Fix result_as_answer handling in ToolUsage class

Co-Authored-By: Joe Moura <joao@crewai.com>
Fix tool_utils to pass original_tools to ToolUsage
2025-12-17 21:08:29 +00:00 · 2025-04-22 16:54:28 +00:00 · 2025-04-22 16:49:23 +00:00 · 2025-04-22 16:47:28 +00:00 · 2025-04-22 16:43:01 +00:00 · 2025-04-22 16:41:42 +00:00
26 changed files with 1970 additions and 178 deletions
--- a/docs/changelog.mdx
+++ b/docs/changelog.mdx
@@ -4,6 +4,36 @@ description: View the latest updates and changes to CrewAI
 icon: timeline
 ---

+<Update label="2025-04-07" description="v0.114.0">
+  ## Release Highlights
+  <Frame>
+    <img src="/images/v01140.png" />
+  </Frame>
+
+  **New Features & Enhancements**
+  - Agents as an atomic unit. (`Agent(...).kickoff()`)
+  - Support for [Custom LLM implementations](https://docs.crewai.com/guides/advanced/custom-llm).
+  - Integrated External Memory and [Opik observability](https://docs.crewai.com/how-to/opik-observability).
+  - Enhanced YAML extraction.
+  - Multimodal agent validation.
+  - Added Secure fingerprints for agents and crews.
+
+  **Core Improvements & Fixes**
+  - Improved serialization, agent copying, and Python compatibility.
+  - Added wildcard support to `emit()`
+  - Added support for additional router calls and context window adjustments.
+  - Fixed typing issues, validation, and import statements.
+  - Improved method performance.
+  - Enhanced agent task handling, event emissions, and memory management.
+  - Fixed CLI issues, conditional tasks, cloning behavior, and tool outputs.
+
+  **Documentation & Guides**
+  - Improved documentation structure, theme, and organization.
+  - Added guides for Local NVIDIA NIM with WSL2, W&B Weave, and Arize Phoenix.
+  - Updated tool configuration examples, prompts, and observability docs.
+  - Guide on using singular agents within Flows.
+</Update>
+
 <Update label="2025-03-17" description="v0.108.0">
  **Features**
  - Converted tabs to spaces in `crew.py` template
--- a/docs/concepts/knowledge.mdx
+++ b/docs/concepts/knowledge.mdx
@@ -42,6 +42,16 @@ CrewAI supports various types of knowledge sources out of the box:
 | `collection_name`          | **str**                              | No       | Name of the collection where the knowledge will be stored. Used to identify different sets of knowledge. Defaults to "knowledge" if not provided.     |
 | `storage`                  | **Optional[KnowledgeStorage]**       | No       | Custom storage configuration for managing how the knowledge is stored and retrieved. If not provided, a default storage will be created.              |

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

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

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

 Here are examples of how to use different types of knowledge sources:
--- a/docs/concepts/llamaindex-tools.mdx
+++ b/docs/concepts/llamaindex-tools.mdx
@@ -1,71 +0,0 @@
---
-title: Using LlamaIndex Tools
-description: Learn how to integrate LlamaIndex tools with CrewAI agents to enhance search-based queries and more.
-icon: toolbox
---
-
-## Using LlamaIndex Tools
-
-<Info>
-    CrewAI seamlessly integrates with LlamaIndex’s comprehensive toolkit for RAG (Retrieval-Augmented Generation) and agentic pipelines, enabling advanced search-based queries and more. 
-</Info>
-
-Here are the available built-in tools offered by LlamaIndex.
-
-```python Code
-from crewai import Agent
-from crewai_tools import LlamaIndexTool
-
-# Example 1: Initialize from FunctionTool
-from llama_index.core.tools import FunctionTool
-
-your_python_function = lambda ...: ...
-og_tool = FunctionTool.from_defaults(
-    your_python_function, 
-    name="<name>", 
-    description='<description>'
-)
-tool = LlamaIndexTool.from_tool(og_tool)
-
-# Example 2: Initialize from LlamaHub Tools
-from llama_index.tools.wolfram_alpha import WolframAlphaToolSpec
-wolfram_spec = WolframAlphaToolSpec(app_id="<app_id>")
-wolfram_tools = wolfram_spec.to_tool_list()
-tools = [LlamaIndexTool.from_tool(t) for t in wolfram_tools]
-
-# Example 3: Initialize Tool from a LlamaIndex Query Engine
-query_engine = index.as_query_engine()
-query_tool = LlamaIndexTool.from_query_engine(
-    query_engine,
-    name="Uber 2019 10K Query Tool",
-    description="Use this tool to lookup the 2019 Uber 10K Annual Report"
-)
-
-# Create and assign the tools to an agent
-agent = Agent(
-    role='Research Analyst',
-    goal='Provide up-to-date market analysis',
-    backstory='An expert analyst with a keen eye for market trends.',
-    tools=[tool, *tools, query_tool]
-)
-
-# rest of the code ...
-```
-
-## Steps to Get Started
-
-To effectively use the LlamaIndexTool, follow these steps:
-
-<Steps>
-    <Step title="Package Installation">
-    Make sure that `crewai[tools]` package is installed in your Python environment:
-    <CodeGroup>
-        ```shell Terminal
-        pip install 'crewai[tools]'
-        ```
-    </CodeGroup>
-    </Step>
-    <Step title="Install and Use LlamaIndex">
-    Follow the LlamaIndex documentation [LlamaIndex Documentation](https://docs.llamaindex.ai/) to set up a RAG/agent pipeline.
-    </Step>
-</Steps>
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -11,22 +11,21 @@
  "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 +78,6 @@
              "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 +105,7 @@
              "tools/hyperbrowserloadtool",
              "tools/linkupsearchtool",
              "tools/llamaindextool",
+              "tools/langchaintool",
              "tools/serperdevtool",
              "tools/s3readertool",
              "tools/s3writertool",
@@ -170,6 +135,40 @@
              "tools/youtubevideosearchtool"
            ]
          },
+          {
+            "group": "Agent Monitoring & Observability",
+            "pages": [
+              "how-to/agentops-observability",
+              "how-to/arize-phoenix-observability",
+              "how-to/langfuse-observability",
+              "how-to/langtrace-observability",
+              "how-to/mlflow-observability",
+              "how-to/openlit-observability",
+              "how-to/opik-observability",
+              "how-to/portkey-observability",
+              "how-to/weave-integration"
+            ]
+          },
+          {
+            "group": "Learn",
+            "pages": [
+              "how-to/conditional-tasks",
+              "how-to/coding-agents",
+              "how-to/create-custom-tools",
+              "how-to/custom-llm",
+              "how-to/custom-manager-agent",
+              "how-to/customizing-agents",
+              "how-to/force-tool-output-as-result",
+              "how-to/hierarchical-process",
+              "how-to/human-input-on-execution",
+              "how-to/kickoff-async",
+              "how-to/kickoff-for-each",
+              "how-to/llm-connections",
+              "how-to/multimodal-agents",
+              "how-to/replay-tasks-from-latest-crew-kickoff",
+              "how-to/sequential-process"
+            ]
+          },
          {
            "group": "Telemetry",
            "pages": [
@@ -188,19 +187,35 @@
            ]
          }
        ]
+      },
+      {
+        "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 +229,12 @@
    "strict": false
  },
  "navbar": {
+    "links": [
+      {
+        "label": "Start Free Trial",
+        "href": "https://app.crewai.com"
+      }
+    ],
    "primary": {
      "type": "github",
      "href": "https://github.com/crewAIInc/crewAI"
--- a/docs/how-to/custom-llm.mdx
+++ b/docs/how-to/custom-llm.mdx
@@ -1,9 +1,13 @@
-# Custom LLM Implementations
+---
+title: Custom LLM Implementation
+description: Learn how to create custom LLM implementations in CrewAI.
+icon: code
+---
+
+## Custom LLM Implementations

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

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

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

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

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

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

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

 <CardGroup cols={2}>
  <Card
--- a/docs/concepts/langchain-tools.mdx
+++ b/docs/concepts/langchain-tools.mdx
@@ -1,10 +1,10 @@
 ---
-title: Using LangChain Tools
-description: Learn how to integrate LangChain tools with CrewAI agents to enhance search-based queries and more.
+title: LangChain Tool
+description: The `LangChainTool` is a wrapper for LangChain tools and query engines.
 icon: link
 ---

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

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

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

    @model_validator(mode="before")
    @classmethod
--- a/src/crewai/cli/tools/main.py
+++ b/src/crewai/cli/tools/main.py
@@ -117,7 +117,9 @@ class ToolCommand(BaseCommand, PlusAPIMixin):

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

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

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

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

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

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

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

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

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

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

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

@@ -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"),
        }

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

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

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

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

 import chromadb
 import chromadb.errors
--- a/src/crewai/tools/tool_usage.py
+++ b/src/crewai/tools/tool_usage.py
@@ -75,6 +75,7 @@ class ToolUsage:
        agent: Optional[Union["BaseAgent", "LiteAgent"]] = None,
        action: Any = None,
        fingerprint_context: Optional[Dict[str, str]] = None,
+        original_tools: List[Any] = [],
    ) -> None:
        self._i18n: I18N = agent.i18n if agent else I18N()
        self._printer: Printer = Printer()
@@ -86,6 +87,7 @@ class ToolUsage:
        self.tools_description = render_text_description_and_args(tools)
        self.tools_names = get_tool_names(tools)
        self.tools_handler = tools_handler
+        self.original_tools = original_tools
        self.tools = tools
        self.task = task
        self.action = action
@@ -191,13 +193,16 @@ class ToolUsage:
            )  # type: ignore
            from_cache = result is not None

+        original_tool = None
+        if hasattr(self, 'original_tools') and self.original_tools:
+            original_tool = next(
+                (ot for ot in self.original_tools if ot.name == tool.name),
+                None
+            )
+        
        available_tool = next(
-            (
-                available_tool
-                for available_tool in self.tools
-                if available_tool.name == tool.name
-            ),
-            None,
+            (at for at in self.tools if at.name == tool.name),
+            None
        )

        if result is None:
@@ -259,10 +264,11 @@ class ToolUsage:

            if self.tools_handler:
                should_cache = True
-                if (
-                    hasattr(available_tool, "cache_function")
-                    and available_tool.cache_function  # type: ignore # Item "None" of "Any | None" has no attribute "cache_function"
-                ):
+                if original_tool and hasattr(original_tool, "cache_function") and original_tool.cache_function:
+                    should_cache = original_tool.cache_function(
+                        calling.arguments, result
+                    )
+                elif available_tool and hasattr(available_tool, "cache_function") and available_tool.cache_function:
                    should_cache = available_tool.cache_function(  # type: ignore # Item "None" of "Any | None" has no attribute "cache_function"
                        calling.arguments, result
                    )
@@ -290,10 +296,10 @@ class ToolUsage:
            result=result,
        )

-        if (
-            hasattr(available_tool, "result_as_answer")
-            and available_tool.result_as_answer  # type: ignore # Item "None" of "Any | None" has no attribute "cache_function"
-        ):
+        if original_tool and hasattr(original_tool, "result_as_answer") and original_tool.result_as_answer:
+            result_as_answer = original_tool.result_as_answer
+            data["result_as_answer"] = result_as_answer
+        elif available_tool and hasattr(available_tool, "result_as_answer") and available_tool.result_as_answer:
            result_as_answer = available_tool.result_as_answer  # type: ignore # Item "None" of "Any | None" has no attribute "result_as_answer"
            data["result_as_answer"] = result_as_answer  # type: ignore

--- a/src/crewai/utilities/tool_utils.py
+++ b/src/crewai/utilities/tool_utils.py
@@ -60,6 +60,7 @@ def execute_tool_and_check_finality(
            task=task,
            agent=agent,
            action=agent_action,
+            original_tools=tools,  # Pass original tools to ensure custom tools work
        )

        # Parse tool calling
--- a/tests/agent_test.py
+++ b/tests/agent_test.py
@@ -10,6 +10,8 @@ from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
 from crewai.agents.crew_agent_executor import AgentFinish, CrewAgentExecutor
 from crewai.agents.parser import CrewAgentParser, OutputParserException
+from crewai.knowledge.knowledge import Knowledge
+from crewai.knowledge.knowledge_config import KnowledgeConfig
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.llm import LLM
@@ -259,7 +261,9 @@ def test_cache_hitting():
    def handle_tool_end(source, event):
        received_events.append(event)

-    with (patch.object(CacheHandler, "read") as read,):
+    with (
+        patch.object(CacheHandler, "read") as read,
+    ):
        read.return_value = "0"
        task = Task(
            description="What is 2 times 6? Ignore correctness and just return the result of the multiplication tool, you must use the tool.",
@@ -1611,6 +1615,78 @@ def test_agent_with_knowledge_sources():
        assert "red" in result.raw.lower()


+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_with_knowledge_sources_with_query_limit_and_score_threshold():
+    content = "Brandon's favorite color is red and he likes Mexican food."
+    string_source = StringKnowledgeSource(content=content)
+    knowledge_config = KnowledgeConfig(results_limit=10, score_threshold=0.5)
+    with patch(
+        "crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"
+    ) as MockKnowledge:
+        mock_knowledge_instance = MockKnowledge.return_value
+        mock_knowledge_instance.sources = [string_source]
+        mock_knowledge_instance.query.return_value = [{"content": content}]
+        with patch.object(Knowledge, "query") as mock_knowledge_query:
+            agent = Agent(
+                role="Information Agent",
+                goal="Provide information based on knowledge sources",
+                backstory="You have access to specific knowledge sources.",
+                llm=LLM(model="gpt-4o-mini"),
+                knowledge_sources=[string_source],
+                knowledge_config=knowledge_config,
+            )
+            task = Task(
+                description="What is Brandon's favorite color?",
+                expected_output="Brandon's favorite color.",
+                agent=agent,
+            )
+            crew = Crew(agents=[agent], tasks=[task])
+            crew.kickoff()
+
+            assert agent.knowledge is not None
+            mock_knowledge_query.assert_called_once_with(
+                [task.prompt()],
+                **knowledge_config.model_dump(),
+            )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default():
+    content = "Brandon's favorite color is red and he likes Mexican food."
+    string_source = StringKnowledgeSource(content=content)
+    knowledge_config = KnowledgeConfig()
+    with patch(
+        "crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"
+    ) as MockKnowledge:
+        mock_knowledge_instance = MockKnowledge.return_value
+        mock_knowledge_instance.sources = [string_source]
+        mock_knowledge_instance.query.return_value = [{"content": content}]
+        with patch.object(Knowledge, "query") as mock_knowledge_query:
+            string_source = StringKnowledgeSource(content=content)
+            knowledge_config = KnowledgeConfig()
+            agent = Agent(
+                role="Information Agent",
+                goal="Provide information based on knowledge sources",
+                backstory="You have access to specific knowledge sources.",
+                llm=LLM(model="gpt-4o-mini"),
+                knowledge_sources=[string_source],
+                knowledge_config=knowledge_config,
+            )
+            task = Task(
+                description="What is Brandon's favorite color?",
+                expected_output="Brandon's favorite color.",
+                agent=agent,
+            )
+            crew = Crew(agents=[agent], tasks=[task])
+            crew.kickoff()
+
+            assert agent.knowledge is not None
+            mock_knowledge_query.assert_called_once_with(
+                [task.prompt()],
+                **knowledge_config.model_dump(),
+            )
+
+
@pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_with_knowledge_sources_extensive_role():
    content = "Brandon's favorite color is red and he likes Mexican food."
--- a/tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold.yaml
+++ b/tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold.yaml
@@ -0,0 +1,330 @@
+interactions:
+- request:
+    body: '{"input": ["Brandon''s favorite color is red and he likes Mexican food."],
+      "model": "text-embedding-3-small", "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '137'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SaWw+yPtfmz59Pced/yrwR2bV9zhAQ2UkRFHEymYAiOxHZtEDfvN99ovdkNicm
+        YiNpu1bXdf1W//Nff/7802V1fp/++feff17VOP3z377PHumU/vPvP//9X3/+/Pnzn7/P/29k3mb5
+        41G9i9/w34/V+5Ev//z7D/9/nvzfQf/+889JZZQeb+UOCJHjaQqtRQfv1mXUaf0OTfTuHjx+CvAU
+        CWC/KEik3pNeZScAwr5Zzkgne4Gqd6jX2+oDW3BxGx8nMkfrxaq0GM2PNaV5G6QZM0P1joRJl32W
+        BVuXtTPPo02jZhRX8gjWdj7MgDz2D+wRexhoUHsaTN9P0RfLw5itFrmbCgzCHVFOdx/wQte1qJvK
+        FxH556YeT0pqoJ0RTNhqPwiskhTe0T7qIpzrwS4arGS24D4uc6y90d4VpMq+wy7hntS8mG297p2B
+        QNrwZ5pV1p4RZ6vPEHEPDtuWVA0L/w451CylgPUZBhFvXaQWWqXwwKobdNmavrcCyvDk4aRDezby
+        2c5Hym33obtXgLKlioYGKUfZovrOBtkSu6cOQbHw6POcJoyE+vmMxtegUst+HNh2ZImhpFTNsJ4V
+        73p1XlWO8NsSscGvH7asThqCqtoe6anKt+6SsI0K91Ef0UtGS5dIB8DD3QV2vtwaybB8lksCj5K7
+        pTjWccSrU5igG+hfVOuSRl+4sPGhtJ4Qtfr4w4g0EQcaRfCgnrKxXVFD8hnSZ6jTk5PN9ax4JxU5
+        T/5MsnTwskU6ARNOHnCJYHpsoPbgFfDzsRYaLe9dPbfLoiDTls800h+6vjruXYDSGiGs3fJFXw5Z
+        2APLfh+ok3y2YDvrfQvLm3/x5fPervlV0QUUF5c33aFAzQRua0JwHeCKb5/FGITQVzsgc1KIg6vA
+        Mmo+Xg5CiY/80LSf2UqSFwdOKDHoMVyBvk6jq0DzTRTs1uUHLFui9ciAyYGq8fHOhDqzzoCpgkE9
+        Ta/q9aW/VnRO/IR6zaVjs8DvQ9Q/byvOji+YzUV7ztGHji4+b4t7LZqHuwO9+NRR9aZ0YFFWKQF8
+        oXu+5D2rgfee2RlmG3/CO+mFXbq0SgJ35cGm+JxKjEnnY6vsjlOI9+aSsPUqdSNMj3FBD3qdMHHA
+        UgCXpjj46xaeI6GBnAZtrfZJOLMKLKg6VrDCz5jaF6K6/LjWGpwt36FHS430JTwlHtrvYIL3q03d
+        JUkWDWVaEtKLvglq9sj4HiRDHtFo3yjuyGe2D/nPY8ER4xwmtq/AQtvoptF7rdiAX9jdgRtn7+Bn
+        tJEZJc2GgD4yNZz3YBjWu3ziAaFrhXenYwImk8wNpOrj/M13t+Y7wz/D3/57Lz0b2K1kHixsVceP
+        ztUy8VYyH90e/AbvXU+sGZ8aDnKhc6LWu9nVPJp3CYqztfBbYCn6DDf9CG16+VBf9VswK6seI7h7
+        nqirt5POrDOr4LC/ExoMssgmx6EzlCfv+s2fnS5e3vIM9VeX0YDfaUxs04EHhXb/4KPzJoC1ac2j
+        jeltac5xgc5gd++B3PYI22Bmw1g9KgFZx+cdGynQMv7ilz7yDuFKkP351LMfTiYsJQCpLhIpWguN
+        76FsiVd6cLRJX4LU5qEFOUQdt3OBGCfJHX7PD/x7H+9L1xThHJQYF+HiUrWYe6DvogzvTlKvM6OP
+        EijuT5i01wcF7Pg6QvgK4pZ6vlzo82dzCmBAD4zuU7MfFvypHbRLREZku91ma5+PBfjGjz8e7mbN
+        sFByKDkcInrs5Iv+oVDhoTppJTYI17LVHD4qvBBo4NB9lmyRDuYMt0bqkQWbJZteYsaBUpZNvFf7
+        Su+cVQ5gr6YI+7u3A0Sev83KJowLXyzuwGV7N5jR68Zc6iWPoB71O63gwiqEtU9sR3wq2yG0nPZE
+        ja7fuKuzmQ10PnUctriPysROHCtogQ3D+JPs3O1a1AGULo+SauHJ0XlpX8ZI350yeqCtmjFn4T0w
+        SHyDz/xqg+2xnU3UZWJP7VURXHaDlgBHg8P00NhvfTy2rgqPRM1pvKIjmPwodNDU8neq2ydTZ2O7
+        C1F5qFKKX8PFHRZvXGFV81eaBMou4wcOjzLwbk/qpxe1/uyMoEAmCc4Yl4GQrZzstsgq+Qe9D4cZ
+        LFkbJCg6NjG9Wy8pWzj/3cBY7VSaymuf0eK2jnBXmRE+bZkJlqdp+NAf6gFbh9saPQ/d7Q6siTtg
+        HG1ubDtLnA8/1fuK/TpfXVbO7gijGR7pQ3e2EVPA2qJ170v+FosWWEPf6iBRgI6dku7Z0ianM2Jl
+        scWq4R/Z9qkd2l98YU3isD7z7UuBtw4V9Hbef+pZu2wEEE/3DCdFdXDF6j7NMOmftg99uXDFME1T
+        MCX6SA/OvAGTcm4tlJ1uFoHzsdQZvxHu8BQ+eurtkiXrcuobMLzW2Tf+TCZka+8or+FpYqypDhBU
+        5eahY3a54ftLBzULDTuF0f3t4X2N7+4QGrsUifHG8We0fdXzbCoOQHjzJlwbKFk/umYDMQsqmunt
+        0RUDj2ko+/QP6ofSW19xoDVQUHHuw289YJf3MiM+vwQ+f5Xf9Xw3OwIT3eNwcu59sDruWUBjOQ/f
+        /FPd+V0FDZKlWPrG71Nf1UJvYOyh2R+rUxQxL88D0KnUoeq8sfTV3+cBME6Pid5uPnDXZBOk6Fyf
+        ZRxe02wQd6LdweOknzHu4zYj42WV0P5QddSbjzv3qydMEMutia3sHgOmk0CDnZ5gjO1HEwm9kUsg
+        7R47cu6j7bBWwVlDfsy9sNHXls5jXV+R6sYt3hdSyJZQdAo4dvGeWtHJGeYUpzEUkpzhg3UT6l5c
+        +hVAw4rxJeUfmejpQYAe7+6CdUM4ZGPt2wW4RvRBTtK2rCdD9yE8lUGK3fdJjNa++ljoKDsbsnkN
+        F53pZyeF72U806h3OnfVpwqiOx8+fbEH2F1lv65QNhUrPp6FYGChsUuQ44QG+XyWpu72qOHhmi4W
+        tqSLrI8lfOXwu/4EWcF+WPwK3OHNF2y8++UP90gq6LuCgdXyqkXisl5N+DS3D38cDjOb2LrpQYap
+        R+1XvGckOz8lKB7gGVtNyA9MLeYO1uSe/I1/sm/kM4Q0FPAh4LfR3JwXH+7ulYbNfa6yZdqPBZyK
+        k0b4Q5zrM4hUAscBB/7mUXRgtsU2hJvLcaDhV691b0uDCJ2G2lcS2YqEX/1Q93NMFi0wIuZTJYQf
+        73yhd1Tm7Lee8Fffn2G0YyR5OTMEiiz81cNzNXkWKOjJwLio9IHXmm6Gh06JCVceLPbyo9BCttTY
+        9EGHhz562zGGhnn1iOQLA1jj65BCw5NaelNnkTGzLGcknMDNp+c0ASztKgWN+mZPeLtvXbYTdx0q
+        J5Zh4/OqgNhc5xWl92tMHca9I4L7xEPcqzDopdvfwGLnxxGQ15nhOMWSPj60xoROc8uwNRhwWC9Z
+        pwFXwzufhMctYKdJilFrhyN1JbQOS+ExCV5KMaA4JUUtkkYkcHekId1J23KYPlc8Q6F+nbHpiAYT
+        /H0cgqbY7nF2/SzDeidTAcXus6exvKsznvVVBWzcaVitLu+azP2OQ3nQ3vFR35rDSuswAN/zi6bc
+        0XZnTnvwEOXrlSyXThyW4v7wIS5eDwJvAj98/VGOXpVWUvVkDBnLrZhAr4MTTQ63NXv1JTThZz8D
+        ejZOlc7sgFNgs9SCr4xwBMOK3AQw8bDHTnhQ3fmcOxVQRVvyW+cdZrNw23RQTsuQXvdvEnXCTezg
+        V/9jXyyFYU7eUwC+649x0A/Z2F6bEH52UovvrviKmGQ0AZQjJPn0W8+WROs0eNPGJ/7uV0ZO4baH
+        7MnLOEorLZtruvGgbGw0uie3sl5W89Er6fFc0KvCDpHYEHuGj6zoaWC/FzDSOMqha60ZvcX3ldEw
+        TRN48Z83ImSSP7ztfeijDzftyLwXm2hpa0GFtVFb1Lrtp3q2XC+AN5+38a1Gu2HN1spCfpC5fu1F
+        Klubq05A9zIdvFPfE2P35xIgpQptvAOew8b+Up1RoEUJWVq31L/+xwKdOjk+SIcxG7/+BT6FmMM7
+        3f/UyzbaqlAe8RG7toOG1RtTC87BpyXKc5gzej51K5DTOiTrz3+MrtlC7Xzf0MygOViFneEgTWMG
+        EU/PdqDQxyr4xruvnP2rK1YCSGDPVkbk1dOjNS83IXynuUV2TjYPrBJYgooP4b/1XAbjwB0IspIX
+        wvjrJxfjcW+g/RjI3/zeEsG1ABUqTNAeopppx5CgQx2bRA53Z33xo9SCX/9CQ6fh9NkQtg5U+qnx
+        pcVadfbYvVV4lOwtdV3dHOayuvLwr5442DAah3uoAilsYuqm2Y0xv0g4aDTWilWeXob+5yerbRHS
+        3OMXtvRjl8DoNu588P0/oVlOZyTprMWHT5jUc1xsW8QB80z3NYb6Kk2tBQzz4vmgrZuaeGNooe/+
+        4Hs7hvo69zsICkuT8eGCz7qwSS0Ic1F442P08CIWJ0n+mx/OT3iumXB8KNAk4Zna25HLuqYJKyV/
+        uRXWb29uIHxnqYg7jDmOv/p5xYHTgs/HWbB52PYubV2nAr1xCjEOoxIsFSYQds1B9cEwCvqH65Cn
+        tLkAqblbeMZW2ZxBe3R3hKvzVV/VxvLh6SjVON9fpYg8thcffuOF7le+yJazUUL4He+DMDjWq9AK
+        Ofz6bep/kBmtgfoJwM+P//QSAcPowcpUF2oNZ6zz2+nSwmePI+p847G/eKIJvzzG59zsOKzFsYOQ
+        K7dbrOW2Fq3skRH48rueujh/RYufcwJMQ2nxV0n9AJ7TLgI8vh8G9oZr/eUxZwOs9v74t77MQWMb
+        cFrhAf/4AlnDdwJrkifY9rpZnwu1smBwMix6KRxVF+JFVmFgCasv3MpXtBYPJ4Bf/uR/84P1nlZ7
+        sDrZIba//n972BYB7ByXYrtGZT13ecYB4zNp1N33VT3xaOBgkjCf2l//skRPysHPTmmpcxzLaN4e
+        hgA+5DjA9qrE7rLDyAdAgwrWpdsH9N94Adc0EPGVxRMYXwKRBN1PMVXdwIrGSpzv6PIIbGorh4e+
+        3MP1DrlPevOVIi7ZOp24EH6su4rdp+nqc7o1eoBs74AzdXPK1s/q3OGzmAm9G45c08tbXuGrkUey
+        kblRX81LoMIg2kRkMa4gm8N+nuFq+hrWw/RabzNPWxEHjDPeqWKRfeshgXypxv6WB9eMNRFvIWJ0
+        2pff2GB94EpBT7uoaGRvJDAE6NSDn5/An6TUZ/JZUmgZqkj9n59Mt0YHvTeqMW5QFTFOnnv0KE3g
+        S9JFdsku6EOIL3dINet4ZswwPsbPj1Kz6gX2V/898tsWm5F20lnwVjsISTQS5uAh+/kLkBi+hfeL
+        a4P1Jdkqsh8f8ounaO2yJYeeax+wh5ZTti2ESoDILDVqA61gLdjLCrw/1AjnXaNFQmqqFpJkofzq
+        rXMtPLJDAwf7qpNNGJVs1Squh0shSr5eTWRgnZYoP/5Hf/V9eegnBzk93JJlSSx3+3EH86/+TJxs
+        0sePw2k/v4F97TW7rDrZBuTX8UT98HgBf+P9wlcXapy2a0Q9PQhhnM0FtnxhYKstqykiUS8RepR0
+        ff6ej+jnv9WrEGWdwB9D+OODNnu9o+X1MM8wf9kVVu3rJluaUuNQuz1wVP2spfv14xU0p8ih2lfv
+        j/1pGuH7cYmw7WIXTOZ+10FWVlsif/VmZa3JqHz1IE6Q2mdTzXcK+PmPmzpfmdjbaovW07mmh1sf
+        slwB+wKi+pLjQ35p3JHgYYXvQr3R5+x8shliwwBBWkzU6U6gZkpshYB1Jv7LE8lbEO+wjo869SWv
+        05dVkRQYO+aLajei12xrEg+ixEM07tddLcZJkENjy084v6V3MJfVk4dKTxu6S/U4E19GKoDlnYXY
+        GODodibRq59/95tOWQZi9887hMcW+BsBnrKuv1Qxep42nE8bpGX0OSUdsvqT9NX7N3196dMK3jGT
+        8Y8v0vvF4+DcKcDnC/rK2NVYC9gmUYXNuW3qsTnLPuT4QvnL36gZWjkgVnHF8VDw0ZJ06Rn89OXh
+        y5/nYotm8KwH2R+Ss66z80hWeLZvnb9aj0O09pJigVbYW2TzfG/qL//t4fvVfDCWudFlfc8F4Fuv
+        /RmUj+FvfP/48zGTXH3eo0aA3SFofHFNunruPlao6PcbwCY7qpFgrQGBJ0f18cXakujzOy/uZPTp
+        MVVeTOQbKf/xJh8Yu1GfnFtC/uphR65EMCpVpaLwg2O6D8I3G7n7cIfh5xhT9cu/tk2pwb/n704o
+        5ZrlUOb++m9POIvscxpzD/C6N/scM69s9kdlhPFbcrGfjL07J+uphfkwQiIAS3HZrAQxOoXPHtuq
+        ttdZ6ZxS2NCtgs3XfaOz1H+EEE/jiUZZsNX71wOkcHFaAWP+1X39b5LA5elCbHCtNyyf10xgfUQT
+        tsL2FgkuYHf441Xu+3TNVuUSeSDMjS3+zg9M9ypa4Tk71PjohoW7dNtUhd4hWKm1nwFgr7zI4U9f
+        eN/6Roqu5cBV0yvy+vLHJXx/PAhvpMV6L6VsNHZlBcUYOfiIPM9d3pakKi+xWagfd+eBedIgKXUV
+        E+zue60WY1LeUX1fH4Trmiqa72OmAtDGM7WGjZqtvixX8DQQ++cHojZLzhWyLmSlh52oAvLVI1Ai
+        RPXnznZqwQTOGZJBOn737wAYy9UZXomI/K6Sg4wqh2sMPvsV+Eyyxay5pHsJSmEb00MPqD5yZnqH
+        h13n+gVYAp0gq+GQ8nzr2KrkOXsqr7KFocZdsEfXSm+8/XGEsekH2NIClQnNoUrhV/9hz8nL7Dt/
+        Dfn87OIo0P1sCuaUh6Of8Pi51FM04scpgYdOinE4LZa7ts1gQOsyrth5C3B4r9E5h29gyT48qaK+
+        wh0KfvoIm6P7AsupWCowjKNMjU451bM1cw388lYfda4W8T//8tO3qL40NZ3C4QzltkMkXa5DvV7e
+        xgjD7WVHrbCVo/Vz5Xl4dYMdPnz546/fBNVrfiLsNDZsLTTY/+XBzlu418365DyABK32pQDPOuOC
+        HUGPdRWwffOBvn75E7D3fuRvP2TOft+V3/ltPOOdvrinZw7H10elKh7e+qwr8vyXJ+jLuxx+fAea
+        B9X20bc/Jy7r0wT1W+KoSUI4rHC3DWBQrTr2PmQEM51LE3KPgFDHPmn1ll7VCpW9EhDu64f7Je16
+        CPJDSv/y09/+QXIa8U14V+53fh3gdq5B/Uxn2boeNPJ3v3+8aL7HjgbsVvH9zVqGNVPNWkWFC3yM
+        maeDWZ3SBB57y8YPN1RdsT4ad3iuY5kweZ3YlHnajMjj8PDrxlwZKVgWKN/8JLydsmGcH64FvvyG
+        2l7yqIXJPDXw16+5uJ445C03E7Sl1egPYVHojNJGQy3sK7LVYkVfvL0yg/FWX+h+cT9gDo6z+ePZ
+        1PsQD/A7fbgrWtH09FLWjT7LmRKD24frCT9fB33clpICnVug4PjC37J5rG0Cw3MXUHVBU0buZKqg
+        9pAbIn/95dZpUAKNIvz2x6gwEJl/8Art04akzwyB1VkOFij8JvKRKZbRXDMmwFLv9vj2kMdo2Vyu
+        IXwKZw5rEoEDO5eage7lOyVojsmwGn53/ulzwmXRC3Q/fbbi7o3d8fqu57MUWCiWGxMb57cyrPHE
+        J3Cjdi+q7kUjEz+N3/x4Az7qzjZjiHox9Iz3RL/nq1v20tGAuXUx8SGWnJpwsttA8VE1VK0uh0E0
+        9WsFke0fiJArn+jbLwgB7qwdVvFwcLfpLr//rV93NfV0QZ96CF3zEGMHZCoQxtkq4MtZL1g7GLo7
+        f/UUcJos80EkGy7jnrWKmizkCbt4G7AU94uHCpBSAvNyD2axGTiYB82dgAFag6iatQY3jZZh/Cgs
+        9u0H8gicu+2X56g1PxmbHF6r4ogvQjOBbhaDFZqmusEnutHB+uuH3o2Vo4ar9+58wKqCEsOzsMtX
+        jM03q+pQrfYMHxVniZaW0zuknfPNr75m7CxGBrSLM4+vn2pwl3Qrj8BiRYKdahrc6ZhgCwqaUmNL
+        /zRg+PYf//qLxxBw0fzrXzqiUdCQShyjXz+tpM6QUe/L9+kkXToI1nuGL1qc6uu9VgVk1G6HHRO/
+        f/mz/vgNdpX247L+eWrR1WogVpOyAV9+3EKBozw2/L0BmKy+O0iiTsJJHL0yui0YD6XLsyTAdh71
+        Mj9mH/7zuxXwX//68+d//G4YtN0jf30vBkz5Mv3H/7kq8B/if4xt+nr9vYZAxrTI//n3/76B8M9n
+        6NrP9D+nrsnf4z///rMV/t41+GfqpvT1/z7/1/dV//Wv/wUAAP//AwBcfFVx4CAAAA==
+    headers:
+      CF-RAY:
+      - 931fcf607c16eb34-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 17 Apr 2025 23:47:53 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=CncSMPCav.9EJL3emmM0sTqugx5GN6_Oy8JPFBssVho-1744933673-1.0.1.1-Q1XMvHbQdrfEWkkCYeeNHwFdZ1NpjAGJ_0jOUYIk_APelFe7nCanjW_xlOj12b3JQql9.iWQDiHvCeYJDTWkdxnNiMQOEiFMYHX5YZXUuJs;
+        path=/; expires=Fri, 18-Apr-25 00:17:53 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=unfPTYCpF5COtm5PuZDuaJqlhefP0iibfjsXHc9lKq0-1744933673515-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '75'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-8687b6cbdb-4qpmr
+      x-envoy-upstream-service-time:
+      - '46'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999986'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_b8c884a7fe2bd4732903ecbdc632576d
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Information Agent.
+      You have access to specific knowledge sources.\nYour personal goal is: Provide
+      information based on knowledge sources\nTo give my best complete final answer
+      to the task respond using the exact following format:\n\nThought: I now can
+      give a great answer\nFinal Answer: Your final answer must be the great and the
+      most complete as possible, it must be outcome described.\n\nI MUST use these
+      formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task:
+      What is Brandon''s favorite color?\n\nThis is the expected criteria for your
+      final answer: Brandon''s favorite color.\nyou MUST return the actual complete
+      content as the final answer, not a summary.\n\nBegin! This is VERY important
+      to you, use the tools available and give your best Final Answer, your job depends
+      on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '926'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jJNNi9swEIbv+RWDLr0ki/NBvm5NYUsplFK29NAuZiKNnWlkjVaSk02X
+        /PdiJxtn2y30YrCeecfvvCM/9QAUG7UEpTeYdOXtYPXp7vbLw7evm4ePmObvt/jrsVgVn9/5dbhj
+        1W8Usv5JOj2rbrRU3lJicSesA2GiputwNpksxuPpbNyCSgzZRlb6NJjIoGLHg1E2mgyy2WA4P6s3
+        wpqiWsL3HgDAU/tsfDpDj2oJWf/5pKIYsSS1vBQBqCC2OVEYI8eELql+B7W4RK61/gGc7EGjg5J3
+        BAhlYxvQxT0FgB/ulh1aeNu+L2EV0BlxbyIUuJPAiUCLlQAcwUkCX68ta3sAI7quyCUywA72bMge
+        AHfIFteWYOtkb8mUBFHqoCneXPsLVNQRm4xcbe0VQOckYZNxm8z9mRwvWVgpfZB1/EOqCnYcN3kg
+        jOKauWMSr1p67AHct5nXL2JUPkjlU55kS+3nhtP5qZ/qVt3R0fQMkyS0V6rFpP9Kv9xQQrbxamtK
+        o96Q6aTdirE2LFegdzX1325e632anF35P+07oDX5RCb3gQzrlxN3ZYGaP+FfZZeUW8MqUtixpjwx
+        hWYThgqs7el+qniIiaq8YFdS8IFPl7TweTZejOajUbbIVO/Y+w0AAP//AwA4a1/QsgMAAA==
+    headers:
+      CF-RAY:
+      - 931fcf649bdbed40-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 17 Apr 2025 23:47:54 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=8vySwO0xqpm0u93_1_rXQwTeEIWa2ei3_CD5sAdoo3o-1744933674-1.0.1.1-iqZDpH5poOUp4Rcnhfrb0N2Z0c2662RBiPEcx_gefNW.m3tBA3qyFa8tmFv7PitH8u9vyYK7jxUwy4lPiSi830QWNbTMgCMTbrJ7iaUV7hY;
+        path=/; expires=Fri, 18-Apr-25 00:17:54 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=IXAyT8eWpFERM53ngcYNmaqhocfGbOHWSoe7SFNdoGI-1744933674288-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '489'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999801'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_151f9d0b786f2022f249ee20ea108b43
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default.yaml
+++ b/tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default.yaml
@@ -0,0 +1,330 @@
+interactions:
+- request:
+    body: '{"input": ["Brandon''s favorite color is red and he likes Mexican food."],
+      "model": "text-embedding-3-small", "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '137'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SaWw+yPtfmz59Pced/yrwR2bV9zhAQ2UkRFHEymYAiOxHZtEDfvN99ovdkNicm
+        YiNpu1bXdf1W//Nff/7802V1fp/++feff17VOP3z377PHumU/vPvP//9X3/+/Pnzn7/P/29k3mb5
+        41G9i9/w34/V+5Ev//z7D/9/nvzfQf/+889JZZQeb+UOCJHjaQqtRQfv1mXUaf0OTfTuHjx+CvAU
+        CWC/KEik3pNeZScAwr5Zzkgne4Gqd6jX2+oDW3BxGx8nMkfrxaq0GM2PNaV5G6QZM0P1joRJl32W
+        BVuXtTPPo02jZhRX8gjWdj7MgDz2D+wRexhoUHsaTN9P0RfLw5itFrmbCgzCHVFOdx/wQte1qJvK
+        FxH556YeT0pqoJ0RTNhqPwiskhTe0T7qIpzrwS4arGS24D4uc6y90d4VpMq+wy7hntS8mG297p2B
+        QNrwZ5pV1p4RZ6vPEHEPDtuWVA0L/w451CylgPUZBhFvXaQWWqXwwKobdNmavrcCyvDk4aRDezby
+        2c5Hym33obtXgLKlioYGKUfZovrOBtkSu6cOQbHw6POcJoyE+vmMxtegUst+HNh2ZImhpFTNsJ4V
+        73p1XlWO8NsSscGvH7asThqCqtoe6anKt+6SsI0K91Ef0UtGS5dIB8DD3QV2vtwaybB8lksCj5K7
+        pTjWccSrU5igG+hfVOuSRl+4sPGhtJ4Qtfr4w4g0EQcaRfCgnrKxXVFD8hnSZ6jTk5PN9ax4JxU5
+        T/5MsnTwskU6ARNOHnCJYHpsoPbgFfDzsRYaLe9dPbfLoiDTls800h+6vjruXYDSGiGs3fJFXw5Z
+        2APLfh+ok3y2YDvrfQvLm3/x5fPervlV0QUUF5c33aFAzQRua0JwHeCKb5/FGITQVzsgc1KIg6vA
+        Mmo+Xg5CiY/80LSf2UqSFwdOKDHoMVyBvk6jq0DzTRTs1uUHLFui9ciAyYGq8fHOhDqzzoCpgkE9
+        Ta/q9aW/VnRO/IR6zaVjs8DvQ9Q/byvOji+YzUV7ztGHji4+b4t7LZqHuwO9+NRR9aZ0YFFWKQF8
+        oXu+5D2rgfee2RlmG3/CO+mFXbq0SgJ35cGm+JxKjEnnY6vsjlOI9+aSsPUqdSNMj3FBD3qdMHHA
+        UgCXpjj46xaeI6GBnAZtrfZJOLMKLKg6VrDCz5jaF6K6/LjWGpwt36FHS430JTwlHtrvYIL3q03d
+        JUkWDWVaEtKLvglq9sj4HiRDHtFo3yjuyGe2D/nPY8ER4xwmtq/AQtvoptF7rdiAX9jdgRtn7+Bn
+        tJEZJc2GgD4yNZz3YBjWu3ziAaFrhXenYwImk8wNpOrj/M13t+Y7wz/D3/57Lz0b2K1kHixsVceP
+        ztUy8VYyH90e/AbvXU+sGZ8aDnKhc6LWu9nVPJp3CYqztfBbYCn6DDf9CG16+VBf9VswK6seI7h7
+        nqirt5POrDOr4LC/ExoMssgmx6EzlCfv+s2fnS5e3vIM9VeX0YDfaUxs04EHhXb/4KPzJoC1ac2j
+        jeltac5xgc5gd++B3PYI22Bmw1g9KgFZx+cdGynQMv7ilz7yDuFKkP351LMfTiYsJQCpLhIpWguN
+        76FsiVd6cLRJX4LU5qEFOUQdt3OBGCfJHX7PD/x7H+9L1xThHJQYF+HiUrWYe6DvogzvTlKvM6OP
+        EijuT5i01wcF7Pg6QvgK4pZ6vlzo82dzCmBAD4zuU7MfFvypHbRLREZku91ma5+PBfjGjz8e7mbN
+        sFByKDkcInrs5Iv+oVDhoTppJTYI17LVHD4qvBBo4NB9lmyRDuYMt0bqkQWbJZteYsaBUpZNvFf7
+        Su+cVQ5gr6YI+7u3A0Sev83KJowLXyzuwGV7N5jR68Zc6iWPoB71O63gwiqEtU9sR3wq2yG0nPZE
+        ja7fuKuzmQ10PnUctriPysROHCtogQ3D+JPs3O1a1AGULo+SauHJ0XlpX8ZI350yeqCtmjFn4T0w
+        SHyDz/xqg+2xnU3UZWJP7VURXHaDlgBHg8P00NhvfTy2rgqPRM1pvKIjmPwodNDU8neq2ydTZ2O7
+        C1F5qFKKX8PFHRZvXGFV81eaBMou4wcOjzLwbk/qpxe1/uyMoEAmCc4Yl4GQrZzstsgq+Qe9D4cZ
+        LFkbJCg6NjG9Wy8pWzj/3cBY7VSaymuf0eK2jnBXmRE+bZkJlqdp+NAf6gFbh9saPQ/d7Q6siTtg
+        HG1ubDtLnA8/1fuK/TpfXVbO7gijGR7pQ3e2EVPA2qJ170v+FosWWEPf6iBRgI6dku7Z0ianM2Jl
+        scWq4R/Z9qkd2l98YU3isD7z7UuBtw4V9Hbef+pZu2wEEE/3DCdFdXDF6j7NMOmftg99uXDFME1T
+        MCX6SA/OvAGTcm4tlJ1uFoHzsdQZvxHu8BQ+eurtkiXrcuobMLzW2Tf+TCZka+8or+FpYqypDhBU
+        5eahY3a54ftLBzULDTuF0f3t4X2N7+4QGrsUifHG8We0fdXzbCoOQHjzJlwbKFk/umYDMQsqmunt
+        0RUDj2ko+/QP6ofSW19xoDVQUHHuw289YJf3MiM+vwQ+f5Xf9Xw3OwIT3eNwcu59sDruWUBjOQ/f
+        /FPd+V0FDZKlWPrG71Nf1UJvYOyh2R+rUxQxL88D0KnUoeq8sfTV3+cBME6Pid5uPnDXZBOk6Fyf
+        ZRxe02wQd6LdweOknzHu4zYj42WV0P5QddSbjzv3qydMEMutia3sHgOmk0CDnZ5gjO1HEwm9kUsg
+        7R47cu6j7bBWwVlDfsy9sNHXls5jXV+R6sYt3hdSyJZQdAo4dvGeWtHJGeYUpzEUkpzhg3UT6l5c
+        +hVAw4rxJeUfmejpQYAe7+6CdUM4ZGPt2wW4RvRBTtK2rCdD9yE8lUGK3fdJjNa++ljoKDsbsnkN
+        F53pZyeF72U806h3OnfVpwqiOx8+fbEH2F1lv65QNhUrPp6FYGChsUuQ44QG+XyWpu72qOHhmi4W
+        tqSLrI8lfOXwu/4EWcF+WPwK3OHNF2y8++UP90gq6LuCgdXyqkXisl5N+DS3D38cDjOb2LrpQYap
+        R+1XvGckOz8lKB7gGVtNyA9MLeYO1uSe/I1/sm/kM4Q0FPAh4LfR3JwXH+7ulYbNfa6yZdqPBZyK
+        k0b4Q5zrM4hUAscBB/7mUXRgtsU2hJvLcaDhV691b0uDCJ2G2lcS2YqEX/1Q93NMFi0wIuZTJYQf
+        73yhd1Tm7Lee8Fffn2G0YyR5OTMEiiz81cNzNXkWKOjJwLio9IHXmm6Gh06JCVceLPbyo9BCttTY
+        9EGHhz562zGGhnn1iOQLA1jj65BCw5NaelNnkTGzLGcknMDNp+c0ASztKgWN+mZPeLtvXbYTdx0q
+        J5Zh4/OqgNhc5xWl92tMHca9I4L7xEPcqzDopdvfwGLnxxGQ15nhOMWSPj60xoROc8uwNRhwWC9Z
+        pwFXwzufhMctYKdJilFrhyN1JbQOS+ExCV5KMaA4JUUtkkYkcHekId1J23KYPlc8Q6F+nbHpiAYT
+        /H0cgqbY7nF2/SzDeidTAcXus6exvKsznvVVBWzcaVitLu+azP2OQ3nQ3vFR35rDSuswAN/zi6bc
+        0XZnTnvwEOXrlSyXThyW4v7wIS5eDwJvAj98/VGOXpVWUvVkDBnLrZhAr4MTTQ63NXv1JTThZz8D
+        ejZOlc7sgFNgs9SCr4xwBMOK3AQw8bDHTnhQ3fmcOxVQRVvyW+cdZrNw23RQTsuQXvdvEnXCTezg
+        V/9jXyyFYU7eUwC+649x0A/Z2F6bEH52UovvrviKmGQ0AZQjJPn0W8+WROs0eNPGJ/7uV0ZO4baH
+        7MnLOEorLZtruvGgbGw0uie3sl5W89Er6fFc0KvCDpHYEHuGj6zoaWC/FzDSOMqha60ZvcX3ldEw
+        TRN48Z83ImSSP7ztfeijDzftyLwXm2hpa0GFtVFb1Lrtp3q2XC+AN5+38a1Gu2HN1spCfpC5fu1F
+        Klubq05A9zIdvFPfE2P35xIgpQptvAOew8b+Up1RoEUJWVq31L/+xwKdOjk+SIcxG7/+BT6FmMM7
+        3f/UyzbaqlAe8RG7toOG1RtTC87BpyXKc5gzej51K5DTOiTrz3+MrtlC7Xzf0MygOViFneEgTWMG
+        EU/PdqDQxyr4xruvnP2rK1YCSGDPVkbk1dOjNS83IXynuUV2TjYPrBJYgooP4b/1XAbjwB0IspIX
+        wvjrJxfjcW+g/RjI3/zeEsG1ABUqTNAeopppx5CgQx2bRA53Z33xo9SCX/9CQ6fh9NkQtg5U+qnx
+        pcVadfbYvVV4lOwtdV3dHOayuvLwr5442DAah3uoAilsYuqm2Y0xv0g4aDTWilWeXob+5yerbRHS
+        3OMXtvRjl8DoNu588P0/oVlOZyTprMWHT5jUc1xsW8QB80z3NYb6Kk2tBQzz4vmgrZuaeGNooe/+
+        4Hs7hvo69zsICkuT8eGCz7qwSS0Ic1F442P08CIWJ0n+mx/OT3iumXB8KNAk4Zna25HLuqYJKyV/
+        uRXWb29uIHxnqYg7jDmOv/p5xYHTgs/HWbB52PYubV2nAr1xCjEOoxIsFSYQds1B9cEwCvqH65Cn
+        tLkAqblbeMZW2ZxBe3R3hKvzVV/VxvLh6SjVON9fpYg8thcffuOF7le+yJazUUL4He+DMDjWq9AK
+        Ofz6bep/kBmtgfoJwM+P//QSAcPowcpUF2oNZ6zz2+nSwmePI+p847G/eKIJvzzG59zsOKzFsYOQ
+        K7dbrOW2Fq3skRH48rueujh/RYufcwJMQ2nxV0n9AJ7TLgI8vh8G9oZr/eUxZwOs9v74t77MQWMb
+        cFrhAf/4AlnDdwJrkifY9rpZnwu1smBwMix6KRxVF+JFVmFgCasv3MpXtBYPJ4Bf/uR/84P1nlZ7
+        sDrZIba//n972BYB7ByXYrtGZT13ecYB4zNp1N33VT3xaOBgkjCf2l//skRPysHPTmmpcxzLaN4e
+        hgA+5DjA9qrE7rLDyAdAgwrWpdsH9N94Adc0EPGVxRMYXwKRBN1PMVXdwIrGSpzv6PIIbGorh4e+
+        3MP1DrlPevOVIi7ZOp24EH6su4rdp+nqc7o1eoBs74AzdXPK1s/q3OGzmAm9G45c08tbXuGrkUey
+        kblRX81LoMIg2kRkMa4gm8N+nuFq+hrWw/RabzNPWxEHjDPeqWKRfeshgXypxv6WB9eMNRFvIWJ0
+        2pff2GB94EpBT7uoaGRvJDAE6NSDn5/An6TUZ/JZUmgZqkj9n59Mt0YHvTeqMW5QFTFOnnv0KE3g
+        S9JFdsku6EOIL3dINet4ZswwPsbPj1Kz6gX2V/898tsWm5F20lnwVjsISTQS5uAh+/kLkBi+hfeL
+        a4P1Jdkqsh8f8ounaO2yJYeeax+wh5ZTti2ESoDILDVqA61gLdjLCrw/1AjnXaNFQmqqFpJkofzq
+        rXMtPLJDAwf7qpNNGJVs1Squh0shSr5eTWRgnZYoP/5Hf/V9eegnBzk93JJlSSx3+3EH86/+TJxs
+        0sePw2k/v4F97TW7rDrZBuTX8UT98HgBf+P9wlcXapy2a0Q9PQhhnM0FtnxhYKstqykiUS8RepR0
+        ff6ej+jnv9WrEGWdwB9D+OODNnu9o+X1MM8wf9kVVu3rJluaUuNQuz1wVP2spfv14xU0p8ih2lfv
+        j/1pGuH7cYmw7WIXTOZ+10FWVlsif/VmZa3JqHz1IE6Q2mdTzXcK+PmPmzpfmdjbaovW07mmh1sf
+        slwB+wKi+pLjQ35p3JHgYYXvQr3R5+x8shliwwBBWkzU6U6gZkpshYB1Jv7LE8lbEO+wjo869SWv
+        05dVkRQYO+aLajei12xrEg+ixEM07tddLcZJkENjy084v6V3MJfVk4dKTxu6S/U4E19GKoDlnYXY
+        GODodibRq59/95tOWQZi9887hMcW+BsBnrKuv1Qxep42nE8bpGX0OSUdsvqT9NX7N3196dMK3jGT
+        8Y8v0vvF4+DcKcDnC/rK2NVYC9gmUYXNuW3qsTnLPuT4QvnL36gZWjkgVnHF8VDw0ZJ06Rn89OXh
+        y5/nYotm8KwH2R+Ss66z80hWeLZvnb9aj0O09pJigVbYW2TzfG/qL//t4fvVfDCWudFlfc8F4Fuv
+        /RmUj+FvfP/48zGTXH3eo0aA3SFofHFNunruPlao6PcbwCY7qpFgrQGBJ0f18cXakujzOy/uZPTp
+        MVVeTOQbKf/xJh8Yu1GfnFtC/uphR65EMCpVpaLwg2O6D8I3G7n7cIfh5xhT9cu/tk2pwb/n704o
+        5ZrlUOb++m9POIvscxpzD/C6N/scM69s9kdlhPFbcrGfjL07J+uphfkwQiIAS3HZrAQxOoXPHtuq
+        ttdZ6ZxS2NCtgs3XfaOz1H+EEE/jiUZZsNX71wOkcHFaAWP+1X39b5LA5elCbHCtNyyf10xgfUQT
+        tsL2FgkuYHf441Xu+3TNVuUSeSDMjS3+zg9M9ypa4Tk71PjohoW7dNtUhd4hWKm1nwFgr7zI4U9f
+        eN/6Roqu5cBV0yvy+vLHJXx/PAhvpMV6L6VsNHZlBcUYOfiIPM9d3pakKi+xWagfd+eBedIgKXUV
+        E+zue60WY1LeUX1fH4Trmiqa72OmAtDGM7WGjZqtvixX8DQQ++cHojZLzhWyLmSlh52oAvLVI1Ai
+        RPXnznZqwQTOGZJBOn737wAYy9UZXomI/K6Sg4wqh2sMPvsV+Eyyxay5pHsJSmEb00MPqD5yZnqH
+        h13n+gVYAp0gq+GQ8nzr2KrkOXsqr7KFocZdsEfXSm+8/XGEsekH2NIClQnNoUrhV/9hz8nL7Dt/
+        Dfn87OIo0P1sCuaUh6Of8Pi51FM04scpgYdOinE4LZa7ts1gQOsyrth5C3B4r9E5h29gyT48qaK+
+        wh0KfvoIm6P7AsupWCowjKNMjU451bM1cw388lYfda4W8T//8tO3qL40NZ3C4QzltkMkXa5DvV7e
+        xgjD7WVHrbCVo/Vz5Xl4dYMdPnz546/fBNVrfiLsNDZsLTTY/+XBzlu418365DyABK32pQDPOuOC
+        HUGPdRWwffOBvn75E7D3fuRvP2TOft+V3/ltPOOdvrinZw7H10elKh7e+qwr8vyXJ+jLuxx+fAea
+        B9X20bc/Jy7r0wT1W+KoSUI4rHC3DWBQrTr2PmQEM51LE3KPgFDHPmn1ll7VCpW9EhDu64f7Je16
+        CPJDSv/y09/+QXIa8U14V+53fh3gdq5B/Uxn2boeNPJ3v3+8aL7HjgbsVvH9zVqGNVPNWkWFC3yM
+        maeDWZ3SBB57y8YPN1RdsT4ad3iuY5kweZ3YlHnajMjj8PDrxlwZKVgWKN/8JLydsmGcH64FvvyG
+        2l7yqIXJPDXw16+5uJ445C03E7Sl1egPYVHojNJGQy3sK7LVYkVfvL0yg/FWX+h+cT9gDo6z+ePZ
+        1PsQD/A7fbgrWtH09FLWjT7LmRKD24frCT9fB33clpICnVug4PjC37J5rG0Cw3MXUHVBU0buZKqg
+        9pAbIn/95dZpUAKNIvz2x6gwEJl/8Art04akzwyB1VkOFij8JvKRKZbRXDMmwFLv9vj2kMdo2Vyu
+        IXwKZw5rEoEDO5eage7lOyVojsmwGn53/ulzwmXRC3Q/fbbi7o3d8fqu57MUWCiWGxMb57cyrPHE
+        J3Cjdi+q7kUjEz+N3/x4Az7qzjZjiHox9Iz3RL/nq1v20tGAuXUx8SGWnJpwsttA8VE1VK0uh0E0
+        9WsFke0fiJArn+jbLwgB7qwdVvFwcLfpLr//rV93NfV0QZ96CF3zEGMHZCoQxtkq4MtZL1g7GLo7
+        f/UUcJos80EkGy7jnrWKmizkCbt4G7AU94uHCpBSAvNyD2axGTiYB82dgAFag6iatQY3jZZh/Cgs
+        9u0H8gicu+2X56g1PxmbHF6r4ogvQjOBbhaDFZqmusEnutHB+uuH3o2Vo4ar9+58wKqCEsOzsMtX
+        jM03q+pQrfYMHxVniZaW0zuknfPNr75m7CxGBrSLM4+vn2pwl3Qrj8BiRYKdahrc6ZhgCwqaUmNL
+        /zRg+PYf//qLxxBw0fzrXzqiUdCQShyjXz+tpM6QUe/L9+kkXToI1nuGL1qc6uu9VgVk1G6HHRO/
+        f/mz/vgNdpX247L+eWrR1WogVpOyAV9+3EKBozw2/L0BmKy+O0iiTsJJHL0yui0YD6XLsyTAdh71
+        Mj9mH/7zuxXwX//68+d//G4YtN0jf30vBkz5Mv3H/7kq8B/if4xt+nr9vYZAxrTI//n3/76B8M9n
+        6NrP9D+nrsnf4z///rMV/t41+GfqpvT1/z7/1/dV//Wv/wUAAP//AwBcfFVx4CAAAA==
+    headers:
+      CF-RAY:
+      - 931fceef786ded38-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 17 Apr 2025 23:47:35 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=fj4RMXSXRDQjE2CFC6CGC3dVcJ8cl2Cbu8alijwMHA8-1744933655-1.0.1.1-M3c3AI4XQa.0GJoanNACuOm2aEL4xjqHR1grxIP3olFvq3e0eFHwQTvCF20YwR_OLiMJUH87eNUwgziawMccsxjR9OVZyDr5._5Wts6CrqA;
+        path=/; expires=Fri, 18-Apr-25 00:17:35 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=MSkpJsQZtdyIGvrl2mIwy0a_We8H6CIrS7etFgRBl2Y-1744933655703-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '140'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-84959bbcd5-rzqvq
+      x-envoy-upstream-service-time:
+      - '110'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999986'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_dd3ef61c4765b46ed7db80ddfe261f41
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Information Agent.
+      You have access to specific knowledge sources.\nYour personal goal is: Provide
+      information based on knowledge sources\nTo give my best complete final answer
+      to the task respond using the exact following format:\n\nThought: I now can
+      give a great answer\nFinal Answer: Your final answer must be the great and the
+      most complete as possible, it must be outcome described.\n\nI MUST use these
+      formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task:
+      What is Brandon''s favorite color?\n\nThis is the expected criteria for your
+      final answer: Brandon''s favorite color.\nyou MUST return the actual complete
+      content as the final answer, not a summary.\n\nBegin! This is VERY important
+      to you, use the tools available and give your best Final Answer, your job depends
+      on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '926'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jFLBbtswDL37KwhdeokLx0mbOLd2WIAC63YZdthWGIpMO9xkUZDkpEWR
+        fx/kpLG7dUAvBszHR733yOcEQFAlViDUVgbVWp3efv66LvKPRd7Q/f57vtaf7m6ePjze774sv23E
+        JDJ48wtVeGFdKm6txkBsjrByKAPGqdPFfF7MZtdXVz3QcoU60hob0jmnLRlK8yyfp9kinS5P7C2T
+        Qi9W8CMBAHjuv1GnqfBRrCCbvFRa9F42KFbnJgDhWMeKkN6TD9IEMRlAxSag6aXfgeE9KGmgoR2C
+        hCbKBmn8Hh3AT7MmIzXc9P8ruHXSVGwuPNRyx44CgmLNDsjDRnd4OX7GYd15Ga2aTusRII3hIGNU
+        vcGHE3I4W9LcWMcb/xdV1GTIb0uH0rOJ8n1gK3r0kAA89NF1r9IQ1nFrQxn4N/bPTa+Xx3li2NgI
+        LU5g4CD1qL5cTN6YV1YYJGk/Cl8oqbZYDdRhU7KriEdAMnL9r5q3Zh+dk2neM34AlEIbsCqtw4rU
+        a8dDm8N40P9rO6fcCxYe3Y4UloHQxU1UWMtOH89M+CcfsC1rMg066+h4a7Uts1mRL/M8KzKRHJI/
+        AAAA//8DALRhJdF5AwAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 931fcef51a67f947-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 17 Apr 2025 23:47:36 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=7agwu5JV1OJvEFNhvfvqdgWf.HoMyIni9D85soRl3WE-1744933656-1.0.1.1-dKUwAZnjjuuiswFKWGsxpwHNBJUpjhYlZvfZpyNQIejxEJrXMCppgPvtQ9wa4SKezLmKqftvn_H.bAx_AEFJD2EWm5V6R_uK8.odneErR6A;
+        path=/; expires=Fri, 18-Apr-25 00:17:36 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=LdTrzwZYrB6ZyQLY7NdaaHVpDVFvIjYm3arSpNy87wU-1744933656504-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '540'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999802'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_8837be6510731522fd5ac4b75c11d486
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_task_with_max_execution_time.yaml
+++ b/tests/cassettes/test_task_with_max_execution_time.yaml
@@ -0,0 +1,643 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
+      an expert researcher, specialized in technology, software engineering, AI and
+      startups. You work as a freelancer and are now working on doing research and
+      analysis for a new customer.\nYour personal goal is: Make the best research
+      and analysis on content about AI and AI agents. Use the tool provided to you.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: what amazing tool\nTool Arguments: {}\nTool
+      Description: My tool\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought:
+      you should always think about what to do\nAction: the action to take, only one
+      name of [what amazing tool], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple JSON object, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
+      all necessary information is gathered, return the following format:\n\n```\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question\n```"}, {"role": "user", "content": "\nCurrent Task: Give me
+      a list of 5 interesting ideas to explore for an article, what makes them unique
+      and interesting.\n\nThis is the expected criteria for your final answer: Bullet
+      point list of 5 interesting ideas.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\n\nBegin! This is VERY important to you,
+      use the tools available and give your best Final Answer, your job depends on
+      it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1666'
+      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:
+    content: "{\n  \"id\": \"chatcmpl-BNNPLDDeGQYegE6neZK6ogJmDOMYs\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744911223,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I need to generate interesting ideas
+      for an article related to AI and AI agents. \\n\\nAction: what amazing tool
+      \ \\nAction Input: {}  \",\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 326,\n    \"completion_tokens\":
+      28,\n    \"total_tokens\": 354,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_0392822090\"\n}\n"
+    headers:
+      CF-RAY:
+      - 931dab4c79581b2e-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 17 Apr 2025 17:33:44 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:
+      - '736'
+      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:
+      - '149999620'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_0767caa75d1851f392ea34a68763b1bc
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CqzaAQokCiIKDHNlcnZpY2UubmFtZRISChBjcmV3QUktdGVsZW1ldHJ5EoLaAQoSChBjcmV3YWku
+      dGVsZW1ldHJ5EpYIChAm+VDVVrKTGFLYrGmqyFN/EgiVIKrLvczC6SoMQ3JldyBDcmVhdGVkMAE5
+      uBnOOYMrNxhBWHDXOYMrNxhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMTQuMEobCg5weXRob25f
+      dmVyc2lvbhIJCgczLjExLjEySi4KCGNyZXdfa2V5EiIKIDVlNmVmZmU2ODBhNWQ5N2RjMzg3M2Ix
+      NDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokMzI4MzZhOTctMGIyYi00MTAwLTgxZDYtYmIwZWJjY2I2
+      ZDYyShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRj
+      cmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBj
+      cmV3X2ZpbmdlcnByaW50EiYKJGQ5YmEwZDE3LTE5YjMtNGQ5Yi04ZTNmLThiMjNhOGM0YzgyM0o7
+      ChtjcmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0My4yMzg4
+      MzhKzQIKC2NyZXdfYWdlbnRzEr0CCroCW3sia2V5IjogIjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdk
+      NDI0MGEyOTRkIiwgImlkIjogImMzMWMwNzRmLTg5Y2YtNGRkNi04ZTY2LWM3NDM1OTc0NmNkMSIs
+      ICJyb2xlIjogIlNjb3JlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1h
+      eF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8t
+      bWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlv
+      bj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K+wEK
+      CmNyZXdfdGFza3MS7AEK6QFbeyJrZXkiOiAiMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFi
+      ODYiLCAiaWQiOiAiYTNiODU1ODAtZTVjNC00YmU2LWI0ZmItMDU1NDU2Y2RkZWJkIiwgImFzeW5j
+      X2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6
+      ICJTY29yZXIiLCAiYWdlbnRfa2V5IjogIjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRk
+      IiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASgAQKED9XhldOUhgSlcVbrT/HuRwSCCF7
+      8YboEaZnKgxUYXNrIENyZWF0ZWQwATlYmeU5gys3GEHwx+c5gys3GEouCghjcmV3X2tleRIiCiA1
+      ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0oxCgdjcmV3X2lkEiYKJDMyODM2YTk3LTBi
+      MmItNDEwMC04MWQ2LWJiMGViY2NiNmQ2MkouCgh0YXNrX2tleRIiCiAyN2VmMzhjYzk5ZGE0YThk
+      ZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0YXNrX2lkEiYKJGEzYjg1NTgwLWU1YzQtNGJlNi1iNGZiLTA1
+      NTQ1NmNkZGViZEo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJGQ5YmEwZDE3LTE5YjMtNGQ5Yi04ZTNm
+      LThiMjNhOGM0YzgyM0o6ChB0YXNrX2ZpbmdlcnByaW50EiYKJDc0OTEwMDcxLTM1MWQtNDljNy1h
+      YmZlLTJmMWZhNWUzZTEyYko7Cht0YXNrX2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0w
+      NC0xN1QxNDozMzo0My4yMzg4MDFKOwoRYWdlbnRfZmluZ2VycHJpbnQSJgokYzMyNmIyMWUtYWJh
+      YS00N2ZjLWE0NGQtMzk2NTQ4ZjczZTRiegIYAYUBAAEAABKYCAoQH3AbYnQyty/P5gHiJzrjLxII
+      PR8P3tNCS74qDENyZXcgQ3JlYXRlZDABOYgCyj6DKzcYQSD71D6DKzcYShsKDmNyZXdhaV92ZXJz
+      aW9uEgkKBzAuMTE0LjBKGwoOcHl0aG9uX3ZlcnNpb24SCQoHMy4xMS4xMkouCghjcmV3X2tleRIi
+      CiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0oxCgdjcmV3X2lkEiYKJDBkY2JhOGY4
+      LTdhYzQtNDdmMC04ZWIxLWE0ZTJkODFjOGZkYkoeCgxjcmV3X3Byb2Nlc3MSDgoMaGllcmFyY2hp
+      Y2FsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jl
+      d19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJDJiYzYzYWE1LWU5
+      YzYtNDAxNi1hMTdiLWFmZDM5ZWJlYmEwNko7ChtjcmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQS
+      HAoaMjAyNS0wNC0xN1QxNDozMzo0My4zMjI3OTlKzQIKC2NyZXdfYWdlbnRzEr0CCroCW3sia2V5
+      IjogIjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgImlkIjogImYyY2Y4YWRlLTdj
+      YmYtNDkwMS1hODMwLWE3ZDkxODA4NjI3NCIsICJyb2xlIjogIlNjb3JlciIsICJ2ZXJib3NlPyI6
+      IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGlu
+      Z19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/Ijog
+      ZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6
+      IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K+wEKCmNyZXdfdGFza3MS7AEK6QFbeyJrZXkiOiAiMjdl
+      ZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODYiLCAiaWQiOiAiMWY3MTljNTktOTJjMC00NGU1
+      LWFmMjUtNzIwYjE1NWE1Njg1IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lu
+      cHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJTY29yZXIiLCAiYWdlbnRfa2V5IjogIjkyZTdl
+      YjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQAB
+      AAASgAQKEIVZhLW3PhEOxntJYQn8IYkSCDNELyrmM+eYKgxUYXNrIENyZWF0ZWQwATlYr+0+gys3
+      GEGIJO4+gys3GEouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2Zh
+      M0oxCgdjcmV3X2lkEiYKJDBkY2JhOGY4LTdhYzQtNDdmMC04ZWIxLWE0ZTJkODFjOGZkYkouCgh0
+      YXNrX2tleRIiCiAyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0YXNrX2lkEiYK
+      JDFmNzE5YzU5LTkyYzAtNDRlNS1hZjI1LTcyMGIxNTVhNTY4NUo6ChBjcmV3X2ZpbmdlcnByaW50
+      EiYKJDJiYzYzYWE1LWU5YzYtNDAxNi1hMTdiLWFmZDM5ZWJlYmEwNko6ChB0YXNrX2ZpbmdlcnBy
+      aW50EiYKJGJmMDU5YjBiLWFlYmYtNGIzMS04YTc4LTA2ZTlmMjcyZDQ2MEo7Cht0YXNrX2Zpbmdl
+      cnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0My4zMjI3NTVKOwoRYWdlbnRf
+      ZmluZ2VycHJpbnQSJgokY2IzZWQ2ZGQtNzEzNC00YTc3LThiMjctZWIwZGRkZGZlMjdiegIYAYUB
+      AAEAABKdAQoQ6S1CnqyOxKwRN/Vq7X81HRIIso7ugOmXnjEqClRvb2wgVXNhZ2UwATnAIk4/gys3
+      GEE4YlU/gys3GEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjExNC4wSigKCXRvb2xfbmFtZRIbChlE
+      ZWxlZ2F0ZSB3b3JrIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASlggKENaM
+      zYnzHCL03v+Ihe5ZidsSCIXobzKG03Z6KgxDcmV3IENyZWF0ZWQwATlQ8uM/gys3GEFIfOk/gys3
+      GEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjExNC4wShsKDnB5dGhvbl92ZXJzaW9uEgkKBzMuMTEu
+      MTJKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4MGE1ZDk3ZGMzODczYjE0ODI1Y2NmYTNKMQoHY3Jl
+      d19pZBImCiQ5ZmYzZmU1ZC01YmYyLTRlNzEtODU0ZS05OTAyZGYxYzIxYTRKHAoMY3Jld19wcm9j
+      ZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rh
+      c2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSjoKEGNyZXdfZmluZ2VycHJpbnQS
+      JgokOTkwOTQ1YmUtOTczMS00ZTQxLTg5ZDAtYzEzMjljNGQ3NjQ5SjsKG2NyZXdfZmluZ2VycHJp
+      bnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjM0MTIyM0rNAgoLY3Jld19hZ2Vu
+      dHMSvQIKugJbeyJrZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQiLCAiaWQi
+      OiAiMGM3NDhlNDgtOGNmNC00ZDJhLWFlYWMtZDY5OTUzMDkwZThmIiwgInJvbGUiOiAiU2NvcmVy
+      IiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDI1LCAibWF4X3JwbSI6IG51bGwsICJm
+      dW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRp
+      b25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4
+      X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUr7AQoKY3Jld190YXNrcxLsAQrp
+      AVt7ImtleSI6ICIyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NiIsICJpZCI6ICI2NzBj
+      MjdhOS1kYTc3LTRhNTQtYmYxYS1mM2M0YjVlNTcwNDkiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZh
+      bHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIlNjb3JlciIsICJhZ2Vu
+      dF9rZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQiLCAidG9vbHNfbmFtZXMi
+      OiBbXX1degIYAYUBAAEAABKABAoQ0PunZB/jswUd8i8ahTz20BIIFtRhrWbDsGIqDFRhc2sgQ3Jl
+      YXRlZDABOejM8z+DKzcYQZAu9D+DKzcYSi4KCGNyZXdfa2V5EiIKIDVlNmVmZmU2ODBhNWQ5N2Rj
+      Mzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokOWZmM2ZlNWQtNWJmMi00ZTcxLTg1NGUtOTkw
+      MmRmMWMyMWE0Si4KCHRhc2tfa2V5EiIKIDI3ZWYzOGNjOTlkYTRhOGRlZDcwZWQ0MDZlNDRhYjg2
+      SjEKB3Rhc2tfaWQSJgokNjcwYzI3YTktZGE3Ny00YTU0LWJmMWEtZjNjNGI1ZTU3MDQ5SjoKEGNy
+      ZXdfZmluZ2VycHJpbnQSJgokOTkwOTQ1YmUtOTczMS00ZTQxLTg5ZDAtYzEzMjljNGQ3NjQ5SjoK
+      EHRhc2tfZmluZ2VycHJpbnQSJgokMjczZmM3YjYtZGJmYS00MzYyLWEwZTEtNzhhNjJjNDY0OTlh
+      SjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjM0
+      MTE5NUo7ChFhZ2VudF9maW5nZXJwcmludBImCiQwNTc3MWI4Ny04ZGIzLTRhZGYtOWJhZC0yNzcw
+      ZjgzYTZiYTN6AhgBhQEAAQAAEpgIChA5RacttE9X5amPuTPHLuYDEgiZ/RIthMTU5yoMQ3JldyBD
+      cmVhdGVkMAE5EC+lQIMrNxhBsJGsQIMrNxhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMTQuMEob
+      Cg5weXRob25fdmVyc2lvbhIJCgczLjExLjEySi4KCGNyZXdfa2V5EiIKIDVlNmVmZmU2ODBhNWQ5
+      N2RjMzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokMTc5MzYxNTItNDJmMi00YmY3LWIzOTEt
+      ZTU0MDU1ZTY2NGU4Sh4KDGNyZXdfcHJvY2VzcxIOCgxoaWVyYXJjaGljYWxKEQoLY3Jld19tZW1v
+      cnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2Vu
+      dHMSAhgBSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokNjI0ZTI1NjEtMDFkOC00YmNkLWJhMjEtZDcx
+      ZTQ0MTZkNGJiSjsKG2NyZXdfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0LTE3VDE0
+      OjMzOjQzLjM1Mzg3M0rNAgoLY3Jld19hZ2VudHMSvQIKugJbeyJrZXkiOiAiOTJlN2ViMTkxNjY0
+      YzkzNTc4NWVkN2Q0MjQwYTI5NGQiLCAiaWQiOiAiYTEyMTFiNmYtMzFhMy00MzY4LWI5YzItZDNh
+      NjA1NTZlOTk2IiwgInJvbGUiOiAiU2NvcmVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRl
+      ciI6IDI1LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxt
+      IjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2Nv
+      ZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVz
+      IjogW119XUr7AQoKY3Jld190YXNrcxLsAQrpAVt7ImtleSI6ICIyN2VmMzhjYzk5ZGE0YThkZWQ3
+      MGVkNDA2ZTQ0YWI4NiIsICJpZCI6ICI3ZjJjNGIxMi00MjNhLTRmMTctOTZiMS0zZmEyNmUzMDM3
+      MmMiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJh
+      Z2VudF9yb2xlIjogIlNjb3JlciIsICJhZ2VudF9rZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVk
+      N2Q0MjQwYTI5NGQiLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQG2i2Mf2AK81I
+      gFDuyTZ4hxIIGTCH8bEW9REqDFRhc2sgQ3JlYXRlZDABOajZvECDKzcYQbArvUCDKzcYSi4KCGNy
+      ZXdfa2V5EiIKIDVlNmVmZmU2ODBhNWQ5N2RjMzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgok
+      MTc5MzYxNTItNDJmMi00YmY3LWIzOTEtZTU0MDU1ZTY2NGU4Si4KCHRhc2tfa2V5EiIKIDI3ZWYz
+      OGNjOTlkYTRhOGRlZDcwZWQ0MDZlNDRhYjg2SjEKB3Rhc2tfaWQSJgokN2YyYzRiMTItNDIzYS00
+      ZjE3LTk2YjEtM2ZhMjZlMzAzNzJjSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokNjI0ZTI1NjEtMDFk
+      OC00YmNkLWJhMjEtZDcxZTQ0MTZkNGJiSjoKEHRhc2tfZmluZ2VycHJpbnQSJgokZjViNmU5YjUt
+      ZjcxMi00YzM3LTkyYjAtMWFjNzQ2ZTYzYWJjSjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9h
+      dBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjM1Mzg0M0o7ChFhZ2VudF9maW5nZXJwcmludBImCiQ1
+      ZjhkM2YwYS1lODZhLTRiMmUtYWFmMC1jOWMyMDg2N2M1ODR6AhgBhQEAAQAAEpwBChBCoZs2F2Pk
+      GqD1dlo+B0jIEgh/8w+r7HLXDioKVG9vbCBVc2FnZTABOfhQHUGDKzcYQeChJUGDKzcYShsKDmNy
+      ZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKJwoJdG9vbF9uYW1lEhoKGEFzayBxdWVzdGlvbiB0byBj
+      b3dvcmtlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpYIChAtKHG1/6WFVXbuKiUU/tulEggA
+      5PFku/BBtSoMQ3JldyBDcmVhdGVkMAE5qOuzQYMrNxhBYNO5QYMrNxhKGwoOY3Jld2FpX3ZlcnNp
+      b24SCQoHMC4xMTQuMEobCg5weXRob25fdmVyc2lvbhIJCgczLjExLjEySi4KCGNyZXdfa2V5EiIK
+      IDVlNmVmZmU2ODBhNWQ5N2RjMzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokNWQzODQyMmQt
+      NTk2MC00NGQ0LWFmZjctYWM5MDFiMjU1NzM5ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFs
+      ShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19u
+      dW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJGZhNWYxODc1LWRiYTQt
+      NDc2MS04ZDk4LTliNzlmNDg2ZTNlY0o7ChtjcmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoa
+      MjAyNS0wNC0xN1QxNDozMzo0My4zNzE2MzZKzQIKC2NyZXdfYWdlbnRzEr0CCroCW3sia2V5Ijog
+      IjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgImlkIjogIjgwZDg1ZDY3LTg3M2Qt
+      NDFhNi05MzY1LWJkODVjYTc5MGI2MyIsICJyb2xlIjogIlNjb3JlciIsICJ2ZXJib3NlPyI6IGZh
+      bHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19s
+      bG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFs
+      c2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIs
+      ICJ0b29sc19uYW1lcyI6IFtdfV1K+wEKCmNyZXdfdGFza3MS7AEK6QFbeyJrZXkiOiAiMjdlZjM4
+      Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODYiLCAiaWQiOiAiZWYwNmQ3NTEtZWY2Yy00YjJiLWI2
+      MTQtMmVhMmU1NGM0MjVlIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0
+      PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJTY29yZXIiLCAiYWdlbnRfa2V5IjogIjkyZTdlYjE5
+      MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAAS
+      gAQKEJUYH+zYJdlQxAU/SEz07wwSCHIyR0YIxKoQKgxUYXNrIENyZWF0ZWQwATnYg8NBgys3GEFQ
+      7cNBgys3GEouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0ox
+      CgdjcmV3X2lkEiYKJDVkMzg0MjJkLTU5NjAtNDRkNC1hZmY3LWFjOTAxYjI1NTczOUouCgh0YXNr
+      X2tleRIiCiAyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0YXNrX2lkEiYKJGVm
+      MDZkNzUxLWVmNmMtNGIyYi1iNjE0LTJlYTJlNTRjNDI1ZUo6ChBjcmV3X2ZpbmdlcnByaW50EiYK
+      JGZhNWYxODc1LWRiYTQtNDc2MS04ZDk4LTliNzlmNDg2ZTNlY0o6ChB0YXNrX2ZpbmdlcnByaW50
+      EiYKJDA1ZTU2ZTIzLWI5YjgtNDIwMy05MWYwLTY2ZmE5MDgzNzYzNUo7Cht0YXNrX2ZpbmdlcnBy
+      aW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0My4zNzE2MDJKOwoRYWdlbnRfZmlu
+      Z2VycHJpbnQSJgokZGZiMDEzYTItNzg0MC00NDFhLTg1YzMtMzI0OWQ1OGJhNmIzegIYAYUBAAEA
+      ABKWCAoQ67KSQgBBFIpwJAjqKwKTNxIIPHptHAGKIGYqDENyZXcgQ3JlYXRlZDABOeB7T0KDKzcY
+      QVhEVUKDKzcYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKGwoOcHl0aG9uX3ZlcnNpb24S
+      CQoHMy4xMS4xMkouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2Zh
+      M0oxCgdjcmV3X2lkEiYKJDRmOTE0YWZhLTVlMTAtNDU3Ni1hYjJjLWVkZmNlZWQzYTZiYkocCgxj
+      cmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1i
+      ZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFKOgoQY3Jld19maW5n
+      ZXJwcmludBImCiQzODFkOTIwYi1iMGE1LTRiNGUtYTQ0OS1kZjg5OGNjZjVmZDdKOwobY3Jld19m
+      aW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIwMjUtMDQtMTdUMTQ6MzM6NDMuMzgxODc1Ss0CCgtj
+      cmV3X2FnZW50cxK9Agq6Alt7ImtleSI6ICI5MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0
+      ZCIsICJpZCI6ICI5ZjVhZTRmOC02MjkwLTQ5NTUtOGI2OC00YmNjOTM5ZjhhMDkiLCAicm9sZSI6
+      ICJTY29yZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJtYXhfcnBtIjog
+      bnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAi
+      ZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFs
+      c2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSvsBCgpjcmV3X3Rh
+      c2tzEuwBCukBW3sia2V5IjogIjI3ZWYzOGNjOTlkYTRhOGRlZDcwZWQ0MDZlNDRhYjg2IiwgImlk
+      IjogIjViODI1OWU3LWI2Y2YtNGJlYi1iYTRiLWY3MDg4Y2E4YWM3NiIsICJhc3luY19leGVjdXRp
+      b24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiU2NvcmVy
+      IiwgImFnZW50X2tleSI6ICI5MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJ0b29s
+      c19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChCDE114uxBCLFPLICeD1DCNEgiFJ3IambqX4yoM
+      VGFzayBDcmVhdGVkMAE5+P9iQoMrNxhBcGljQoMrNxhKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4
+      MGE1ZDk3ZGMzODczYjE0ODI1Y2NmYTNKMQoHY3Jld19pZBImCiQ0ZjkxNGFmYS01ZTEwLTQ1NzYt
+      YWIyYy1lZGZjZWVkM2E2YmJKLgoIdGFza19rZXkSIgogMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQw
+      NmU0NGFiODZKMQoHdGFza19pZBImCiQ1YjgyNTllNy1iNmNmLTRiZWItYmE0Yi1mNzA4OGNhOGFj
+      NzZKOgoQY3Jld19maW5nZXJwcmludBImCiQzODFkOTIwYi1iMGE1LTRiNGUtYTQ0OS1kZjg5OGNj
+      ZjVmZDdKOgoQdGFza19maW5nZXJwcmludBImCiRmZWIzZDVjYy0yMzEwLTRhNDgtOWQ5My1jMzQ5
+      MTI0MGU3NTlKOwobdGFza19maW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIwMjUtMDQtMTdUMTQ6
+      MzM6NDMuMzgxODQ4SjsKEWFnZW50X2ZpbmdlcnByaW50EiYKJDdhYzY3YTkzLTkwNjctNGJjNC1i
+      NmFmLTcxZWVjZmRjNzEzOHoCGAGFAQABAAASmAgKEGmCIFMw9GayxClAketnXWsSCPvb3mKDZYhn
+      KgxDcmV3IENyZWF0ZWQwATkA88JGgys3GEGAhMpGgys3GEobCg5jcmV3YWlfdmVyc2lvbhIJCgcw
+      LjExNC4wShsKDnB5dGhvbl92ZXJzaW9uEgkKBzMuMTEuMTJKLgoIY3Jld19rZXkSIgogNWU2ZWZm
+      ZTY4MGE1ZDk3ZGMzODczYjE0ODI1Y2NmYTNKMQoHY3Jld19pZBImCiRmNmE1MGVkMy02ODk5LTQ4
+      MTItODVkNy1iNDZlYTQyNzUwN2FKHgoMY3Jld19wcm9jZXNzEg4KDGhpZXJhcmNoaWNhbEoRCgtj
+      cmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVy
+      X29mX2FnZW50cxICGAFKOgoQY3Jld19maW5nZXJwcmludBImCiQzYzRlM2VmZS01YmQ0LTRkNDgt
+      YThmNS0yOGY0NDdhNDI0OGRKOwobY3Jld19maW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIwMjUt
+      MDQtMTdUMTQ6MzM6NDMuNDU2MDg4Ss0CCgtjcmV3X2FnZW50cxK9Agq6Alt7ImtleSI6ICI5MmU3
+      ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJpZCI6ICJmNzMwNTE0Mi1jOTViLTQ0MmQt
+      YjJiOS1jYTVhN2IzMzZlYjMiLCAicm9sZSI6ICJTY29yZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwg
+      Im1heF9pdGVyIjogMjUsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjog
+      IiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAi
+      YWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9v
+      bHNfbmFtZXMiOiBbXX1dSvsBCgpjcmV3X3Rhc2tzEuwBCukBW3sia2V5IjogIjI3ZWYzOGNjOTlk
+      YTRhOGRlZDcwZWQ0MDZlNDRhYjg2IiwgImlkIjogIjU5MDRiMDg5LTMzNzYtNDZhMy04NWU1LTRk
+      ZTc0NDQyYTljYyIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBm
+      YWxzZSwgImFnZW50X3JvbGUiOiAiU2NvcmVyIiwgImFnZW50X2tleSI6ICI5MmU3ZWIxOTE2NjRj
+      OTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChD9
+      DkCz0iVsHA4a1S3+yN8lEgjsMseCiYSvFioMVGFzayBDcmVhdGVkMAE5+ATcRoMrNxhB0F7cRoMr
+      NxhKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4MGE1ZDk3ZGMzODczYjE0ODI1Y2NmYTNKMQoHY3Jl
+      d19pZBImCiRmNmE1MGVkMy02ODk5LTQ4MTItODVkNy1iNDZlYTQyNzUwN2FKLgoIdGFza19rZXkS
+      IgogMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFza19pZBImCiQ1OTA0YjA4
+      OS0zMzc2LTQ2YTMtODVlNS00ZGU3NDQ0MmE5Y2NKOgoQY3Jld19maW5nZXJwcmludBImCiQzYzRl
+      M2VmZS01YmQ0LTRkNDgtYThmNS0yOGY0NDdhNDI0OGRKOgoQdGFza19maW5nZXJwcmludBImCiQ3
+      MjExMmY3OS1iMWU3LTRkYTctYTg4YS00NjU3NTJiZTIwZDdKOwobdGFza19maW5nZXJwcmludF9j
+      cmVhdGVkX2F0EhwKGjIwMjUtMDQtMTdUMTQ6MzM6NDMuNDU2MDU5SjsKEWFnZW50X2ZpbmdlcnBy
+      aW50EiYKJGJiMzQ0NzIxLTE3M2QtNGRmNS1iMWRmLWQ2NjBkZjZlZmVjZnoCGAGFAQABAAASnAEK
+      EOg/b+TBCd7kQOaEdNwvgZoSCGYJctohLuuaKgpUb29sIFVzYWdlMAE58JA0R4MrNxhBqOM9R4Mr
+      NxhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMTQuMEonCgl0b29sX25hbWUSGgoYQXNrIHF1ZXN0
+      aW9uIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASlwoKEMn/aYwi4Jc7AohP
+      Y7puRXsSCB83OjVnCZfLKgxDcmV3IENyZWF0ZWQwATlw8dVHgys3GEGA9NtHgys3GEobCg5jcmV3
+      YWlfdmVyc2lvbhIJCgcwLjExNC4wShsKDnB5dGhvbl92ZXJzaW9uEgkKBzMuMTEuMTJKLgoIY3Jl
+      d19rZXkSIgogZDQyNjA4MzNhYjBjMjBiYjQ0OTIyYzc5OWFhOTZiNGFKMQoHY3Jld19pZBImCiQx
+      ZjA0NjU0YS05ODE5LTQ0MTEtOTVlZC1kMmMwMTJlNWU3YjJKHAoMY3Jld19wcm9jZXNzEgwKCnNl
+      cXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAkob
+      ChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokYjhhYjU0
+      YzEtYjFjZS00OGIyLTlkODMtNDVkNzkyMTkxOWQ0SjsKG2NyZXdfZmluZ2VycHJpbnRfY3JlYXRl
+      ZF9hdBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjQ3NDIyN0rlAgoLY3Jld19hZ2VudHMS1QIK0gJb
+      eyJrZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQiLCAiaWQiOiAiMjg5YzIz
+      NzgtNWUxOC00YzJiLWE1NDMtNzVkOTk5YWUyYWQyIiwgInJvbGUiOiAiU2NvcmVyIiwgInZlcmJv
+      c2U/IjogdHJ1ZSwgIm1heF9pdGVyIjogMjUsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2Nh
+      bGxpbmdfbGxtIjogImdwdC0zLjUtdHVyYm8tMDEyNSIsICJsbG0iOiAiZ3B0LTQtMDEyNS1wcmV2
+      aWV3IiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9u
+      PyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUrkAwoK
+      Y3Jld190YXNrcxLVAwrSA1t7ImtleSI6ICIyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4
+      NiIsICJpZCI6ICJiNTAxMWUwNi02YTdmLTQzYWItYWQzNy1mNGI4ODBhMmJlYjgiLCAiYXN5bmNf
+      ZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjog
+      IlNjb3JlciIsICJhZ2VudF9rZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQi
+      LCAidG9vbHNfbmFtZXMiOiBbXX0sIHsia2V5IjogIjYwOWRlZTM5MTA4OGNkMWM4N2I4ZmE2NmFh
+      NjdhZGJlIiwgImlkIjogIjRiODE5NjQ5LTYyMjQtNGQ3Mi1hZDFkLTM0ODZhYzBkODQwNSIsICJh
+      c3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3Jv
+      bGUiOiAiU2NvcmVyIiwgImFnZW50X2tleSI6ICI5MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBh
+      Mjk0ZCIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChCdiwcYoV5twj//vpjaNfMl
+      EghUv7y5H7+dXioMVGFzayBDcmVhdGVkMAE5wN3kR4MrNxhBsDPlR4MrNxhKLgoIY3Jld19rZXkS
+      IgogZDQyNjA4MzNhYjBjMjBiYjQ0OTIyYzc5OWFhOTZiNGFKMQoHY3Jld19pZBImCiQxZjA0NjU0
+      YS05ODE5LTQ0MTEtOTVlZC1kMmMwMTJlNWU3YjJKLgoIdGFza19rZXkSIgogMjdlZjM4Y2M5OWRh
+      NGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFza19pZBImCiRiNTAxMWUwNi02YTdmLTQzYWItYWQz
+      Ny1mNGI4ODBhMmJlYjhKOgoQY3Jld19maW5nZXJwcmludBImCiRiOGFiNTRjMS1iMWNlLTQ4YjIt
+      OWQ4My00NWQ3OTIxOTE5ZDRKOgoQdGFza19maW5nZXJwcmludBImCiQ3NDcyMTM3Yi0wYzBkLTRi
+      OTEtYTgwYy01YzZkYWQwZmM3YTBKOwobdGFza19maW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIw
+      MjUtMDQtMTdUMTQ6MzM6NDMuNDc0MTc1SjsKEWFnZW50X2ZpbmdlcnByaW50EiYKJDVlMWU1Nzdh
+      LWY5N2QtNDA2OS04NzNmLTc1ZjYyMDE0ZWJlNnoCGAGFAQABAAASgAQKEA6OsjCwXi+o2MUfKyS+
+      TmgSCOIWlM7TtxNCKgxUYXNrIENyZWF0ZWQwATmQ915Igys3GEHYaF9Igys3GEouCghjcmV3X2tl
+      eRIiCiBkNDI2MDgzM2FiMGMyMGJiNDQ5MjJjNzk5YWE5NmI0YUoxCgdjcmV3X2lkEiYKJDFmMDQ2
+      NTRhLTk4MTktNDQxMS05NWVkLWQyYzAxMmU1ZTdiMkouCgh0YXNrX2tleRIiCiA2MDlkZWUzOTEw
+      ODhjZDFjODdiOGZhNjZhYTY3YWRiZUoxCgd0YXNrX2lkEiYKJDRiODE5NjQ5LTYyMjQtNGQ3Mi1h
+      ZDFkLTM0ODZhYzBkODQwNUo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJGI4YWI1NGMxLWIxY2UtNDhi
+      Mi05ZDgzLTQ1ZDc5MjE5MTlkNEo6ChB0YXNrX2ZpbmdlcnByaW50EiYKJGYwZWUxMjY2LWExNzIt
+      NDhiMi1iMTM2LTczN2I3YWNkYWYwNko7Cht0YXNrX2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoa
+      MjAyNS0wNC0xN1QxNDozMzo0My40NzQyMDVKOwoRYWdlbnRfZmluZ2VycHJpbnQSJgokNWUxZTU3
+      N2EtZjk3ZC00MDY5LTg3M2YtNzVmNjIwMTRlYmU2egIYAYUBAAEAABL/CQoQOon8z16iVXeCtEnr
+      visR+hII1ztFvfUBPyAqDENyZXcgQ3JlYXRlZDABOYC2CUmDKzcYQVhjEUmDKzcYShsKDmNyZXdh
+      aV92ZXJzaW9uEgkKBzAuMTE0LjBKGwoOcHl0aG9uX3ZlcnNpb24SCQoHMy4xMS4xMkouCghjcmV3
+      X2tleRIiCiBhOTU0MGNkMGVhYTUzZjY3NTQzN2U5YmQ0ZmE1ZTQ0Y0oxCgdjcmV3X2lkEiYKJDFh
+      MDA5NjZhLTcwYmQtNDc4OS1hZmQxLTY5NjgzMzZjYjc2NkocCgxjcmV3X3Byb2Nlc3MSDAoKc2Vx
+      dWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgCShsK
+      FWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFKOgoQY3Jld19maW5nZXJwcmludBImCiRjOGI1ZDUx
+      My0xNzY0LTQyYWQtOGVlYS0wYWU0MDAzZTRmNTRKOwobY3Jld19maW5nZXJwcmludF9jcmVhdGVk
+      X2F0EhwKGjIwMjUtMDQtMTdUMTQ6MzM6NDMuNDk0ODMySs0CCgtjcmV3X2FnZW50cxK9Agq6Alt7
+      ImtleSI6ICI5MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJpZCI6ICIwZTg1MzFl
+      YS05MmM4LTQzMGQtYmE0Yy1jMmIxYzkwZDBlMWQiLCAicm9sZSI6ICJTY29yZXIiLCAidmVyYm9z
+      ZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2Nh
+      bGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVk
+      PyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGlt
+      aXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSuQDCgpjcmV3X3Rhc2tzEtUDCtIDW3sia2V5Ijog
+      IjI3ZWYzOGNjOTlkYTRhOGRlZDcwZWQ0MDZlNDRhYjg2IiwgImlkIjogImI2NWQ1ZGUzLWY5MjAt
+      NDVhZi1hOTgwLTA2NjBkMDU5YzdiZiIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1h
+      bl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiU2NvcmVyIiwgImFnZW50X2tleSI6ICI5
+      MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJr
+      ZXkiOiAiYjBkMzRhNmY2MjFhN2IzNTgwZDVkMWY0ZTI2NjViOTIiLCAiaWQiOiAiZjk2MDU5NzMt
+      YzYyMi00NzRjLWFhZjktYWJiOWMwZWZhYmQ0IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwg
+      Imh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJTY29yZXIiLCAiYWdlbnRfa2V5
+      IjogIjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgInRvb2xzX25hbWVzIjogW119
+      XXoCGAGFAQABAAASgAQKEGysuSY/RpRwwsmMtZmmkLgSCB3RCKVN5vMGKgxUYXNrIENyZWF0ZWQw
+      ATmYyRpJgys3GEFwIxtJgys3GEouCghjcmV3X2tleRIiCiBhOTU0MGNkMGVhYTUzZjY3NTQzN2U5
+      YmQ0ZmE1ZTQ0Y0oxCgdjcmV3X2lkEiYKJDFhMDA5NjZhLTcwYmQtNDc4OS1hZmQxLTY5NjgzMzZj
+      Yjc2NkouCgh0YXNrX2tleRIiCiAyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0
+      YXNrX2lkEiYKJGI2NWQ1ZGUzLWY5MjAtNDVhZi1hOTgwLTA2NjBkMDU5YzdiZko6ChBjcmV3X2Zp
+      bmdlcnByaW50EiYKJGM4YjVkNTEzLTE3NjQtNDJhZC04ZWVhLTBhZTQwMDNlNGY1NEo6ChB0YXNr
+      X2ZpbmdlcnByaW50EiYKJDZjNDhlMTkxLTViMjEtNDBmNi1iNmQwLWRjMWY3ZmM2YWQzN0o7Cht0
+      YXNrX2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0My40OTQ3NzdK
+      OwoRYWdlbnRfZmluZ2VycHJpbnQSJgokNTZmYTQ1MTYtM2RiNS00Mjk3LTg3NzUtOTI2MWVhNWI4
+      OWI2egIYAYUBAAEAABKABAoQJRURFvAOz5/5e2bQNRT4ChIIpSiy2tnBCrsqDFRhc2sgQ3JlYXRl
+      ZDABOdgreEmDKzcYQSCdeEmDKzcYSi4KCGNyZXdfa2V5EiIKIGE5NTQwY2QwZWFhNTNmNjc1NDM3
+      ZTliZDRmYTVlNDRjSjEKB2NyZXdfaWQSJgokMWEwMDk2NmEtNzBiZC00Nzg5LWFmZDEtNjk2ODMz
+      NmNiNzY2Si4KCHRhc2tfa2V5EiIKIGIwZDM0YTZmNjIxYTdiMzU4MGQ1ZDFmNGUyNjY1YjkySjEK
+      B3Rhc2tfaWQSJgokZjk2MDU5NzMtYzYyMi00NzRjLWFhZjktYWJiOWMwZWZhYmQ0SjoKEGNyZXdf
+      ZmluZ2VycHJpbnQSJgokYzhiNWQ1MTMtMTc2NC00MmFkLThlZWEtMGFlNDAwM2U0ZjU0SjoKEHRh
+      c2tfZmluZ2VycHJpbnQSJgokMWI0YzI5NTYtMDZkOC00NWNjLWFmYWMtNmZhZDk0MzdkNTZmSjsK
+      G3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjQ5NDgw
+      OEo7ChFhZ2VudF9maW5nZXJwcmludBImCiQ1NmZhNDUxNi0zZGI1LTQyOTctODc3NS05MjYxZWE1
+      Yjg5YjZ6AhgBhQEAAQAAEpYIChCt1KD2VBrK6+JIjPGbSQYWEghyEaRdKejivSoMQ3JldyBDcmVh
+      dGVkMAE54Fn7SYMrNxhBMPkBSoMrNxhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMTQuMEobCg5w
+      eXRob25fdmVyc2lvbhIJCgczLjExLjEySi4KCGNyZXdfa2V5EiIKIDVlNmVmZmU2ODBhNWQ5N2Rj
+      Mzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokMDQ4ZDQ5MzctNmU3OC00OWFkLTllZDMtYzVi
+      MjdlNDgyNThlShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQ
+      AEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIY
+      AUo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJDIxYjViOWQ3LWVjNTktNDBhYi1iZjY1LTk1NzM2M2Fl
+      ZDRkZEo7ChtjcmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0
+      My41MTA0NjZKzQIKC2NyZXdfYWdlbnRzEr0CCroCW3sia2V5IjogIjkyZTdlYjE5MTY2NGM5MzU3
+      ODVlZDdkNDI0MGEyOTRkIiwgImlkIjogImFkN2ExMTJiLWY5NDQtNDViYy05YzE4LWJjOWQzMDE4
+      NjE1OCIsICJyb2xlIjogIlNjb3JlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAy
+      NSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJn
+      cHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4
+      ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtd
+      fV1K+wEKCmNyZXdfdGFza3MS7AEK6QFbeyJrZXkiOiAiMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQw
+      NmU0NGFiODYiLCAiaWQiOiAiZTJmMDI3YzItZWQ2NC00MDU4LThkNzUtNjQ1OWMzYTllYWIwIiwg
+      ImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRf
+      cm9sZSI6ICJTY29yZXIiLCAiYWdlbnRfa2V5IjogIjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0
+      MGEyOTRkIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASgAQKELdQRmZyaC0pfEDI4tAa
+      vRsSCCE13pISM1wEKgxUYXNrIENyZWF0ZWQwATmwBwpKgys3GEG4WQpKgys3GEouCghjcmV3X2tl
+      eRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0oxCgdjcmV3X2lkEiYKJDA0OGQ0
+      OTM3LTZlNzgtNDlhZC05ZWQzLWM1YjI3ZTQ4MjU4ZUouCgh0YXNrX2tleRIiCiAyN2VmMzhjYzk5
+      ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0YXNrX2lkEiYKJGUyZjAyN2MyLWVkNjQtNDA1OC04
+      ZDc1LTY0NTljM2E5ZWFiMEo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJDIxYjViOWQ3LWVjNTktNDBh
+      Yi1iZjY1LTk1NzM2M2FlZDRkZEo6ChB0YXNrX2ZpbmdlcnByaW50EiYKJDNmMDU4NDE1LTNkNzUt
+      NDZhNi05OWFjLTIyZmM5OWM4OTBmM0o7Cht0YXNrX2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoa
+      MjAyNS0wNC0xN1QxNDozMzo0My41MTA0NDBKOwoRYWdlbnRfZmluZ2VycHJpbnQSJgokMjViMTgx
+      NjYtYjk3My00ZDM3LWI0OTUtMTI4YmIyMzQyNjhmegIYAYUBAAEAABKWCAoQuKzLEfp7NclRHh6f
+      Sm2/nxIIucJxIhUlkkwqDENyZXcgQ3JlYXRlZDABOfDOa0qDKzcYQfh/cUqDKzcYShsKDmNyZXdh
+      aV92ZXJzaW9uEgkKBzAuMTE0LjBKGwoOcHl0aG9uX3ZlcnNpb24SCQoHMy4xMS4xMkouCghjcmV3
+      X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0oxCgdjcmV3X2lkEiYKJDhl
+      YzE2ZWQ3LTNiYjItNDkxZC04YjYxLTI3MWYxNmZlOGFlMUocCgxjcmV3X3Byb2Nlc3MSDAoKc2Vx
+      dWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsK
+      FWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFKOgoQY3Jld19maW5nZXJwcmludBImCiQxN2MxN2Qz
+      NC1mZWZkLTQ1ZTktYWM2NS00ODY2ZTBlNTgwYTBKOwobY3Jld19maW5nZXJwcmludF9jcmVhdGVk
+      X2F0EhwKGjIwMjUtMDQtMTdUMTQ6MzM6NDMuNTE4MDI0Ss0CCgtjcmV3X2FnZW50cxK9Agq6Alt7
+      ImtleSI6ICI5MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJpZCI6ICJhODk2OTRm
+      ZS1lNjE1LTQzOWItOTQ4MC02MmVmZTRiNGY4ODUiLCAicm9sZSI6ICJTY29yZXIiLCAidmVyYm9z
+      ZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2Nh
+      bGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVk
+      PyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGlt
+      aXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSvsBCgpjcmV3X3Rhc2tzEuwBCukBW3sia2V5Ijog
+      IjI3ZWYzOGNjOTlkYTRhOGRlZDcwZWQ0MDZlNDRhYjg2IiwgImlkIjogIjMwYjNmYmQ4LWM0MmMt
+      NDhlYi1hNDdlLTAzNzFlOTFmYTAxYiIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1h
+      bl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiU2NvcmVyIiwgImFnZW50X2tleSI6ICI5
+      MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgB
+      hQEAAQAAEoAEChBSqrS4nl90w/7Z/EGzEvYpEgj54GNjf+XWQyoMVGFzayBDcmVhdGVkMAE5GJ55
+      SoMrNxhBOOx5SoMrNxhKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4MGE1ZDk3ZGMzODczYjE0ODI1
+      Y2NmYTNKMQoHY3Jld19pZBImCiQ4ZWMxNmVkNy0zYmIyLTQ5MWQtOGI2MS0yNzFmMTZmZThhZTFK
+      LgoIdGFza19rZXkSIgogMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFza19p
+      ZBImCiQzMGIzZmJkOC1jNDJjLTQ4ZWItYTQ3ZS0wMzcxZTkxZmEwMWJKOgoQY3Jld19maW5nZXJw
+      cmludBImCiQxN2MxN2QzNC1mZWZkLTQ1ZTktYWM2NS00ODY2ZTBlNTgwYTBKOgoQdGFza19maW5n
+      ZXJwcmludBImCiQ5MGYyODZhZC1lOWQ4LTRkOWUtYjA5MC05YTQyY2I3ZjYzNDhKOwobdGFza19m
+      aW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIwMjUtMDQtMTdUMTQ6MzM6NDMuNTE3OTk4SjsKEWFn
+      ZW50X2ZpbmdlcnByaW50EiYKJDhhMTliOTQxLWI4MTgtNDU3MC05NmJjLWZlYWQ4MWNkMjk1NXoC
+      GAGFAQABAAASlggKEFFBQgm1QyQTSqKMpRKbGjwSCCoFcjlB3aOLKgxDcmV3IENyZWF0ZWQwATlY
+      /RVLgys3GEEwLR1Lgys3GEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjExNC4wShsKDnB5dGhvbl92
+      ZXJzaW9uEgkKBzMuMTEuMTJKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4MGE1ZDk3ZGMzODczYjE0
+      ODI1Y2NmYTNKMQoHY3Jld19pZBImCiQ5NDYyMGE5YS1jMjc1LTRjMjItYjk1OC0zZmZlYWRiOGFl
+      ZGJKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNy
+      ZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSjoKEGNy
+      ZXdfZmluZ2VycHJpbnQSJgokNzQzZDgxNDYtZTM0My00Njk0LTljODUtMmVmZWRkMzZhYTlkSjsK
+      G2NyZXdfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjUyOTAz
+      MkrNAgoLY3Jld19hZ2VudHMSvQIKugJbeyJrZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0
+      MjQwYTI5NGQiLCAiaWQiOiAiZWE5NTMyZDktZDczNy00ZTIyLWE3MjItMDg2ODQ4NGViMmY5Iiwg
+      InJvbGUiOiAiU2NvcmVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDI1LCAibWF4
+      X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1t
+      aW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9u
+      PyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUr7AQoK
+      Y3Jld190YXNrcxLsAQrpAVt7ImtleSI6ICIyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4
+      NiIsICJpZCI6ICIyMmUyMjZiNC1kNmI5LTRiMzgtOTQwMi05NDY0NTBhOWExZjUiLCAiYXN5bmNf
+      ZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjog
+      IlNjb3JlciIsICJhZ2VudF9rZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQi
+      LCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQBNXlZK0H3tATZKP2Uw7bBxII0nvw
+      9UluHcgqDFRhc2sgQ3JlYXRlZDABOXhiJ0uDKzcYQZiwJ0uDKzcYSi4KCGNyZXdfa2V5EiIKIDVl
+      NmVmZmU2ODBhNWQ5N2RjMzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokOTQ2MjBhOWEtYzI3
+      NS00YzIyLWI5NTgtM2ZmZWFkYjhhZWRiSi4KCHRhc2tfa2V5EiIKIDI3ZWYzOGNjOTlkYTRhOGRl
+      ZDcwZWQ0MDZlNDRhYjg2SjEKB3Rhc2tfaWQSJgokMjJlMjI2YjQtZDZiOS00YjM4LTk0MDItOTQ2
+      NDUwYTlhMWY1SjoKEGNyZXdfZmluZ2VycHJpbnQSJgokNzQzZDgxNDYtZTM0My00Njk0LTljODUt
+      MmVmZWRkMzZhYTlkSjoKEHRhc2tfZmluZ2VycHJpbnQSJgokYjI3M2Q1OTMtYzcxZC00ZWRmLWI0
+      NmMtMTkyMmIxY2ZmZjY1SjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0
+      LTE3VDE0OjMzOjQzLjUyOTAwMko7ChFhZ2VudF9maW5nZXJwcmludBImCiQ5ZWYxZjc4Ny1lZTIz
+      LTRlNGUtOGJkYi04NGJiNjkwZjlkZjV6AhgBhQEAAQAAEpYIChCLERZYyvqc04xX3gWXPO59EggU
+      L4MaGDu+FyoMQ3JldyBDcmVhdGVkMAE54NLGS4MrNxhBeGbNS4MrNxhKGwoOY3Jld2FpX3ZlcnNp
+      b24SCQoHMC4xMTQuMEobCg5weXRob25fdmVyc2lvbhIJCgczLjExLjEySi4KCGNyZXdfa2V5EiIK
+      IDVlNmVmZmU2ODBhNWQ5N2RjMzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokZWI4MDdlMzEt
+      MGFiZS00NjQ0LWEwZjEtMDM4N2ZkZTYzYWQ1ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFs
+      ShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19u
+      dW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJDBkZDRmNDNlLTEzNzEt
+      NDVlNS1iMGNmLWY2ZDE5YTNjNzZkOUo7ChtjcmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoa
+      MjAyNS0wNC0xN1QxNDozMzo0My41NDA2MzhKzQIKC2NyZXdfYWdlbnRzEr0CCroCW3sia2V5Ijog
+      IjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgImlkIjogImY0ZDM5NzdlLTg4YjAt
+      NDQ2Zi04YzQ5LThkMjc0NDgwOGQ4NiIsICJyb2xlIjogIlNjb3JlciIsICJ2ZXJib3NlPyI6IGZh
+      bHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19s
+      bG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFs
+      c2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIs
+      ICJ0b29sc19uYW1lcyI6IFtdfV1K+wEKCmNyZXdfdGFza3MS7AEK6QFbeyJrZXkiOiAiMjdlZjM4
+      Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODYiLCAiaWQiOiAiYjA4MTZmY2QtYjcyMS00YTZkLTk0
+      ODQtNDc4YWM4ZDdkYTg4IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0
+      PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJTY29yZXIiLCAiYWdlbnRfa2V5IjogIjkyZTdlYjE5
+      MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAAS
+      gAQKEB0emJtWTE8969Cle2pbw8QSCFZbdjoOT655KgxUYXNrIENyZWF0ZWQwATlgt9VLgys3GEFo
+      CdZLgys3GEouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0ox
+      CgdjcmV3X2lkEiYKJGViODA3ZTMxLTBhYmUtNDY0NC1hMGYxLTAzODdmZGU2M2FkNUouCgh0YXNr
+      X2tleRIiCiAyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0YXNrX2lkEiYKJGIw
+      ODE2ZmNkLWI3MjEtNGE2ZC05NDg0LTQ3OGFjOGQ3ZGE4OEo6ChBjcmV3X2ZpbmdlcnByaW50EiYK
+      JDBkZDRmNDNlLTEzNzEtNDVlNS1iMGNmLWY2ZDE5YTNjNzZkOUo6ChB0YXNrX2ZpbmdlcnByaW50
+      EiYKJGM1ODIyZGM4LWIyYmYtNDUyZS04YjQ2LWRkNjAyMDNkNTA0Zko7Cht0YXNrX2ZpbmdlcnBy
+      aW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0My41NDA2MDlKOwoRYWdlbnRfZmlu
+      Z2VycHJpbnQSJgokZjZhMjA0MDYtOTM0Yy00ZjVmLWI1MzMtMDYwMTQwMGUxMTM1egIYAYUBAAEA
+      ABL4BwoQxJQoNY/stf/qihFVNGkp1hII9x5mkc7Cz5AqDENyZXcgQ3JlYXRlZDABOcB+REyDKzcY
+      QYA7SkyDKzcYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKGwoOcHl0aG9uX3ZlcnNpb24S
+      CQoHMy4xMS4xMkouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2Zh
+      M0oxCgdjcmV3X2lkEiYKJDY3NmIxNjlhLTI5YTYtNDVhOC05NmNjLTY4MjMyNzgzYmU3NUoeCgxj
+      cmV3X3Byb2Nlc3MSDgoMaGllcmFyY2hpY2FsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251
+      bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3X2Zp
+      bmdlcnByaW50EiYKJDMzZDRkZWU1LWIxOTEtNDAzYy04OWEwLTYyNWJiNjVmMmYxOUo7ChtjcmV3
+      X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0My41NDg4OThKzQIK
+      C2NyZXdfYWdlbnRzEr0CCroCW3sia2V5IjogIjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEy
+      OTRkIiwgImlkIjogImE0Mzc1OWYyLTY0NDEtNDNiMy1hOGRjLWYxYmQzMTU3MDdlZiIsICJyb2xl
+      IjogIlNjb3JlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0i
+      OiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIs
+      ICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBm
+      YWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K2wEKCmNyZXdf
+      dGFza3MSzAEKyQFbeyJrZXkiOiAiMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODYiLCAi
+      aWQiOiAiMDVmYzk4OWItMDY5Mi00ODAzLTgyMTMtMWQ2ODY5YTYwMTBlIiwgImFzeW5jX2V4ZWN1
+      dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJOb25l
+      IiwgImFnZW50X2tleSI6IG51bGwsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChDT
+      QOB/rAOBZumhFuP0yYFYEggS6cvMoHzBYioMVGFzayBDcmVhdGVkMAE5cB9dTIMrNxhBeHFdTIMr
+      NxhKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4MGE1ZDk3ZGMzODczYjE0ODI1Y2NmYTNKMQoHY3Jl
+      d19pZBImCiQ2NzZiMTY5YS0yOWE2LTQ1YTgtOTZjYy02ODIzMjc4M2JlNzVKLgoIdGFza19rZXkS
+      IgogMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFza19pZBImCiQwNWZjOTg5
+      Yi0wNjkyLTQ4MDMtODIxMy0xZDY4NjlhNjAxMGVKOgoQY3Jld19maW5nZXJwcmludBImCiQzM2Q0
+      ZGVlNS1iMTkxLTQwM2MtODlhMC02MjViYjY1ZjJmMTlKOgoQdGFza19maW5nZXJwcmludBImCiQ2
+      MGIzYTVkNi04MWUxLTQzOGYtOTE3Yy0yNjU4MzU4NjdmNzZKOwobdGFza19maW5nZXJwcmludF9j
+      cmVhdGVkX2F0EhwKGjIwMjUtMDQtMTdUMTQ6MzM6NDMuNTQ4ODcwSjsKEWFnZW50X2ZpbmdlcnBy
+      aW50EiYKJDgwZjQ2NDkxLWM0YjItNDExNy05MTM2LTZhOTQxZjI5ODBiZHoCGAGFAQABAAASnAEK
+      EObnhSrs8UQiBg/0Bricu2cSCMFW2rX4WlIFKgpUb29sIFVzYWdlMAE5CJ26TIMrNxhBmE/DTIMr
+      NxhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMTQuMEonCgl0b29sX25hbWUSGgoYQXNrIHF1ZXN0
+      aW9uIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAAS0AoKEBk04hfXjSFQOWWK
+      xJFMHB8SCLGFr6R51/OhKgxDcmV3IENyZWF0ZWQwATl4TzNNgys3GEFIMzlNgys3GEobCg5jcmV3
+      YWlfdmVyc2lvbhIJCgcwLjExNC4wShsKDnB5dGhvbl92ZXJzaW9uEgkKBzMuMTEuMTJKLgoIY3Jl
+      d19rZXkSIgogNzQyNzU3MzEyZWY3YmI0ZWUwYjA2NjJkMWMyZTIxNzlKMQoHY3Jld19pZBImCiQ2
+      MWRiMTdjYi0xODQ3LTRmYzktOWNkMy1hMDY3ZjRkOGExMzRKHAoMY3Jld19wcm9jZXNzEgwKCnNl
+      cXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUob
+      ChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokNjQ3OGY2
+      MjItZGVlOC00OWYyLTljMDktOGNiOTBjMjEwYzNjSjsKG2NyZXdfZmluZ2VycHJpbnRfY3JlYXRl
+      ZF9hdBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjU2NDI2NEqGBQoLY3Jld19hZ2VudHMS9gQK8wRb
+      eyJrZXkiOiAiODljZjMxMWI0OGI1MjE2OWQ0MmYzOTI1YzViZTFjNWEiLCAiaWQiOiAiM2E3YjUx
+      ZGItYzhhZC00ZDU3LWE1OGUtOGIzY2EyYzIxZTI2IiwgInJvbGUiOiAiTWFuYWdlciIsICJ2ZXJi
+      b3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25f
+      Y2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJs
+      ZWQ/IjogdHJ1ZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xp
+      bWl0IjogMiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICI5MmU3ZWIxOTE2NjRjOTM1Nzg1
+      ZWQ3ZDQyNDBhMjk0ZCIsICJpZCI6ICIxNWZiMjExOC0zOTE0LTQ2ZTctODRkZi05M2E5ZDA0ZWVj
+      M2YiLCAicm9sZSI6ICJTY29yZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUs
+      ICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0
+      LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IHRydWUsICJhbGxvd19jb2RlX2V4ZWN1
+      dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K
+      /AEKCmNyZXdfdGFza3MS7QEK6gFbeyJrZXkiOiAiMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0
+      NGFiODYiLCAiaWQiOiAiMzcwNTE2YzQtNWNhMC00NDBjLWE3YTctNWFhMjZiMDQ4MmFmIiwgImFz
+      eW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9s
+      ZSI6ICJNYW5hZ2VyIiwgImFnZW50X2tleSI6ICI4OWNmMzExYjQ4YjUyMTY5ZDQyZjM5MjVjNWJl
+      MWM1YSIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChBGCATWQjaQu6Zpx66QI8ik
+      Egg05IWKCa/6oyoMVGFzayBDcmVhdGVkMAE54CVFTYMrNxhB0HtFTYMrNxhKLgoIY3Jld19rZXkS
+      IgogNzQyNzU3MzEyZWY3YmI0ZWUwYjA2NjJkMWMyZTIxNzlKMQoHY3Jld19pZBImCiQ2MWRiMTdj
+      Yi0xODQ3LTRmYzktOWNkMy1hMDY3ZjRkOGExMzRKLgoIdGFza19rZXkSIgogMjdlZjM4Y2M5OWRh
+      NGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFza19pZBImCiQzNzA1MTZjNC01Y2EwLTQ0MGMtYTdh
+      Ny01YWEyNmIwNDgyYWZKOgoQY3Jld19maW5nZXJwcmludBImCiQ2NDc4ZjYyMi1kZWU4LTQ5ZjIt
+      OWMwOS04Y2I5MGMyMTBjM2NKOgoQdGFza19maW5nZXJwcmludBImCiQxMWU1ZDRhNi04ODc5LTQx
+      ZDktYWE3ZS04OTdhNDMzMDhlZWVKOwobdGFza19maW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIw
+      MjUtMDQtMTdUMTQ6MzM6NDMuNTY0MjMzSjsKEWFnZW50X2ZpbmdlcnByaW50EiYKJGUyMzRlYzA5
+      LTk3MzktNGE3Zi04MDgxLTBhNjJkYzNlNzY1ZHoCGAGFAQABAAASnQEKEFjGvzVUde99Ey+6qDaD
+      oG4SCFWLiXG8McaKKgpUb29sIFVzYWdlMAE5kI2lTYMrNxhBMG2tTYMrNxhKGwoOY3Jld2FpX3Zl
+      cnNpb24SCQoHMC4xMTQuMEooCgl0b29sX25hbWUSGwoZRGVsZWdhdGUgd29yayB0byBjb3dvcmtl
+      ckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEooIChCB+QR8dk6jPImbeJiKh5UYEgj00bY0zkAX
+      LSoMQ3JldyBDcmVhdGVkMAE5cAkrToMrNxhBKNM1ToMrNxhKGwoOY3Jld2FpX3ZlcnNpb24SCQoH
+      MC4xMTQuMEobCg5weXRob25fdmVyc2lvbhIJCgczLjExLjEySi4KCGNyZXdfa2V5EiIKIDMwM2I4
+      ZWRkNWIwMDg3MTBkNzZhYWY4MjVhNzA5ZTU1SjEKB2NyZXdfaWQSJgokNmUzM2ZiOTItNTZjMC00
+      OTY3LTk1MjItZGQ3ZWFhOWY5NjFlSh4KDGNyZXdfcHJvY2VzcxIOCgxoaWVyYXJjaGljYWxKEQoL
+      Y3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJl
+      cl9vZl9hZ2VudHMSAhgBSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokNDY5MjUyODctOTY2OS00MTRl
+      LWEwNzctZGVjNDE2ZTE3NDRlSjsKG2NyZXdfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1
+      LTA0LTE3VDE0OjMzOjQzLjU4MDUyM0rfAgoLY3Jld19hZ2VudHMSzwIKzAJbeyJrZXkiOiAiOTJl
+      N2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQiLCAiaWQiOiAiNzllZTU5MjktNjdlMy00NjNi
+      LTljYjEtMjFlNTdjNjZlNGQ4IiwgInJvbGUiOiAiU2NvcmVyIiwgInZlcmJvc2U/IjogZmFsc2Us
+      ICJtYXhfaXRlciI6IDI1LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6
+      ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwg
+      ImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRv
+      b2xzX25hbWVzIjogWyJzY29yaW5nX2V4YW1wbGVzIl19XUrbAQoKY3Jld190YXNrcxLMAQrJAVt7
+      ImtleSI6ICJmMzU3NWIwMTNjMjI5NGI3Y2M4ZTgwMzE1NWM4YmE0NiIsICJpZCI6ICJhZTlmMjgz
+      MC1hY2NhLTRiNmQtOGRjNy01MjMzZmZlYmJhM2QiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNl
+      LCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIk5vbmUiLCAiYWdlbnRfa2V5
+      IjogbnVsbCwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASgAQKEHOf6gKzlTQXpW3qTaF+
+      AlQSCIXd9+wt3hyiKgxUYXNrIENyZWF0ZWQwATkws0hOgys3GEE4BUlOgys3GEouCghjcmV3X2tl
+      eRIiCiAzMDNiOGVkZDViMDA4NzEwZDc2YWFmODI1YTcwOWU1NUoxCgdjcmV3X2lkEiYKJDZlMzNm
+      YjkyLTU2YzAtNDk2Ny05NTIyLWRkN2VhYTlmOTYxZUouCgh0YXNrX2tleRIiCiBmMzU3NWIwMTNj
+      MjI5NGI3Y2M4ZTgwMzE1NWM4YmE0NkoxCgd0YXNrX2lkEiYKJGFlOWYyODMwLWFjY2EtNGI2ZC04
+      ZGM3LTUyMzNmZmViYmEzZEo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJDQ2OTI1Mjg3LTk2NjktNDE0
+      ZS1hMDc3LWRlYzQxNmUxNzQ0ZUo6ChB0YXNrX2ZpbmdlcnByaW50EiYKJDU4ZGVjODNjLWFjZTQt
+      NGI1Ni05YzhjLWQyZGQ1YjVlMWYyNUo7Cht0YXNrX2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoa
+      MjAyNS0wNC0xN1QxNDozMzo0My41ODA0OTNKOwoRYWdlbnRfZmluZ2VycHJpbnQSJgokMGVjNzAw
+      NWEtOGMzOC00N2RlLWI5YzctNjc3ZmFkOTU2ZmMzegIYAYUBAAEAABJpChDdogUTH/ocvPeyU/F2
+      dgcNEghEqOA/7aEsiyoQVG9vbCBVc2FnZSBFcnJvcjABOVBbt06DKzcYQajPvU6DKzcYShsKDmNy
+      ZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjB6AhgBhQEAAQAAEp0BChD7kRw1jX3K2nusXZXPvHyGEghl
+      QFQp8mFhuCoKVG9vbCBVc2FnZTABORCS/E6DKzcYQXDPBE+DKzcYShsKDmNyZXdhaV92ZXJzaW9u
+      EgkKBzAuMTE0LjBKKAoJdG9vbF9uYW1lEhsKGURlbGVnYXRlIHdvcmsgdG8gY293b3JrZXJKDgoI
+      YXR0ZW1wdHMSAhgBegIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '27952'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.31.1
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Thu, 17 Apr 2025 17:33:47 GMT
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_task_with_max_execution_time_exceeded.yaml
+++ b/tests/cassettes/test_task_with_max_execution_time_exceeded.yaml
@@ -0,0 +1,81 @@
+interactions:
+- request:
+    body: '{"contents": [{"role": "user", "parts": [{"text": "\nCurrent Task: Give
+      me a list of 5 interesting ideas to explore for an article, what makes them
+      unique and interesting.\n\nThis is the expected criteria for your final answer:
+      Bullet point list of 5 interesting ideas.\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:"}]}], "system_instruction": {"parts": [{"text": "You are
+      Researcher. You''re an expert researcher, specialized in technology, software
+      engineering, AI and startups. You work as a freelancer and are now working on
+      doing research and analysis for a new customer.\nYour personal goal is: Make
+      the best research and analysis on content about AI and AI agents. Use the tool
+      provided to you.\nYou ONLY have access to the following tools, and should NEVER
+      make up tools that are not listed here:\n\nTool Name: what amazing tool\nTool
+      Arguments: {}\nTool Description: My tool\n\nIMPORTANT: Use the following format
+      in your response:\n\n```\nThought: you should always think about what to do\nAction:
+      the action to take, only one name of [what amazing tool], just the name, exactly
+      as it''s written.\nAction Input: the input to the action, just a simple JSON
+      object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
+      the result of the action\n```\n\nOnce all necessary information is gathered,
+      return the following format:\n\n```\nThought: I now know the final answer\nFinal
+      Answer: the final answer to the original input question\n```"}]}, "generationConfig":
+      {"temperature": 0.7, "stop_sequences": ["\nObservation:"]}}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1718'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      user-agent:
+      - litellm/1.60.2
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-pro-latest:generateContent
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAC/61STWvbQBC961cMe+klFnJUy8S30JZiaGloTQlEOaylibRktavujtKkxv+9s3Lk
+        rE2PFUha9r2Z9+ZjlwCISppa1ZLQixXc8Q3AbvwGzBpCQwxMV3zZS0dv3MOzi85MIXwOQWLT2qFp
+        aQVrMIg1kIUGDTpWA1Wj9PBgHUgDnFJVGkFu7UBwvea7evwxnXwKsH6nNQwegVp+rdUhV4u6hw5h
+        66Qynqzr0tKU5roiZc0KfreSQHbyjzLNGDNBsDb9wK52pfg1oHsp2WspPk/OFqC4bIeeQuA/feJz
+        r60L8LnXC6ZWgw8QC40WOvmIHlBW7ZgMBqNYdgyLhNJS7EXUxv3xfH/x1nxnNYbOdrZGPdH3E0E8
+        KKN8+50dWxNoPzbfbsQRlU/NF9v0zm7D/GZZml1dLoti8X4+X+RFvszzPJmkR1ExeK7qK5LkBZHH
+        NRCcoutpYx/RfLDDuCB5nh10ooU6IRTLV5wsSX0aezVhUWL/kWWVjjctWkKuX2pFL+OWfbrdiKhH
+        dOZr6lISNfPc5X9SK5anYsnrcA7z+onOq8NgGux4VLN5uphxzbMsuxTJPvkLk2fgU5EDAAA=
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Thu, 17 Apr 2025 19:00:14 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=1972
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - nosniff
+      X-Frame-Options:
+      - SAMEORIGIN
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/task_test.py
+++ b/tests/task_test.py
@@ -3,6 +3,7 @@
 import hashlib
 import json
 import os
+import time
 from functools import partial
 from typing import Tuple, Union
 from unittest.mock import MagicMock, patch
@@ -1368,3 +1369,90 @@ def test_interpolate_valid_types():
    assert parsed["optional"] is None
    assert parsed["nested"]["flag"] is True
    assert parsed["nested"]["empty"] is None
+
+
+def test_task_with_no_max_execution_time():
+    researcher = Agent(
+    role="Researcher",
+    goal="Make the best research and analysis on content about AI and AI agents",
+    backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
+    allow_delegation=False,
+    max_execution_time=None
+    )
+
+    task = Task(
+        description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
+        expected_output="Bullet point list of 5 interesting ideas.",
+        agent=researcher,
+    )
+
+    with patch.object(Agent, "_execute_without_timeout", return_value = "ok") as execute:
+        result = task.execute_sync(agent=researcher)
+        assert result.raw == "ok"
+        execute.assert_called_once()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_task_with_max_execution_time():
+    from crewai.tools import tool
+    """Test that execution raises TimeoutError when max_execution_time is exceeded."""
+
+    @tool("what amazing tool", result_as_answer=True)
+    def my_tool() -> str:
+        "My tool"
+        time.sleep(1)
+        return "okay"
+
+    researcher = Agent(
+        role="Researcher",
+        goal="Make the best research and analysis on content about AI and AI agents. Use the tool provided to you.",
+        backstory=(
+            "You're an expert researcher, specialized in technology, software engineering, AI and startups. "
+            "You work as a freelancer and are now working on doing research and analysis for a new customer."
+        ),
+        allow_delegation=False,
+        tools=[my_tool],
+        max_execution_time=4
+    )
+
+    task = Task(
+        description="Give me a list of 5 interesting ideas to explore for an article, what makes them unique and interesting.",
+        expected_output="Bullet point list of 5 interesting ideas.",
+        agent=researcher,
+    )
+
+    result = task.execute_sync(agent=researcher)
+    assert result.raw == "okay"
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_task_with_max_execution_time_exceeded():
+    from crewai.tools import tool
+    """Test that execution raises TimeoutError when max_execution_time is exceeded."""
+
+    @tool("what amazing tool", result_as_answer=True)
+    def my_tool() -> str:
+        "My tool"
+        time.sleep(10)
+        return "okay"
+
+    researcher = Agent(
+        role="Researcher",
+        goal="Make the best research and analysis on content about AI and AI agents. Use the tool provided to you.",
+        backstory=(
+            "You're an expert researcher, specialized in technology, software engineering, AI and startups. "
+            "You work as a freelancer and are now working on doing research and analysis for a new customer."
+        ),
+        allow_delegation=False,
+        tools=[my_tool],
+        max_execution_time=1
+    )
+
+    task = Task(
+        description="Give me a list of 5 interesting ideas to explore for an article, what makes them unique and interesting.",
+        expected_output="Bullet point list of 5 interesting ideas.",
+        agent=researcher,
+    )
+
+    with pytest.raises(TimeoutError):
+        task.execute_sync(agent=researcher)
--- a/tests/tools/test_custom_tool_invocation.py
+++ b/tests/tools/test_custom_tool_invocation.py
@@ -0,0 +1,77 @@
+from unittest.mock import MagicMock
+
+import pytest
+from pydantic import BaseModel, Field
+
+from crewai import Agent, Task
+from crewai.agents.crew_agent_executor import CrewAgentExecutor
+from crewai.agents.parser import AgentAction
+from crewai.agents.tools_handler import ToolsHandler
+from crewai.tools import BaseTool
+from crewai.utilities.i18n import I18N
+from crewai.utilities.tool_utils import execute_tool_and_check_finality
+
+
+class TestToolInput(BaseModel):
+    test_param: str = Field(..., description="A test parameter")
+
+
+class TestCustomTool(BaseTool):
+    name: str = "Test Custom Tool"
+    description: str = "A test tool to verify custom tool invocation"
+    args_schema: type[BaseModel] = TestToolInput
+
+    def _run(self, test_param: str) -> str:
+        return f"Tool executed with param: {test_param}"
+
+
+def test_custom_tool_invocation():
+    custom_tool = TestCustomTool()
+    
+    mock_agent = MagicMock()
+    mock_task = MagicMock()
+    mock_llm = MagicMock()
+    mock_crew = MagicMock()
+    tools_handler = ToolsHandler()
+    
+    executor = CrewAgentExecutor(
+        llm=mock_llm,
+        task=mock_task,
+        crew=mock_crew,
+        agent=mock_agent,
+        prompt={},
+        max_iter=5,
+        tools=[custom_tool],
+        tools_names="Test Custom Tool",
+        stop_words=[],
+        tools_description="A test tool to verify custom tool invocation",
+        tools_handler=tools_handler,
+        original_tools=[custom_tool]
+    )
+    
+    action = AgentAction(
+        tool="Test Custom Tool",
+        tool_input={"test_param": "test_value"},
+        thought="I'll use the custom tool",
+        text="I'll use the Test Custom Tool to get a result"
+    )
+    
+    i18n = I18N()
+    
+    mock_agent.key = "test_agent"
+    mock_agent.role = "test_role"
+    
+    result = execute_tool_and_check_finality(
+        agent_action=action,
+        tools=[custom_tool],
+        i18n=i18n,
+        agent_key=mock_agent.key,
+        agent_role=mock_agent.role,
+        tools_handler=tools_handler,
+        task=mock_task,
+        agent=mock_agent,
+        function_calling_llm=mock_llm
+    )
+    
+    assert "Tool executed with param: test_value" in result.result
+    assert result.result_as_answer is False
Author	SHA1	Message	Date
Devin AI	fc72e2bd9f	Fix result_as_answer handling in ToolUsage class Co-Authored-By: Joe Moura <joao@crewai.com>	2025-04-22 16:54:28 +00:00
Devin AI	c7d126ade0	Fix tool_utils to pass original_tools to ToolUsage Co-Authored-By: Joe Moura <joao@crewai.com>	2025-04-22 16:49:23 +00:00
Devin AI	6dc8c1ad74	Fix test to use execute_tool_and_check_finality function Co-Authored-By: Joe Moura <joao@crewai.com>	2025-04-22 16:47:28 +00:00
Devin AI	9c6cc590f5	Fix import sorting in test file with ruff Co-Authored-By: Joe Moura <joao@crewai.com>	2025-04-22 16:43:01 +00:00
Devin AI	4f4b283885	Fix AgentAction constructor call in test Co-Authored-By: Joe Moura <joao@crewai.com>	2025-04-22 16:41:42 +00:00
Devin AI	6f7261f026	Fix import sorting in test file Co-Authored-By: Joe Moura <joao@crewai.com>	2025-04-22 16:38:52 +00:00
Devin AI	bcb472eff9	Fix issue #2664 : Custom tools not being called by the agent Co-Authored-By: Joe Moura <joao@crewai.com>	2025-04-22 16:36:52 +00:00
Vini Brasil	3d9000495c	Change CLI tool publish message (#2662 )	2025-04-22 13:09:30 -03:00
Tony Kipkemboi	6d0039b117	docs: 0.114.0 release notes, navigation restructure, new guides, deploy video, and cleanup (#2653 ) Some checks are pending Notify Downstream / notify-downstream (push) Waiting to run Details - Add v0.114.0 release notes with highlights image and doc links - Restructure docs navigation (Strategy group, Releases tab, navbar links) - Update quickstart with deployment video and clearer instructions - Add/rename guides (Custom Manager Agent, Custom LLM) - Remove legacy concept/tool docs - Add new images and tool docs - Minor formatting and content improvements throughout	2025-04-21 19:18:21 -04:00
Lorenze Jay	311a078ca6	Enhance knowledge management in CrewAI (#2637 ) Some checks failed Notify Downstream / notify-downstream (push) Has been cancelled Details * Enhance knowledge management in CrewAI - Added `KnowledgeConfig` class to configure knowledge retrieval parameters such as `limit` and `score_threshold`. - Updated `Agent` and `Crew` classes to utilize the new knowledge configuration for querying knowledge sources. - Enhanced documentation to clarify the addition of knowledge sources at both agent and crew levels. - Introduced new tips in documentation to guide users on knowledge source management and configuration. * Refactor knowledge configuration parameters in CrewAI - Renamed `limit` to `results_limit` in `KnowledgeConfig`, `query_knowledge`, and `query` methods for consistency and clarity. - Updated related documentation to reflect the new parameter name, ensuring users understand the configuration options for knowledge retrieval. * Refactor agent tests to utilize mock knowledge storage - Updated test cases in `agent_test.py` to use `KnowledgeStorage` for mocking knowledge sources, enhancing test reliability and clarity. - Renamed `limit` to `results_limit` in `KnowledgeConfig` for consistency with recent changes. - Ensured that knowledge queries are properly mocked to return expected results during tests. * Add VCR support for agent tests with query limits and score thresholds - Introduced `@pytest.mark.vcr` decorator in `agent_test.py` for tests involving knowledge sources, ensuring consistent recording of HTTP interactions. - Added new YAML cassette files for `test_agent_with_knowledge_sources_with_query_limit_and_score_threshold` and `test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default`, capturing the expected API responses for these tests. - Enhanced test reliability by utilizing VCR to manage external API calls during testing. * Update documentation to format parameter names in code style - Changed the formatting of `results_limit` and `score_threshold` in the documentation to use code style for better clarity and emphasis. - Ensured consistency in documentation presentation to enhance user understanding of configuration options. * Enhance KnowledgeConfig with field descriptions - Updated `results_limit` and `score_threshold` in `KnowledgeConfig` to use Pydantic's `Field` for improved documentation and clarity. - Added descriptions to both parameters to provide better context for their usage in knowledge retrieval configuration. * docstrings added	2025-04-18 18:33:04 -07:00
Vidit Ostwal	371f19f3cd	Support set max_execution_time to Agent (#2610 ) Some checks are pending Notify Downstream / notify-downstream (push) Waiting to run Details * Fixed fake max_execution_time paramenter --------- Co-authored-by: Lucas Gomide <lucaslg200@gmail.com>	2025-04-17 16:03:00 -04:00