025 14:25:05 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=1219
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - nosniff
+      X-Frame-Options:
+      - SAMEORIGIN
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_gemini_models[gemini-gemini-2.0-flash-lite-001].yaml
+++ b/tests/cassettes/test_gemini_models[gemini-gemini-2.0-flash-lite-001].yaml
@@ -0,0 +1,59 @@
+interactions:
+- request:
+    body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
+      of France?"}]}], "generationConfig": {"stop_sequences": []}}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '131'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      user-agent:
+      - litellm/1.60.2
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-lite-001:generateContent
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAC/61RTU+EMBC98yuanhdSiMjq1Y+Txo0SY6J7GGGARmhJ2zUawn+3wMIWvdpDM5n3
+        Zt7Mm84jhGYgcp6DQU0vyavNENKN/4BJYVAYC8wpm2xBmRN3ep0TW4rBr6GIphWSDFpuoCayILcK
+        RIaEa7IDxXXwJqhT1y/xfnNSU7LGoVUjc6xnej8TaMEF19UjgpZioD2lDzu6oPBZ3smyVfJ9GNhn
+        AQuTMIpjFl/EZyxKwuTcm6VHUXrQUOI9GrCOwLI3tS2a1qTyA8WVPIyOJJOK498K3h5hI+3yKySM
+        N3+a6msryWvXVsdxuzvU3HyPlt68pNTxx6xmmv3xHBt/T/hPWtu1lne8ynSoZ1SaTxcpsbE38qOA
+        +UUNuvJtd/QZC6nXez+t5iqFggIAAA==
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 22 Apr 2025 14:25:06 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=1090
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - nosniff
+      X-Frame-Options:
+      - SAMEORIGIN
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_gemini_models[gemini-gemini-2.0-flash-thinking-exp-01-21].yaml
+++ b/tests/cassettes/test_gemini_models[gemini-gemini-2.0-flash-thinking-exp-01-21].yaml
@@ -0,0 +1,58 @@
+interactions:
+- request:
+    body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
+      of France?"}]}], "generationConfig": {"stop_sequences": []}}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '131'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      user-agent:
+      - litellm/1.60.2
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-thinking-exp-01-21:generateContent
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAC/22QQWuEMBCF7/6KkKNsFt1DKb2221vp0koplD0M66jDxkSSWbCI/71Rq+vS5pCE
+        eW9meF8XCSFPYHLKgdHLB/EVKkJ04z1o1jAaDsJcCsUGHF+90+lW/2BhbIcmmVUoTtAQgxa2EM8O
+        zAkFeRHHB3Dk43grV5398j9urvuc1TgMq22Oerb3s0EWZMhXbwjemsH2nr0e5KKSybEN5SSaF4yj
+        5cVDiS/IEJLDkk82ztYNZ/aM5tFexuT306wVp39ltiHkjZLebf4M9U9hJek1vhXZkBA08feIbv+Z
+        yRUFvlk6UxjfY/TLY0L0gc7TxKLEOtBRu22iCg2+UlyROZMpFbaNSlK1S2XURz/Fy1P+CAIAAA==
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 22 Apr 2025 14:25:04 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=764
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - nosniff
+      X-Frame-Options:
+      - SAMEORIGIN
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_gemini_models[gemini-gemini-2.5-flash-preview-04-17].yaml
+++ b/tests/cassettes/test_gemini_models[gemini-gemini-2.5-flash-preview-04-17].yaml
@@ -0,0 +1,59 @@
+interactions:
+- request:
+    body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
+      of France?"}]}], "generationConfig": {"stop_sequences": []}}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '131'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      user-agent:
+      - litellm/1.60.2
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-preview-04-17:generateContent
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAC/2WQT0+EMBDF7/0UTY9k2ewaDerVPzfjRokxMR4mMEBjaUk76BrCd7fAslvcHppm
+        5s2bvl/HOBcZ6FzmQOjELf/wFc678R56RhNq8o255IsNWDppp9MFby8h3A9DIq2QZ9BIAsVNwR8t
+        6Ay5dDyKdmCli6K1CCb74/tzddpnjcLBrDY5qlnezwJRSC1d9YLgjB5kr+nzThy7Uue49+UNmxeM
+        1qJ1UOITEvjkcMwnGmvqhlLzhfrOtGPy68kr4LRoJzeHPhmfcjmZrM5c3b3fKVXIL0DrI4KS9Duy
+        e3hPRYCBFtYzBhbQElSZtqzo3we37IBrIviG1skJVYm1hxdfrK/iQoGr4sbit8SfeHMZbxPBevYH
+        O2bXiSICAAA=
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 22 Apr 2025 14:25:28 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=20971
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - nosniff
+      X-Frame-Options:
+      - SAMEORIGIN
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_gemini_models[gemini-gemini-2.5-pro-exp-03-25].yaml
+++ b/tests/cassettes/test_gemini_models[gemini-gemini-2.5-pro-exp-03-25].yaml
@@ -0,0 +1,59 @@
+interactions:
+- request:
+    body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
+      of France?"}]}], "generationConfig": {"stop_sequences": []}}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '131'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      user-agent:
+      - litellm/1.60.2
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro-exp-03-25:generateContent
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAC/12QT2uEMBDF7/kUIUepi2tZaHttu7fSpZVSKD0MOquhmkgygkX87o26cWM9SJj3
+        5s/7DYxzkYMqZAGEVjzwL1fhfJj/k6YVoSIn+JIrtmDo6l2+IXg7C2E/NYmsQp5DKwlqrs/8aEDl
+        yKXlUXQCI20U7UTQOa7v75vrPqNrnIY1usDa20dvEGeppK3eEKxWk+09ez2JVZWqwN6VE+YXzKNF
+        Z6HEFyRwyWHNJ1qjm5Yy/YPqUXdz8rtlVsBpI++T5GIg7WL+03xzMNc+ua2yDgkGcF1IqCX9zvSe
+        PzMRgKDNWR4EC3gJqnRXVrQ98T5lF2ALww80Vi6wSmwcvjjdHWJ3Yox9Gye3cXoQbGR/TedYqx4C
+        AAA=
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 22 Apr 2025 14:25:30 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=2418
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - nosniff
+      X-Frame-Options:
+      - SAMEORIGIN
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_gemma3[gemini-gemma-3-12b-it].yaml
+++ b/tests/cassettes/test_gemma3[gemini-gemma-3-12b-it].yaml
@@ -0,0 +1,59 @@
+interactions:
+- request:
+    body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
+      of France?"}]}], "generationConfig": {"stop_sequences": []}}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '131'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      user-agent:
+      - litellm/1.60.2
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemma-3-12b-it:generateContent
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAC/2WRTWvDMAyG7/kVwpdBSEvX7jB23QfsMFa2MAZbD2qipGaOFWwFWkr/+5ykaVPq
+        gGP0SvLrR/sIQGVoc52jkFcP8BMiAPtubzW2QlaCMIRCsEYn59x+7UfnkCK0bYtUuiHIsNaCBriA
+        F4c2I9Ae4niJTvs4nv7a/nuVGw9oPIOEIoOuJC+QadmBtkNlsAoIpeF1aJgFZ+SgYAfBUQIF+o1m
+        m0CJXhxbrnZJV5E1RhpHUzUyeTidV8n5aY4Ntb4rzskM6YchQRXaar/5IPRs27TP9H2pTqq2OW1D
+        eBYNF3StVeOxpDcSDJDxhFLVjqtaUv4j+8hNB/m+7zUayYW8mB914QD0QrqbJVdd/VO4U5vxqEZT
+        DE9EE+h2Y3r+TtUIg1yYGjB0/1V0BNIz+iLndQ+jpKrCyWJyO19PtKjoEP0DlZtdIF8CAAA=
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 22 Apr 2025 14:25:39 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=3835
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - nosniff
+      X-Frame-Options:
+      - SAMEORIGIN
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_gemma3[gemini-gemma-3-1b-it].yaml
+++ b/tests/cassettes/test_gemma3[gemini-gemma-3-1b-it].yaml
@@ -0,0 +1,60 @@
+interactions:
+- request:
+    body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
+      of France?"}]}], "generationConfig": {"stop_sequences": []}}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '131'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      user-agent:
+      - litellm/1.60.2
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemma-3-1b-it:generateContent
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAC/2VRy07DQAy85yusPUZtBSoIxJWHxAFRQYSQKAc3cVqL7DrKuqKlqsRv8Ht8CZuk
+        aVOxh314xuP1eBMBmBRdxhkqeXMFbyECsGn2GhOn5DQAXSgES6z0wG3XpncPFKVVnWSSBUGKJSsW
+        IDncVehSAvYQxxOs2MfxCKZu6u719/vHA0Iq1ooDyz6UTqlUDi9doELDr1M1aMbiinXcSQ9gtlTg
+        VqOGJc855VAztAZWvMInZ1SsoaJU5o6/KANxNDK9X2/39/fBoddKCqobsRLyO/q2I5icHfvFE6EX
+        V9Oek8eJ2aPsMlqF8EnUFWikzdLjnB5IMbiOe29NWYktNZEPcteybFy/bLV6MzqCxxc7XCXYcASd
+        nQ/+qfqbUJOL/ux6Yw0tYsG6buZ2+5qYng169KnOhuZ8j3aGtB69UOW5NWNO1uJwPDydDVlNtI3+
+        AD6XWQdvAgAA
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 22 Apr 2025 14:25:32 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=1535
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - nosniff
+      X-Frame-Options:
+      - SAMEORIGIN
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_gemma3[gemini-gemma-3-27b-it].yaml
+++ b/tests/cassettes/test_gemma3[gemini-gemma-3-27b-it].yaml
@@ -0,0 +1,60 @@
+interactions:
+- request:
+    body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
+      of France?"}]}], "generationConfig": {"stop_sequences": []}}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '131'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      user-agent:
+      - litellm/1.60.2
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemma-3-27b-it:generateContent
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAC/2VRXUvDMBR976+45EUo3RDnUHwTnSA4HFpEcHuI7e16aZqU5NZNxv67abtuHTbQ
+        hHPu5zm7AEAkUqeUSkYn7uDLIwC79t9wRjNq9kQPebCSlk+x3bcbvH0I47ZJEnGOkMiKWCowGTxZ
+        qRMEchCGC2nJheEYlnqpn/nCQaHNRkNmLJDvSwkoP1kpbeFAUYHAvtiMsgwVxGaDNmqRF1P/WIR5
+        7bAuI/ApLXxvE0gRYkumrHL0hIMNKtXcxA4y6XIyOoKkJkcau8ykVlxbHDczNUcM1tof36voJIY1
+        CptNS5Oi6sP3fYDISJPL31A6o5uw9/h1IY4s6RS3Hr4M+gZtaVE7ucY5svS2yKP4orJ+F45NgfrB
+        1K0tt12tgYln9PX0wLPxFpxR00n0r6p79D1JDc0d+O5XlIr4tzV29hmLgQx8NlQvQ3uvgoMgnUYf
+        aB11YqyxLOVoMrq6+R4Ri2Af/AEDrXcbkQIAAA==
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 22 Apr 2025 14:25:41 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=2447
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - nosniff
+      X-Frame-Options:
+      - SAMEORIGIN
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_gemma3[gemini-gemma-3-4b-it].yaml
+++ b/tests/cassettes/test_gemma3[gemini-gemma-3-4b-it].yaml
@@ -0,0 +1,60 @@
+interactions:
+- request:
+    body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
+      of France?"}]}], "generationConfig": {"stop_sequences": []}}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '131'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      user-agent:
+      - litellm/1.60.2
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemma-3-4b-it:generateContent
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAC/2WRzUrDQBDH73mKYY+lLUKLiBcPfoAHsWhQwXqYJtNk6WYn7E6woRQ8+wR68t18
+        Ah/BbWraFPeQXeb/z3z8ZhUBqARtqlMU8uoUnkMEYNV8NxpbIStBaEMhWKKTvXd7Vp13sAgtNz+p
+        OCdIsNSCBngOVw5tQqA99HoTdNr3ekOY2qm9lu+3Tw8ImeFZ8CahKDmYs4NQrA9z9Llm24cMvTi2
+        XNQQ2oakMlI5GsLP18d7k+mRK5NCzRUYvSAQhoXl12CuJdc2g4IdAc64Emg6OFOdzte790t/P69j
+        Q5thCk7JtPZ1a1BzbbXP7wg9243tPr6dqJ2qbUrLED6K2gJNalV5zOiGBAN53PFVpeOilJgXZM+5
+        asifbHN19nQgj1pdOFA+kMbH/X9Z/UWoqU13f53VhhHRaKmb3V0+xaqDQQ6aajE090v0B2TL6IGc
+        11sYGRUFDkaD8WygRUXr6BcxmBLccwIAAA==
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Tue, 22 Apr 2025 14:25:35 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=2349
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - nosniff
+      X-Frame-Options:
+      - SAMEORIGIN
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_gpt_4_1[gpt-4.1-mini-2025-04-14].yaml
+++ b/tests/cassettes/test_gpt_4_1[gpt-4.1-mini-2025-04-14].yaml
@@ -0,0 +1,101 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the capital of France?"}],
+      "model": "gpt-4.1-mini-2025-04-14", "stop": []}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '125'
+      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:
+      - 3.11.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jJJPb9swDMXv/hSCznEQe+7S5LgAGzDs0P3paSgMRqJtZrIkSPTQoch3
+        H2Snsbt1wC4+8MdHv0fxKRNCkpZ7IVUHrHpv8nd3t4eIH77w4ePX+/b+8XP56bTdHE7dgb2Sq6Rw
+        xxMqflatleu9QSZnJ6wCAmOaWmyrmzflrqrejqB3Gk2StZ7zal3kPVnKy015k2+qvKgu8s6Rwij3
+        4nsmhBBP4zcZtRof5V5sVs+VHmOEFuX+2iSEDM6kioQYKTJYlqsZKmcZ7ej9W4dCgScGI1wj3gew
+        CgVFcQeB4nqpCtgMEZJ1OxizAGCtY0jRR78PF3K+OjSu9cEd4x9S2ZCl2NUBITqb3ER2Xo70nAnx
+        MG5ieBFO+uB6zzW7Hzj+rqimcXJ+gBneXhg7BjOXy3L1yrBaIwOZuFikVKA61LNy3joMmtwCZIvI
+        f3t5bfYUm2z7P+NnoBR6Rl37gJrUy7xzW8B0nf9qu654NCwjhp+ksGbCkJ5BYwODmU5Gxl+Rsa8b
+        si0GH2i6m8bX291xuztiVTQyO2e/AQAA//8DAP7WRo9GAwAA
+    headers:
+      CF-RAY:
+      - 93458dcf6d0ef53b-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 22 Apr 2025 13:44:07 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1391'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999989'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_74408ec81f430b6e9795cf5332262b8d
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_gpt_4_1[gpt-4.1-nano-2025-04-14].yaml
+++ b/tests/cassettes/test_gpt_4_1[gpt-4.1-nano-2025-04-14].yaml
@@ -0,0 +1,101 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the capital of France?"}],
+      "model": "gpt-4.1-nano-2025-04-14", "stop": []}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '125'
+      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:
+      - 3.11.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jJJPb9swDMXv/hSCznEQuwrq5bgNBbZTh7aHYigMRqJtbbKkSXT/oMh3
+        L2Snsdt1wC4+8MdHv0fxOWOMa8V3jMsOSPbe5J8vqy/D96K/+PPjSn/Fh5szMewfb/eiar/d8lVS
+        uP0vlPSqWkvXe4OknZ2wDAiEaWpxLrZn5SchqhH0TqFJstZTLtZFbsG6vNyU23wj8kIc5Z3TEiPf
+        sZ8ZY4w9j99k1Cp85Du2Wb1WeowRWuS7UxNjPDiTKhxi1JHAEl/NUDpLaEfv1x0yCV4TGOYadhHA
+        SmQ6sksIOq6XqoDNECFZt4MxCwDWOoIUffR7dySHk0PjWh/cPr6T8kZbHbs6IERnk5tIzvORHjLG
+        7sZNDG/CcR9c76km9xvH3xViGsfnB5hhdWTkCMxcLsvVB8NqhQTaxMUiuQTZoZqV89ZhUNotQLaI
+        /LeXj2ZPsbVt/2f8DKRET6hqH1Bp+Tbv3BYwXee/2k4rHg3ziOFeS6xJY0jPoLCBwUwnw+NTJOzr
+        RtsWgw96upvG14gKq2ajxJZnh+wFAAD//wMATWCJPkYDAAA=
+    headers:
+      CF-RAY:
+      - 93458dd9aebff53b-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 22 Apr 2025 13:44:08 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '134'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999990'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_0ba738662e063fb55ea01793aafdcecc
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_gpt_4_1[gpt-4.1].yaml
+++ b/tests/cassettes/test_gpt_4_1[gpt-4.1].yaml
@@ -0,0 +1,101 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the capital of France?"}],
+      "model": "gpt-4.1", "stop": []}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '109'
+      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:
+      - 3.11.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4xSwYrbMBC9+yvEHEMcHMeh3dx2SwttoYTSW1nMRB7b2pUlIY27XZb8e5GdxM5u
+        C734MG/e83tP85IIAaqCnQDZIsvO6fRu//6Db26fnvTtx8/5t7v95rmT3y1+pc0XDcvIsIcHknxm
+        raTtnCZW1oyw9IRMUXX9rthu8pui2A5AZyvSkdY4TovVOs2zfJtmRbouTszWKkkBduJnIoQQL8M3
+        ejQV/YadyJbnSUchYEOwuywJAd7qOAEMQQVGw7CcQGkNkxls/2hJSHSKUQtbi08ejSShglgs9uhV
+        WCxWc6anug8YnZte6xmAxljGmHzwfH9CjheX2jbO20N4RYVaGRXa0hMGa6KjwNbBgB4TIe6HNvqr
+        gOC87RyXbB9p+N26GOVg6n8GnpoCtox6mudn0pVaWRGj0mHWJkiULVUTc6oe+0rZGZDMMr818zft
+        Mbcyzf/IT4CU5Jiq0nmqlLwOPK15itf5r7VLx4NhCOR/KUklK/LxHSqqsdfj3UB4DkxdWSvTkHde
+        jcdTuxJllh2yLMskJMfkDwAAAP//AwC4aq9JRgMAAA==
+    headers:
+      CF-RAY:
+      - 93458dcc1b9df53b-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 22 Apr 2025 13:44:06 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '296'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999989'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_7b4e1628a0608e9547e71e7857a29b58
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cli/test_plot_flow.py
+++ b/tests/cli/test_plot_flow.py
@@ -1,37 +0,0 @@
-import os
-import tempfile
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-from crewai.cli.plot_flow import plot_flow
-
-
-class TestPlotFlow:
-    def test_plot_flow_no_main_file(self):
-        """Test plot_flow when main.py doesn't exist."""
-        with tempfile.TemporaryDirectory() as temp_dir:
-            original_dir = os.getcwd()
-            try:
-                os.chdir(temp_dir)
-                with patch("click.echo") as mock_echo:
-                    plot_flow()
-                    mock_echo.assert_called_with(
-                        "Error: Could not find main.py in the current directory", err=True
-                    )
-            finally:
-                os.chdir(original_dir)
-
-    def test_plot_flow_with_main_file(self):
-        """Test plot_flow with a mock main.py that has plot function."""
-        with tempfile.TemporaryDirectory() as temp_dir:
-            with patch("importlib.util.spec_from_file_location") as mock_spec_from_file:
-                with patch("click.echo"):
-                    mock_module = MagicMock()
-                    mock_spec = MagicMock()
-                    mock_spec_from_file.return_value = mock_spec
-                    mock_spec.loader = MagicMock()
-                    
-                    with patch("os.path.exists", return_value=True):
-                        plot_flow()
-                        mock_spec.loader.exec_module.assert_called_once()
--- a/tests/llm_test.py
+++ b/tests/llm_test.py
@@ -256,6 +256,52 @@ def test_validate_call_params_no_response_format():
    llm._validate_call_params()


+@pytest.mark.vcr(filter_headers=["authorization"], filter_query_parameters=["key"])
+@pytest.mark.parametrize(
+    "model",
+    [
+        "gemini/gemini-2.0-flash-thinking-exp-01-21",
+        "gemini/gemini-2.0-flash-001",
+        "gemini/gemini-2.0-flash-lite-001",
+        "gemini/gemini-2.5-flash-preview-04-17",
+        "gemini/gemini-2.5-pro-exp-03-25",
+    ],
+)
+def test_gemini_models(model):
+    llm = LLM(model=model)
+    result = llm.call("What is the capital of France?")
+    assert isinstance(result, str)
+    assert "Paris" in result
+
+
+@pytest.mark.vcr(filter_headers=["authorization"], filter_query_parameters=["key"])
+@pytest.mark.parametrize(
+    "model",
+    [
+        "gemini/gemma-3-1b-it",
+        "gemini/gemma-3-4b-it",
+        "gemini/gemma-3-12b-it",
+        "gemini/gemma-3-27b-it",
+    ],
+)
+def test_gemma3(model):
+    llm = LLM(model=model)
+    result = llm.call("What is the capital of France?")
+    assert isinstance(result, str)
+    assert "Paris" in result
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.parametrize(
+    "model", ["gpt-4.1", "gpt-4.1-mini-2025-04-14", "gpt-4.1-nano-2025-04-14"]
+)
+def test_gpt_4_1(model):
+    llm = LLM(model=model)
+    result = llm.call("What is the capital of France?")
+    assert isinstance(result, str)
+    assert "Paris" in result
+
+
@pytest.mark.vcr(filter_headers=["authorization"])
 def test_o3_mini_reasoning_effort_high():
    llm = LLM(
@@ -327,6 +373,45 @@ def get_weather_tool_schema():
        },
    }

+def test_context_window_exceeded_error_handling():
+    """Test that litellm.ContextWindowExceededError is converted to LLMContextLengthExceededException."""
+    from litellm.exceptions import ContextWindowExceededError
+
+    from crewai.utilities.exceptions.context_window_exceeding_exception import (
+        LLMContextLengthExceededException,
+    )
+
+    llm = LLM(model="gpt-4")
+
+    # Test non-streaming response
+    with patch("litellm.completion") as mock_completion:
+        mock_completion.side_effect = ContextWindowExceededError(
+            "This model's maximum context length is 8192 tokens. However, your messages resulted in 10000 tokens.",
+            model="gpt-4",
+            llm_provider="openai"
+        )
+
+        with pytest.raises(LLMContextLengthExceededException) as excinfo:
+            llm.call("This is a test message")
+
+        assert "context length exceeded" in str(excinfo.value).lower()
+        assert "8192 tokens" in str(excinfo.value)
+
+    # Test streaming response
+    llm = LLM(model="gpt-4", stream=True)
+    with patch("litellm.completion") as mock_completion:
+        mock_completion.side_effect = ContextWindowExceededError(
+            "This model's maximum context length is 8192 tokens. However, your messages resulted in 10000 tokens.",
+            model="gpt-4",
+            llm_provider="openai"
+        )
+
+        with pytest.raises(LLMContextLengthExceededException) as excinfo:
+            llm.call("This is a test message")
+
+        assert "context length exceeded" in str(excinfo.value).lower()
+        assert "8192 tokens" in str(excinfo.value)
+

@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.fixture
--- a/tests/test_crew_plot.py
+++ b/tests/test_crew_plot.py
@@ -1,20 +0,0 @@
-import pytest
-
-from crewai.agent import Agent
-from crewai.crew import Crew
-
-
-def test_crew_plot_method_not_implemented():
-    """Test that trying to plot a Crew raises the correct error."""
-    agent = Agent(
-        role="Test Agent",
-        goal="Test Goal",
-        backstory="Test Backstory"
-    )
-    crew = Crew(agents=[agent], tasks=[])
-    
-    with pytest.raises(NotImplementedError) as excinfo:
-        crew.plot()
-    
-    assert "plot method is not available for Crew objects" in str(excinfo.value)
-    assert "Plot functionality is only available for Flow objects" in str(excinfo.value)
--- a/tests/utilities/test_embedding_configurator.py
+++ b/tests/utilities/test_embedding_configurator.py
@@ -0,0 +1,37 @@
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from crewai.utilities.embedding_configurator import EmbeddingConfigurator
+from crewai.utilities.embedding_functions import FixedGoogleVertexEmbeddingFunction
+
+
+class TestEmbeddingConfigurator:
+    @pytest.fixture
+    def embedding_configurator(self):
+        return EmbeddingConfigurator()
+    
+    def test_configure_vertexai(self, embedding_configurator):
+        with patch('crewai.utilities.embedding_functions.FixedGoogleVertexEmbeddingFunction') as mock_class:
+            mock_instance = MagicMock()
+            mock_class.return_value = mock_instance
+            
+            config = {
+                "provider": "vertexai",
+                "config": {
+                    "api_key": "test-key",
+                    "model": "test-model",
+                    "project_id": "test-project",
+                    "region": "test-region"
+                }
+            }
+            
+            result = embedding_configurator.configure_embedder(config)
+            
+            mock_class.assert_called_once_with(
+                model_name="test-model",
+                api_key="test-key",
+                project_id="test-project",
+                region="test-region"
+            )
+            assert result == mock_instance
--- a/tests/utilities/test_embedding_functions.py
+++ b/tests/utilities/test_embedding_functions.py
@@ -0,0 +1,57 @@
+from unittest.mock import MagicMock, patch
+
+import pytest
+import requests
+
+from crewai.utilities.embedding_functions import FixedGoogleVertexEmbeddingFunction
+
+
+class TestFixedGoogleVertexEmbeddingFunction:
+    @pytest.fixture
+    def embedding_function(self):
+        with patch('requests.post') as mock_post:
+            mock_response = MagicMock()
+            mock_response.json.return_value = {"predictions": [[0.1, 0.2, 0.3]]}
+            mock_post.return_value = mock_response
+            
+            function = FixedGoogleVertexEmbeddingFunction(
+                model_name="test-model",
+                api_key="test-key"
+            )
+            
+            yield function, mock_post
+            
+            if hasattr(function, '_original_post'):
+                requests.post = function._original_post
+            
+    def test_url_correction(self, embedding_function):
+        function, mock_post = embedding_function
+        
+        typo_url = "https://us-central1-aiplatform.googleapis.com/v1/projects/test-project/locations/us-central1/publishers/goole/models/test-model:predict"
+        
+        expected_url = "https://us-central1-aiplatform.googleapis.com/v1/projects/test-project/locations/us-central1/publishers/google/models/test-model:predict"
+        
+        with patch.object(function, '_original_post') as mock_original_post:
+            mock_response = MagicMock()
+            mock_response.json.return_value = {"predictions": [[0.1, 0.2, 0.3]]}
+            mock_original_post.return_value = mock_response
+            
+            response = function._patched_post(typo_url, json={})
+            
+            mock_original_post.assert_called_once()
+            call_args = mock_original_post.call_args
+            assert call_args[0][0] == expected_url
+            
+    def test_embedding_call(self, embedding_function):
+        function, mock_post = embedding_function
+        
+        mock_response = MagicMock()
+        mock_response.json.return_value = {"predictions": [[0.1, 0.2, 0.3]]}
+        mock_post.return_value = mock_response
+        
+        embeddings = function(["test text"])
+        
+        mock_post.assert_called_once()
+        
+        assert isinstance(embeddings, list)
+        assert len(embeddings) > 0
Author	SHA1	Message	Date
Devin AI	5623e2c851	Fix type error and test issues Co-Authored-By: Joe Moura <joao@crewai.com>	2025-04-25 21:03:36 +00:00
Devin AI	50059c7120	Fix import sorting with ruff Co-Authored-By: Joe Moura <joao@crewai.com>	2025-04-25 20:58:24 +00:00
Devin AI	335f1dfdf8	Fix lint and type errors Co-Authored-By: Joe Moura <joao@crewai.com>	2025-04-25 20:56:22 +00:00
Devin AI	1f2def2cbe	Fix Vertex AI embeddings URL typo (publishers/goole -> publishers/google) Co-Authored-By: Joe Moura <joao@crewai.com>	2025-04-25 20:51:36 +00:00
Lucas Gomide	b2969e9441	style: fix linter issue (#2686 ) Some checks are pending Notify Downstream / notify-downstream (push) Waiting to run Details	2025-04-25 09:34:00 -04:00
João Moura	5b9606e8b6	fix contenxt windown	2025-04-24 23:09:23 -07:00
Kunal Lunia	685d20f46c	added gpt-4.1 models and gemini-2.0 and 2.5 pro models (#2609 ) Some checks failed Notify Downstream / notify-downstream (push) Has been cancelled Details * added gpt4.1 models and gemini 2.0 and 2.5 models * added flash model * Updated test fun to all models * Added Gemma3 test cases and passed all google test case * added gemini 2.5 flash * added gpt4.1 models and gemini 2.0 and 2.5 models * added flash model * Updated test fun to all models * Added Gemma3 test cases and passed all google test case * added gemini 2.5 flash * added gpt4.1 models and gemini 2.0 and 2.5 models * added flash model * Updated test fun to all models * Added Gemma3 test cases and passed all google test case * added gemini 2.5 flash * test: add missing cassettes * test: ignore authorization key from gemini/gemma3 request --------- Co-authored-by: Lucas Gomide <lucaslg200@gmail.com> Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>	2025-04-23 11:20:32 -07:00
Lucas Gomide	9ebf3aa043	docs(CodeInterpreterTool): update docs (#2675 )	2025-04-23 10:27:25 -07:00
Tony Kipkemboi	2e4c97661a	Add enterprise deployment documentation to CLI docs (#2670 ) Some checks are pending Notify Downstream / notify-downstream (push) Waiting to run Details	2025-04-22 13:27:58 -07:00
Tony Kipkemboi	16eb4df556	docs: update docs.json with contextual options, SEO, and 404 redirect (#2654 ) * docs: 0.114.0 release notes, navigation restructure, new guides, deploy video, and cleanup - Add v0.114.0 release notes with highlights image and doc links - Restructure docs navigation (Strategy group, Releases tab, navbar links) - Update quickstart with deployment video and clearer instructions - Add/rename guides (Custom Manager Agent, Custom LLM) - Remove legacy concept/tool docs - Add new images and tool docs - Minor formatting and content improvements throughout * docs: update docs.json with contextual options, SEO indexing, and 404 redirect settings	2025-04-22 09:52:27 -07:00
Vini Brasil	3d9000495c	Change CLI tool publish message (#2662 )	2025-04-22 13:09:30 -03:00
Tony Kipkemboi	6d0039b117	docs: 0.114.0 release notes, navigation restructure, new guides, deploy video, and cleanup (#2653 ) Some checks are pending Notify Downstream / notify-downstream (push) Waiting to run Details - Add v0.114.0 release notes with highlights image and doc links - Restructure docs navigation (Strategy group, Releases tab, navbar links) - Update quickstart with deployment video and clearer instructions - Add/rename guides (Custom Manager Agent, Custom LLM) - Remove legacy concept/tool docs - Add new images and tool docs - Minor formatting and content improvements throughout	2025-04-21 19:18:21 -04:00
Lorenze Jay	311a078ca6	Enhance knowledge management in CrewAI (#2637 ) Some checks failed Notify Downstream / notify-downstream (push) Has been cancelled Details * Enhance knowledge management in CrewAI - Added `KnowledgeConfig` class to configure knowledge retrieval parameters such as `limit` and `score_threshold`. - Updated `Agent` and `Crew` classes to utilize the new knowledge configuration for querying knowledge sources. - Enhanced documentation to clarify the addition of knowledge sources at both agent and crew levels. - Introduced new tips in documentation to guide users on knowledge source management and configuration. * Refactor knowledge configuration parameters in CrewAI - Renamed `limit` to `results_limit` in `KnowledgeConfig`, `query_knowledge`, and `query` methods for consistency and clarity. - Updated related documentation to reflect the new parameter name, ensuring users understand the configuration options for knowledge retrieval. * Refactor agent tests to utilize mock knowledge storage - Updated test cases in `agent_test.py` to use `KnowledgeStorage` for mocking knowledge sources, enhancing test reliability and clarity. - Renamed `limit` to `results_limit` in `KnowledgeConfig` for consistency with recent changes. - Ensured that knowledge queries are properly mocked to return expected results during tests. * Add VCR support for agent tests with query limits and score thresholds - Introduced `@pytest.mark.vcr` decorator in `agent_test.py` for tests involving knowledge sources, ensuring consistent recording of HTTP interactions. - Added new YAML cassette files for `test_agent_with_knowledge_sources_with_query_limit_and_score_threshold` and `test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default`, capturing the expected API responses for these tests. - Enhanced test reliability by utilizing VCR to manage external API calls during testing. * Update documentation to format parameter names in code style - Changed the formatting of `results_limit` and `score_threshold` in the documentation to use code style for better clarity and emphasis. - Ensured consistency in documentation presentation to enhance user understanding of configuration options. * Enhance KnowledgeConfig with field descriptions - Updated `results_limit` and `score_threshold` in `KnowledgeConfig` to use Pydantic's `Field` for improved documentation and clarity. - Added descriptions to both parameters to provide better context for their usage in knowledge retrieval configuration. * docstrings added	2025-04-18 18:33:04 -07:00