Fix type-checker issues with proper type annotations

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

README.md

@@ -688,6 +688,26 @@ A: Yes, CrewAI can integrate with custom-trained or fine-tuned models, allowing
 ### Q: Can CrewAI agents interact with external tools and APIs?
 A: Absolutely! CrewAI agents can easily integrate with external tools, APIs, and databases, empowering them to leverage real-world data and resources.
 
+CrewAI also supports connecting your tools to the Management Control Plane (MCP) via Server-Sent Events (SSE), enabling real-time tool execution from the Crew Control Plane:
+
+```python
+from crewai.tools import MCPToolConnector, Tool
+
+# Define your tools
+search_tool = Tool(
+    name="search",
+    description="Search for information",
+    func=lambda query: f"Results for {query}"
+)
+
+# Connect tools to MCP
+connector = MCPToolConnector(tools=[search_tool])
+connector.connect()
+
+# Listen for tool events from MCP
+connector.listen()  # This will block until interrupted
+```
+
 ### Q: Is CrewAI suitable for production environments?
 A: Yes, CrewAI is explicitly designed with production-grade standards, ensuring reliability, stability, and scalability for enterprise deployments.
 

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

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.
 

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:

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>

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": [
@@ -178,6 +180,42 @@
           }
         ]
       },
+      {
+        "tab": "Enterprise",
+        "groups": [
+          {
+            "group": "Getting Started",
+            "pages": [
+              "enterprise/introduction"
+            ]
+          },
+          {
+            "group": "How-To Guides",
+            "pages": [
+              "enterprise/guides/build-crew",
+              "enterprise/guides/deploy-crew",
+              "enterprise/guides/kickoff-crew",
+              "enterprise/guides/update-crew",
+              "enterprise/guides/use-crew-api",
+              "enterprise/guides/enable-crew-studio"
+            ]
+          },
+          {
+            "group": "Features",
+            "pages": [
+              "enterprise/features/tool-repository",
+              "enterprise/features/webhook-streaming",
+              "enterprise/features/traces"
+            ]
+          },
+          {
+            "group": "Resources",
+            "pages": [
+              "enterprise/resources/frequently-asked-questions"
+            ]
+          }
+        ]
+      },
       {
         "tab": "Examples",
         "groups": [
@@ -188,19 +226,35 @@
             ]
           }
         ]
+      },
+      {
+        "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 +268,12 @@
     "strict": false
   },
   "navbar": {
+    "links": [
+      {
+        "label": "Start Free Trial",
+        "href": "https://app.crewai.com"
+      }
+    ],
     "primary": {
       "type": "github",
       "href": "https://github.com/crewAIInc/crewAI"
@@ -223,7 +283,12 @@
     "prompt": "Search CrewAI docs"
   },
   "seo": {
-    "indexing": "navigable"
+    "indexing": "all"
+  },
+  "errors": {
+    "404": {
+      "redirect": true
+    }
   },
   "footer": {
     "socials": {

docs/enterprise/features/tool-repository.mdx

@@ -0,0 +1,106 @@
+---
+title: Tool Repository
+description: "Using the Tool Repository to manage your tools"
+icon: "toolbox"
+---
+
+## Overview
+
+The Tool Repository is a package manager for CrewAI tools. It allows users to publish, install, and manage tools that integrate with CrewAI crews and flows.
+
+Tools can be:
+
+- **Private**: accessible only within your organization (default)
+- **Public**: accessible to all CrewAI users if published with the `--public` flag
+
+The repository is not a version control system. Use Git to track code changes and enable collaboration.
+
+## Prerequisites
+
+Before using the Tool Repository, ensure you have:
+
+- A [CrewAI Enterprise](https://app.crewai.com) account
+- [CrewAI CLI](https://docs.crewai.com/concepts/cli#cli) installed
+- [Git](https://git-scm.com) installed and configured
+- Access permissions to publish or install tools in your CrewAI Enterprise organization
+
+## Installing Tools
+
+To install a tool:
+
+```bash
+crewai tool install <tool-name>
+```
+
+This installs the tool and adds it to `pyproject.toml`.
+
+## Creating and Publishing Tools
+
+To create a new tool project:
+
+```bash
+crewai tool create <tool-name>
+```
+
+This generates a scaffolded tool project locally.
+
+After making changes, initialize a Git repository and commit the code:
+
+```bash
+git init
+git add .
+git commit -m "Initial version"
+```
+
+To publish the tool:
+
+```bash
+crewai tool publish
+```
+
+By default, tools are published as private. To make a tool public:
+
+```bash
+crewai tool publish --public
+```
+
+For more details on how to build tools, see [Creating your own tools](https://docs.crewai.com/concepts/tools#creating-your-own-tools).
+
+## Updating Tools
+
+To update a published tool:
+
+1. Modify the tool locally
+2. Update the version in `pyproject.toml` (e.g., from `0.1.0` to `0.1.1`)
+3. Commit the changes and publish
+
+```bash
+git commit -m "Update version to 0.1.1"
+crewai tool publish
+```
+
+## Deleting Tools
+
+To delete a tool:
+
+1. Go to [CrewAI Enterprise](https://app.crewai.com)
+2. Navigate to **Tools**
+3. Select the tool
+4. Click **Delete**
+
+<Warning>
+Deletion is permanent. Deleted tools cannot be restored or re-installed.
+</Warning>
+
+## Security Checks
+
+Every published version undergoes automated security checks, and are only available to install after they pass. 
+
+You can check the security check status of a tool at:
+
+`CrewAI Enterprise > Tools > Your Tool > Versions`
+
+
+<Card title="Need Help?" icon="headset" href="mailto:support@crewai.com">
+  Contact our support team for assistance with API integration or troubleshooting.
+</Card>

docs/enterprise/features/traces.mdx

@@ -0,0 +1,146 @@
+---
+title: Traces
+description: "Using Traces to monitor your Crews"
+icon: "timeline"
+---
+
+## Overview
+
+Traces provide comprehensive visibility into your crew executions, helping you monitor performance, debug issues, and optimize your AI agent workflows.
+
+## What are Traces?
+
+Traces in CrewAI Enterprise are detailed execution records that capture every aspect of your crew's operation, from initial inputs to final outputs. They record:
+
+- Agent thoughts and reasoning
+- Task execution details
+- Tool usage and outputs
+- Token consumption metrics
+- Execution times
+- Cost estimates
+
+<Frame>
+  ![Traces Overview](/images/enterprise/traces-overview.png)
+</Frame>
+
+## Accessing Traces
+
+<Steps>
+  <Step title="Navigate to the Traces Tab">
+    Once in your CrewAI Enterprise dashboard, click on the **Traces** to view all execution records.
+  </Step>
+  
+  <Step title="Select an Execution">
+    You'll see a list of all crew executions, sorted by date. Click on any execution to view its detailed trace.
+  </Step>
+</Steps>
+
+## Understanding the Trace Interface
+
+The trace interface is divided into several sections, each providing different insights into your crew's execution:
+
+### 1. Execution Summary
+
+The top section displays high-level metrics about the execution:
+
+- **Total Tokens**: Number of tokens consumed across all tasks
+- **Prompt Tokens**: Tokens used in prompts to the LLM
+- **Completion Tokens**: Tokens generated in LLM responses
+- **Requests**: Number of API calls made
+- **Execution Time**: Total duration of the crew run
+- **Estimated Cost**: Approximate cost based on token usage
+
+<Frame>
+  ![Execution Summary](/images/enterprise/trace-summary.png)
+</Frame>
+
+### 2. Tasks & Agents
+
+This section shows all tasks and agents that were part of the crew execution:
+
+- Task name and agent assignment
+- Agents and LLMs used for each task
+- Status (completed/failed)
+- Individual execution time of the task
+
+<Frame>
+  ![Task List](/images/enterprise/trace-tasks.png)
+</Frame>
+
+### 3. Final Output
+
+Displays the final result produced by the crew after all tasks are completed.
+
+<Frame>
+  ![Final Output](/images/enterprise/final-output.png)
+</Frame>
+
+### 4. Execution Timeline
+
+A visual representation of when each task started and ended, helping you identify bottlenecks or parallel execution patterns.
+
+<Frame>
+  ![Execution Timeline](/images/enterprise/trace-timeline.png)
+</Frame>
+
+### 5. Detailed Task View
+
+When you click on a specific task in the timeline or task list, you'll see:
+
+<Frame>
+  ![Detailed Task View](/images/enterprise/trace-detailed-task.png)
+</Frame>
+
+- **Task Key**: Unique identifier for the task
+- **Task ID**: Technical identifier in the system
+- **Status**: Current state (completed/running/failed)
+- **Agent**: Which agent performed the task
+- **LLM**: Language model used for this task
+- **Start/End Time**: When the task began and completed
+- **Execution Time**: Duration of this specific task
+- **Task Description**: What the agent was instructed to do
+- **Expected Output**: What output format was requested
+- **Input**: Any input provided to this task from previous tasks
+- **Output**: The actual result produced by the agent
+
+
+## Using Traces for Debugging
+
+Traces are invaluable for troubleshooting issues with your crews:
+
+<Steps>
+  <Step title="Identify Failure Points">
+    When a crew execution doesn't produce the expected results, examine the trace to find where things went wrong. Look for:
+    
+    - Failed tasks
+    - Unexpected agent decisions
+    - Tool usage errors
+    - Misinterpreted instructions
+
+    <Frame>
+      ![Failure Points](/images/enterprise/failure.png)
+    </Frame>
+  </Step>
+  
+  <Step title="Optimize Performance">
+    Use execution metrics to identify performance bottlenecks:
+    
+    - Tasks that took longer than expected
+    - Excessive token usage
+    - Redundant tool operations
+    - Unnecessary API calls
+  </Step>
+  
+  <Step title="Improve Cost Efficiency">
+    Analyze token usage and cost estimates to optimize your crew's efficiency:
+    
+    - Consider using smaller models for simpler tasks
+    - Refine prompts to be more concise
+    - Cache frequently accessed information
+    - Structure tasks to minimize redundant operations
+  </Step>
+</Steps>
+
+<Card title="Need Help?" icon="headset" href="mailto:support@crewai.com">
+  Contact our support team for assistance with trace analysis or any other CrewAI Enterprise features.
+</Card>

docs/enterprise/features/webhook-streaming.mdx

@@ -0,0 +1,82 @@
+---
+title: Webhook Streaming
+description: "Using Webhook Streaming to stream events to your webhook"
+icon: "webhook"
+---
+
+## Overview
+
+Enterprise Event Streaming lets you receive real-time webhook updates about your crews and flows deployed to 
+CrewAI Enterprise, such as model calls, tool usage, and flow steps.
+
+## Usage
+
+When using the Kickoff API, include a `webhooks` object to your request, for example:
+
+```json
+{
+  "inputs": {"foo": "bar"},
+  "webhooks": {
+    "events": ["crew_kickoff_started", "llm_call_started"],
+    "url": "https://your.endpoint/webhook",
+    "realtime": false,
+    "authentication": {
+      "strategy": "bearer",
+      "token": "my-secret-token"
+    }
+  }
+}
+```
+
+If `realtime` is set to `true`, each event is delivered individually and immediately, at the cost of crew/flow performance.
+
+## Webhook Format
+
+Each webhook sends a list of events:
+
+```json
+{
+  "events": [
+    {
+      "id": "event-id",
+      "execution_id": "crew-run-id",
+      "timestamp": "2025-02-16T10:58:44.965Z",
+      "type": "llm_call_started",
+      "data": {
+        "model": "gpt-4",
+        "messages": [
+          {"role": "system", "content": "You are an assistant."},
+          {"role": "user", "content": "Summarize this article."}
+        ]
+      }
+    }
+  ]
+}
+```
+
+The `data` object structure varies by event type. Refer to the [event list](https://github.com/crewAIInc/crewAI/tree/main/src/crewai/utilities/events) on GitHub.
+
+As requests are sent over HTTP, the order of events can't be guaranteed. If you need ordering, use the `timestamp` field.
+
+## Supported Events
+
+CrewAI supports both system events and custom events in Enterprise Event Streaming. These events are sent to your configured webhook endpoint during crew and flow execution.
+
+- `crew_kickoff_started`
+- `crew_step_started`
+- `crew_step_completed`
+- `crew_execution_completed`
+- `llm_call_started`
+- `llm_call_completed`
+- `tool_usage_started`
+- `tool_usage_completed`
+- `crew_test_failed`
+- *...and others*
+
+Event names match the internal event bus. See [GitHub source](https://github.com/crewAIInc/crewAI/tree/main/src/crewai/utilities/events) for the full list.
+
+You can emit your own custom events, and they will be delivered through the webhook stream alongside system events.
+
+<Card title="Need Help?" icon="headset" href="mailto:support@crewai.com">
+  Contact our support team for assistance with webhook integration or troubleshooting.
+</Card>

docs/enterprise/guides/build-crew.mdx

@@ -0,0 +1,43 @@
+---
+title: "Build Crew"
+description: "A Crew is a group of agents that work together to complete a task."
+icon: "people-arrows"
+---
+
+<Tip>
+[CrewAI Enterprise](https://app.crewai.com) streamlines the process of **creating**, **deploying**, and **managing** your AI agents in production environments.
+</Tip>
+
+## Getting Started
+
+<iframe 
+    width="100%"
+    height="400"
+    src="https://www.youtube.com/embed/d1Yp8eeknDk?si=tIxnTRI5UlyCp3z_" 
+    title="Building Crews with CrewAI CLI" 
+    frameborder="0"
+    style={{ borderRadius: '10px' }}
+    allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
+    allowfullscreen
+></iframe>
+
+### Installation and Setup
+
+<Card title="Follow Standard Installation" icon="wrench" href="/installation">
+  Follow our standard installation guide to set up CrewAI CLI and create your first project.
+</Card>
+
+### Building Your Crew
+
+<Card title="Quickstart Tutorial" icon="rocket" href="/quickstart">
+  Follow our quickstart guide to create your first agent crew using YAML configuration.
+</Card>
+
+## Support and Resources
+
+For Enterprise-specific support or questions, contact our dedicated support team at [support@crewai.com](mailto:support@crewai.com).
+
+
+<Card title="Schedule a Demo" icon="calendar" href="mailto:support@crewai.com">
+  Book time with our team to learn more about Enterprise features and how they can benefit your organization.
+</Card>

docs/enterprise/guides/deploy-crew.mdx

@@ -0,0 +1,216 @@
+---
+title: "Deploy Crew"
+description: "Deploy your local CrewAI project to the Enterprise platform"
+icon: "cloud-arrow-up"
+---
+
+## Option 1: CLI Deployment
+
+<Tip>
+This video tutorial walks you through the process of deploying your locally developed CrewAI project to the CrewAI Enterprise platform, 
+transforming it into a production-ready API endpoint.
+</Tip>
+
+<iframe 
+    width="100%"
+    height="400"
+    src="https://www.youtube.com/embed/3EqSV-CYDZA" 
+    title="Deploying a Crew to CrewAI Enterprise" 
+    frameborder="0"
+    style={{ borderRadius: '10px' }}
+    allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
+    allowfullscreen
+></iframe>
+
+## Prerequisites
+
+Before starting the deployment process, make sure you have:
+
+- A CrewAI project built locally ([follow our quickstart guide](/quickstart) if you haven't created one yet)
+- Your code pushed to a GitHub repository
+- The latest version of the CrewAI CLI installed (`uv tool install crewai`)
+
+<Note>
+For a quick reference project, you can clone our example repository at [github.com/tonykipkemboi/crewai-latest-ai-development](https://github.com/tonykipkemboi/crewai-latest-ai-development).
+</Note>
+
+
+
+### Step 1: Authenticate with the Enterprise Platform
+
+First, you need to authenticate your CLI with the CrewAI Enterprise platform:
+
+```bash
+# If you already have a CrewAI Enterprise account
+crewai login
+
+# If you're creating a new account
+crewai signup
+```
+
+When you run either command, the CLI will:
+1. Display a URL and a unique device code
+2. Open your browser to the authentication page
+3. Prompt you to confirm the device
+4. Complete the authentication process
+
+Upon successful authentication, you'll see a confirmation message in your terminal!
+
+### Step 2: Create a Deployment
+
+From your project directory, run:
+
+```bash
+crewai deploy create
+```
+
+This command will:
+1. Detect your GitHub repository information
+2. Identify environment variables in your local `.env` file
+3. Securely transfer these variables to the Enterprise platform
+4. Create a new deployment with a unique identifier
+
+On successful creation, you'll see a message like:
+```shell
+Deployment created successfully!
+Name: your_project_name
+Deployment ID: 01234567-89ab-cdef-0123-456789abcdef
+Current Status: Deploy Enqueued
+```
+
+### Step 3: Monitor Deployment Progress
+
+Track the deployment status with:
+
+```bash
+crewai deploy status
+```
+
+For detailed logs of the build process:
+
+```bash
+crewai deploy logs
+```
+
+<Tip>
+The first deployment typically takes 10-15 minutes as it builds the container images. Subsequent deployments are much faster.
+</Tip>
+
+### Additional CLI Commands
+
+The CrewAI CLI offers several commands to manage your deployments:
+
+```bash
+# List all your deployments
+crewai deploy list
+
+# Get the status of your deployment
+crewai deploy status
+
+# View the logs of your deployment
+crewai deploy logs
+
+# Push updates after code changes
+crewai deploy push
+
+# Remove a deployment
+crewai deploy remove <deployment_id>
+```
+
+## Option 2: Deploy Directly via Web Interface
+
+You can also deploy your crews directly through the CrewAI Enterprise web interface by connecting your GitHub account. This approach doesn't require using the CLI on your local machine.
+
+### Step 1: Pushing to GitHub
+
+First, you need to push your crew to a GitHub repository. If you haven't created a crew yet, you can [follow this tutorial](/quickstart).
+
+### Step 2: Connecting GitHub to CrewAI Enterprise
+
+1. Log in to [CrewAI Enterprise](https://app.crewai.com)
+2. Click on the button "Connect GitHub" 
+
+<Frame>
+  ![Connect GitHub Button](/images/enterprise/connect-github.png)
+</Frame>
+
+### Step 3: Select the Repository
+
+After connecting your GitHub account, you'll be able to select which repository to deploy:
+
+<Frame>
+  ![Select Repository](/images/enterprise/select-repo.png)
+</Frame>
+
+### Step 4: Set Environment Variables
+
+Before deploying, you'll need to set up your environment variables to connect to your LLM provider or other services:
+
+1. You can add variables individually or in bulk
+2. Enter your environment variables in `KEY=VALUE` format (one per line)
+
+<Frame>
+  ![Set Environment Variables](/images/enterprise/set-env-variables.png)
+</Frame>
+
+### Step 5: Deploy Your Crew
+
+1. Click the "Deploy" button to start the deployment process
+2. You can monitor the progress through the progress bar
+3. The first deployment typically takes around 10-15 minutes; subsequent deployments will be faster
+
+<Frame>
+  ![Deploy Progress](/images/enterprise/deploy-progress.png)
+</Frame>
+
+Once deployment is complete, you'll see:
+- Your crew's unique URL
+- A Bearer token to protect your crew API
+- A "Delete" button if you need to remove the deployment
+
+### Interact with Your Deployed Crew
+
+Once deployment is complete, you can access your crew through:
+
+1. **REST API**: The platform generates a unique HTTPS endpoint with these key routes:
+   - `/inputs`: Lists the required input parameters
+   - `/kickoff`: Initiates an execution with provided inputs
+   - `/status/{kickoff_id}`: Checks the execution status
+
+2. **Web Interface**: Visit [app.crewai.com](https://app.crewai.com) to access:
+   - **Status tab**: View deployment information, API endpoint details, and authentication token
+   - **Run tab**: Visual representation of your crew's structure
+   - **Executions tab**: History of all executions
+   - **Metrics tab**: Performance analytics
+   - **Traces tab**: Detailed execution insights
+
+### Trigger an Execution
+
+From the Enterprise dashboard, you can:
+
+1. Click on your crew's name to open its details
+2. Select "Trigger Crew" from the management interface
+3. Enter the required inputs in the modal that appears
+4. Monitor progress as the execution moves through the pipeline
+
+## Monitoring and Analytics
+
+The Enterprise platform provides comprehensive observability features:
+
+- **Execution Management**: Track active and completed runs
+- **Traces**: Detailed breakdowns of each execution
+- **Metrics**: Token usage, execution times, and costs
+- **Timeline View**: Visual representation of task sequences
+
+## Advanced Features
+
+The Enterprise platform also offers:
+
+- **Environment Variables Management**: Securely store and manage API keys
+- **LLM Connections**: Configure integrations with various LLM providers
+- **Custom Tools Repository**: Create, share, and install tools
+- **Crew Studio**: Build crews through a chat interface without writing code
+
+<Card title="Need Help?" icon="headset" href="mailto:support@crewai.com">
+  Contact our support team for assistance with deployment issues or questions about the Enterprise platform.
+</Card>

docs/enterprise/guides/enable-crew-studio.mdx

@@ -0,0 +1,166 @@
+---
+title: "Enable Crew Studio"
+description: "Enabling Crew Studio on CrewAI Enterprise"
+icon: "comments"
+---
+
+<Tip>
+Crew Studio is a powerful **no-code/low-code** tool that allows you to quickly scaffold or build Crews through a conversational interface. 
+</Tip>
+
+## What is Crew Studio?
+
+Crew Studio is an innovative way to create AI agent crews without writing code. 
+
+<Frame>
+  ![Crew Studio Interface](/images/enterprise/crew-studio-interface.png)
+</Frame>
+
+With Crew Studio, you can:
+
+- Chat with the Crew Assistant to describe your problem
+- Automatically generate agents and tasks
+- Select appropriate tools
+- Configure necessary inputs
+- Generate downloadable code for customization
+- Deploy directly to the CrewAI Enterprise platform
+
+## Configuration Steps
+
+Before you can start using Crew Studio, you need to configure your LLM connections:
+
+<Steps>
+  <Step title="Set Up LLM Connection">
+    Go to the **LLM Connections** tab in your CrewAI Enterprise dashboard and create a new LLM connection.
+
+    <Note>
+      Feel free to use any LLM provider you want that is supported by CrewAI.
+    </Note>
+    
+    Configure your LLM connection:
+    
+    - Enter a `Connection Name` (e.g., `OpenAI`)
+    - Select your model provider: `openai` or `azure`
+    - Select models you'd like to use in your Studio-generated Crews
+      - We recommend at least `gpt-4o`, `o1-mini`, and `gpt-4o-mini`
+    - Add your API key as an environment variable:
+      - For OpenAI: Add `OPENAI_API_KEY` with your API key
+      - For Azure OpenAI: Refer to [this article](https://blog.crewai.com/configuring-azure-openai-with-crewai-a-comprehensive-guide/) for configuration details
+    - Click `Add Connection` to save your configuration
+    
+    <Frame>
+      ![LLM Connection Configuration](/images/enterprise/llm-connection-config.png)
+    </Frame>
+  </Step>
+  
+  <Step title="Verify Connection Added">
+    Once you complete the setup, you'll see your new connection added to the list of available connections.
+    
+    <Frame>
+      ![Connection Added](/images/enterprise/connection-added.png)
+    </Frame>
+  </Step>
+  
+  <Step title="Configure LLM Defaults">
+    In the main menu, go to **Settings → Defaults** and configure the LLM Defaults settings:
+    
+    - Select default models for agents and other components
+    - Set default configurations for Crew Studio
+    
+    Click `Save Settings` to apply your changes.
+    
+    <Frame>
+      ![LLM Defaults Configuration](/images/enterprise/llm-defaults.png)
+    </Frame>
+  </Step>
+</Steps>
+
+## Using Crew Studio
+
+Now that you've configured your LLM connection and default settings, you're ready to start using Crew Studio!
+
+<Steps>
+  <Step title="Access Studio">
+    Navigate to the **Studio** section in your CrewAI Enterprise dashboard.
+  </Step>
+  
+  <Step title="Start a Conversation">
+    Start a conversation with the Crew Assistant by describing the problem you want to solve:
+    
+    ```md
+    I need a crew that can research the latest AI developments and create a summary report.
+    ```
+    
+    The Crew Assistant will ask clarifying questions to better understand your requirements.
+  </Step>
+  
+  <Step title="Review Generated Crew">
+    Review the generated crew configuration, including:
+    
+    - Agents and their roles
+    - Tasks to be performed
+    - Required inputs
+    - Tools to be used
+    
+    This is your opportunity to refine the configuration before proceeding.
+  </Step>
+  
+  <Step title="Deploy or Download">
+    Once you're satisfied with the configuration, you can:
+    
+    - Download the generated code for local customization
+    - Deploy the crew directly to the CrewAI Enterprise platform
+    - Modify the configuration and regenerate the crew
+  </Step>
+  
+  <Step title="Test Your Crew">
+    After deployment, test your crew with sample inputs to ensure it performs as expected.
+  </Step>
+</Steps>
+
+<Tip>
+For best results, provide clear, detailed descriptions of what you want your crew to accomplish. Include specific inputs and expected outputs in your description.
+</Tip>
+
+## Example Workflow
+
+Here's a typical workflow for creating a crew with Crew Studio:
+
+<Steps>
+  <Step title="Describe Your Problem">
+    Start by describing your problem:
+    
+    ```md
+    I need a crew that can analyze financial news and provide investment recommendations
+    ```
+  </Step>
+  
+  <Step title="Answer Questions">
+    Respond to clarifying questions from the Crew Assistant to refine your requirements.
+  </Step>
+  
+  <Step title="Review the Plan">
+    Review the generated crew plan, which might include:
+    
+    - A Research Agent to gather financial news
+    - An Analysis Agent to interpret the data
+    - A Recommendations Agent to provide investment advice
+  </Step>
+  
+  <Step title="Approve or Modify">
+    Approve the plan or request changes if necessary.
+  </Step>
+  
+  <Step title="Download or Deploy">
+    Download the code for customization or deploy directly to the platform.
+  </Step>
+  
+  <Step title="Test and Refine">
+    Test your crew with sample inputs and refine as needed.
+  </Step>
+</Steps>
+
+<Card title="Need Help?" icon="headset" href="mailto:support@crewai.com">
+  Contact our support team for assistance with Crew Studio or any other CrewAI Enterprise features.
+</Card>
+

docs/enterprise/guides/kickoff-crew.mdx

@@ -0,0 +1,186 @@
+---
+title: "Kickoff Crew"
+description: "Kickoff a Crew on CrewAI Enterprise"
+icon: "flag-checkered"
+---
+
+# Kickoff a Crew on CrewAI Enterprise
+
+Once you've deployed your crew to the CrewAI Enterprise platform, you can kickoff executions through the web interface or the API. This guide covers both approaches.
+
+## Method 1: Using the Web Interface
+
+### Step 1: Navigate to Your Deployed Crew
+
+1. Log in to [CrewAI Enterprise](https://app.crewai.com)
+2. Click on the crew name from your projects list
+3. You'll be taken to the crew's detail page
+
+<Frame>
+  ![Crew Dashboard](/images/enterprise/crew-dashboard.png)
+</Frame>
+
+### Step 2: Initiate Execution
+
+From your crew's detail page, you have two options to kickoff an execution:
+
+#### Option A: Quick Kickoff
+
+1. Click the `Kickoff` link in the Test Endpoints section
+2. Enter the required input parameters for your crew in the JSON editor
+3. Click the `Send Request` button
+
+<Frame>
+  ![Kickoff Endpoint](/images/enterprise/kickoff-endpoint.png)
+</Frame>
+
+#### Option B: Using the Visual Interface
+
+1. Click the `Run` tab in the crew detail page
+2. Enter the required inputs in the form fields
+3. Click the `Run Crew` button
+
+<Frame>
+  ![Run Crew](/images/enterprise/run-crew.png)
+</Frame>
+
+### Step 3: Monitor Execution Progress
+
+After initiating the execution:
+
+1. You'll receive a response containing a `kickoff_id` - **copy this ID**
+2. This ID is essential for tracking your execution
+
+<Frame>
+  ![Copy Task ID](/images/enterprise/copy-task-id.png)
+</Frame>
+
+### Step 4: Check Execution Status
+
+To monitor the progress of your execution:
+
+1. Click the "Status" endpoint in the Test Endpoints section
+2. Paste the `kickoff_id` into the designated field
+3. Click the "Get Status" button
+
+<Frame>
+  ![Get Status](/images/enterprise/get-status.png)
+</Frame>
+
+The status response will show:
+- Current execution state (`running`, `completed`, etc.)
+- Details about which tasks are in progress
+- Any outputs produced so far
+
+### Step 5: View Final Results
+
+Once execution is complete:
+
+1. The status will change to `completed`
+2. You can view the full execution results and outputs
+3. For a more detailed view, check the `Executions` tab in the crew detail page
+
+## Method 2: Using the API
+
+You can also kickoff crews programmatically using the CrewAI Enterprise REST API.
+
+### Authentication
+
+All API requests require a bearer token for authentication:
+
+```bash
+curl -H "Authorization: Bearer YOUR_CREW_TOKEN" https://your-crew-url.crewai.com
+```
+
+Your bearer token is available on the Status tab of your crew's detail page.
+
+### Checking Crew Health
+
+Before executing operations, you can verify that your crew is running properly:
+
+```bash
+curl -H "Authorization: Bearer YOUR_CREW_TOKEN" https://your-crew-url.crewai.com
+```
+
+A successful response will return a message indicating the crew is operational:
+
+```
+Healthy%
+```
+
+### Step 1: Retrieve Required Inputs
+
+First, determine what inputs your crew requires:
+
+```bash
+curl -X GET \
+  -H "Authorization: Bearer YOUR_CREW_TOKEN" \
+  https://your-crew-url.crewai.com/inputs
+```
+
+The response will be a JSON object containing an array of required input parameters, for example:
+
+```json
+{"inputs":["topic","current_year"]}
+```
+
+This example shows that this particular crew requires two inputs: `topic` and `current_year`.
+
+### Step 2: Kickoff Execution
+
+Initiate execution by providing the required inputs:
+
+```bash
+curl -X POST \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer YOUR_CREW_TOKEN" \
+  -d '{"inputs": {"topic": "AI Agent Frameworks", "current_year": "2025"}}' \
+  https://your-crew-url.crewai.com/kickoff
+```
+
+The response will include a `kickoff_id` that you'll need for tracking:
+
+```json
+{"kickoff_id":"abcd1234-5678-90ef-ghij-klmnopqrstuv"}
+```
+
+### Step 3: Check Execution Status
+
+Monitor the execution progress using the kickoff_id:
+
+```bash
+curl -X GET \
+  -H "Authorization: Bearer YOUR_CREW_TOKEN" \
+  https://your-crew-url.crewai.com/status/abcd1234-5678-90ef-ghij-klmnopqrstuv
+```
+
+## Handling Executions
+
+### Long-Running Executions
+
+For executions that may take a long time:
+
+1. Consider implementing a polling mechanism to check status periodically
+2. Use webhooks (if available) for notification when execution completes
+3. Implement error handling for potential timeouts
+
+### Execution Context
+
+The execution context includes:
+
+- Inputs provided at kickoff
+- Environment variables configured during deployment
+- Any state maintained between tasks
+
+### Debugging Failed Executions
+
+If an execution fails:
+
+1. Check the "Executions" tab for detailed logs
+2. Review the "Traces" tab for step-by-step execution details
+3. Look for LLM responses and tool usage in the trace details
+
+<Card title="Need Help?" icon="headset" href="mailto:support@crewai.com">
+  Contact our support team for assistance with execution issues or questions about the Enterprise platform.
+</Card>
+

docs/enterprise/guides/update-crew.mdx

@@ -0,0 +1,89 @@
+---
+title: "Update Crew"
+description: "Updating a Crew on CrewAI Enterprise"
+icon: "pencil"
+---
+
+<Note>
+After deploying your crew to CrewAI Enterprise, you may need to make updates to the code, security settings, or configuration. 
+This guide explains how to perform these common update operations.
+</Note>
+
+## Why Update Your Crew?
+
+CrewAI won't automatically pick up GitHub updates by default, so you'll need to manually trigger updates, unless you checked the `Auto-update` option when deploying your crew.
+
+There are several reasons you might want to update your crew deployment:
+- You want to update the code with a latest commit you pushed to GitHub
+- You want to reset the bearer token for security reasons
+- You want to update environment variables
+
+## 1. Updating Your Crew Code for a Latest Commit
+
+When you've pushed new commits to your GitHub repository and want to update your deployment:
+
+1. Navigate to your crew in the CrewAI Enterprise platform
+2. Click on the `Re-deploy` button on your crew details page
+
+<Frame>
+  ![Re-deploy Button](/images/enterprise/redeploy-button.png)
+</Frame>
+
+This will trigger an update that you can track using the progress bar. The system will pull the latest code from your repository and rebuild your deployment.
+
+## 2. Resetting Bearer Token
+
+If you need to generate a new bearer token (for example, if you suspect the current token might have been compromised):
+
+1. Navigate to your crew in the CrewAI Enterprise platform
+2. Find the `Bearer Token` section
+3. Click the `Reset` button next to your current token
+
+<Frame>
+  ![Reset Token](/images/enterprise/reset-token.png)
+</Frame>
+
+<Warning>
+Resetting your bearer token will invalidate the previous token immediately. Make sure to update any applications or scripts that are using the old token.
+</Warning>
+
+## 3. Updating Environment Variables
+
+To update the environment variables for your crew:
+
+1. First access the deployment page by clicking on your crew's name
+
+<Frame>
+  ![Environment Variables Button](/images/enterprise/env-vars-button.png)
+</Frame>
+
+2. Locate the `Environment Variables` section (you will need to click the `Settings` icon to access it)
+3. Edit the existing variables or add new ones in the fields provided
+4. Click the `Update` button next to each variable you modify
+
+<Frame>
+  ![Update Environment Variables](/images/enterprise/update-env-vars.png)
+</Frame>
+
+5. Finally, click the `Update Deployment` button at the bottom of the page to apply the changes
+
+<Note>
+Updating environment variables will trigger a new deployment, but this will only update the environment configuration and not the code itself.
+</Note>
+
+## After Updating
+
+After performing any update:
+
+1. The system will rebuild and redeploy your crew
+2. You can monitor the deployment progress in real-time
+3. Once complete, test your crew to ensure the changes are working as expected
+
+<Tip>
+If you encounter any issues after updating, you can view deployment logs in the platform or contact support for assistance.
+</Tip>
+
+<Card title="Need Help?" icon="headset" href="mailto:support@crewai.com">
+  Contact our support team for assistance with updating your crew or troubleshooting deployment issues.
+</Card>
+

docs/enterprise/guides/use-crew-api.mdx

@@ -0,0 +1,319 @@
+---
+title: "Trigger Deployed Crew API"
+description: "Using your deployed crew's API on CrewAI Enterprise"
+icon: "arrow-up-right-from-square"
+---
+
+Once you have deployed your crew to CrewAI Enterprise, it automatically becomes available as a REST API. This guide explains how to interact with your crew programmatically.
+
+## API Basics
+
+Your deployed crew exposes several endpoints that allow you to:
+1. Discover required inputs
+2. Start crew executions
+3. Monitor execution status
+4. Receive results
+
+### Authentication
+
+All API requests require a bearer token for authentication, which is generated when you deploy your crew:
+
+```bash
+curl -H "Authorization: Bearer YOUR_CREW_TOKEN" https://your-crew-url.crewai.com/...
+```
+
+<Tip>
+You can find your bearer token in the Status tab of your crew's detail page in the CrewAI Enterprise dashboard.
+</Tip>
+
+<Frame>
+  ![Bearer Token](/images/enterprise/bearer-token.png)
+</Frame>
+
+## Available Endpoints
+
+Your crew API provides three main endpoints:
+
+| Endpoint | Method | Description |
+|----------|--------|-------------|
+| `/inputs` | GET | Lists all required inputs for crew execution |
+| `/kickoff` | POST | Starts a crew execution with provided inputs |
+| `/status/{kickoff_id}` | GET | Retrieves the status and results of an execution |
+
+## GET /inputs
+
+The inputs endpoint allows you to discover what parameters your crew requires:
+
+```bash
+curl -X GET \
+  -H "Authorization: Bearer YOUR_CREW_TOKEN" \
+  https://your-crew-url.crewai.com/inputs
+```
+
+### Response
+
+```json
+{
+  "inputs": ["budget", "interests", "duration", "age"]
+}
+```
+
+This response indicates that your crew expects four input parameters: `budget`, `interests`, `duration`, and `age`.
+
+## POST /kickoff
+
+The kickoff endpoint starts a new crew execution:
+
+```bash
+curl -X POST \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer YOUR_CREW_TOKEN" \
+  -d '{
+    "inputs": {
+      "budget": "1000 USD",
+      "interests": "games, tech, ai, relaxing hikes, amazing food",
+      "duration": "7 days",
+      "age": "35"
+    }
+  }' \
+  https://your-crew-url.crewai.com/kickoff
+```
+
+### Request Parameters
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `inputs` | Object | Yes | Key-value pairs of all required inputs |
+| `meta` | Object | No | Additional metadata to pass to the crew |
+| `taskWebhookUrl` | String | No | Callback URL executed after each task |
+| `stepWebhookUrl` | String | No | Callback URL executed after each agent thought |
+| `crewWebhookUrl` | String | No | Callback URL executed when the crew finishes |
+
+### Example with Webhooks
+
+```json
+{
+  "inputs": {
+    "budget": "1000 USD",
+    "interests": "games, tech, ai, relaxing hikes, amazing food",
+    "duration": "7 days",
+    "age": "35"
+  },
+  "meta": {
+    "requestId": "user-request-12345",
+    "source": "mobile-app"
+  },
+  "taskWebhookUrl": "https://your-server.com/webhooks/task",
+  "stepWebhookUrl": "https://your-server.com/webhooks/step",
+  "crewWebhookUrl": "https://your-server.com/webhooks/crew"
+}
+```
+
+### Response
+
+```json
+{
+  "kickoff_id": "abcd1234-5678-90ef-ghij-klmnopqrstuv"
+}
+```
+
+The `kickoff_id` is used to track and retrieve the execution results.
+
+## GET /status/{kickoff_id}
+
+The status endpoint allows you to check the progress and results of a crew execution:
+
+```bash
+curl -X GET \
+  -H "Authorization: Bearer YOUR_CREW_TOKEN" \
+  https://your-crew-url.crewai.com/status/abcd1234-5678-90ef-ghij-klmnopqrstuv
+```
+
+### Response Structure
+
+The response structure will vary depending on the execution state:
+
+#### In Progress
+
+```json
+{
+  "status": "running",
+  "current_task": "research_task",
+  "progress": {
+    "completed_tasks": 0,
+    "total_tasks": 2
+  }
+}
+```
+
+#### Completed
+
+```json
+{
+  "status": "completed",
+  "result": {
+    "output": "Comprehensive travel itinerary...",
+    "tasks": [
+      {
+        "task_id": "research_task",
+        "output": "Research findings...",
+        "agent": "Researcher",
+        "execution_time": 45.2
+      },
+      {
+        "task_id": "planning_task",
+        "output": "7-day itinerary plan...",
+        "agent": "Trip Planner",
+        "execution_time": 62.8
+      }
+    ]
+  },
+  "execution_time": 108.5
+}
+```
+
+## Webhook Integration
+
+When you provide webhook URLs in your kickoff request, the system will make POST requests to those URLs at specific points in the execution:
+
+### taskWebhookUrl
+
+Called when each task completes:
+
+```json
+{
+  "kickoff_id": "abcd1234-5678-90ef-ghij-klmnopqrstuv",
+  "task_id": "research_task",
+  "status": "completed",
+  "output": "Research findings...",
+  "agent": "Researcher",
+  "execution_time": 45.2
+}
+```
+
+### stepWebhookUrl
+
+Called after each agent thought or action:
+
+```json
+{
+  "kickoff_id": "abcd1234-5678-90ef-ghij-klmnopqrstuv",
+  "task_id": "research_task",
+  "agent": "Researcher",
+  "step_type": "thought",
+  "content": "I should first search for popular destinations that match these interests..."
+}
+```
+
+### crewWebhookUrl
+
+Called when the entire crew execution completes:
+
+```json
+{
+  "kickoff_id": "abcd1234-5678-90ef-ghij-klmnopqrstuv",
+  "status": "completed",
+  "result": {
+    "output": "Comprehensive travel itinerary...",
+    "tasks": [
+      {
+        "task_id": "research_task",
+        "output": "Research findings...",
+        "agent": "Researcher",
+        "execution_time": 45.2
+      },
+      {
+        "task_id": "planning_task",
+        "output": "7-day itinerary plan...",
+        "agent": "Trip Planner",
+        "execution_time": 62.8
+      }
+    ]
+  },
+  "execution_time": 108.5,
+  "meta": {
+    "requestId": "user-request-12345",
+    "source": "mobile-app"
+  }
+}
+```
+
+## Best Practices
+
+### Handling Long-Running Executions
+
+Crew executions can take anywhere from seconds to minutes depending on their complexity. Consider these approaches:
+
+1. **Webhooks (Recommended)**: Set up webhook endpoints to receive notifications when the execution completes
+2. **Polling**: Implement a polling mechanism with exponential backoff
+3. **Client-Side Timeout**: Set appropriate timeouts for your API requests
+
+### Error Handling
+
+The API may return various error codes:
+
+| Code | Description | Recommended Action |
+|------|-------------|-------------------|
+| 401 | Unauthorized | Check your bearer token |
+| 404 | Not Found | Verify your crew URL and kickoff_id |
+| 422 | Validation Error | Ensure all required inputs are provided |
+| 500 | Server Error | Contact support with the error details |
+
+### Sample Code
+
+Here's a complete Python example for interacting with your crew API:
+
+```python
+import requests
+import time
+
+# Configuration
+CREW_URL = "https://your-crew-url.crewai.com"
+BEARER_TOKEN = "your-crew-token"
+HEADERS = {
+    "Authorization": f"Bearer {BEARER_TOKEN}",
+    "Content-Type": "application/json"
+}
+
+# 1. Get required inputs
+response = requests.get(f"{CREW_URL}/inputs", headers=HEADERS)
+required_inputs = response.json()["inputs"]
+print(f"Required inputs: {required_inputs}")
+
+# 2. Start crew execution
+payload = {
+    "inputs": {
+        "budget": "1000 USD",
+        "interests": "games, tech, ai, relaxing hikes, amazing food",
+        "duration": "7 days",
+        "age": "35"
+    }
+}
+
+response = requests.post(f"{CREW_URL}/kickoff", headers=HEADERS, json=payload)
+kickoff_id = response.json()["kickoff_id"]
+print(f"Execution started with ID: {kickoff_id}")
+
+# 3. Poll for results
+MAX_RETRIES = 30
+POLL_INTERVAL = 10  # seconds
+for i in range(MAX_RETRIES):
+    print(f"Checking status (attempt {i+1}/{MAX_RETRIES})...")
+    response = requests.get(f"{CREW_URL}/status/{kickoff_id}", headers=HEADERS)
+    data = response.json()
+    
+    if data["status"] == "completed":
+        print("Execution completed!")
+        print(f"Result: {data['result']['output']}")
+        break
+    elif data["status"] == "error":
+        print(f"Execution failed: {data.get('error', 'Unknown error')}")
+        break
+    else:
+        print(f"Status: {data['status']}, waiting {POLL_INTERVAL} seconds...")
+        time.sleep(POLL_INTERVAL)
+```
+
+<Card title="Need Help?" icon="headset" href="mailto:support@crewai.com">
+  Contact our support team for assistance with API integration or troubleshooting.
+</Card>

docs/enterprise/introduction.mdx

@@ -0,0 +1,67 @@
+---
+title: "CrewAI Enterprise"
+description: "Deploy, monitor, and scale your AI agent workflows"
+icon: "globe"
+---
+
+## Introduction
+
+CrewAI Enterprise provides a platform for deploying, monitoring, and scaling your crews and agents in a production environment.
+
+CrewAI Enterprise extends the power of the open-source framework with features designed for production deployments, collaboration, and scalability. Deploy your crews to a managed infrastructure and monitor their execution in real-time.
+
+## Key Features
+
+<CardGroup cols={2}>
+  <Card title="Crew Deployments" icon="rocket">
+    Deploy your crews to a managed infrastructure with a few clicks
+  </Card>
+  <Card title="API Access" icon="code">
+    Access your deployed crews via REST API for integration with existing systems
+  </Card>
+  <Card title="Observability" icon="chart-line">
+    Monitor your crews with detailed execution traces and logs
+  </Card>
+  <Card title="Tool Repository" icon="toolbox">
+    Publish and install tools to enhance your crews' capabilities
+  </Card>
+  <Card title="Webhook Streaming" icon="webhook">
+    Stream real-time events and updates to your systems
+  </Card>
+  <Card title="Crew Studio" icon="paintbrush">
+    Create and customize crews using a no-code/low-code interface
+  </Card>
+</CardGroup>
+
+## Deployment Options
+
+<CardGroup cols={3}>
+  <Card title="GitHub Integration" icon="github">
+    Connect directly to your GitHub repositories to deploy code
+  </Card>
+  <Card title="Crew Studio" icon="palette">
+    Deploy crews created through the no-code Crew Studio interface
+  </Card>
+  <Card title="CLI Deployment" icon="terminal">
+    Use the CrewAI CLI for more advanced deployment workflows
+  </Card>
+</CardGroup>
+
+## Getting Started
+
+<Steps>
+  <Step title="Sign up for an account">
+    Create your account at [app.crewai.com](https://app.crewai.com)
+  </Step>
+  <Step title="Create your first crew">
+    Use code or Crew Studio to create your crew
+  </Step>
+  <Step title="Deploy your crew">
+    Deploy your crew to the Enterprise platform
+  </Step>
+  <Step title="Access your crew">
+    Integrate with your crew via the generated API endpoints
+  </Step>
+</Steps>
+
+For detailed instructions, check out our [deployment guide](/enterprise/guides/deploy-crew) or click the button below to get started.

docs/enterprise/resources/frequently-asked-questions.mdx

@@ -0,0 +1,181 @@
+---
+title: FAQs
+description: "Frequently asked questions about CrewAI Enterprise"
+icon: "code"
+---
+
+<AccordionGroup>
+    <Accordion title="How is task execution handled in the hierarchical process?">
+        In the hierarchical process, a manager agent is automatically created and coordinates the workflow, delegating tasks and validating outcomes for
+        streamlined and effective execution. The manager agent utilizes tools to facilitate task delegation and execution by agents under the manager's guidance.
+        The manager LLM is crucial for the hierarchical process and must be set up correctly for proper function.
+    </Accordion>
+
+    <Accordion title="Where can I get the latest CrewAI documentation?">
+        The most up-to-date documentation for CrewAI is available on our official documentation website; https://docs.crewai.com/
+        <Card href="https://docs.crewai.com/" icon="books">CrewAI Docs</Card>
+    </Accordion>
+
+    <Accordion title="What are the key differences between Hierarchical and Sequential Processes in CrewAI?">
+        #### Hierarchical Process:
+        Tasks are delegated and executed based on a structured chain of command.
+        A manager language model (`manager_llm`) must be specified for the manager agent.
+        Manager agent oversees task execution, planning, delegation, and validation.
+        Tasks are not pre-assigned; the manager allocates tasks to agents based on their capabilities.
+
+        #### Sequential Process:
+        Tasks are executed one after another, ensuring tasks are completed in an orderly progression.
+        Output of one task serves as context for the next.
+        Task execution follows the predefined order in the task list.
+
+        #### Which Process is Better Suited for Complex Projects?
+
+        The hierarchical process is better suited for complex projects because it allows for:
+
+        - **Dynamic task allocation and delegation**: Manager agent can assign tasks based on agent capabilities, allowing for efficient resource utilization.
+        - **Structured validation and oversight**: Manager agent reviews task outputs and ensures task completion, increasing reliability and accuracy.
+        - **Complex task management**: Assigning tools at the agent level allows for precise control over tool availability, facilitating the execution of intricate tasks.
+    </Accordion>
+
+    <Accordion title="What are the benefits of using memory in the CrewAI framework?">
+        - **Adaptive Learning**: Crews become more efficient over time, adapting to new information and refining their approach to tasks.
+        - **Enhanced Personalization**: Memory enables agents to remember user preferences and historical interactions, leading to personalized experiences.
+        - **Improved Problem Solving**: Access to a rich memory store aids agents in making more informed decisions, drawing on past learnings and contextual insights.
+    </Accordion>
+
+    <Accordion title="What is the purpose of setting a maximum RPM limit for an agent?">
+        Setting a maximum RPM limit for an agent prevents the agent from making too many requests to external services, which can help to avoid rate limits and improve performance.
+    </Accordion>
+
+    <Accordion title="What role does human input play in the execution of tasks within a CrewAI crew?">
+        It allows agents to request additional information or clarification when necessary.
+        This feature is crucial in complex decision-making processes or when agents require more details to complete a task effectively.
+
+        To integrate human input into agent execution, set the `human_input` flag in the task definition. When enabled, the agent prompts the user for input before delivering its final answer. 
+        This input can provide extra context, clarify ambiguities, or validate the agent's output.
+    </Accordion>
+
+    <Accordion title="What advanced customization options are available for tailoring and enhancing agent behavior and capabilities in CrewAI?">
+        CrewAI provides a range of advanced customization options to tailor and enhance agent behavior and capabilities:
+        
+        - **Language Model Customization**: Agents can be customized with specific language models (`llm`) and function-calling language models (`function_calling_llm`), offering advanced control over their processing and decision-making abilities.
+
+        - **Performance and Debugging Settings**: Adjust an agent's performance and monitor its operations for efficient task execution.
+
+        - **Verbose Mode**: Enables detailed logging of an agent's actions, useful for debugging and optimization.
+
+        - **RPM Limit**: Sets the maximum number of requests per minute (`max_rpm`).
+
+        - **Maximum Iterations for Task Execution**: The `max_iter` attribute allows users to define the maximum number of iterations an agent can perform for a single task, preventing infinite loops or excessively long executions.
+
+        - **Delegation and Autonomy**: Control an agent's ability to delegate or ask questions, tailoring its autonomy and collaborative dynamics within the CrewAI framework. By default, the `allow_delegation` attribute is set to True, enabling agents to seek assistance or delegate tasks as needed. This default behavior promotes collaborative problem-solving and efficiency within the CrewAI ecosystem. If needed, delegation can be disabled to suit specific operational requirements.
+
+        - **Human Input in Agent Execution**: Human input is critical in several agent execution scenarios, allowing agents to request additional information or clarification when necessary. This feature is especially useful in complex decision-making processes or when agents require more details to complete a task effectively.
+    </Accordion>
+
+    <Accordion title="In what scenarios is human input particularly useful in agent execution?">
+        Human input is particularly useful in agent execution when:
+        - **Agents require additional information or clarification**: When agents encounter ambiguity or incomplete data, human input can provide the necessary context to complete the task effectively.
+        - **Agents need to make complex or sensitive decisions**: Human input can assist agents in ethical or nuanced decision-making, ensuring responsible and informed outcomes.
+        - **Oversight and validation of agent output**: Human input can help validate the results generated by agents, ensuring accuracy and preventing any misinterpretation or errors.
+        - **Customizing agent behavior**: Human input can provide feedback on agent responses, allowing users to refine the agent's behavior and responses over time.
+        - **Identifying and resolving errors or limitations**: Human input can help identify and address any errors or limitations in the agent's capabilities, enabling continuous improvement and optimization.
+    </Accordion>
+
+    <Accordion title="What are the different types of memory that are available in crewAI?">
+        The different types of memory available in CrewAI are:
+        - `short-term memory`
+        - `long-term memory`
+        - `entity memory`
+        - `contextual memory`
+
+        Learn more about the different types of memory here:
+        <Card href="https://docs.crewai.com/concepts/memory" icon="brain">CrewAI Memory</Card>
+    </Accordion>
+
+    <Accordion title="How can I create custom tools for my CrewAI agents?">
+        You can create custom tools by subclassing the `BaseTool` class provided by CrewAI or by using the tool decorator. Subclassing involves defining a new class that inherits from `BaseTool`, specifying the name, description, and the `_run` method for operational logic. The tool decorator allows you to create a `Tool` object directly with the required attributes and a functional logic.
+        Click here for more details:
+        <Card href="https://docs.crewai.com/how-to/create-custom-tools" icon="code">CrewAI Tools</Card>
+    </Accordion>
+
+    <Accordion title="How do I use Output Pydantic in a Task?">
+        To use Output Pydantic in a task, you need to define the expected output of the task as a Pydantic model. Here's an example:
+        <Steps>
+            <Step title="Define a Pydantic model">
+                First, you need to define a Pydantic model. For instance, let's create a simple model for a user:
+
+                ```python
+                from pydantic import BaseModel
+
+                class User(BaseModel):
+                    name: str
+                    age: int
+                ```
+            </Step>
+
+            <Step title="Then, when creating a task, specify the expected output as this Pydantic model:">
+
+                ```python
+                from crewai import Task, Crew, Agent
+
+                # Import the User model
+                from my_models import User
+
+                # Create a task with Output Pydantic
+                task = Task(
+                    description="Create a user with the provided name and age",
+                    expected_output=User,  # This is the Pydantic model
+                    agent=agent,
+                    tools=[tool1, tool2]
+                )
+                ```
+            </Step>
+
+            <Step title="In your agent, make sure to set the output_pydantic attribute to the Pydantic model you're using:">
+
+                ```python
+                from crewai import Agent
+
+                # Import the User model
+                from my_models import User
+
+                # Create an agent with Output Pydantic
+                agent = Agent(
+                    role='User Creator',
+                    goal='Create users',
+                    backstory='I am skilled in creating user accounts',
+                    tools=[tool1, tool2],
+                    output_pydantic=User
+                )
+                ```
+            </Step>
+
+            <Step title="When executing the crew, the output of the task will be a User object:">
+
+                ```python
+                from crewai import Crew
+
+                # Create a crew with the agent and task
+                crew = Crew(agents=[agent], tasks=[task])
+
+                # Kick off the crew
+                result = crew.kickoff()
+
+                # The output of the task will be a User object
+                print(result.tasks[0].output)
+                ``` 
+            </Step>
+        </Steps>
+        Here's a tutorial on how to consistently get structured outputs from your agents:
+            <Frame>
+                <iframe 
+                height="400"
+                width="100%"
+                src="https://www.youtube.com/embed/dNpKQk5uxHw" 
+                title="YouTube video player" frameborder="0" 
+                allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" 
+                allowfullscreen></iframe>
+            </Frame>
+    </Accordion>
+</AccordionGroup>

docs/how-to/bring-your-own-agent.mdx

@@ -0,0 +1,443 @@
+---
+title: Bring your own agent
+description: Learn how to bring your own agents that work within a Crew.
+icon: robots
+---
+
+Interoperability is a core concept in CrewAI. This guide will show you how to bring your own agents that work within a Crew.
+
+
+## Adapter Guide for Bringing your own agents (Langgraph Agents, OpenAI Agents, etc...)
+We require 3 adapters to turn any agent from different frameworks to work within crew.
+
+1. BaseAgentAdapter
+2. BaseToolAdapter
+3. BaseConverter
+
+
+## BaseAgentAdapter
+This abstract class defines the common interface and functionality that all
+agent adapters must implement. It extends BaseAgent to maintain compatibility
+with the CrewAI framework while adding adapter-specific requirements.
+
+Required Methods:
+
+1. `def configure_tools`
+2. `def configure_structured_output`
+
+## Creating your own Adapter
+To integrate an agent from a different framework (e.g., LangGraph, Autogen, OpenAI Assistants) into CrewAI, you need to create a custom adapter by inheriting from `BaseAgentAdapter`. This adapter acts as a compatibility layer, translating between the CrewAI interfaces and the specific requirements of your external agent.
+
+Here's how you implement your custom adapter:
+
+1.  **Inherit from `BaseAgentAdapter`**:
+    ```python
+    from crewai.agents.agent_adapters.base_agent_adapter import BaseAgentAdapter
+    from crewai.tools import BaseTool
+    from typing import List, Optional, Any, Dict
+
+    class MyCustomAgentAdapter(BaseAgentAdapter):
+        # ... implementation details ...
+    ```
+
+2.  **Implement `__init__`**:
+    The constructor should call the parent class constructor `super().__init__(**kwargs)` and perform any initialization specific to your external agent. You can use the optional `agent_config` dictionary passed during CrewAI's `Agent` initialization to configure your adapter and the underlying agent.
+
+    ```python
+    def __init__(self, agent_config: Optional[Dict[str, Any]] = None, **kwargs: Any):
+        super().__init__(agent_config=agent_config, **kwargs)
+        # Initialize your external agent here, possibly using agent_config
+        # Example: self.external_agent = initialize_my_agent(agent_config)
+        print(f"Initializing MyCustomAgentAdapter with config: {agent_config}")
+    ```
+
+3.  **Implement `configure_tools`**:
+    This abstract method is crucial. It receives a list of CrewAI `BaseTool` instances. Your implementation must convert or adapt these tools into the format expected by your external agent framework. This might involve wrapping them, extracting specific attributes, or registering them with the external agent instance.
+
+    ```python
+    def configure_tools(self, tools: Optional[List[BaseTool]] = None) -> None:
+        if tools:
+            adapted_tools = []
+            for tool in tools:
+                # Adapt CrewAI BaseTool to the format your agent expects
+                # Example: adapted_tool = adapt_to_my_framework(tool)
+                # adapted_tools.append(adapted_tool)
+                pass # Replace with your actual adaptation logic
+
+            # Configure the external agent with the adapted tools
+            # Example: self.external_agent.set_tools(adapted_tools)
+            print(f"Configuring tools for MyCustomAgentAdapter: {adapted_tools}") # Placeholder
+        else:
+            # Handle the case where no tools are provided
+            # Example: self.external_agent.set_tools([])
+            print("No tools provided for MyCustomAgentAdapter.")
+    ```
+
+4.  **Implement `configure_structured_output`**:
+    This method is called when the CrewAI `Agent` is configured with structured output requirements (e.g., `output_json` or `output_pydantic`). Your adapter needs to ensure the external agent is set up to comply with these requirements. This might involve setting specific parameters on the external agent or ensuring its underlying model supports the requested format. If the external agent doesn't support structured output in a way compatible with CrewAI's expectations, you might need to handle the conversion or raise an appropriate error.
+
+    ```python
+    def configure_structured_output(self, structured_output: Any) -> None:
+        # Configure your external agent to produce output in the specified format
+        # Example: self.external_agent.set_output_format(structured_output)
+        self.adapted_structured_output = True # Signal that structured output is handled
+        print(f"Configuring structured output for MyCustomAgentAdapter: {structured_output}")
+    ```
+
+By implementing these methods, your `MyCustomAgentAdapter` will allow your custom agent implementation to function correctly within a CrewAI crew, interacting with tasks and tools seamlessly. Remember to replace the example comments and print statements with your actual adaptation logic specific to the external agent framework you are integrating.
+
+## BaseToolAdapter implementation
+The `BaseToolAdapter` class is responsible for converting CrewAI's native `BaseTool` objects into a format that your specific external agent framework can understand and utilize. Different agent frameworks (like LangGraph, OpenAI Assistants, etc.) have their own unique ways of defining and handling tools, and the `BaseToolAdapter` acts as the translator.
+
+Here's how you implement your custom tool adapter:
+
+1.  **Inherit from `BaseToolAdapter`**:
+    ```python
+    from crewai.agents.agent_adapters.base_tool_adapter import BaseToolAdapter
+    from crewai.tools import BaseTool
+    from typing import List, Any
+
+    class MyCustomToolAdapter(BaseToolAdapter):
+        # ... implementation details ...
+    ```
+
+2.  **Implement `configure_tools`**:
+    This is the core abstract method you must implement. It receives a list of CrewAI `BaseTool` instances provided to the agent. Your task is to iterate through this list, adapt each `BaseTool` into the format expected by your external framework, and store the converted tools in the `self.converted_tools` list (which is initialized in the base class constructor).
+
+    ```python
+    def configure_tools(self, tools: List[BaseTool]) -> None:
+        """Configure and convert CrewAI tools for the specific implementation."""
+        self.converted_tools = [] # Reset in case it's called multiple times
+        for tool in tools:
+            # Sanitize the tool name if required by the target framework
+            sanitized_name = self.sanitize_tool_name(tool.name)
+
+            # --- Your Conversion Logic Goes Here ---
+            # Example: Convert BaseTool to a dictionary format for LangGraph
+            # converted_tool = {
+            #     "name": sanitized_name,
+            #     "description": tool.description,
+            #     "parameters": tool.args_schema.schema() if tool.args_schema else {},
+            #     # Add any other framework-specific fields
+            # }
+
+            # Example: Convert BaseTool to an OpenAI function definition
+            # converted_tool = {
+            #     "type": "function",
+            #     "function": {
+            #         "name": sanitized_name,
+            #         "description": tool.description,
+            #         "parameters": tool.args_schema.schema() if tool.args_schema else {"type": "object", "properties": {}},
+            #     }
+            # }
+
+            # --- Replace above examples with your actual adaptation ---
+            converted_tool = self.adapt_tool_to_my_framework(tool, sanitized_name) # Placeholder
+
+            self.converted_tools.append(converted_tool)
+            print(f"Adapted tool '{tool.name}' to '{sanitized_name}' for MyCustomToolAdapter") # Placeholder
+
+        print(f"MyCustomToolAdapter finished configuring tools: {len(self.converted_tools)} adapted.") # Placeholder
+
+    # --- Helper method for adaptation (Example) ---
+    def adapt_tool_to_my_framework(self, tool: BaseTool, sanitized_name: str) -> Any:
+        # Replace this with the actual logic to convert a CrewAI BaseTool
+        # to the format needed by your specific external agent framework.
+        # This will vary greatly depending on the target framework.
+        adapted_representation = {
+            "framework_specific_name": sanitized_name,
+            "framework_specific_description": tool.description,
+            "inputs": tool.args_schema.schema() if tool.args_schema else None,
+            "implementation_reference": tool.run # Or however the framework needs to call it
+        }
+        # Also ensure the tool works both sync and async
+        async def async_tool_wrapper(*args, **kwargs):
+            output = tool.run(*args, **kwargs)
+            if inspect.isawaitable(output):
+                return await output
+            else:
+                return output
+
+        adapted_tool = MyFrameworkTool(
+            name=sanitized_name,
+            description=tool.description,
+            inputs=tool.args_schema.schema() if tool.args_schema else None,
+            implementation_reference=async_tool_wrapper
+        )
+        
+        return adapted_representation
+
+    ```
+
+3.  **Using the Adapter**:
+    Typically, you would instantiate your `MyCustomToolAdapter` within your `MyCustomAgentAdapter`'s `configure_tools` method and use it to process the tools before configuring your external agent.
+
+    ```python
+    # Inside MyCustomAgentAdapter.configure_tools
+    def configure_tools(self, tools: Optional[List[BaseTool]] = None) -> None:
+        if tools:
+            tool_adapter = MyCustomToolAdapter() # Instantiate your tool adapter
+            tool_adapter.configure_tools(tools)  # Convert the tools
+            adapted_tools = tool_adapter.tools() # Get the converted tools
+
+            # Now configure your external agent with the adapted_tools
+            # Example: self.external_agent.set_tools(adapted_tools)
+            print(f"Configuring external agent with adapted tools: {adapted_tools}") # Placeholder
+        else:
+            # Handle no tools case
+            print("No tools provided for MyCustomAgentAdapter.")
+    ```
+
+By creating a `BaseToolAdapter`, you decouple the tool conversion logic from the agent adaptation, making the integration cleaner and more modular. Remember to replace the placeholder examples with the actual conversion logic required by your specific external agent framework.
+
+## BaseConverter
+The `BaseConverterAdapter` plays a crucial role when a CrewAI `Task` requires an agent to return its final output in a specific structured format, such as JSON or a Pydantic model. It bridges the gap between CrewAI's structured output requirements and the capabilities of your external agent.
+
+Its primary responsibilities are:
+1.  **Configuring the Agent for Structured Output:** Based on the `Task`'s requirements (`output_json` or `output_pydantic`), it instructs the associated `BaseAgentAdapter` (and indirectly, the external agent) on what format is expected.
+2.  **Enhancing the System Prompt:** It modifies the agent's system prompt to include clear instructions on *how* to generate the output in the required structure.
+3.  **Post-processing the Result:** It takes the raw output from the agent and attempts to parse, validate, and format it according to the required structure, ultimately returning a string representation (e.g., a JSON string).
+
+Here's how you implement your custom converter adapter:
+
+1.  **Inherit from `BaseConverterAdapter`**:
+    ```python
+    from crewai.agents.agent_adapters.base_converter_adapter import BaseConverterAdapter
+    # Assuming you have your MyCustomAgentAdapter defined
+    # from .my_custom_agent_adapter import MyCustomAgentAdapter
+    from crewai.task import Task
+    from typing import Any
+
+    class MyCustomConverterAdapter(BaseConverterAdapter):
+        # Store the expected output type (e.g., 'json', 'pydantic', 'text')
+        _output_type: str = 'text' 
+        _output_schema: Any = None # Store JSON schema or Pydantic model
+
+        # ... implementation details ...
+    ```
+
+2.  **Implement `__init__`**:
+    The constructor must accept the corresponding `agent_adapter` instance it will work with.
+
+    ```python
+    def __init__(self, agent_adapter: Any): # Use your specific AgentAdapter type hint
+        self.agent_adapter = agent_adapter
+        print(f"Initializing MyCustomConverterAdapter for agent adapter: {type(agent_adapter).__name__}")
+    ```
+
+3.  **Implement `configure_structured_output`**:
+    This method receives the CrewAI `Task` object. You need to check the task's `output_json` and `output_pydantic` attributes to determine the required output structure. Store this information (e.g., in `_output_type` and `_output_schema`) and potentially call configuration methods on your `self.agent_adapter` if the external agent needs specific setup for structured output (which might have been partially handled in the agent adapter's `configure_structured_output` already).
+
+    ```python
+    def configure_structured_output(self, task: Task) -> None:
+        """Configure the expected structured output based on the task."""
+        if task.output_pydantic:
+            self._output_type = 'pydantic'
+            self._output_schema = task.output_pydantic
+            print(f"Converter: Configured for Pydantic output: {self._output_schema.__name__}")
+        elif task.output_json:
+            self._output_type = 'json'
+            self._output_schema = task.output_json
+            print(f"Converter: Configured for JSON output with schema: {self._output_schema}")
+        else:
+            self._output_type = 'text'
+            self._output_schema = None
+            print("Converter: Configured for standard text output.")
+
+        # Optionally, inform the agent adapter if needed
+        # self.agent_adapter.set_output_mode(self._output_type, self._output_schema)
+    ```
+
+4.  **Implement `enhance_system_prompt`**:
+    This method takes the agent's base system prompt string and should append instructions tailored to the currently configured `_output_type` and `_output_schema`. The goal is to guide the LLM powering the agent to produce output in the correct format.
+
+    ```python
+    def enhance_system_prompt(self, base_prompt: str) -> str:
+        """Enhance the system prompt with structured output instructions."""
+        if self._output_type == 'text':
+            return base_prompt # No enhancement needed for plain text
+
+        instructions = "\n\nYour final answer MUST be formatted as "
+        if self._output_type == 'json':
+            schema_str = json.dumps(self._output_schema, indent=2)
+            instructions += f"a JSON object conforming to the following schema:\n```json\n{schema_str}\n```"
+        elif self._output_type == 'pydantic':
+            schema_str = json.dumps(self._output_schema.model_json_schema(), indent=2)
+            instructions += f"a JSON object conforming to the Pydantic model '{self._output_schema.__name__}' with the following schema:\n```json\n{schema_str}\n```"
+
+        instructions += "\nEnsure your entire response is ONLY the valid JSON object, without any introductory text, explanations, or concluding remarks."
+        
+        print(f"Converter: Enhancing prompt for {self._output_type} output.")
+        return base_prompt + instructions
+    ```
+    *Note: The exact prompt engineering might need tuning based on the agent/LLM being used.* 
+
+5.  **Implement `post_process_result`**:
+    This method receives the raw string output from the agent. If structured output was requested (`json` or `pydantic`), you should attempt to parse the string into the expected format. Handle potential parsing errors (e.g., log them, attempt simple fixes, or raise an exception). Crucially, the method must **always return a string**, even if the intermediate format was a dictionary or Pydantic object (e.g., by serializing it back to a JSON string).
+
+    ```python
+    import json
+    from pydantic import ValidationError
+
+    def post_process_result(self, result: str) -> str:
+        """Post-process the agent's result to ensure it matches the expected format."""
+        print(f"Converter: Post-processing result for {self._output_type} output.")
+        if self._output_type == 'json':
+            try:
+                # Attempt to parse and re-serialize to ensure validity and consistent format
+                parsed_json = json.loads(result)
+                # Optional: Validate against self._output_schema if it's a JSON schema dictionary
+                # from jsonschema import validate
+                # validate(instance=parsed_json, schema=self._output_schema)
+                return json.dumps(parsed_json)
+            except json.JSONDecodeError as e:
+                print(f"Error: Failed to parse JSON output: {e}\nRaw output:\n{result}")
+                # Handle error: return raw, raise exception, or try to fix
+                return result # Example: return raw output on failure
+            # except Exception as e: # Catch validation errors if using jsonschema
+            #     print(f"Error: JSON output failed schema validation: {e}\nRaw output:\n{result}")
+            #     return result
+        elif self._output_type == 'pydantic':
+            try:
+                # Attempt to parse into the Pydantic model
+                model_instance = self._output_schema.model_validate_json(result)
+                # Return the model serialized back to JSON
+                return model_instance.model_dump_json()
+            except ValidationError as e:
+                print(f"Error: Failed to validate Pydantic output: {e}\nRaw output:\n{result}")
+                # Handle error
+                return result # Example: return raw output on failure
+            except json.JSONDecodeError as e:
+                 print(f"Error: Failed to parse JSON for Pydantic model: {e}\nRaw output:\n{result}")
+                 return result
+        else: # 'text'
+            return result # No processing needed for plain text
+    ```
+
+By implementing these methods, your `MyCustomConverterAdapter` ensures that structured output requests from CrewAI tasks are correctly handled by your integrated external agent, improving the reliability and usability of your custom agent within the CrewAI framework.
+
+## Out of the Box Adapters
+
+We provide out of the box adapters for the following frameworks:
+1. LangGraph
+2. OpenAI Agents
+
+## Kicking off a crew with adapted agents:
+
+```python
+import json
+import os
+from typing import List
+
+from crewai_tools import SerperDevTool
+from src.crewai import Agent, Crew, Task
+from langchain_openai import ChatOpenAI
+from pydantic import BaseModel
+
+from crewai.agents.agent_adapters.langgraph.langgraph_adapter import (
+    LangGraphAgentAdapter,
+)
+from crewai.agents.agent_adapters.openai_agents.openai_adapter import OpenAIAgentAdapter
+
+# CrewAI Agent
+code_helper_agent = Agent(
+    role="Code Helper",
+    goal="Help users solve coding problems effectively and provide clear explanations.",
+    backstory="You are an experienced programmer with deep knowledge across multiple programming languages and frameworks. You specialize in solving complex coding challenges and explaining solutions clearly.",
+    allow_delegation=False,
+    verbose=True,
+)
+# OpenAI Agent Adapter
+link_finder_agent = OpenAIAgentAdapter(
+    role="Link Finder",
+    goal="Find the most relevant and high-quality resources for coding tasks.",
+    backstory="You are a research specialist with a talent for finding the most helpful resources. You're skilled at using search tools to discover documentation, tutorials, and examples that directly address the user's coding needs.",
+    tools=[SerperDevTool()],
+    allow_delegation=False,
+    verbose=True,
+)
+
+# LangGraph Agent Adapter
+reporter_agent = LangGraphAgentAdapter(
+    role="Reporter",
+    goal="Report the results of the tasks.",
+    backstory="You are a reporter who reports the results of the other tasks",
+    llm=ChatOpenAI(model="gpt-4o"),
+    allow_delegation=True,
+    verbose=True,
+)
+
+
+class Code(BaseModel):
+    code: str
+
+
+task = Task(
+    description="Give an answer to the coding question: {task}",
+    expected_output="A thorough answer to the coding question: {task}",
+    agent=code_helper_agent,
+    output_json=Code,
+)
+task2 = Task(
+    description="Find links to resources that can help with coding tasks. Use the serper tool to find resources that can help.",
+    expected_output="A list of links to resources that can help with coding tasks",
+    agent=link_finder_agent,
+)
+
+
+class Report(BaseModel):
+    code: str
+    links: List[str]
+
+
+task3 = Task(
+    description="Report the results of the tasks.",
+    expected_output="A report of the results of the tasks. this is the code produced and then the links to the resources that can help with the coding task.",
+    agent=reporter_agent,
+    output_json=Report,
+)
+# Use in CrewAI
+crew = Crew(
+    agents=[code_helper_agent, link_finder_agent, reporter_agent],
+    tasks=[task, task2, task3],
+    verbose=True,
+)
+
+result = crew.kickoff(
+    inputs={"task": "How do you implement an abstract class in python?"}
+)
+
+# Print raw result first
+print("Raw result:", result)
+
+# Handle result based on its type
+if hasattr(result, "json_dict") and result.json_dict:
+    json_result = result.json_dict
+    print("\nStructured JSON result:")
+    print(f"{json.dumps(json_result, indent=2)}")
+
+    # Access fields safely
+    if isinstance(json_result, dict):
+        if "code" in json_result:
+            print("\nCode:")
+            print(
+                json_result["code"][:200] + "..."
+                if len(json_result["code"]) > 200
+                else json_result["code"]
+            )
+
+        if "links" in json_result:
+            print("\nLinks:")
+            for link in json_result["links"][:5]:  # Print first 5 links
+                print(f"- {link}")
+            if len(json_result["links"]) > 5:
+                print(f"...and {len(json_result['links']) - 5} more links")
+elif hasattr(result, "pydantic") and result.pydantic:
+    print("\nPydantic model result:")
+    print(result.pydantic.model_dump_json(indent=2))
+else:
+    # Fallback to raw output
+    print("\nNo structured result available, using raw output:")
+    print(result.raw[:500] + "..." if len(result.raw) > 500 else result.raw)
+
+```

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

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
 ---

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:
 

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

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
 

docs/tools/jsonsearchtool.mdx

@@ -30,7 +30,7 @@ pip install 'crewai[tools]'
 Here are updated examples on how to utilize the JSONSearchTool effectively for searching within JSON files. These examples take into account the current implementation and usage patterns identified in the codebase.
 
 ```python Code
-from crewai.json_tools import JSONSearchTool  # Updated import path
+from crewai_tools import JSONSearchTool
 
 # General JSON content search
 # This approach is suitable when the JSON path is either known beforehand or can be dynamically identified.

docs/tools/langchaintool.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.

examples/mcp_sse_tool_example.py

@@ -0,0 +1,67 @@
+import logging
+import os
+import signal
+import sys
+import time
+
+from crewai.tools import MCPToolConnector, Tool
+
+
+def setup_logging():
+    """Set up logging configuration."""
+    logging.basicConfig(
+        level=logging.INFO,
+        format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+        handlers=[logging.StreamHandler()]
+    )
+
+
+def handle_exit(signum, frame):
+    """Handle exit signals gracefully."""
+    print("\nExiting...")
+    sys.exit(0)
+
+
+def main():
+    """Main function to demonstrate MCP SSE tool connection."""
+    setup_logging()
+    signal.signal(signal.SIGINT, handle_exit)
+    
+    print("CrewAI MCP SSE Tool Connection Example")
+    print("--------------------------------------")
+    print("This example connects tools to the MCP SSE server.")
+    print("Make sure you're logged in with 'crewai login' first.")
+    print("Press Ctrl+C to exit.")
+    print()
+    
+    def search(query: str) -> str:
+        """Search for information."""
+        return f"Searching for: {query}"
+    
+    search_tool = Tool(
+        name="search",
+        description="Search for information",
+        func=search
+    )
+    
+    tools = [search_tool]
+    
+    connector = MCPToolConnector(tools=tools)
+    
+    try:
+        print("Connecting to MCP SSE server...")
+        connector.connect()
+        print("Connected! Listening for tool events...")
+        
+        connector.listen()
+        
+    except KeyboardInterrupt:
+        print("\nExiting...")
+    except Exception as e:
+        print(f"Error: {str(e)}")
+    finally:
+        connector.close()
+
+
+if __name__ == "__main__":
+    main()

pyproject.toml

@@ -81,10 +81,10 @@ dev-dependencies = [
     "pillow>=10.2.0",
     "cairosvg>=2.7.1",
     "pytest>=8.0.0",
-    "pytest-vcr>=1.0.2",
     "python-dotenv>=1.0.0",
     "pytest-asyncio>=0.23.7",
     "pytest-subprocess>=1.5.2",
+    "pytest-recording>=0.13.2",
 ]
 
 [project.scripts]

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):
@@ -177,7 +185,7 @@ class Agent(BaseAgent):
         self,
         task: Task,
         context: Optional[str] = None,
-        tools: Optional[List[BaseTool]] = None,
+        tools: Optional[List[BaseTool]] = None
     ) -> str:
         """Execute a task with the agent.
 
@@ -188,6 +196,11 @@ class Agent(BaseAgent):
 
         Returns:
             Output of the agent
+
+        Raises:
+            TimeoutError: If execution exceeds the maximum execution time.
+            ValueError: If the max execution time is not a positive integer.
+            RuntimeError: If the agent execution fails for other reasons.
         """
         if self.tools_handler:
             self.tools_handler.last_used_tool = {}  # type: ignore # Incompatible types in assignment (expression has type "dict[Never, Never]", variable has type "ToolCalling")
@@ -229,22 +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)
@@ -264,14 +285,26 @@ class Agent(BaseAgent):
                     task=task,
                 ),
             )
-            result = self.agent_executor.invoke(
-                {
-                    "input": task_prompt,
-                    "tool_names": self.agent_executor.tools_names,
-                    "tools": self.agent_executor.tools_description,
-                    "ask_for_human_input": task.human_input,
-                }
-            )["output"]
+
+            # Determine execution method based on timeout setting
+            if self.max_execution_time is not None:
+                if not isinstance(self.max_execution_time, int) or self.max_execution_time <= 0:
+                    raise ValueError("Max Execution time must be a positive integer greater than zero")
+                result = self._execute_with_timeout(task_prompt, task, self.max_execution_time)
+            else:
+                result = self._execute_without_timeout(task_prompt, task)
+                
+        except TimeoutError as e:
+            # Propagate TimeoutError without retry
+            crewai_event_bus.emit(
+                self,
+                event=AgentExecutionErrorEvent(
+                    agent=self,
+                    task=task,
+                    error=str(e),
+                ),
+            )
+            raise e
         except Exception as e:
             if e.__class__.__module__.startswith("litellm"):
                 # Do not retry on litellm errors
@@ -312,6 +345,66 @@ class Agent(BaseAgent):
         )
         return result
 
+    def _execute_with_timeout(
+        self,
+        task_prompt: str,
+        task: Task,
+        timeout: int
+    ) -> str:
+        """Execute a task with a timeout.
+        
+        Args:
+            task_prompt: The prompt to send to the agent.
+            task: The task being executed.
+            timeout: Maximum execution time in seconds.
+            
+        Returns:
+            The output of the agent.
+            
+        Raises:
+            TimeoutError: If execution exceeds the timeout.
+            RuntimeError: If execution fails for other reasons.
+        """
+        import concurrent.futures
+        with concurrent.futures.ThreadPoolExecutor() as executor:
+            future = executor.submit(
+                self._execute_without_timeout,
+                task_prompt=task_prompt,
+                task=task
+            )
+            
+            try:
+                return future.result(timeout=timeout)
+            except concurrent.futures.TimeoutError:
+                future.cancel()
+                raise TimeoutError(f"Task '{task.description}' execution timed out after {timeout} seconds. Consider increasing max_execution_time or optimizing the task.")
+            except Exception as e:
+                future.cancel()
+                raise RuntimeError(f"Task execution failed: {str(e)}")
+
+    def _execute_without_timeout(
+        self,
+        task_prompt: str,
+        task: Task
+    ) -> str:
+        """Execute a task without a timeout.
+        
+        Args:
+            task_prompt: The prompt to send to the agent.
+            task: The task being executed.
+            
+        Returns:
+            The output of the agent.
+        """
+        return self.agent_executor.invoke(
+            {
+                "input": task_prompt,
+                "tool_names": self.agent_executor.tools_names,
+                "tools": self.agent_executor.tools_description,
+                "ask_for_human_input": task.human_input,
+            }
+        )["output"]
+
     def create_agent_executor(
         self, tools: Optional[List[BaseTool]] = None, task=None
     ) -> None:

src/crewai/agents/agent_adapters/base_agent_adapter.py

@@ -0,0 +1,42 @@
+from abc import ABC, abstractmethod
+from typing import Any, Dict, List, Optional
+
+from pydantic import PrivateAttr
+
+from crewai.agent import BaseAgent
+from crewai.tools import BaseTool
+
+
+class BaseAgentAdapter(BaseAgent, ABC):
+    """Base class for all agent adapters in CrewAI.
+
+    This abstract class defines the common interface and functionality that all
+    agent adapters must implement. It extends BaseAgent to maintain compatibility
+    with the CrewAI framework while adding adapter-specific requirements.
+    """
+
+    adapted_structured_output: bool = False
+    _agent_config: Optional[Dict[str, Any]] = PrivateAttr(default=None)
+
+    model_config = {"arbitrary_types_allowed": True}
+
+    def __init__(self, agent_config: Optional[Dict[str, Any]] = None, **kwargs: Any):
+        super().__init__(adapted_agent=True, **kwargs)
+        self._agent_config = agent_config
+
+    @abstractmethod
+    def configure_tools(self, tools: Optional[List[BaseTool]] = None) -> None:
+        """Configure and adapt tools for the specific agent implementation.
+
+        Args:
+            tools: Optional list of BaseTool instances to be configured
+        """
+        pass
+
+    def configure_structured_output(self, structured_output: Any) -> None:
+        """Configure the structured output for the specific agent implementation.
+
+        Args:
+            structured_output: The structured output to be configured
+        """
+        pass

src/crewai/agents/agent_adapters/base_converter_adapter.py

@@ -0,0 +1,29 @@
+from abc import ABC, abstractmethod
+
+
+class BaseConverterAdapter(ABC):
+    """Base class for all converter adapters in CrewAI.
+
+    This abstract class defines the common interface and functionality that all
+    converter adapters must implement for converting structured output.
+    """
+
+    def __init__(self, agent_adapter):
+        self.agent_adapter = agent_adapter
+
+    @abstractmethod
+    def configure_structured_output(self, task) -> None:
+        """Configure agents to return structured output.
+        Must support json and pydantic output.
+        """
+        pass
+
+    @abstractmethod
+    def enhance_system_prompt(self, base_prompt: str) -> str:
+        """Enhance the system prompt with structured output instructions."""
+        pass
+
+    @abstractmethod
+    def post_process_result(self, result: str) -> str:
+        """Post-process the result to ensure it matches the expected format: string."""
+        pass

src/crewai/agents/agent_adapters/base_tool_adapter.py

@@ -0,0 +1,37 @@
+from abc import ABC, abstractmethod
+from typing import Any, List, Optional
+
+from crewai.tools.base_tool import BaseTool
+
+
+class BaseToolAdapter(ABC):
+    """Base class for all tool adapters in CrewAI.
+
+    This abstract class defines the common interface that all tool adapters
+    must implement. It provides the structure for adapting CrewAI tools to
+    different frameworks and platforms.
+    """
+
+    original_tools: List[BaseTool]
+    converted_tools: List[Any]
+
+    def __init__(self, tools: Optional[List[BaseTool]] = None):
+        self.original_tools = tools or []
+        self.converted_tools = []
+
+    @abstractmethod
+    def configure_tools(self, tools: List[BaseTool]) -> None:
+        """Configure and convert tools for the specific implementation.
+
+        Args:
+            tools: List of BaseTool instances to be configured and converted
+        """
+        pass
+
+    def tools(self) -> List[Any]:
+        """Return all converted tools."""
+        return self.converted_tools
+
+    def sanitize_tool_name(self, tool_name: str) -> str:
+        """Sanitize tool name for API compatibility."""
+        return tool_name.replace(" ", "_")

src/crewai/agents/agent_adapters/langgraph/langgraph_adapter.py

@@ -0,0 +1,226 @@
+from typing import Any, AsyncIterable, Dict, List, Optional
+
+from pydantic import Field, PrivateAttr
+
+from crewai.agents.agent_adapters.base_agent_adapter import BaseAgentAdapter
+from crewai.agents.agent_adapters.langgraph.langgraph_tool_adapter import (
+    LangGraphToolAdapter,
+)
+from crewai.agents.agent_adapters.langgraph.structured_output_converter import (
+    LangGraphConverterAdapter,
+)
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.tools.agent_tools.agent_tools import AgentTools
+from crewai.tools.base_tool import BaseTool
+from crewai.utilities import Logger
+from crewai.utilities.converter import Converter
+from crewai.utilities.events import crewai_event_bus
+from crewai.utilities.events.agent_events import (
+    AgentExecutionCompletedEvent,
+    AgentExecutionErrorEvent,
+    AgentExecutionStartedEvent,
+)
+
+try:
+    from langchain_core.messages import ToolMessage
+    from langgraph.checkpoint.memory import MemorySaver
+    from langgraph.prebuilt import create_react_agent
+
+    LANGGRAPH_AVAILABLE = True
+except ImportError:
+    LANGGRAPH_AVAILABLE = False
+
+
+class LangGraphAgentAdapter(BaseAgentAdapter):
+    """Adapter for LangGraph agents to work with CrewAI."""
+
+    model_config = {"arbitrary_types_allowed": True}
+
+    _logger: Logger = PrivateAttr(default_factory=lambda: Logger())
+    _tool_adapter: LangGraphToolAdapter = PrivateAttr()
+    _graph: Any = PrivateAttr(default=None)
+    _memory: Any = PrivateAttr(default=None)
+    _max_iterations: int = PrivateAttr(default=10)
+    function_calling_llm: Any = Field(default=None)
+    step_callback: Any = Field(default=None)
+
+    model: str = Field(default="gpt-4o")
+    verbose: bool = Field(default=False)
+
+    def __init__(
+        self,
+        role: str,
+        goal: str,
+        backstory: str,
+        tools: Optional[List[BaseTool]] = None,
+        llm: Any = None,
+        max_iterations: int = 10,
+        agent_config: Optional[Dict[str, Any]] = None,
+        **kwargs,
+    ):
+        """Initialize the LangGraph agent adapter."""
+        if not LANGGRAPH_AVAILABLE:
+            raise ImportError(
+                "LangGraph Agent Dependencies are not installed. Please install it using `uv add langchain-core langgraph`"
+            )
+        super().__init__(
+            role=role,
+            goal=goal,
+            backstory=backstory,
+            tools=tools,
+            llm=llm or self.model,
+            agent_config=agent_config,
+            **kwargs,
+        )
+        self._tool_adapter = LangGraphToolAdapter(tools=tools)
+        self._converter_adapter = LangGraphConverterAdapter(self)
+        self._max_iterations = max_iterations
+        self._setup_graph()
+
+    def _setup_graph(self) -> None:
+        """Set up the LangGraph workflow graph."""
+        try:
+            self._memory = MemorySaver()
+
+            converted_tools: List[Any] = self._tool_adapter.tools()
+            if self._agent_config:
+                self._graph = create_react_agent(
+                    model=self.llm,
+                    tools=converted_tools,
+                    checkpointer=self._memory,
+                    debug=self.verbose,
+                    **self._agent_config,
+                )
+            else:
+                self._graph = create_react_agent(
+                    model=self.llm,
+                    tools=converted_tools or [],
+                    checkpointer=self._memory,
+                    debug=self.verbose,
+                )
+
+        except ImportError as e:
+            self._logger.log(
+                "error", f"Failed to import LangGraph dependencies: {str(e)}"
+            )
+            raise
+        except Exception as e:
+            self._logger.log("error", f"Error setting up LangGraph agent: {str(e)}")
+            raise
+
+    def _build_system_prompt(self) -> str:
+        """Build a system prompt for the LangGraph agent."""
+        base_prompt = f"""
+            You are {self.role}.
+        
+            Your goal is: {self.goal}
+
+            Your backstory: {self.backstory}
+
+            When working on tasks, think step-by-step and use the available tools when necessary.
+        """
+        return self._converter_adapter.enhance_system_prompt(base_prompt)
+
+    def execute_task(
+        self,
+        task: Any,
+        context: Optional[str] = None,
+        tools: Optional[List[BaseTool]] = None,
+    ) -> str:
+        """Execute a task using the LangGraph workflow."""
+        self.create_agent_executor(tools)
+
+        self.configure_structured_output(task)
+
+        try:
+            task_prompt = task.prompt() if hasattr(task, "prompt") else str(task)
+
+            if context:
+                task_prompt = self.i18n.slice("task_with_context").format(
+                    task=task_prompt, context=context
+                )
+
+            crewai_event_bus.emit(
+                self,
+                event=AgentExecutionStartedEvent(
+                    agent=self,
+                    tools=self.tools,
+                    task_prompt=task_prompt,
+                    task=task,
+                ),
+            )
+
+            session_id = f"task_{id(task)}"
+
+            config = {"configurable": {"thread_id": session_id}}
+
+            result = self._graph.invoke(
+                {
+                    "messages": [
+                        ("system", self._build_system_prompt()),
+                        ("user", task_prompt),
+                    ]
+                },
+                config,
+            )
+
+            messages = result.get("messages", [])
+            last_message = messages[-1] if messages else None
+
+            final_answer = ""
+            if isinstance(last_message, dict):
+                final_answer = last_message.get("content", "")
+            elif hasattr(last_message, "content"):
+                final_answer = getattr(last_message, "content", "")
+
+            final_answer = (
+                self._converter_adapter.post_process_result(final_answer)
+                or "Task execution completed but no clear answer was provided."
+            )
+            crewai_event_bus.emit(
+                self,
+                event=AgentExecutionCompletedEvent(
+                    agent=self, task=task, output=final_answer
+                ),
+            )
+
+            return final_answer
+
+        except Exception as e:
+            self._logger.log("error", f"Error executing LangGraph task: {str(e)}")
+            crewai_event_bus.emit(
+                self,
+                event=AgentExecutionErrorEvent(
+                    agent=self,
+                    task=task,
+                    error=str(e),
+                ),
+            )
+            raise
+
+    def create_agent_executor(self, tools: Optional[List[BaseTool]] = None) -> None:
+        """Configure the LangGraph agent for execution."""
+        self.configure_tools(tools)
+
+    def configure_tools(self, tools: Optional[List[BaseTool]] = None) -> None:
+        """Configure tools for the LangGraph agent."""
+        if tools:
+            all_tools = list(self.tools or []) + list(tools or [])
+            self._tool_adapter.configure_tools(all_tools)
+            available_tools = self._tool_adapter.tools()
+            self._graph.tools = available_tools
+
+    def get_delegation_tools(self, agents: List[BaseAgent]) -> List[BaseTool]:
+        """Implement delegation tools support for LangGraph."""
+        agent_tools = AgentTools(agents=agents)
+        return agent_tools.tools()
+
+    def get_output_converter(
+        self, llm: Any, text: str, model: Any, instructions: str
+    ) -> Any:
+        """Convert output format if needed."""
+        return Converter(llm=llm, text=text, model=model, instructions=instructions)
+
+    def configure_structured_output(self, task) -> None:
+        """Configure the structured output for LangGraph."""
+        self._converter_adapter.configure_structured_output(task)

src/crewai/agents/agent_adapters/langgraph/langgraph_tool_adapter.py

@@ -0,0 +1,61 @@
+import inspect
+from typing import Any, List, Optional
+
+from crewai.agents.agent_adapters.base_tool_adapter import BaseToolAdapter
+from crewai.tools.base_tool import BaseTool
+
+
+class LangGraphToolAdapter(BaseToolAdapter):
+    """Adapts CrewAI tools to LangGraph agent tool compatible format"""
+
+    def __init__(self, tools: Optional[List[BaseTool]] = None):
+        self.original_tools = tools or []
+        self.converted_tools = []
+
+    def configure_tools(self, tools: List[BaseTool]) -> None:
+        """
+        Configure and convert CrewAI tools to LangGraph-compatible format.
+        LangGraph expects tools in langchain_core.tools format.
+        """
+        from langchain_core.tools import BaseTool, StructuredTool
+
+        converted_tools = []
+        if self.original_tools:
+            all_tools = tools + self.original_tools
+        else:
+            all_tools = tools
+        for tool in all_tools:
+            if isinstance(tool, BaseTool):
+                converted_tools.append(tool)
+                continue
+
+            sanitized_name = self.sanitize_tool_name(tool.name)
+
+            async def tool_wrapper(*args, tool=tool, **kwargs):
+                output = None
+                if len(args) > 0 and isinstance(args[0], str):
+                    output = tool.run(args[0])
+                elif "input" in kwargs:
+                    output = tool.run(kwargs["input"])
+                else:
+                    output = tool.run(**kwargs)
+
+                if inspect.isawaitable(output):
+                    result = await output
+                else:
+                    result = output
+                return result
+
+            converted_tool = StructuredTool(
+                name=sanitized_name,
+                description=tool.description,
+                func=tool_wrapper,
+                args_schema=tool.args_schema,
+            )
+
+            converted_tools.append(converted_tool)
+
+        self.converted_tools = converted_tools
+
+    def tools(self) -> List[Any]:
+        return self.converted_tools or []

src/crewai/agents/agent_adapters/langgraph/structured_output_converter.py

@@ -0,0 +1,80 @@
+import json
+
+from crewai.agents.agent_adapters.base_converter_adapter import BaseConverterAdapter
+from crewai.utilities.converter import generate_model_description
+
+
+class LangGraphConverterAdapter(BaseConverterAdapter):
+    """Adapter for handling structured output conversion in LangGraph agents"""
+
+    def __init__(self, agent_adapter):
+        """Initialize the converter adapter with a reference to the agent adapter"""
+        self.agent_adapter = agent_adapter
+        self._output_format = None
+        self._schema = None
+        self._system_prompt_appendix = None
+
+    def configure_structured_output(self, task) -> None:
+        """Configure the structured output for LangGraph."""
+        if not (task.output_json or task.output_pydantic):
+            self._output_format = None
+            self._schema = None
+            self._system_prompt_appendix = None
+            return
+
+        if task.output_json:
+            self._output_format = "json"
+            self._schema = generate_model_description(task.output_json)
+        elif task.output_pydantic:
+            self._output_format = "pydantic"
+            self._schema = generate_model_description(task.output_pydantic)
+
+        self._system_prompt_appendix = self._generate_system_prompt_appendix()
+
+    def _generate_system_prompt_appendix(self) -> str:
+        """Generate an appendix for the system prompt to enforce structured output"""
+        if not self._output_format or not self._schema:
+            return ""
+
+        return f"""
+Important: Your final answer MUST be provided in the following structured format:
+
+{self._schema}
+
+DO NOT include any markdown code blocks, backticks, or other formatting around your response. 
+The output should be raw JSON that exactly matches the specified schema.
+"""
+
+    def enhance_system_prompt(self, original_prompt: str) -> str:
+        """Add structured output instructions to the system prompt if needed"""
+        if not self._system_prompt_appendix:
+            return original_prompt
+
+        return f"{original_prompt}\n{self._system_prompt_appendix}"
+
+    def post_process_result(self, result: str) -> str:
+        """Post-process the result to ensure it matches the expected format"""
+        if not self._output_format:
+            return result
+
+        # Try to extract valid JSON if it's wrapped in code blocks or other text
+        if self._output_format in ["json", "pydantic"]:
+            try:
+                # First, try to parse as is
+                json.loads(result)
+                return result
+            except json.JSONDecodeError:
+                # Try to extract JSON from the text
+                import re
+
+                json_match = re.search(r"(\{.*\})", result, re.DOTALL)
+                if json_match:
+                    try:
+                        extracted = json_match.group(1)
+                        # Validate it's proper JSON
+                        json.loads(extracted)
+                        return extracted
+                    except:
+                        pass
+
+        return result

src/crewai/agents/agent_adapters/openai_agents/openai_adapter.py

@@ -0,0 +1,178 @@
+from typing import Any, List, Optional
+
+from pydantic import Field, PrivateAttr
+
+from crewai.agents.agent_adapters.base_agent_adapter import BaseAgentAdapter
+from crewai.agents.agent_adapters.openai_agents.structured_output_converter import (
+    OpenAIConverterAdapter,
+)
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.tools import BaseTool
+from crewai.tools.agent_tools.agent_tools import AgentTools
+from crewai.utilities import Logger
+from crewai.utilities.events import crewai_event_bus
+from crewai.utilities.events.agent_events import (
+    AgentExecutionCompletedEvent,
+    AgentExecutionErrorEvent,
+    AgentExecutionStartedEvent,
+)
+
+try:
+    from agents import Agent as OpenAIAgent  # type: ignore
+    from agents import Runner, enable_verbose_stdout_logging  # type: ignore
+
+    from .openai_agent_tool_adapter import OpenAIAgentToolAdapter
+
+    OPENAI_AVAILABLE = True
+except ImportError:
+    OPENAI_AVAILABLE = False
+
+
+class OpenAIAgentAdapter(BaseAgentAdapter):
+    """Adapter for OpenAI Assistants"""
+
+    model_config = {"arbitrary_types_allowed": True}
+
+    _openai_agent: "OpenAIAgent" = PrivateAttr()
+    _logger: Logger = PrivateAttr(default_factory=lambda: Logger())
+    _active_thread: Optional[str] = PrivateAttr(default=None)
+    function_calling_llm: Any = Field(default=None)
+    step_callback: Any = Field(default=None)
+    _tool_adapter: "OpenAIAgentToolAdapter" = PrivateAttr()
+    _converter_adapter: OpenAIConverterAdapter = PrivateAttr()
+
+    def __init__(
+        self,
+        model: str = "gpt-4o-mini",
+        tools: Optional[List[BaseTool]] = None,
+        agent_config: Optional[dict] = None,
+        **kwargs,
+    ):
+        if not OPENAI_AVAILABLE:
+            raise ImportError(
+                "OpenAI Agent Dependencies are not installed. Please install it using `uv add openai-agents`"
+            )
+        else:
+            role = kwargs.pop("role", None)
+            goal = kwargs.pop("goal", None)
+            backstory = kwargs.pop("backstory", None)
+            super().__init__(
+                role=role,
+                goal=goal,
+                backstory=backstory,
+                tools=tools,
+                agent_config=agent_config,
+                **kwargs,
+            )
+            self._tool_adapter = OpenAIAgentToolAdapter(tools=tools)
+            self.llm = model
+            self._converter_adapter = OpenAIConverterAdapter(self)
+
+    def _build_system_prompt(self) -> str:
+        """Build a system prompt for the OpenAI agent."""
+        base_prompt = f"""
+            You are {self.role}.
+        
+            Your goal is: {self.goal}
+
+            Your backstory: {self.backstory}
+
+            When working on tasks, think step-by-step and use the available tools when necessary.
+        """
+        return self._converter_adapter.enhance_system_prompt(base_prompt)
+
+    def execute_task(
+        self,
+        task: Any,
+        context: Optional[str] = None,
+        tools: Optional[List[BaseTool]] = None,
+    ) -> str:
+        """Execute a task using the OpenAI Assistant"""
+        self._converter_adapter.configure_structured_output(task)
+        self.create_agent_executor(tools)
+
+        if self.verbose:
+            enable_verbose_stdout_logging()
+
+        try:
+            task_prompt = task.prompt()
+            if context:
+                task_prompt = self.i18n.slice("task_with_context").format(
+                    task=task_prompt, context=context
+                )
+            crewai_event_bus.emit(
+                self,
+                event=AgentExecutionStartedEvent(
+                    agent=self,
+                    tools=self.tools,
+                    task_prompt=task_prompt,
+                    task=task,
+                ),
+            )
+            result = self.agent_executor.run_sync(self._openai_agent, task_prompt)
+            final_answer = self.handle_execution_result(result)
+            crewai_event_bus.emit(
+                self,
+                event=AgentExecutionCompletedEvent(
+                    agent=self, task=task, output=final_answer
+                ),
+            )
+            return final_answer
+
+        except Exception as e:
+            self._logger.log("error", f"Error executing OpenAI task: {str(e)}")
+            crewai_event_bus.emit(
+                self,
+                event=AgentExecutionErrorEvent(
+                    agent=self,
+                    task=task,
+                    error=str(e),
+                ),
+            )
+            raise
+
+    def create_agent_executor(self, tools: Optional[List[BaseTool]] = None) -> None:
+        """
+        Configure the OpenAI agent for execution.
+        While OpenAI handles execution differently through Runner,
+        we can use this method to set up tools and configurations.
+        """
+        all_tools = list(self.tools or []) + list(tools or [])
+
+        instructions = self._build_system_prompt()
+        self._openai_agent = OpenAIAgent(
+            name=self.role,
+            instructions=instructions,
+            model=self.llm,
+            **self._agent_config or {},
+        )
+
+        if all_tools:
+            self.configure_tools(all_tools)
+
+        self.agent_executor = Runner
+
+    def configure_tools(self, tools: Optional[List[BaseTool]] = None) -> None:
+        """Configure tools for the OpenAI Assistant"""
+        if tools:
+            self._tool_adapter.configure_tools(tools)
+            if self._tool_adapter.converted_tools:
+                self._openai_agent.tools = self._tool_adapter.converted_tools
+
+    def handle_execution_result(self, result: Any) -> str:
+        """Process OpenAI Assistant execution result converting any structured output to a string"""
+        return self._converter_adapter.post_process_result(result.final_output)
+
+    def get_delegation_tools(self, agents: List[BaseAgent]) -> List[BaseTool]:
+        """Implement delegation tools support"""
+        agent_tools = AgentTools(agents=agents)
+        tools = agent_tools.tools()
+        return tools
+
+    def configure_structured_output(self, task) -> None:
+        """Configure the structured output for the specific agent implementation.
+
+        Args:
+            structured_output: The structured output to be configured
+        """
+        self._converter_adapter.configure_structured_output(task)

src/crewai/agents/agent_adapters/openai_agents/openai_agent_tool_adapter.py

@@ -0,0 +1,91 @@
+import inspect
+from typing import Any, List, Optional
+
+from agents import FunctionTool, Tool
+
+from crewai.agents.agent_adapters.base_tool_adapter import BaseToolAdapter
+from crewai.tools import BaseTool
+
+
+class OpenAIAgentToolAdapter(BaseToolAdapter):
+    """Adapter for OpenAI Assistant tools"""
+
+    def __init__(self, tools: Optional[List[BaseTool]] = None):
+        self.original_tools = tools or []
+
+    def configure_tools(self, tools: List[BaseTool]) -> None:
+        """Configure tools for the OpenAI Assistant"""
+        if self.original_tools:
+            all_tools = tools + self.original_tools
+        else:
+            all_tools = tools
+        if all_tools:
+            self.converted_tools = self._convert_tools_to_openai_format(all_tools)
+
+    def _convert_tools_to_openai_format(
+        self, tools: Optional[List[BaseTool]]
+    ) -> List[Tool]:
+        """Convert CrewAI tools to OpenAI Assistant tool format"""
+        if not tools:
+            return []
+
+        def sanitize_tool_name(name: str) -> str:
+            """Convert tool name to match OpenAI's required pattern"""
+            import re
+
+            sanitized = re.sub(r"[^a-zA-Z0-9_-]", "_", name).lower()
+            return sanitized
+
+        def create_tool_wrapper(tool: BaseTool):
+            """Create a wrapper function that handles the OpenAI function tool interface"""
+
+            async def wrapper(context_wrapper: Any, arguments: Any) -> Any:
+                # Get the parameter name from the schema
+                param_name = list(
+                    tool.args_schema.model_json_schema()["properties"].keys()
+                )[0]
+
+                # Handle different argument types
+                if isinstance(arguments, dict):
+                    args_dict = arguments
+                elif isinstance(arguments, str):
+                    try:
+                        import json
+
+                        args_dict = json.loads(arguments)
+                    except json.JSONDecodeError:
+                        args_dict = {param_name: arguments}
+                else:
+                    args_dict = {param_name: str(arguments)}
+
+                # Run the tool with the processed arguments
+                output = tool._run(**args_dict)
+
+                # Await if the tool returned a coroutine
+                if inspect.isawaitable(output):
+                    result = await output
+                else:
+                    result = output
+
+                # Ensure the result is JSON serializable
+                if isinstance(result, (dict, list, str, int, float, bool, type(None))):
+                    return result
+                return str(result)
+
+            return wrapper
+
+        openai_tools = []
+        for tool in tools:
+            schema = tool.args_schema.model_json_schema()
+
+            schema.update({"additionalProperties": False, "type": "object"})
+
+            openai_tool = FunctionTool(
+                name=sanitize_tool_name(tool.name),
+                description=tool.description,
+                params_json_schema=schema,
+                on_invoke_tool=create_tool_wrapper(tool),
+            )
+            openai_tools.append(openai_tool)
+
+        return openai_tools

src/crewai/agents/agent_adapters/openai_agents/structured_output_converter.py

@@ -0,0 +1,122 @@
+import json
+import re
+
+from crewai.agents.agent_adapters.base_converter_adapter import BaseConverterAdapter
+from crewai.utilities.converter import generate_model_description
+from crewai.utilities.i18n import I18N
+
+
+class OpenAIConverterAdapter(BaseConverterAdapter):
+    """
+    Adapter for handling structured output conversion in OpenAI agents.
+
+    This adapter enhances the OpenAI agent to handle structured output formats
+    and post-processes the results when needed.
+
+    Attributes:
+        _output_format: The expected output format (json, pydantic, or None)
+        _schema: The schema description for the expected output
+        _output_model: The Pydantic model for the output
+    """
+
+    def __init__(self, agent_adapter):
+        """Initialize the converter adapter with a reference to the agent adapter"""
+        self.agent_adapter = agent_adapter
+        self._output_format = None
+        self._schema = None
+        self._output_model = None
+
+    def configure_structured_output(self, task) -> None:
+        """
+        Configure the structured output for OpenAI agent based on task requirements.
+
+        Args:
+            task: The task containing output format requirements
+        """
+        # Reset configuration
+        self._output_format = None
+        self._schema = None
+        self._output_model = None
+
+        # If no structured output is required, return early
+        if not (task.output_json or task.output_pydantic):
+            return
+
+        # Configure based on task output format
+        if task.output_json:
+            self._output_format = "json"
+            self._schema = generate_model_description(task.output_json)
+            self.agent_adapter._openai_agent.output_type = task.output_json
+            self._output_model = task.output_json
+        elif task.output_pydantic:
+            self._output_format = "pydantic"
+            self._schema = generate_model_description(task.output_pydantic)
+            self.agent_adapter._openai_agent.output_type = task.output_pydantic
+            self._output_model = task.output_pydantic
+
+    def enhance_system_prompt(self, base_prompt: str) -> str:
+        """
+        Enhance the base system prompt with structured output requirements if needed.
+
+        Args:
+            base_prompt: The original system prompt
+
+        Returns:
+            Enhanced system prompt with output format instructions if needed
+        """
+        if not self._output_format:
+            return base_prompt
+
+        output_schema = (
+            I18N()
+            .slice("formatted_task_instructions")
+            .format(output_format=self._schema)
+        )
+
+        return f"{base_prompt}\n\n{output_schema}"
+
+    def post_process_result(self, result: str) -> str:
+        """
+        Post-process the result to ensure it matches the expected format.
+
+        This method attempts to extract valid JSON from the result if necessary.
+
+        Args:
+            result: The raw result from the agent
+
+        Returns:
+            Processed result conforming to the expected output format
+        """
+        if not self._output_format:
+            return result
+        # Try to extract valid JSON if it's wrapped in code blocks or other text
+        if isinstance(result, str) and self._output_format in ["json", "pydantic"]:
+            # First, try to parse as is
+            try:
+                json.loads(result)
+                return result
+            except json.JSONDecodeError:
+                # Try to extract JSON from markdown code blocks
+                code_block_pattern = r"```(?:json)?\s*([\s\S]*?)```"
+                code_blocks = re.findall(code_block_pattern, result)
+
+                for block in code_blocks:
+                    try:
+                        json.loads(block.strip())
+                        return block.strip()
+                    except json.JSONDecodeError:
+                        continue
+
+                # Try to extract any JSON-like structure
+                json_pattern = r"(\{[\s\S]*\})"
+                json_matches = re.findall(json_pattern, result, re.DOTALL)
+
+                for match in json_matches:
+                    try:
+                        json.loads(match)
+                        return match
+                    except json.JSONDecodeError:
+                        continue
+
+        # If all extraction attempts fail, return the original
+        return str(result)

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
@@ -62,8 +63,6 @@ class BaseAgent(ABC, BaseModel):
             Abstract method to execute a task.
         create_agent_executor(tools=None) -> None:
             Abstract method to create an agent executor.
-        _parse_tools(tools: List[BaseTool]) -> List[Any]:
-            Abstract method to parse tools.
         get_delegation_tools(agents: List["BaseAgent"]):
             Abstract method to set the agents task tools for handling delegation and question asking to other agents in crew.
         get_output_converter(llm, model, instructions):
@@ -154,6 +153,13 @@ class BaseAgent(ABC, BaseModel):
     callbacks: List[Callable] = Field(
         default=[], description="Callbacks to be used for the agent"
     )
+    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
@@ -170,15 +176,15 @@ class BaseAgent(ABC, BaseModel):
         tool meets these criteria, it is processed and added to the list of
         tools. Otherwise, a ValueError is raised.
         """
+        if not tools:
+            return []
+
         processed_tools = []
+        required_attrs = ["name", "func", "description"]
         for tool in tools:
             if isinstance(tool, BaseTool):
                 processed_tools.append(tool)
-            elif (
-                hasattr(tool, "name")
-                and hasattr(tool, "func")
-                and hasattr(tool, "description")
-            ):
+            elif all(hasattr(tool, attr) for attr in required_attrs):
                 # Tool has the required attributes, create a Tool instance
                 processed_tools.append(Tool.from_langchain(tool))
             else:
@@ -260,13 +266,6 @@ class BaseAgent(ABC, BaseModel):
         """Set the task tools that init BaseAgenTools class."""
         pass
 
-    @abstractmethod
-    def get_output_converter(
-        self, llm: Any, text: str, model: type[BaseModel] | None, instructions: str
-    ) -> Converter:
-        """Get the converter class for the agent to create json/pydantic outputs."""
-        pass
-
     def copy(self: T) -> T:  # type: ignore # Signature of "copy" incompatible with supertype "BaseModel"
         """Create a deep copy of the Agent."""
         exclude = {

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",

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

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)
 
@@ -1403,7 +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"),
         }
 

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
 

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",
+    )

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

src/crewai/llm.py

@@ -4,9 +4,12 @@ import os
 import sys
 import threading
 import warnings
+from collections import defaultdict
 from contextlib import contextmanager
+from types import SimpleNamespace
 from typing import (
     Any,
+    DefaultDict,
     Dict,
     List,
     Literal,
@@ -18,7 +21,8 @@ from typing import (
 )
 
 from dotenv import load_dotenv
-from pydantic import BaseModel
+from litellm.types.utils import ChatCompletionDeltaToolCall
+from pydantic import BaseModel, Field
 
 from crewai.utilities.events.llm_events import (
     LLMCallCompletedEvent,
@@ -33,6 +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,
     )
@@ -77,14 +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
@@ -219,6 +236,15 @@ class StreamingChoices(TypedDict):
     finish_reason: Optional[str]
 
 
+class FunctionArgs(BaseModel):
+    name: str = ""
+    arguments: str = ""
+
+
+class AccumulatedToolArgs(BaseModel):
+    function: FunctionArgs = Field(default_factory=FunctionArgs)
+
+
 class LLM(BaseLLM):
     def __init__(
         self,
@@ -371,6 +397,11 @@ class LLM(BaseLLM):
         last_chunk = None
         chunk_count = 0
         usage_info = None
+        tool_calls = None
+
+        accumulated_tool_args: DefaultDict[int, AccumulatedToolArgs] = defaultdict(
+            AccumulatedToolArgs
+        )
 
         # --- 2) Make sure stream is set to True and include usage metrics
         params["stream"] = True
@@ -428,6 +459,20 @@ class LLM(BaseLLM):
                             if chunk_content is None and isinstance(delta, dict):
                                 # Some models might send empty content chunks
                                 chunk_content = ""
+
+                            # Enable tool calls using streaming
+                            if "tool_calls" in delta:
+                                tool_calls = delta["tool_calls"]
+
+                                if tool_calls:
+                                    result = self._handle_streaming_tool_calls(
+                                        tool_calls=tool_calls,
+                                        accumulated_tool_args=accumulated_tool_args,
+                                        available_functions=available_functions,
+                                    )
+                                    if result is not None:
+                                        chunk_content = result
+
                 except Exception as e:
                     logging.debug(f"Error extracting content from chunk: {e}")
                     logging.debug(f"Chunk format: {type(chunk)}, content: {chunk}")
@@ -442,7 +487,6 @@ class LLM(BaseLLM):
                         self,
                         event=LLMStreamChunkEvent(chunk=chunk_content),
                     )
-
             # --- 4) Fallback to non-streaming if no content received
             if not full_response.strip() and chunk_count == 0:
                 logging.warning(
@@ -501,7 +545,7 @@ class LLM(BaseLLM):
                         )
 
             # --- 6) If still empty, raise an error instead of using a default response
-            if not full_response.strip():
+            if not full_response.strip() and len(accumulated_tool_args) == 0:
                 raise Exception(
                     "No content received from streaming response. Received empty chunks or failed to extract content."
                 )
@@ -533,8 +577,8 @@ class LLM(BaseLLM):
                                 tool_calls = getattr(message, "tool_calls")
             except Exception as e:
                 logging.debug(f"Error checking for tool calls: {e}")
-
             # --- 8) If no tool calls or no available functions, return the text response directly
+
             if not tool_calls or not available_functions:
                 # Log token usage if available in streaming mode
                 self._handle_streaming_callbacks(callbacks, usage_info, last_chunk)
@@ -554,6 +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():
@@ -568,6 +617,47 @@ class LLM(BaseLLM):
             )
             raise Exception(f"Failed to get streaming response: {str(e)}")
 
+    def _handle_streaming_tool_calls(
+        self,
+        tool_calls: List[ChatCompletionDeltaToolCall],
+        accumulated_tool_args: DefaultDict[int, AccumulatedToolArgs],
+        available_functions: Optional[Dict[str, Any]] = None,
+    ) -> None | str:
+        for tool_call in tool_calls:
+            current_tool_accumulator = accumulated_tool_args[tool_call.index]
+
+            if tool_call.function.name:
+                current_tool_accumulator.function.name = tool_call.function.name
+
+            if tool_call.function.arguments:
+                current_tool_accumulator.function.arguments += (
+                    tool_call.function.arguments
+                )
+
+            crewai_event_bus.emit(
+                self,
+                event=LLMStreamChunkEvent(
+                    tool_call=tool_call.to_dict(),
+                    chunk=tool_call.function.arguments,
+                ),
+            )
+
+            if (
+                current_tool_accumulator.function.name
+                and current_tool_accumulator.function.arguments
+                and available_functions
+            ):
+                try:
+                    json.loads(current_tool_accumulator.function.arguments)
+
+                    return self._handle_tool_call(
+                        [current_tool_accumulator],
+                        available_functions,
+                    )
+                except json.JSONDecodeError:
+                    continue
+        return None
+
     def _handle_streaming_callbacks(
         self,
         callbacks: Optional[List[Any]],
@@ -627,7 +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)[
@@ -786,15 +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):

src/crewai/tools/__init__.py

@@ -1 +1,15 @@
 from .base_tool import BaseTool, tool
+
+__all__ = [
+    "BaseTool",
+    "tool",
+]
+
+from .base_tool import Tool, to_langchain
+from .mcp_connector import MCPToolConnector
+
+__all__ += [
+    "Tool",
+    "to_langchain",
+    "MCPToolConnector",
+]

src/crewai/tools/mcp_connector.py

@@ -0,0 +1,115 @@
+import logging
+from typing import Any, Callable, Dict, List, Mapping, Optional, Union
+
+from crewai.cli.authentication.utils import TokenManager
+from crewai.tools import BaseTool
+from crewai.utilities.sse_client import SSEClient
+
+
+class MCPToolConnector:
+    """Connects tools to the Management Control Plane (MCP) via SSE."""
+
+    MCP_BASE_URL = "https://app.crewai.com"
+    SSE_ENDPOINT = "/api/v1/tools/events"
+    
+    def __init__(
+        self, 
+        tools: Optional[List[BaseTool]] = None,
+        timeout: int = 30
+    ):
+        """Initialize the MCP Tool Connector.
+        
+        Args:
+            tools: List of tools to connect to the MCP.
+            timeout: Connection timeout in seconds.
+        """
+        self.tools = tools or []
+        self.timeout = timeout
+        self.logger = logging.getLogger(__name__)
+        self.token_manager = TokenManager()
+        self._sse_client: Optional[SSEClient] = None
+
+    def connect(self) -> None:
+        """Connect to the MCP SSE server for tools."""
+        token = self.token_manager.get_token()
+        if not token:
+            self.logger.error("Authentication token not found. Please log in first.")
+            raise ValueError("Authentication token not found. Please log in first.")
+        
+        headers = {
+            "Authorization": f"Bearer {token}",
+            "Accept": "text/event-stream",
+            "Cache-Control": "no-cache",
+            "X-Requested-With": "XMLHttpRequest",
+        }
+        
+        tool_data = {}
+        for tool in self.tools:
+            tool_data[tool.name] = {
+                "name": tool.name,
+                "description": tool.description,
+                "schema": tool.args_schema.model_json_schema() if hasattr(tool.args_schema, "model_json_schema") else {},
+            }
+            
+        
+        self._sse_client = SSEClient(
+            base_url=self.MCP_BASE_URL,
+            endpoint=self.SSE_ENDPOINT,
+            headers=headers,
+            timeout=self.timeout
+        )
+        
+        try:
+            if self._sse_client is not None:
+                self._sse_client.connect()
+        except Exception as e:
+            self.logger.error(f"Failed to connect to MCP SSE server: {str(e)}")
+            raise
+
+    def listen(self) -> None:
+        """Listen for tool events from the MCP SSE server."""
+        if not self._sse_client:
+            self.connect()
+            
+        event_handlers = {
+            "tool_request": self._handle_tool_request,
+            "connection_closed": self._handle_connection_closed,
+        }
+        
+        try:
+            if self._sse_client is not None:
+                self._sse_client.listen(event_handlers)
+            else:
+                self.logger.error("SSE client is not initialized")
+                raise ValueError("SSE client is not initialized")
+        except Exception as e:
+            self.logger.error(f"Error listening to MCP SSE events: {str(e)}")
+            raise
+
+    def _handle_tool_request(self, data: Dict[str, Any]) -> None:
+        """Handle a tool request event from the MCP SSE server."""
+        try:
+            tool_name = data.get("tool_name")
+            arguments = data.get("arguments", {})
+            request_id = data.get("request_id")
+            
+            tool = next((t for t in self.tools if t.name == tool_name), None)
+            if not tool:
+                self.logger.error(f"Tool '{tool_name}' not found")
+                return
+                
+            result = tool.run(**arguments)
+            
+            
+        except Exception as e:
+            self.logger.error(f"Error handling tool request: {str(e)}")
+
+    def _handle_connection_closed(self, data: Any) -> None:
+        """Handle a connection closed event from the MCP SSE server."""
+        self.logger.info("MCP SSE connection closed")
+
+    def close(self) -> None:
+        """Close the MCP SSE connection."""
+        if self._sse_client:
+            self._sse_client.close()
+            self._sse_client = None

src/crewai/utilities/converter.py

@@ -216,7 +216,7 @@ def convert_with_instructions(
 
 def get_conversion_instructions(model: Type[BaseModel], llm: Any) -> str:
     instructions = "Please convert the following text into valid JSON."
-    if llm.supports_function_calling():
+    if llm and not isinstance(llm, str) and llm.supports_function_calling():
         model_schema = PydanticSchemaParser(model=model).get_schema()
         instructions += (
             f"\n\nOutput ONLY the valid JSON and nothing else.\n\n"

src/crewai/utilities/events/llm_events.py

@@ -1,6 +1,8 @@
 from enum import Enum
 from typing import Any, Dict, List, Optional, Union
 
+from pydantic import BaseModel
+
 from crewai.utilities.events.base_events import BaseEvent
 
 
@@ -41,8 +43,21 @@ class LLMCallFailedEvent(BaseEvent):
     type: str = "llm_call_failed"
 
 
+class FunctionCall(BaseModel):
+    arguments: str
+    name: Optional[str] = None
+
+
+class ToolCall(BaseModel):
+    id: Optional[str] = None
+    function: FunctionCall
+    type: Optional[str] = None
+    index: int
+
+
 class LLMStreamChunkEvent(BaseEvent):
     """Event emitted when a streaming chunk is received"""
 
     type: str = "llm_stream_chunk"
     chunk: str
+    tool_call: Optional[ToolCall] = None

src/crewai/utilities/sse_client.py

@@ -0,0 +1,152 @@
+import json
+import logging
+from typing import Any, Callable, Dict, Mapping, Optional, Union
+from urllib.parse import urljoin
+
+import requests
+import sseclient
+
+from crewai.utilities.events import crewai_event_bus
+from crewai.utilities.events.base_events import BaseEvent
+
+
+class SSEConnectionStartedEvent(BaseEvent):
+    """Event emitted when an SSE connection is started"""
+    type: str = "sse_connection_started"
+    endpoint: str
+    headers: Dict[str, str]
+
+
+class SSEConnectionErrorEvent(BaseEvent):
+    """Event emitted when an SSE connection encounters an error"""
+    type: str = "sse_connection_error"
+    endpoint: str
+    error: str
+
+
+class SSEMessageReceivedEvent(BaseEvent):
+    """Event emitted when an SSE message is received"""
+    type: str = "sse_message_received"
+    endpoint: str
+    event: str
+    data: Any
+
+
+class SSEClient:
+    """Client for connecting to Server-Sent Events (SSE) endpoints"""
+
+    def __init__(
+        self,
+        base_url: str,
+        endpoint: str = "",
+        headers: Optional[Dict[str, str]] = None,
+        timeout: int = 30,
+    ):
+        """Initialize the SSE client.
+        
+        Args:
+            base_url: Base URL for the SSE server.
+            endpoint: Endpoint path to connect to (will be joined with base_url).
+            headers: Headers to include in the SSE request.
+            timeout: Connection timeout in seconds.
+        """
+        self.base_url = base_url
+        self.endpoint = endpoint
+        self.headers = headers or {}
+        self.timeout = timeout
+        self.logger = logging.getLogger(__name__)
+        self._client: Optional[sseclient.SSEClient] = None
+        self._response: Optional[requests.Response] = None
+
+    def connect(self) -> None:
+        """Establish a connection to the SSE server."""
+        try:
+            url = urljoin(self.base_url, self.endpoint)
+            self.logger.info(f"Connecting to SSE server at {url}")
+            
+            crewai_event_bus.emit(
+                self,
+                event=SSEConnectionStartedEvent(
+                    endpoint=url,
+                    headers=self.headers
+                )
+            )
+            
+            self._response = requests.get(
+                url,
+                headers=self.headers,
+                stream=True,
+                timeout=self.timeout
+            )
+            if self._response is not None:
+                self._response.raise_for_status()
+                self._client = sseclient.SSEClient(self._response)
+            
+        except Exception as e:
+            self.logger.error(f"Error connecting to SSE server: {str(e)}")
+            crewai_event_bus.emit(
+                self,
+                event=SSEConnectionErrorEvent(
+                    endpoint=urljoin(self.base_url, self.endpoint),
+                    error=str(e)
+                )
+            )
+            raise
+
+    def listen(self, event_handlers: Optional[Mapping[str, Callable[[Any], None]]] = None) -> None:
+        """Listen for SSE events and process them with registered handlers.
+        
+        Args:
+            event_handlers: Dictionary mapping event types to handler functions.
+        """
+        if self._client is None:
+            self.connect()
+        
+        event_handlers = event_handlers or {}
+        
+        try:
+            if self._client is None:
+                self.logger.error("SSE client is not initialized")
+                return
+                
+            for event in self._client:
+                event_type = event.event or "message"
+                data = None
+                
+                try:
+                    data = json.loads(event.data)
+                except (json.JSONDecodeError, TypeError):
+                    data = event.data
+                
+                crewai_event_bus.emit(
+                    self,
+                    event=SSEMessageReceivedEvent(
+                        endpoint=urljoin(self.base_url, self.endpoint),
+                        event=event_type,
+                        data=data
+                    )
+                )
+                
+                handler = event_handlers.get(event_type)
+                if handler:
+                    handler(data)
+                    
+        except Exception as e:
+            self.logger.error(f"Error processing SSE events: {str(e)}")
+            crewai_event_bus.emit(
+                self,
+                event=SSEConnectionErrorEvent(
+                    endpoint=urljoin(self.base_url, self.endpoint),
+                    error=str(e)
+                )
+            )
+            raise
+        finally:
+            self.close()
+
+    def close(self) -> None:
+        """Close the SSE connection."""
+        if self._response:
+            self._response.close()
+            self._response = None
+            self._client = None

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."

tests/agents/agent_adapters/test_base_agent_adapter.py

@@ -0,0 +1,113 @@
+from typing import Any, Dict, List, Optional
+
+import pytest
+from pydantic import BaseModel
+
+from crewai.agent import BaseAgent
+from crewai.agents.agent_adapters.base_agent_adapter import BaseAgentAdapter
+from crewai.tools import BaseTool
+from crewai.utilities.token_counter_callback import TokenProcess
+
+
+# Concrete implementation for testing
+class ConcreteAgentAdapter(BaseAgentAdapter):
+    def configure_tools(
+        self, tools: Optional[List[BaseTool]] = None, **kwargs: Any
+    ) -> None:
+        # Simple implementation for testing
+        self.tools = tools or []
+
+    def execute_task(
+        self,
+        task: Any,
+        context: Optional[str] = None,
+        tools: Optional[List[Any]] = None,
+    ) -> str:
+        # Dummy implementation needed due to BaseAgent inheritance
+        return "Task executed"
+
+    def create_agent_executor(self, tools: Optional[List[BaseTool]] = None) -> Any:
+        # Dummy implementation
+        return None
+
+    def get_delegation_tools(
+        self, tools: List[BaseTool], tool_map: Optional[Dict[str, BaseTool]]
+    ) -> List[BaseTool]:
+        # Dummy implementation
+        return []
+
+    def _parse_output(self, agent_output: Any, token_process: TokenProcess):
+        # Dummy implementation
+        pass
+
+    def get_output_converter(self, tools: Optional[List[BaseTool]] = None) -> Any:
+        # Dummy implementation
+        return None
+
+
+def test_base_agent_adapter_initialization():
+    """Test initialization of the concrete agent adapter."""
+    adapter = ConcreteAgentAdapter(
+        role="test role", goal="test goal", backstory="test backstory"
+    )
+    assert isinstance(adapter, BaseAgent)
+    assert isinstance(adapter, BaseAgentAdapter)
+    assert adapter.role == "test role"
+    assert adapter._agent_config is None
+    assert adapter.adapted_structured_output is False
+
+
+def test_base_agent_adapter_initialization_with_config():
+    """Test initialization with agent_config."""
+    config = {"model": "gpt-4"}
+    adapter = ConcreteAgentAdapter(
+        agent_config=config,
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+    )
+    assert adapter._agent_config == config
+
+
+def test_configure_tools_method_exists():
+    """Test that configure_tools method exists and can be called."""
+    adapter = ConcreteAgentAdapter(
+        role="test role", goal="test goal", backstory="test backstory"
+    )
+    # Create dummy tools if needed, or pass None
+    tools = []
+    adapter.configure_tools(tools)
+    assert hasattr(adapter, "tools")
+    assert adapter.tools == tools
+
+
+def test_configure_structured_output_method_exists():
+    """Test that configure_structured_output method exists and can be called."""
+    adapter = ConcreteAgentAdapter(
+        role="test role", goal="test goal", backstory="test backstory"
+    )
+
+    # Define a dummy structure or pass None/Any
+    class DummyOutput(BaseModel):
+        data: str
+
+    structured_output = DummyOutput
+    adapter.configure_structured_output(structured_output)
+    # Add assertions here if configure_structured_output modifies state
+    # For now, just ensuring it runs without error is sufficient
+    pass
+
+
+def test_base_agent_adapter_inherits_base_agent():
+    """Test that BaseAgentAdapter inherits from BaseAgent."""
+    assert issubclass(BaseAgentAdapter, BaseAgent)
+
+
+class ConcreteAgentAdapterWithoutRequiredMethods(BaseAgentAdapter):
+    pass
+
+
+def test_base_agent_adapter_fails_without_required_methods():
+    """Test that BaseAgentAdapter fails without required methods."""
+    with pytest.raises(TypeError):
+        ConcreteAgentAdapterWithoutRequiredMethods()  # type: ignore

tests/agents/agent_adapters/test_base_tool_adapter.py

@@ -0,0 +1,94 @@
+from typing import Any, List
+from unittest.mock import Mock
+
+import pytest
+
+from crewai.agents.agent_adapters.base_tool_adapter import BaseToolAdapter
+from crewai.tools.base_tool import BaseTool
+
+
+class ConcreteToolAdapter(BaseToolAdapter):
+    def configure_tools(self, tools: List[BaseTool]) -> None:
+        self.converted_tools = [f"converted_{tool.name}" for tool in tools]
+
+
+@pytest.fixture
+def mock_tool_1():
+    tool = Mock(spec=BaseTool)
+    tool.name = "Mock Tool 1"
+    return tool
+
+
+@pytest.fixture
+def mock_tool_2():
+    tool = Mock(spec=BaseTool)
+    tool.name = "MockTool2"
+    return tool
+
+
+@pytest.fixture
+def tools_list(mock_tool_1, mock_tool_2):
+    return [mock_tool_1, mock_tool_2]
+
+
+def test_initialization_with_tools(tools_list):
+    adapter = ConcreteToolAdapter(tools=tools_list)
+    assert adapter.original_tools == tools_list
+    assert adapter.converted_tools == []  # Conversion happens in configure_tools
+
+
+def test_initialization_without_tools():
+    adapter = ConcreteToolAdapter()
+    assert adapter.original_tools == []
+    assert adapter.converted_tools == []
+
+
+def test_configure_tools(tools_list):
+    adapter = ConcreteToolAdapter()
+    adapter.configure_tools(tools_list)
+    assert adapter.converted_tools == ["converted_Mock Tool 1", "converted_MockTool2"]
+    assert adapter.original_tools == []  # original_tools is only set in init
+
+    adapter_with_init_tools = ConcreteToolAdapter(tools=tools_list)
+    adapter_with_init_tools.configure_tools(tools_list)
+    assert adapter_with_init_tools.converted_tools == [
+        "converted_Mock Tool 1",
+        "converted_MockTool2",
+    ]
+    assert adapter_with_init_tools.original_tools == tools_list
+
+
+def test_tools_method(tools_list):
+    adapter = ConcreteToolAdapter()
+    adapter.configure_tools(tools_list)
+    assert adapter.tools() == ["converted_Mock Tool 1", "converted_MockTool2"]
+
+
+def test_tools_method_empty():
+    adapter = ConcreteToolAdapter()
+    assert adapter.tools() == []
+
+
+def test_sanitize_tool_name_with_spaces():
+    adapter = ConcreteToolAdapter()
+    assert adapter.sanitize_tool_name("Tool With Spaces") == "Tool_With_Spaces"
+
+
+def test_sanitize_tool_name_without_spaces():
+    adapter = ConcreteToolAdapter()
+    assert adapter.sanitize_tool_name("ToolWithoutSpaces") == "ToolWithoutSpaces"
+
+
+def test_sanitize_tool_name_empty():
+    adapter = ConcreteToolAdapter()
+    assert adapter.sanitize_tool_name("") == ""
+
+
+class ConcreteToolAdapterWithoutRequiredMethods(BaseToolAdapter):
+    pass
+
+
+def test_tool_adapted_fails_without_required_methods():
+    """Test that BaseToolAdapter fails without required methods."""
+    with pytest.raises(TypeError):
+        ConcreteToolAdapterWithoutRequiredMethods()  # type: ignore

tests/agents/agent_builder/base_agent_test.py

@@ -18,9 +18,6 @@ class MockAgent(BaseAgent):
 
     def create_agent_executor(self, tools=None) -> None: ...
 
-    def _parse_tools(self, tools: List[BaseTool]) -> List[BaseTool]:
-        return []
-
     def get_delegation_tools(self, agents: List["BaseAgent"]): ...
 
     def get_output_converter(

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

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

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

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

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

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

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

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

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

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

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

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

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