type improvements

This reverts commit 2eda5fdeed.

src/crewai/agent.py

@@ -17,6 +17,7 @@ from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.task import Task
 from crewai.tools import BaseTool
 from crewai.tools.agent_tools.agent_tools import AgentTools
+from crewai.tools.base_tool import Tool
 from crewai.utilities import Converter, Prompts
 from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
 from crewai.utilities.converter import generate_model_description
@@ -114,6 +115,10 @@ class Agent(BaseAgent):
         default=2,
         description="Maximum number of retries for an agent to execute a task when an error occurs.",
     )
+    multimodal: bool = Field(
+        default=False,
+        description="Whether the agent is multimodal.",
+    )
     code_execution_mode: Literal["safe", "unsafe"] = Field(
         default="safe",
         description="Mode for code execution: 'safe' (using Docker) or 'unsafe' (direct execution).",
@@ -406,6 +411,10 @@ class Agent(BaseAgent):
         tools = agent_tools.tools()
         return tools
 
+    def get_multimodal_tools(self) -> List[Tool]:
+        from crewai.tools.agent_tools.add_image_tool import AddImageTool
+        return [AddImageTool()]
+
     def get_code_execution_tools(self):
         try:
             from crewai_tools import CodeInterpreterTool

src/crewai/agents/crew_agent_executor.py

@@ -143,10 +143,20 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         tool_result = self._execute_tool_and_check_finality(
                             formatted_answer
                         )
-                        if self.step_callback:
-                            self.step_callback(tool_result)
 
-                        formatted_answer.text += f"\nObservation: {tool_result.result}"
+                        # Directly append the result to the messages if the
+                        # tool is "Add image to content" in case of multimodal
+                        # agents
+                        if formatted_answer.tool == self._i18n.tools("add_image")["name"]:
+                            self.messages.append(tool_result.result)
+                            continue
+
+                        else:
+                            if self.step_callback:
+                                self.step_callback(tool_result)
+
+                            formatted_answer.text += f"\nObservation: {tool_result.result}"
+
                         formatted_answer.result = tool_result.result
                         if tool_result.result_as_answer:
                             return AgentFinish(

src/crewai/crew.py

@@ -35,6 +35,7 @@ from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry import Telemetry
 from crewai.tools.agent_tools.agent_tools import AgentTools
+from crewai.tools.base_tool import Tool
 from crewai.types.usage_metrics import UsageMetrics
 from crewai.utilities import I18N, FileHandler, Logger, RPMController
 from crewai.utilities.constants import TRAINING_DATA_FILE
@@ -533,9 +534,6 @@ class Crew(BaseModel):
             if not agent.function_calling_llm:  # type: ignore # "BaseAgent" has no attribute "function_calling_llm"
                 agent.function_calling_llm = self.function_calling_llm  # type: ignore # "BaseAgent" has no attribute "function_calling_llm"
 
-            if agent.allow_code_execution:  # type: ignore # BaseAgent" has no attribute "allow_code_execution"
-                agent.tools += agent.get_code_execution_tools()  # type: ignore # "BaseAgent" has no attribute "get_code_execution_tools"; maybe "get_delegation_tools"?
-
             if not agent.step_callback:  # type: ignore # "BaseAgent" has no attribute "step_callback"
                 agent.step_callback = self.step_callback  # type: ignore # "BaseAgent" has no attribute "step_callback"
 
@@ -672,7 +670,6 @@ class Crew(BaseModel):
                 )
                 manager.tools = []
                 raise Exception("Manager agent should not have tools")
-            manager.tools = self.manager_agent.get_delegation_tools(self.agents)
         else:
             self.manager_llm = (
                 getattr(self.manager_llm, "model_name", None)
@@ -684,6 +681,7 @@ class Crew(BaseModel):
                 goal=i18n.retrieve("hierarchical_manager_agent", "goal"),
                 backstory=i18n.retrieve("hierarchical_manager_agent", "backstory"),
                 tools=AgentTools(agents=self.agents).tools(),
+                allow_delegation=True,
                 llm=self.manager_llm,
                 verbose=self.verbose,
             )
@@ -726,7 +724,14 @@ class Crew(BaseModel):
                     f"No agent available for task: {task.description}. Ensure that either the task has an assigned agent or a manager agent is provided."
                 )
 
-            self._prepare_agent_tools(task)
+            # Determine which tools to use - task tools take precedence over agent tools
+            tools_for_task = task.tools or agent_to_use.tools or []
+            tools_for_task = self._prepare_tools(
+                agent_to_use,
+                task,
+                tools_for_task
+            )
+
             self._log_task_start(task, agent_to_use.role)
 
             if isinstance(task, ConditionalTask):
@@ -743,7 +748,7 @@ class Crew(BaseModel):
                 future = task.execute_async(
                     agent=agent_to_use,
                     context=context,
-                    tools=agent_to_use.tools,
+                    tools=tools_for_task,
                 )
                 futures.append((task, future, task_index))
             else:
@@ -755,7 +760,7 @@ class Crew(BaseModel):
                 task_output = task.execute_sync(
                     agent=agent_to_use,
                     context=context,
-                    tools=agent_to_use.tools,
+                    tools=tools_for_task,
                 )
                 task_outputs = [task_output]
                 self._process_task_result(task, task_output)
@@ -792,45 +797,67 @@ class Crew(BaseModel):
             return skipped_task_output
         return None
 
-    def _prepare_agent_tools(self, task: Task):
-        if self.process == Process.hierarchical:
-            if self.manager_agent:
-                self._update_manager_tools(task)
-            else:
-                raise ValueError("Manager agent is required for hierarchical process.")
-        elif task.agent and task.agent.allow_delegation:
-            self._add_delegation_tools(task)
+    def _prepare_tools(self, agent: BaseAgent, task: Task, tools: List[Tool]) -> List[Tool]:
+        # Add delegation tools if agent allows delegation
+        if agent.allow_delegation:
+            if self.process == Process.hierarchical:
+                if self.manager_agent:
+                    tools = self._update_manager_tools(task, tools)
+                else:
+                    raise ValueError("Manager agent is required for hierarchical process.")
+
+            elif agent and agent.allow_delegation:
+                tools = self._add_delegation_tools(task, tools)
+
+        # Add code execution tools if agent allows code execution
+        if agent.allow_code_execution:
+            tools = self._add_code_execution_tools(agent, tools)
+
+        if agent and agent.multimodal:
+            tools = self._add_multimodal_tools(agent, tools)
+
+        return tools
 
     def _get_agent_to_use(self, task: Task) -> Optional[BaseAgent]:
         if self.process == Process.hierarchical:
             return self.manager_agent
         return task.agent
 
-    def _add_delegation_tools(self, task: Task):
+    def _merge_tools(self, existing_tools: List[Tool], new_tools: List[Tool]) -> List[Tool]:
+        """Merge new tools into existing tools list, avoiding duplicates by tool name."""
+        if not new_tools:
+            return existing_tools
+
+        # Create mapping of tool names to new tools
+        new_tool_map = {tool.name: tool for tool in new_tools}
+
+        # Remove any existing tools that will be replaced
+        tools = [tool for tool in existing_tools if tool.name not in new_tool_map]
+
+        # Add all new tools
+        tools.extend(new_tools)
+
+        return tools
+
+    def _inject_delegation_tools(self, tools: List[Tool], task_agent: BaseAgent, agents: List[BaseAgent]):
+        delegation_tools = task_agent.get_delegation_tools(agents)
+        return self._merge_tools(tools, delegation_tools)
+
+    def _add_multimodal_tools(self, agent: BaseAgent, tools: List[Tool]):
+        multimodal_tools = agent.get_multimodal_tools()
+        return self._merge_tools(tools, multimodal_tools)
+
+    def _add_code_execution_tools(self, agent: BaseAgent, tools: List[Tool]):
+        code_tools = agent.get_code_execution_tools()
+        return self._merge_tools(tools, code_tools)
+
+    def _add_delegation_tools(self, task: Task, tools: List[Tool]):
         agents_for_delegation = [agent for agent in self.agents if agent != task.agent]
         if len(self.agents) > 1 and len(agents_for_delegation) > 0 and task.agent:
-            delegation_tools = task.agent.get_delegation_tools(agents_for_delegation)
-
-            # Add tools if they are not already in task.tools
-            for new_tool in delegation_tools:
-                # Find the index of the tool with the same name
-                existing_tool_index = next(
-                    (
-                        index
-                        for index, tool in enumerate(task.tools or [])
-                        if tool.name == new_tool.name
-                    ),
-                    None,
-                )
-                if not task.tools:
-                    task.tools = []
-
-                if existing_tool_index is not None:
-                    # Replace the existing tool
-                    task.tools[existing_tool_index] = new_tool
-                else:
-                    # Add the new tool
-                    task.tools.append(new_tool)
+            if not tools:
+                tools = []
+            tools = self._inject_delegation_tools(tools, task.agent, agents_for_delegation)
+        return tools
 
     def _log_task_start(self, task: Task, role: str = "None"):
         if self.output_log_file:
@@ -838,14 +865,13 @@ class Crew(BaseModel):
                 task_name=task.name, task=task.description, agent=role, status="started"
             )
 
-    def _update_manager_tools(self, task: Task):
+    def _update_manager_tools(self, task: Task, tools: List[Tool]):
         if self.manager_agent:
             if task.agent:
-                self.manager_agent.tools = task.agent.get_delegation_tools([task.agent])
+                tools = self._inject_delegation_tools(tools, task.agent, [task.agent])
             else:
-                self.manager_agent.tools = self.manager_agent.get_delegation_tools(
-                    self.agents
-                )
+                tools = self._inject_delegation_tools(tools, self.manager_agent, self.agents)
+        return tools
 
     def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
         context = (

src/crewai/llm.py

@@ -64,6 +64,8 @@ LLM_CONTEXT_WINDOW_SIZES = {
     "llama3-70b-8192": 8192,
     "llama3-8b-8192": 8192,
     "mixtral-8x7b-32768": 32768,
+    "llama-3.3-70b-versatile": 128000,
+    "llama-3.3-70b-instruct": 128000,
 }
 
 DEFAULT_CONTEXT_WINDOW_SIZE = 8192

src/crewai/tools/agent_tools/add_image_tool.py

@@ -0,0 +1,45 @@
+from typing import Dict, Optional, Union
+
+from pydantic import BaseModel, Field
+
+from crewai.tools.base_tool import BaseTool
+from crewai.utilities import I18N
+
+i18n = I18N()
+
+class AddImageToolSchema(BaseModel):
+    image_url: str = Field(..., description="The URL or path of the image to add")
+    action: Optional[str] = Field(
+        default=None,
+        description="Optional context or question about the image"
+    )
+
+
+class AddImageTool(BaseTool):
+    """Tool for adding images to the content"""
+
+    name: str = Field(default_factory=lambda: i18n.tools("add_image")["name"])  # type: ignore
+    description: str = Field(default_factory=lambda: i18n.tools("add_image")["description"])  # type: ignore
+    args_schema: type[BaseModel] = AddImageToolSchema
+
+    def _run(
+        self,
+        image_url: str,
+        action: Optional[str] = None,
+        **kwargs,
+    ) -> dict:
+        action = action or i18n.tools("add_image")["default_action"]  # type: ignore
+        content = [
+            {"type": "text", "text": action},
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": image_url,
+                },
+            }
+        ]
+
+        return {
+            "role": "user",
+            "content": content
+        }

src/crewai/tools/agent_tools/agent_tools.py

@@ -20,13 +20,13 @@ class AgentTools:
         delegate_tool = DelegateWorkTool(
             agents=self.agents,
             i18n=self.i18n,
-            description=self.i18n.tools("delegate_work").format(coworkers=coworkers),
+            description=self.i18n.tools("delegate_work").format(coworkers=coworkers),  # type: ignore
         )
 
         ask_tool = AskQuestionTool(
             agents=self.agents,
             i18n=self.i18n,
-            description=self.i18n.tools("ask_question").format(coworkers=coworkers),
+            description=self.i18n.tools("ask_question").format(coworkers=coworkers),  # type: ignore
         )
 
         return [delegate_tool, ask_tool]

src/crewai/tools/tool_usage.py

@@ -10,6 +10,7 @@ from crewai.agents.tools_handler import ToolsHandler
 from crewai.task import Task
 from crewai.telemetry import Telemetry
 from crewai.tools import BaseTool
+from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.tools.tool_calling import InstructorToolCalling, ToolCalling
 from crewai.tools.tool_usage_events import ToolUsageError, ToolUsageFinished
 from crewai.utilities import I18N, Converter, ConverterError, Printer
@@ -18,8 +19,7 @@ try:
     import agentops  # type: ignore
 except ImportError:
     agentops = None
-
-OPENAI_BIGGER_MODELS = ["gpt-4", "gpt-4o", "o1-preview", "o1-mini"]
+OPENAI_BIGGER_MODELS = ["gpt-4", "gpt-4o", "o1-preview", "o1-mini", "o1", "o3", "o3-mini"]
 
 
 class ToolUsageErrorException(Exception):
@@ -103,6 +103,19 @@ class ToolUsage:
             if self.agent.verbose:
                 self._printer.print(content=f"\n\n{error}\n", color="red")
             return error
+
+        if isinstance(tool, CrewStructuredTool) and tool.name == self._i18n.tools("add_image")["name"]:  # type: ignore
+            try:
+                result = self._use(tool_string=tool_string, tool=tool, calling=calling)
+                return result
+
+            except Exception as e:
+                error = getattr(e, "message", str(e))
+                self.task.increment_tools_errors()
+                if self.agent.verbose:
+                    self._printer.print(content=f"\n\n{error}\n", color="red")
+                return error
+
         return f"{self._use(tool_string=tool_string, tool=tool, calling=calling)}"  # type: ignore # BUG?: "_use" of "ToolUsage" does not return a value (it only ever returns None)
 
     def _use(

src/crewai/translations/en.json

@@ -37,6 +37,11 @@
   },
   "tools": {
     "delegate_work": "Delegate a specific task to one of the following coworkers: {coworkers}\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolute everything you know, don't reference things but instead explain them.",
-    "ask_question": "Ask a specific question to one of the following coworkers: {coworkers}\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolute everything you know, don't reference things but instead explain them."
+    "ask_question": "Ask a specific question to one of the following coworkers: {coworkers}\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolute everything you know, don't reference things but instead explain them.",
+    "add_image": {
+      "name": "Add image to content",
+      "description": "See image to understand it's content, you can optionally ask a question about the image",
+      "default_action": "Please provide a detailed description of this image, including all visual elements, context, and any notable details you can observe."
+    }
   }
 }

src/crewai/utilities/i18n.py

@@ -1,6 +1,6 @@
 import json
 import os
-from typing import Dict, Optional
+from typing import Dict, Optional, Union
 
 from pydantic import BaseModel, Field, PrivateAttr, model_validator
 
@@ -41,8 +41,8 @@ class I18N(BaseModel):
     def errors(self, error: str) -> str:
         return self.retrieve("errors", error)
 
-    def tools(self, error: str) -> str:
-        return self.retrieve("tools", error)
+    def tools(self, tool: str) -> Union[str, Dict[str, str]]:
+        return self.retrieve("tools", tool)
 
     def retrieve(self, kind, key) -> str:
         try:

tests/cassettes/test_crew_with_delegating_agents.yaml

@@ -3,223 +3,17 @@ interactions:
     body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
       time CEO of a content creation agency with a Senior Writer on the team. You''re
       now working on a new project and want to make sure the content produced is amazing.\nYour
-      personal goal is: Make sure the writers in your company produce amazing content.\nYou
-      ONLY have access to the following tools, and should NEVER make up tools that
-      are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
-      str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a
-      specific task to one of the following coworkers: Senior Writer\nThe input to
-      this tool should be the coworker, the task you want them to do, and ALL necessary
-      context to execute the task, they know nothing about the task, so share absolute
-      everything you know, don''t reference things but instead explain them.\nTool
-      Arguments: {''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'':
-      {''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
-      ''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
-      Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
-      = None, **kwargs)\nTool Description: Ask a specific question to one of the following
-      coworkers: Senior Writer\nThe input to this tool should be the coworker, the
-      question you have for them, and ALL necessary context to ask the question properly,
-      they know nothing about the question, so share absolute everything you know,
-      don''t reference things but instead explain them.\nTool Arguments: {''question'':
-      {''title'': ''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'',
-      ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
-      ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
-      format:\n\nThought: you should always think about what to do\nAction: the action
-      to take, only one name of [Delegate work to coworker, Ask question to coworker],
-      just the name, exactly as it''s written.\nAction Input: the input to the action,
-      just a simple python dictionary, enclosed in curly braces, using \" to wrap
-      keys and values.\nObservation: the result of the action\n\nOnce all necessary
-      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
-      the final answer to the original input question\n"}, {"role": "user", "content":
-      "\nCurrent Task: Produce and amazing 1 paragraph draft of an article about AI
-      Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
-      article about AI.\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"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2762'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
-        _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.47.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.47.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-AB7ZvxqgeOayGTQWwR61ASlZp0s74\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1727214103,\n  \"model\": \"gpt-4o-2024-05-13\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Thought: To ensure the content is amazing,
-      I'll delegate the task of producing a one-paragraph draft of an article about
-      AI Agents to the Senior Writer with all necessary context.\\n\\nAction: Delegate
-      work to coworker\\nAction Input: \\n{\\n    \\\"coworker\\\": \\\"Senior Writer\\\",
-      \\n    \\\"task\\\": \\\"Produce a one paragraph draft of an article about AI
-      Agents\\\", \\n    \\\"context\\\": \\\"We need an amazing one-paragraph draft
-      as the beginning of a 4-paragraph article about AI Agents. This is for a high-stakes
-      project that critically impacts our company. The paragraph should highlight
-      what AI Agents are, their significance, and how they are transforming various
-      industries. The tone should be professional yet engaging. Make sure the content
-      is original, insightful, and thoroughly researched.\\\"\\n}\",\n        \"refusal\":
-      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
-      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 608,\n    \"completion_tokens\":
-      160,\n    \"total_tokens\": 768,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
-      0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8c85f0b038a71cf3-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 24 Sep 2024 21:41:45 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '1826'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '30000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '29999325'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 1ms
-      x-request-id:
-      - req_79054638deeb01da76c5bba273bffc28
-    http_version: HTTP/1.1
-    status_code: 200
-- request:
-    body: !!binary |
-      Cq8OCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkShg4KEgoQY3Jld2FpLnRl
-      bGVtZXRyeRKQAgoQg15EMIBbDpydrcK3GAUYfBII5VYz5B10kmgqDlRhc2sgRXhlY3V0aW9uMAE5
-      aGIpYwtM+BdBIO6VVRNM+BdKLgoIY3Jld19rZXkSIgogZTNmZGEwZjMxMTBmZTgwYjE4OTQ3YzAx
-      NDcxNDMwYTRKMQoHY3Jld19pZBImCiRjNzM1NzdhYi0xYThhLTQzMGYtYjYyZi01MTBlYWMyMWI3
-      MThKLgoIdGFza19rZXkSIgogNWZhNjVjMDZhOWUzMWYyYzY5NTQzMjY2OGFjZDYyZGRKMQoHdGFz
-      a19pZBImCiQ3MjAzMjYyMC0yMzJmLTQ5ZTMtOGMyNy0xYzBlOWJhNjFiZDB6AhgBhQEAAQAAEssJ
-      ChB+du4H1wHcku5blhLQBtuoEgiXVguc5KA1RyoMQ3JldyBDcmVhdGVkMAE54IJsVxNM+BdBcCN4
-      VxNM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMu
-      MTEuN0ouCghjcmV3X2tleRIiCiBlNjQ5NTczYTI2ZTU4NzkwY2FjMjFhMzdjZDQ0NDM3YUoxCgdj
-      cmV3X2lkEiYKJDI4ZTY0YmQ3LWNlYWMtNDYxOS04MmM3LTIzNmRkNTQxOGM4N0ocCgxjcmV3X3By
-      b2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2Zf
-      dGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAJKgAUKC2NyZXdfYWdlbnRzEvAE
-      Cu0EW3sia2V5IjogIjMyODIxN2I2YzI5NTliZGZjNDdjYWQwMGU4NDg5MGQwIiwgImlkIjogIjQ1
-      NjMxMmU3LThkMmMtNDcyMi1iNWNkLTlhMGRhMzg5MmM3OCIsICJyb2xlIjogIkNFTyIsICJ2ZXJi
-      b3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAxNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25f
-      Y2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6
-      IHRydWUsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6
-      IDIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiOWE1MDE1ZWY0ODk1ZGM2Mjc4ZDU0ODE4
-      YmE0NDZhZjciLCAiaWQiOiAiMTM0MDg5MjAtNzVjOC00MTk3LWIwNmQtY2I4MmNkZjhkZDhhIiwg
-      InJvbGUiOiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAx
-      NSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJn
-      cHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRp
-      b24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSvgB
-      CgpjcmV3X3Rhc2tzEukBCuYBW3sia2V5IjogIjBiOWQ2NWRiNmI3YWVkZmIzOThjNTllMmE5Zjcx
-      ZWM1IiwgImlkIjogImQ0YjVhZmE2LTczNTEtNDUxMy04NzY2LTIzOGNjYTk5ZjRlZiIsICJhc3lu
-      Y19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUi
-      OiAiQ0VPIiwgImFnZW50X2tleSI6ICIzMjgyMTdiNmMyOTU5YmRmYzQ3Y2FkMDBlODQ4OTBkMCIs
-      ICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChCLEGLGYlBkv0YucoYjY1NeEghRpGin
-      zpZUiSoMVGFzayBDcmVhdGVkMAE5KCA2WBNM+BdBaLw2WBNM+BdKLgoIY3Jld19rZXkSIgogZTY0
-      OTU3M2EyNmU1ODc5MGNhYzIxYTM3Y2Q0NDQzN2FKMQoHY3Jld19pZBImCiQyOGU2NGJkNy1jZWFj
-      LTQ2MTktODJjNy0yMzZkZDU0MThjODdKLgoIdGFza19rZXkSIgogMGI5ZDY1ZGI2YjdhZWRmYjM5
-      OGM1OWUyYTlmNzFlYzVKMQoHdGFza19pZBImCiRkNGI1YWZhNi03MzUxLTQ1MTMtODc2Ni0yMzhj
-      Y2E5OWY0ZWZ6AhgBhQEAAQAA
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '1842'
-      Content-Type:
-      - application/x-protobuf
-      User-Agent:
-      - OTel-OTLP-Exporter-Python/1.27.0
-    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:
-      - Tue, 24 Sep 2024 21:41:46 GMT
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are Senior Writer. You''re
-      a senior writer, specialized in technology, software engineering, AI and startups.
-      You work as a freelancer and are now working on writing content for a new customer.\nYour
-      personal goal is: Write the best content about AI and AI agents.\nTo give my
-      best complete final answer to the task use the exact following format:\n\nThought:
+      personal goal is: Make sure the writers in your company produce amazing content.\nTo
+      give my best complete final answer to the task use 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: Produce a one paragraph draft of an article about AI Agents\n\nThis is
-      the expect criteria for your final answer: Your best answer to your coworker
-      asking you this, accounting for the context shared.\nyou MUST return the actual
-      complete content as the final answer, not a summary.\n\nThis is the context
-      you''re working with:\nWe need an amazing one-paragraph draft as the beginning
-      of a 4-paragraph article about AI Agents. This is for a high-stakes project
-      that critically impacts our company. The paragraph should highlight what AI
-      Agents are, their significance, and how they are transforming various industries.
-      The tone should be professional yet engaging. Make sure the content is original,
-      insightful, and thoroughly researched.\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"}'
+      Task: Produce and amazing 1 paragraph draft of an article about AI Agents.\n\nThis
+      is the expect criteria for your final answer: A 4 paragraph article about AI.\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:"], "stream": false}'
     headers:
       accept:
       - application/json
@@ -228,16 +22,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1545'
+      - '1105'
       content-type:
       - application/json
-      cookie:
-      - __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
-        _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.47.0
+      - OpenAI/Python 1.52.1
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -247,9 +38,11 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.47.0
+      - 1.52.1
       x-stainless-raw-response:
       - 'true'
+      x-stainless-retry-count:
+      - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -257,31 +50,51 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-AB7ZxDYcPlSiBZsftdRs2cWbUJllW\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1727214105,\n  \"model\": \"gpt-4o-2024-05-13\",\n
+    content: "{\n  \"id\": \"chatcmpl-Ahe7liUPejwfqxMe8aEWmKGJ837em\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734965705,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
       \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
       \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
-      Answer: Artificial Intelligence (AI) Agents are sophisticated computer programs
-      designed to perform tasks that typically require human intelligence, such as
-      decision making, problem-solving, and learning. These agents operate autonomously,
-      utilizing vast amounts of data, advanced algorithms, and machine learning techniques
-      to analyze their environment, adapt to new information, and improve their performance
-      over time. The significance of AI Agents lies in their transformative potential
-      across various industries. In healthcare, they assist in diagnosing diseases
-      with greater accuracy; in finance, they predict market trends and manage risks;
-      in customer service, they provide personalized and efficient responses. As these
-      AI-powered entities continue to evolve, they are not only enhancing operational
-      efficiencies but also driving innovation and creating new opportunities for
-      growth and development in every sector they penetrate.\",\n        \"refusal\":
-      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
-      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 297,\n    \"completion_tokens\":
-      160,\n    \"total_tokens\": 457,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
-      0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
+      Answer: In the rapidly evolving landscape of technology, AI agents have emerged
+      as formidable tools, revolutionizing how we interact with data and automate
+      tasks. These sophisticated systems leverage machine learning and natural language
+      processing to perform a myriad of functions, from virtual personal assistants
+      to complex decision-making companions in industries such as finance, healthcare,
+      and education. By mimicking human intelligence, AI agents can analyze massive
+      data sets at unparalleled speeds, enabling businesses to uncover valuable insights,
+      enhance productivity, and elevate user experiences to unprecedented levels.\\n\\nOne
+      of the most striking aspects of AI agents is their adaptability; they learn
+      from their interactions and continuously improve their performance over time.
+      This feature is particularly valuable in customer service where AI agents can
+      address inquiries, resolve issues, and provide personalized recommendations
+      without the limitations of human fatigue. Moreover, with intuitive interfaces,
+      AI agents enhance user interactions, making technology more accessible and user-friendly,
+      thereby breaking down barriers that have historically hindered digital engagement.\\n\\nDespite
+      their immense potential, the deployment of AI agents raises important ethical
+      and practical considerations. Issues related to privacy, data security, and
+      the potential for job displacement necessitate thoughtful dialogue and proactive
+      measures. Striking a balance between technological innovation and societal impact
+      will be crucial as organizations integrate these agents into their operations.
+      Additionally, ensuring transparency in AI decision-making processes is vital
+      to maintain public trust as AI agents become an integral part of daily life.\\n\\nLooking
+      ahead, the future of AI agents appears bright, with ongoing advancements promising
+      even greater capabilities. As we continue to harness the power of AI, we can
+      expect these agents to play a transformative role in shaping various sectors\u2014streamlining
+      workflows, enabling smarter decision-making, and fostering more personalized
+      experiences. Embracing this technology responsibly can lead to a future where
+      AI agents not only augment human effort but also inspire creativity and efficiency
+      across the board, ultimately redefining our interaction with the digital world.\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 208,\n    \"completion_tokens\":
+      382,\n    \"total_tokens\": 590,\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  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8c85f0c0cf961cf3-GRU
+      - 8f6930c97a33ae54-GRU
       Connection:
       - keep-alive
       Content-Encoding:
@@ -289,45 +102,77 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 24 Sep 2024 21:41:48 GMT
+      - Mon, 23 Dec 2024 14:55:10 GMT
       Server:
       - cloudflare
+      Set-Cookie:
+      - __cf_bm=g58erGPkGAltcfYpDRU4IsdEEzb955dGmBOAZacFlPA-1734965710-1.0.1.1-IiodiX3uxbT5xSa4seI7M.gRM4Jj46h2d6ZW2wCkSUYUAX.ivRh_sGQN2hucEMzdG8O87pc00dCl7E5W8KkyEA;
+        path=/; expires=Mon, 23-Dec-24 15:25:10 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=eQzzWvIXDS8Me1OIBdCG5F1qFyVfAo3sumvYRE7J41E-1734965710778-0.0.1.1-604800000;
+        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:
-      - '2468'
+      - '5401'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
       x-ratelimit-limit-requests:
-      - '10000'
+      - '30000'
       x-ratelimit-limit-tokens:
-      - '30000000'
+      - '150000000'
       x-ratelimit-remaining-requests:
-      - '9999'
+      - '29999'
       x-ratelimit-remaining-tokens:
-      - '29999625'
+      - '149999746'
       x-ratelimit-reset-requests:
-      - 6ms
+      - 2ms
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_66c8801b42ac865249246d98225c1492
+      - req_30791533923ae20626ef35a03ae66172
     http_version: HTTP/1.1
     status_code: 200
 - request:
     body: !!binary |
-      CtwBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSswEKEgoQY3Jld2FpLnRl
-      bGVtZXRyeRKcAQoQROg/k5NCUGdgfvfLrFlQDxIIlfh6oMbmqu0qClRvb2wgVXNhZ2UwATlws+Wj
-      FEz4F0EwBeijFEz4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBKKAoJdG9vbF9uYW1lEhsK
-      GURlbGVnYXRlIHdvcmsgdG8gY293b3JrZXJKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAAA==
+      CqYMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS/QsKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRLVCQoQLH3VghpS+l/DatJl8rrpvRIIUpNEm7ELU08qDENyZXcgQ3JlYXRlZDABObgs
+      nNId1hMYQfgVpdId1hMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogZTY0OTU3M2EyNmU1ODc5MGNhYzIxYTM3Y2Q0
+      NDQzN2FKMQoHY3Jld19pZBImCiQzYjVkNDFjNC1kZWJiLTQ2MzItYmIwMC1mNTdhNmM2M2QwMThK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSooFCgtjcmV3
+      X2FnZW50cxL6BAr3BFt7ImtleSI6ICIzMjgyMTdiNmMyOTU5YmRmYzQ3Y2FkMDBlODQ4OTBkMCIs
+      ICJpZCI6ICI1Yjk4NDA2OS03MjVlLTQxOWYtYjdiZS1mMDdjMTYyOGNkZjIiLCAicm9sZSI6ICJD
+      RU8iLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjAsICJtYXhfcnBtIjogbnVsbCwg
+      ImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdh
+      dGlvbl9lbmFibGVkPyI6IHRydWUsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1h
+      eF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiOWE1MDE1ZWY0
+      ODk1ZGM2Mjc4ZDU0ODE4YmE0NDZhZjciLCAiaWQiOiAiZjkwZWI0ZmItMzUyMC00ZDAyLTlhNDYt
+      NDE2ZTNlNTQ5NWYxIiwgInJvbGUiOiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJib3NlPyI6IGZhbHNl
+      LCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0i
+      OiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2Us
+      ICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0
+      b29sc19uYW1lcyI6IFtdfV1K+AEKCmNyZXdfdGFza3MS6QEK5gFbeyJrZXkiOiAiMGI5ZDY1ZGI2
+      YjdhZWRmYjM5OGM1OWUyYTlmNzFlYzUiLCAiaWQiOiAiNzdmNDY3MDYtNzRjZi00ZGVkLThlMDUt
+      NmRlZGM0MmYwZDliIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6
+      IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJDRU8iLCAiYWdlbnRfa2V5IjogIjMyODIxN2I2YzI5NTli
+      ZGZjNDdjYWQwMGU4NDg5MGQwIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEBvb
+      LkoAnHiD1gUnbftefpYSCNb1+4JxldizKgxUYXNrIENyZWF0ZWQwATmwYcTSHdYTGEEQz8TSHdYT
+      GEouCghjcmV3X2tleRIiCiBlNjQ5NTczYTI2ZTU4NzkwY2FjMjFhMzdjZDQ0NDM3YUoxCgdjcmV3
+      X2lkEiYKJDNiNWQ0MWM0LWRlYmItNDYzMi1iYjAwLWY1N2E2YzYzZDAxOEouCgh0YXNrX2tleRIi
+      CiAwYjlkNjVkYjZiN2FlZGZiMzk4YzU5ZTJhOWY3MWVjNUoxCgd0YXNrX2lkEiYKJDc3ZjQ2NzA2
+      LTc0Y2YtNGRlZC04ZTA1LTZkZWRjNDJmMGQ5YnoCGAGFAQABAAA=
     headers:
       Accept:
       - '*/*'
@@ -336,7 +181,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '223'
+      - '1577'
       Content-Type:
       - application/x-protobuf
       User-Agent:
@@ -352,213 +197,8 @@ interactions:
       Content-Type:
       - application/x-protobuf
       Date:
-      - Tue, 24 Sep 2024 21:41:51 GMT
+      - Mon, 23 Dec 2024 14:55:10 GMT
     status:
       code: 200
       message: OK
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
-      time CEO of a content creation agency with a Senior Writer on the team. You''re
-      now working on a new project and want to make sure the content produced is amazing.\nYour
-      personal goal is: Make sure the writers in your company produce amazing content.\nYou
-      ONLY have access to the following tools, and should NEVER make up tools that
-      are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
-      str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a
-      specific task to one of the following coworkers: Senior Writer\nThe input to
-      this tool should be the coworker, the task you want them to do, and ALL necessary
-      context to execute the task, they know nothing about the task, so share absolute
-      everything you know, don''t reference things but instead explain them.\nTool
-      Arguments: {''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'':
-      {''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
-      ''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
-      Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
-      = None, **kwargs)\nTool Description: Ask a specific question to one of the following
-      coworkers: Senior Writer\nThe input to this tool should be the coworker, the
-      question you have for them, and ALL necessary context to ask the question properly,
-      they know nothing about the question, so share absolute everything you know,
-      don''t reference things but instead explain them.\nTool Arguments: {''question'':
-      {''title'': ''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'',
-      ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
-      ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
-      format:\n\nThought: you should always think about what to do\nAction: the action
-      to take, only one name of [Delegate work to coworker, Ask question to coworker],
-      just the name, exactly as it''s written.\nAction Input: the input to the action,
-      just a simple python dictionary, enclosed in curly braces, using \" to wrap
-      keys and values.\nObservation: the result of the action\n\nOnce all necessary
-      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
-      the final answer to the original input question\n"}, {"role": "user", "content":
-      "\nCurrent Task: Produce and amazing 1 paragraph draft of an article about AI
-      Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
-      article about AI.\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:"},
-      {"role": "assistant", "content": "Thought: To ensure the content is amazing,
-      I''ll delegate the task of producing a one-paragraph draft of an article about
-      AI Agents to the Senior Writer with all necessary context.\n\nAction: Delegate
-      work to coworker\nAction Input: \n{\n    \"coworker\": \"Senior Writer\", \n    \"task\":
-      \"Produce a one paragraph draft of an article about AI Agents\", \n    \"context\":
-      \"We need an amazing one-paragraph draft as the beginning of a 4-paragraph article
-      about AI Agents. This is for a high-stakes project that critically impacts our
-      company. The paragraph should highlight what AI Agents are, their significance,
-      and how they are transforming various industries. The tone should be professional
-      yet engaging. Make sure the content is original, insightful, and thoroughly
-      researched.\"\n}\nObservation: Artificial Intelligence (AI) Agents are sophisticated
-      computer programs designed to perform tasks that typically require human intelligence,
-      such as decision making, problem-solving, and learning. These agents operate
-      autonomously, utilizing vast amounts of data, advanced algorithms, and machine
-      learning techniques to analyze their environment, adapt to new information,
-      and improve their performance over time. The significance of AI Agents lies
-      in their transformative potential across various industries. In healthcare,
-      they assist in diagnosing diseases with greater accuracy; in finance, they predict
-      market trends and manage risks; in customer service, they provide personalized
-      and efficient responses. As these AI-powered entities continue to evolve, they
-      are not only enhancing operational efficiencies but also driving innovation
-      and creating new opportunities for growth and development in every sector they
-      penetrate."}], "model": "gpt-4o"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '4536'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
-        _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.47.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.47.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-AB7a1PO3pMNybn76wXDFc5HE7ZRsL\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1727214109,\n  \"model\": \"gpt-4o-2024-05-13\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Thought: The paragraph provided by the
-      Senior Writer is well-detailed and engaging. I will now structure the 4-paragraph
-      article around this draft, adding an introduction, expanding on the specific
-      applications in various industries, and concluding with the potential future
-      impact of AI Agents.\\n\\nFinal Answer:\\n\\nArtificial Intelligence (AI) Agents
-      are sophisticated computer programs designed to perform tasks that typically
-      require human intelligence, such as decision making, problem-solving, and learning.
-      These agents operate autonomously, utilizing vast amounts of data, advanced
-      algorithms, and machine learning techniques to analyze their environment, adapt
-      to new information, and improve their performance over time.\\n\\nThe significance
-      of AI Agents lies in their transformative potential across various industries.
-      In healthcare, for example, they assist in diagnosing diseases with greater
-      accuracy and speed than human practitioners, offering personalized treatment
-      plans by analyzing patient data. In finance, AI Agents predict market trends,
-      manage risks, and even execute trades, contributing to more stable and profitable
-      financial systems. Customer service sectors benefit significantly from AI Agents,
-      as they provide personalized and efficient responses, often resolving issues
-      faster than traditional methods.\\n\\nMoreover, AI Agents are also making substantial
-      contributions in fields like education and manufacturing. In education, they
-      offer tailored learning experiences by assessing individual student needs and
-      adjusting teaching methods accordingly. They help educators identify students
-      who might need additional support and provide resources to enhance learning
-      outcomes. In manufacturing, AI Agents optimize production lines, predict equipment
-      failures, and improve supply chain management, thus boosting productivity and
-      reducing downtime.\\n\\nAs these AI-powered entities continue to evolve, they
-      are not only enhancing operational efficiencies but also driving innovation
-      and creating new opportunities for growth and development in every sector they
-      penetrate. The future of AI Agents looks promising, with the potential to revolutionize
-      the way we live and work, making processes more efficient, decisions more data-driven,
-      and solutions more innovative than ever before.\\n\\nThis is now a well-rounded,
-      four-paragraph article that comprehensively covers the topic of AI Agents.\\n\\nFinal
-      Answer: This is the complete content as specified:\\nArtificial Intelligence
-      (AI) Agents are sophisticated computer programs designed to perform tasks that
-      typically require human intelligence, such as decision making, problem-solving,
-      and learning. These agents operate autonomously, utilizing vast amounts of data,
-      advanced algorithms, and machine learning techniques to analyze their environment,
-      adapt to new information, and improve their performance over time.\\n\\nThe
-      significance of AI Agents lies in their transformative potential across various
-      industries. In healthcare, for example, they assist in diagnosing diseases with
-      greater accuracy and speed than human practitioners, offering personalized treatment
-      plans by analyzing patient data. In finance, AI Agents predict market trends,
-      manage risks, and even execute trades, contributing to more stable and profitable
-      financial systems. Customer service sectors benefit significantly from AI Agents,
-      as they provide personalized and efficient responses, often resolving issues
-      faster than traditional methods.\\n\\nMoreover, AI Agents are also making substantial
-      contributions in fields like education and manufacturing. In education, they
-      offer tailored learning experiences by assessing individual student needs and
-      adjusting teaching methods accordingly. They help educators identify students
-      who might need additional support and provide resources to enhance learning
-      outcomes. In manufacturing, AI Agents optimize production lines, predict equipment
-      failures, and improve supply chain management, thus boosting productivity and
-      reducing downtime.\\n\\nAs these AI-powered entities continue to evolve, they
-      are not only enhancing operational efficiencies but also driving innovation
-      and creating new opportunities for growth and development in every sector they
-      penetrate. The future of AI Agents looks promising, with the potential to revolutionize
-      the way we live and work, making processes more efficient, decisions more data-driven,
-      and solutions more innovative than ever before.\",\n        \"refusal\": null\n
-      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
-      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 923,\n    \"completion_tokens\":
-      715,\n    \"total_tokens\": 1638,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
-      0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8c85f0d2f90c1cf3-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 24 Sep 2024 21:41:58 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '8591'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '30000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '29998895'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 2ms
-      x-request-id:
-      - req_2b51b5cff02148d29b04284b40ca6081
-    http_version: HTTP/1.1
-    status_code: 200
 version: 1

tests/cassettes/test_crew_with_delegating_agents_should_not_override_agent_tools.yaml

@@ -0,0 +1,480 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
+      time CEO of a content creation agency with a Senior Writer on the team. You''re
+      now working on a new project and want to make sure the content produced is amazing.\nYour
+      personal goal is: Make sure the writers in your company produce amazing content.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
+      ''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
+      just returns the input\n\nUse the following format:\n\nThought: you should always
+      think about what to do\nAction: the action to take, only one name of [Test Tool],
+      just the name, exactly as it''s written.\nAction Input: the input to the action,
+      just a simple python dictionary, enclosed in curly braces, using \" to wrap
+      keys and values.\nObservation: the result of the action\n\nOnce all necessary
+      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
+      the final answer to the original input question"}, {"role": "user", "content":
+      "\nCurrent Task: Produce and amazing 1 paragraph draft of an article about AI
+      Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
+      article about AI.\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:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1581'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhLsKP8xKkISk8ntUscyUKL30xRXW\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734895556,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I need to gather information to create
+      an amazing paragraph draft about AI Agents that aligns with the expected criteria
+      of a 4-paragraph article about AI. \\n\\nAction: Test Tool  \\nAction Input:
+      {\\\"query\\\": \\\"Write a captivating and informative paragraph about AI Agents,
+      focusing on their capabilities, applications, and significance in modern technology.\\\"}
+      \ \",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 309,\n    \"completion_tokens\":
+      68,\n    \"total_tokens\": 377,\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  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f62802d0b3f00d5-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 22 Dec 2024 19:25:57 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=vwBNilrHRgMLd8ALWzYrBO5Lm8ieJzbQ3WCVOgmuJ.s-1734895557-1.0.1.1-z.QnDsynL_Ndu.JkWrh_wGMo57vvpK88nWDBTA8P.6prlSRmA91GQLpP62yRUbCW6yoKFbDxroSaYO6qrzZPRg;
+        path=/; expires=Sun, 22-Dec-24 19:55:57 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000;
+        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:
+      - '1075'
+      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:
+      - '149999630'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_80fbcef3505afac708a24ef167b701bb
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
+      time CEO of a content creation agency with a Senior Writer on the team. You''re
+      now working on a new project and want to make sure the content produced is amazing.\nYour
+      personal goal is: Make sure the writers in your company produce amazing content.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
+      ''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
+      just returns the input\n\nUse the following format:\n\nThought: you should always
+      think about what to do\nAction: the action to take, only one name of [Test Tool],
+      just the name, exactly as it''s written.\nAction Input: the input to the action,
+      just a simple python dictionary, enclosed in curly braces, using \" to wrap
+      keys and values.\nObservation: the result of the action\n\nOnce all necessary
+      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
+      the final answer to the original input question"}, {"role": "user", "content":
+      "\nCurrent Task: Produce and amazing 1 paragraph draft of an article about AI
+      Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
+      article about AI.\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:"},
+      {"role": "assistant", "content": "I need to gather information to create an
+      amazing paragraph draft about AI Agents that aligns with the expected criteria
+      of a 4-paragraph article about AI. \n\nAction: Test Tool  \nAction Input: {\"query\":
+      \"Write a captivating and informative paragraph about AI Agents, focusing on
+      their capabilities, applications, and significance in modern technology.\"}  \nObservation:
+      Processed: Write a captivating and informative paragraph about AI Agents, focusing
+      on their capabilities, applications, and significance in modern technology."}],
+      "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2153'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=vwBNilrHRgMLd8ALWzYrBO5Lm8ieJzbQ3WCVOgmuJ.s-1734895557-1.0.1.1-z.QnDsynL_Ndu.JkWrh_wGMo57vvpK88nWDBTA8P.6prlSRmA91GQLpP62yRUbCW6yoKFbDxroSaYO6qrzZPRg;
+        _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhLsMt1AgrzynC2TSJZZSwr9El8FV\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734895558,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I have received the content
+      related to AI Agents, which I need to now use as a foundation for creating a
+      complete 4-paragraph article about AI. \\n\\nAction: Test Tool  \\nAction Input:
+      {\\\"query\\\": \\\"Based on the previous paragraph about AI Agents, write a
+      4-paragraph article about AI, including an introduction, discussion of AI Agents,
+      their applications, and a conclusion on the future of AI.\\\"}  \",\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 409,\n    \"completion_tokens\":
+      88,\n    \"total_tokens\": 497,\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  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f6280352b9400d5-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 22 Dec 2024 19:25:59 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1346'
+      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:
+      - '149999498'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_e25b377af34ef03b9a6955c9cfca5738
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CtoOCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSsQ4KEgoQY3Jld2FpLnRl
+      bGVtZXRyeRLrCQoQHzrcBLmZm6+CB9ZGtTnz1BIISnyRX3cExT4qDENyZXcgQ3JlYXRlZDABOdCK
+      UxFRlhMYQdiyWhFRlhMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogZTY0OTU3M2EyNmU1ODc5MGNhYzIxYTM3Y2Q0
+      NDQzN2FKMQoHY3Jld19pZBImCiQyYWFjYzYwZC0xYzE5LTRjZGYtYmJhNy1iM2RiMGM4YzFlZWZK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSpUFCgtjcmV3
+      X2FnZW50cxKFBQqCBVt7ImtleSI6ICIzMjgyMTdiNmMyOTU5YmRmYzQ3Y2FkMDBlODQ4OTBkMCIs
+      ICJpZCI6ICJlZmE4ZWRlNS0wN2IyLTQzOWUtYWQ4Yi1iNmQ0Nzg5NjBkNzkiLCAicm9sZSI6ICJD
+      RU8iLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjAsICJtYXhfcnBtIjogbnVsbCwg
+      ImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdh
+      dGlvbl9lbmFibGVkPyI6IHRydWUsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1h
+      eF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFsidGVzdCB0b29sIl19LCB7ImtleSI6
+      ICI5YTUwMTVlZjQ4OTVkYzYyNzhkNTQ4MThiYTQ0NmFmNyIsICJpZCI6ICIxMDE2MGEzMC0zM2U4
+      LTRlN2YtOTAzOC1lODU3Zjc2MzI0ZTUiLCAicm9sZSI6ICJTZW5pb3IgV3JpdGVyIiwgInZlcmJv
+      c2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9j
+      YWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxl
+      ZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xp
+      bWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUqDAgoKY3Jld190YXNrcxL0AQrxAVt7ImtleSI6
+      ICIwYjlkNjVkYjZiN2FlZGZiMzk4YzU5ZTJhOWY3MWVjNSIsICJpZCI6ICJiNjYyZWVkOS1kYzcy
+      LTQ1NTEtYTdmMC1kY2E4ZTk3MmU3NjciLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVt
+      YW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIkNFTyIsICJhZ2VudF9rZXkiOiAiMzI4
+      MjE3YjZjMjk1OWJkZmM0N2NhZDAwZTg0ODkwZDAiLCAidG9vbHNfbmFtZXMiOiBbInRlc3QgdG9v
+      bCJdfV16AhgBhQEAAQAAEo4CChDkOw+7vfeJwW1bc0PIIqxeEggzmQQt0SPl+ioMVGFzayBDcmVh
+      dGVkMAE5OBlxEVGWExhBwKlxEVGWExhKLgoIY3Jld19rZXkSIgogZTY0OTU3M2EyNmU1ODc5MGNh
+      YzIxYTM3Y2Q0NDQzN2FKMQoHY3Jld19pZBImCiQyYWFjYzYwZC0xYzE5LTRjZGYtYmJhNy1iM2Ri
+      MGM4YzFlZWZKLgoIdGFza19rZXkSIgogMGI5ZDY1ZGI2YjdhZWRmYjM5OGM1OWUyYTlmNzFlYzVK
+      MQoHdGFza19pZBImCiRiNjYyZWVkOS1kYzcyLTQ1NTEtYTdmMC1kY2E4ZTk3MmU3Njd6AhgBhQEA
+      AQAAEowBChDS1rm7Q+c0w96t+encwsGJEgjRF+jTQh1PCyoKVG9vbCBVc2FnZTABOaAiFGtRlhMY
+      QdiVImtRlhMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoYCgl0b29sX25hbWUSCwoJVGVz
+      dCBUb29sSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASjAEKECYGxNLnTRLCS76uAAOuzGwSCPmX
+      kSTjWKCcKgpUb29sIFVzYWdlMAE5CH3Wx1GWExhBGH/xx1GWExhKGgoOY3Jld2FpX3ZlcnNpb24S
+      CAoGMC44Ni4wShgKCXRvb2xfbmFtZRILCglUZXN0IFRvb2xKDgoIYXR0ZW1wdHMSAhgBegIYAYUB
+      AAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1885'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    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:
+      - Sun, 22 Dec 2024 19:26:01 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
+      time CEO of a content creation agency with a Senior Writer on the team. You''re
+      now working on a new project and want to make sure the content produced is amazing.\nYour
+      personal goal is: Make sure the writers in your company produce amazing content.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
+      ''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
+      just returns the input\n\nUse the following format:\n\nThought: you should always
+      think about what to do\nAction: the action to take, only one name of [Test Tool],
+      just the name, exactly as it''s written.\nAction Input: the input to the action,
+      just a simple python dictionary, enclosed in curly braces, using \" to wrap
+      keys and values.\nObservation: the result of the action\n\nOnce all necessary
+      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
+      the final answer to the original input question"}, {"role": "user", "content":
+      "\nCurrent Task: Produce and amazing 1 paragraph draft of an article about AI
+      Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
+      article about AI.\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:"},
+      {"role": "assistant", "content": "I need to gather information to create an
+      amazing paragraph draft about AI Agents that aligns with the expected criteria
+      of a 4-paragraph article about AI. \n\nAction: Test Tool  \nAction Input: {\"query\":
+      \"Write a captivating and informative paragraph about AI Agents, focusing on
+      their capabilities, applications, and significance in modern technology.\"}  \nObservation:
+      Processed: Write a captivating and informative paragraph about AI Agents, focusing
+      on their capabilities, applications, and significance in modern technology."},
+      {"role": "assistant", "content": "Thought: I have received the content related
+      to AI Agents, which I need to now use as a foundation for creating a complete
+      4-paragraph article about AI. \n\nAction: Test Tool  \nAction Input: {\"query\":
+      \"Based on the previous paragraph about AI Agents, write a 4-paragraph article
+      about AI, including an introduction, discussion of AI Agents, their applications,
+      and a conclusion on the future of AI.\"}  \nObservation: Processed: Based on
+      the previous paragraph about AI Agents, write a 4-paragraph article about AI,
+      including an introduction, discussion of AI Agents, their applications, and
+      a conclusion on the future of AI."}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2820'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=vwBNilrHRgMLd8ALWzYrBO5Lm8ieJzbQ3WCVOgmuJ.s-1734895557-1.0.1.1-z.QnDsynL_Ndu.JkWrh_wGMo57vvpK88nWDBTA8P.6prlSRmA91GQLpP62yRUbCW6yoKFbDxroSaYO6qrzZPRg;
+        _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhLsNJa6GxRIHF8l8eViU7D6CyBHP\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734895559,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I have gathered the complete
+      article on AI, which aligns with the expected criteria. Now I will present the
+      final answer as required. \\n\\nFinal Answer: \\n\\nArtificial Intelligence
+      (AI) has rapidly evolved to become an integral part of our modern world, driving
+      significant advancements across various industries. AI refers to the simulation
+      of human intelligence in machines programmed to think and learn like humans.
+      This technology enables machines to analyze data, recognize patterns, and make
+      decisions with minimal human intervention, paving the way for innovation in
+      fields like healthcare, finance, and transportation.\\n\\nAI Agents, in particular,
+      embody the future of artificial intelligence by acting autonomously to perform
+      complex tasks. These agents leverage machine learning and natural language processing
+      to interact with users and understand their needs. They're deployed in customer
+      service applications, virtual assistants, and personal scheduling tools, showcasing
+      their capability to streamline processes and enhance user experience. By mimicking
+      human reasoning, AI Agents can adapt to changing situations and provide personalized
+      solutions.\\n\\nThe applications of AI Agents extend beyond mere task completion;
+      they are transforming the way businesses operate. In the realm of customer engagement,
+      AI Agents analyze customer behavior to provide insights that help companies
+      tailor their offerings. In healthcare, they assist in diagnosing illnesses by
+      analyzing patient data and suggesting treatments. The versatility of AI Agents
+      makes them invaluable assets in our increasingly automated world.\\n\\nAs we
+      look to the future, the potential of AI continues to expand. With ongoing advancements
+      in technology, AI Agents are set to become even more sophisticated, further
+      bridging the gap between humans and machines. The prospects of AI promise not
+      only to improve efficiency and productivity but also to change the way we live
+      and work, promising a future where intelligent, autonomous agents support us
+      in our daily lives.\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      546,\n    \"completion_tokens\": 343,\n    \"total_tokens\": 889,\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  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f62803eed8100d5-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 22 Dec 2024 19:26:04 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '4897'
+      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:
+      - '149999342'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_65fdf94aa8bbc10f64f2a27ccdcc5cc8
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_crew_with_delegating_agents_should_not_override_task_tools.yaml

@@ -0,0 +1,623 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
+      time CEO of a content creation agency with a Senior Writer on the team. You''re
+      now working on a new project and want to make sure the content produced is amazing.\nYour
+      personal goal is: Make sure the writers in your company produce amazing content.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
+      ''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
+      just returns the input\nTool Name: Delegate work to coworker\nTool Arguments:
+      {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
+      {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
+      {''description'': ''The role/name of the coworker to delegate to'', ''type'':
+      ''str''}}\nTool Description: Delegate a specific task to one of the following
+      coworkers: Senior Writer\nThe input to this tool should be the coworker, the
+      task you want them to do, and ALL necessary context to execute the task, they
+      know nothing about the task, so share absolute everything you know, don''t reference
+      things but instead explain them.\nTool Name: Ask question to coworker\nTool
+      Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
+      ''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
+      ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
+      ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
+      of the following coworkers: Senior Writer\nThe input to this tool should be
+      the coworker, the question you have for them, and ALL necessary context to ask
+      the question properly, they know nothing about the question, so share absolute
+      everything you know, don''t reference things but instead explain them.\n\nUse
+      the following format:\n\nThought: you should always think about what to do\nAction:
+      the action to take, only one name of [Test Tool, Delegate work to coworker,
+      Ask question to coworker], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple python dictionary, enclosed in
+      curly braces, using \" to wrap keys and values.\nObservation: the result of
+      the action\n\nOnce all necessary information is gathered:\n\nThought: I now
+      know the final answer\nFinal Answer: the final answer to the original input
+      question"}, {"role": "user", "content": "\nCurrent Task: Produce and amazing
+      1 paragraph draft of an article about AI Agents.\n\nThis is the expect criteria
+      for your final answer: A 4 paragraph article about AI.\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:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2892'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhLQELAjJpn76wiLmWBinm3sqf32l\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734893814,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I need to gather information and insights
+      to ensure the Senior Writer produces a high-quality draft about AI Agents, which
+      will then serve as a foundation for the complete article.\\n\\nAction: Ask question
+      to coworker  \\nAction Input: {\\\"question\\\":\\\"Can you provide a detailed
+      overview of what AI Agents are, their functionalities, and their applications
+      in real-world scenarios? Please include examples of how they are being used
+      in various industries, and discuss their potential impact on the future of technology
+      and society.\\\",\\\"context\\\":\\\"We are looking to create a comprehensive
+      understanding of AI Agents as part of a four-paragraph article. This will help
+      generate a high-quality draft for the article.\\\",\\\"coworker\\\":\\\"Senior
+      Writer\\\"}  \",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      604,\n    \"completion_tokens\": 138,\n    \"total_tokens\": 742,\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  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f6255a1bf08a519-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 22 Dec 2024 18:56:56 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=rVquIlcnYXc7wMkbKG5Ii90HxfQ_ukNJjDgSHhsWb1k-1734893816-1.0.1.1-33qDl8KNWcxLAGBuPhT8FrZ6QUnEy9oOYh2Fp2hIjDnF.cQlyrgxiWcuHljTTxG_mH7eQrf1AHJ6p8sxZJZ30A;
+        path=/; expires=Sun, 22-Dec-24 19:26:56 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=xqgLJsf3h5lBKZFTADRNNUqizeChNBBFoLvWiR2WPnw-1734893816555-0.0.1.1-604800000;
+        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:
+      - '2340'
+      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:
+      - '149999305'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_53956b48bd1188451efc104e8a234ef4
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CrEMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSiAwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRLgCQoQg/HA64g3phKbzz/hvUtbahIIpu+Csq+uWc0qDENyZXcgQ3JlYXRlZDABOSDm
+      Uli7lBMYQcgRXFi7lBMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogZTY0OTU3M2EyNmU1ODc5MGNhYzIxYTM3Y2Q0
+      NDQzN2FKMQoHY3Jld19pZBImCiRhMWFjMTc0Ny0xMTA0LTRlZjItODZkNi02ZGRhNTFmMDlmMTdK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSooFCgtjcmV3
+      X2FnZW50cxL6BAr3BFt7ImtleSI6ICIzMjgyMTdiNmMyOTU5YmRmYzQ3Y2FkMDBlODQ4OTBkMCIs
+      ICJpZCI6ICI4YWUwNGY0Yy0wMjNiLTRkNWQtODAwZC02ZjlkMWFmMWExOTkiLCAicm9sZSI6ICJD
+      RU8iLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjAsICJtYXhfcnBtIjogbnVsbCwg
+      ImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdh
+      dGlvbl9lbmFibGVkPyI6IHRydWUsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1h
+      eF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiOWE1MDE1ZWY0
+      ODk1ZGM2Mjc4ZDU0ODE4YmE0NDZhZjciLCAiaWQiOiAiNDg2MWQ4YTMtMjMxYS00Mzc5LTk2ZmEt
+      MWQwZmQyZDI1MGYxIiwgInJvbGUiOiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJib3NlPyI6IGZhbHNl
+      LCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0i
+      OiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2Us
+      ICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0
+      b29sc19uYW1lcyI6IFtdfV1KgwIKCmNyZXdfdGFza3MS9AEK8QFbeyJrZXkiOiAiMGI5ZDY1ZGI2
+      YjdhZWRmYjM5OGM1OWUyYTlmNzFlYzUiLCAiaWQiOiAiY2IyMmIxMzctZTA3ZC00NDA5LWI5NmMt
+      ZWQ2ZDU3MjFhNDNiIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6
+      IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJDRU8iLCAiYWdlbnRfa2V5IjogIjMyODIxN2I2YzI5NTli
+      ZGZjNDdjYWQwMGU4NDg5MGQwIiwgInRvb2xzX25hbWVzIjogWyJ0ZXN0IHRvb2wiXX1degIYAYUB
+      AAEAABKOAgoQB7Z9AEDI9OTStHqguBSbLxIIj9dttVFJs9cqDFRhc2sgQ3JlYXRlZDABOYDae1i7
+      lBMYQeBHfFi7lBMYSi4KCGNyZXdfa2V5EiIKIGU2NDk1NzNhMjZlNTg3OTBjYWMyMWEzN2NkNDQ0
+      MzdhSjEKB2NyZXdfaWQSJgokYTFhYzE3NDctMTEwNC00ZWYyLTg2ZDYtNmRkYTUxZjA5ZjE3Si4K
+      CHRhc2tfa2V5EiIKIDBiOWQ2NWRiNmI3YWVkZmIzOThjNTllMmE5ZjcxZWM1SjEKB3Rhc2tfaWQS
+      JgokY2IyMmIxMzctZTA3ZC00NDA5LWI5NmMtZWQ2ZDU3MjFhNDNiegIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1588'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    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:
+      - Sun, 22 Dec 2024 18:56:59 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Senior Writer. You''re
+      a senior writer, specialized in technology, software engineering, AI and startups.
+      You work as a freelancer and are now working on writing content for a new customer.\nYour
+      personal goal is: Write the best content about AI and AI agents.\nTo give my
+      best complete final answer to the task use 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: Can you provide a detailed overview of what AI Agents are, their functionalities,
+      and their applications in real-world scenarios? Please include examples of how
+      they are being used in various industries, and discuss their potential impact
+      on the future of technology and society.\n\nThis is the expect criteria for
+      your final answer: Your best answer to your coworker asking you this, accounting
+      for the context shared.\nyou MUST return the actual complete content as the
+      final answer, not a summary.\n\nThis is the context you''re working with:\nWe
+      are looking to create a comprehensive understanding of AI Agents as part of
+      a four-paragraph article. This will help generate a high-quality draft for the
+      article.\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:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1572'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rVquIlcnYXc7wMkbKG5Ii90HxfQ_ukNJjDgSHhsWb1k-1734893816-1.0.1.1-33qDl8KNWcxLAGBuPhT8FrZ6QUnEy9oOYh2Fp2hIjDnF.cQlyrgxiWcuHljTTxG_mH7eQrf1AHJ6p8sxZJZ30A;
+        _cfuvid=xqgLJsf3h5lBKZFTADRNNUqizeChNBBFoLvWiR2WPnw-1734893816555-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhLQG5ubl99yeBYm6TTV0sodagMND\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734893816,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: \\n\\n**Overview of AI Agents**  \\nAI agents are advanced software
+      systems designed to autonomously perform tasks, make decisions, and learn from
+      their environments without needing constant human intervention. They leverage
+      machine learning, natural language processing, and various AI techniques to
+      simulate human-like understanding and autonomy. These agents can be categorized
+      into three types: reactive agents (which operate purely based on their environment),
+      deliberative agents (which can make decisions based on reasoning), and hybrid
+      agents that incorporate aspects of both types. Their ability to adapt and learn
+      over time makes them instrumental in automating processes across various domains.\\n\\n**Functionalities
+      of AI Agents**  \\nThe core functionalities of AI agents include perception,
+      action, learning, and interaction. They perceive data through sensors or data
+      feeds, process information through algorithms, and take actions based on this
+      data. Machine learning allows them to refine their performance over time by
+      analyzing outcomes and adjusting their strategies accordingly. Interaction capabilities
+      enable them to communicate with users, providing insights, answering queries,
+      or even negotiating in some cases. These functionalities make AI agents invaluable
+      for tasks such as predictive analytics, personal assistance, and real-time decision-making
+      in complex systems.\\n\\n**Applications in Various Industries**  \\nAI agents
+      are already being utilized across multiple industries, demonstrating their versatility
+      and efficiency. In healthcare, AI agents assist in diagnostics by analyzing
+      medical records and suggesting treatment plans tailored to individual patients.
+      In finance, they power robo-advisors that manage investment portfolios, automate
+      trading strategies, and provide financial advice based on real-time market analysis.
+      Furthermore, in customer service, AI chatbots serve as virtual assistants, enhancing
+      user experience by providing instant support and resolving queries without human
+      intervention. The logistics and supply chain industries have also seen AI agents
+      optimize inventory management and route planning, significantly improving operational
+      efficiency.\\n\\n**Future Impact on Technology and Society**  \\nThe ongoing
+      development of AI agents is poised to have a profound impact on technology and
+      society. As these agents become more sophisticated, we can anticipate a shift
+      towards increased automation in both professional and personal spheres, leading
+      to enhanced productivity and new business models. However, this automation introduces
+      challenges such as job displacement and ethical considerations regarding decision-making
+      by AI. It is essential to foster an ongoing dialogue on the implications of
+      AI agents to ensure responsible development and integration into our daily lives.
+      As AI agents continue to evolve, they will undoubtedly play a pivotal role in
+      shaping the future of technology and its intersection with societal dynamics,
+      making it critical for us to engage thoughtfully with this emerging paradigm.\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 289,\n    \"completion_tokens\":
+      506,\n    \"total_tokens\": 795,\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  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f6255b1f832a519-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 22 Dec 2024 18:57:04 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '7836'
+      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:
+      - '149999630'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_c14268346d6ce72ceea4b1472f73c5ae
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CtsBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSsgEKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKbAQoQ7U/1ZgBSTkCXtesUNPA2URIIrnRWFVT58Z8qClRvb2wgVXNhZ2UwATl4lN3i
+      vZQTGEGgevzivZQTGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKJwoJdG9vbF9uYW1lEhoK
+      GEFzayBxdWVzdGlvbiB0byBjb3dvcmtlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '222'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    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:
+      - Sun, 22 Dec 2024 18:57:09 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
+      time CEO of a content creation agency with a Senior Writer on the team. You''re
+      now working on a new project and want to make sure the content produced is amazing.\nYour
+      personal goal is: Make sure the writers in your company produce amazing content.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
+      ''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
+      just returns the input\nTool Name: Delegate work to coworker\nTool Arguments:
+      {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
+      {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
+      {''description'': ''The role/name of the coworker to delegate to'', ''type'':
+      ''str''}}\nTool Description: Delegate a specific task to one of the following
+      coworkers: Senior Writer\nThe input to this tool should be the coworker, the
+      task you want them to do, and ALL necessary context to execute the task, they
+      know nothing about the task, so share absolute everything you know, don''t reference
+      things but instead explain them.\nTool Name: Ask question to coworker\nTool
+      Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
+      ''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
+      ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
+      ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
+      of the following coworkers: Senior Writer\nThe input to this tool should be
+      the coworker, the question you have for them, and ALL necessary context to ask
+      the question properly, they know nothing about the question, so share absolute
+      everything you know, don''t reference things but instead explain them.\n\nUse
+      the following format:\n\nThought: you should always think about what to do\nAction:
+      the action to take, only one name of [Test Tool, Delegate work to coworker,
+      Ask question to coworker], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple python dictionary, enclosed in
+      curly braces, using \" to wrap keys and values.\nObservation: the result of
+      the action\n\nOnce all necessary information is gathered:\n\nThought: I now
+      know the final answer\nFinal Answer: the final answer to the original input
+      question"}, {"role": "user", "content": "\nCurrent Task: Produce and amazing
+      1 paragraph draft of an article about AI Agents.\n\nThis is the expect criteria
+      for your final answer: A 4 paragraph article about AI.\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:"}, {"role": "assistant", "content": "I need
+      to gather information and insights to ensure the Senior Writer produces a high-quality
+      draft about AI Agents, which will then serve as a foundation for the complete
+      article.\n\nAction: Ask question to coworker  \nAction Input: {\"question\":\"Can
+      you provide a detailed overview of what AI Agents are, their functionalities,
+      and their applications in real-world scenarios? Please include examples of how
+      they are being used in various industries, and discuss their potential impact
+      on the future of technology and society.\",\"context\":\"We are looking to create
+      a comprehensive understanding of AI Agents as part of a four-paragraph article.
+      This will help generate a high-quality draft for the article.\",\"coworker\":\"Senior
+      Writer\"}  \nObservation: **Overview of AI Agents**  \nAI agents are advanced
+      software systems designed to autonomously perform tasks, make decisions, and
+      learn from their environments without needing constant human intervention. They
+      leverage machine learning, natural language processing, and various AI techniques
+      to simulate human-like understanding and autonomy. These agents can be categorized
+      into three types: reactive agents (which operate purely based on their environment),
+      deliberative agents (which can make decisions based on reasoning), and hybrid
+      agents that incorporate aspects of both types. Their ability to adapt and learn
+      over time makes them instrumental in automating processes across various domains.\n\n**Functionalities
+      of AI Agents**  \nThe core functionalities of AI agents include perception,
+      action, learning, and interaction. They perceive data through sensors or data
+      feeds, process information through algorithms, and take actions based on this
+      data. Machine learning allows them to refine their performance over time by
+      analyzing outcomes and adjusting their strategies accordingly. Interaction capabilities
+      enable them to communicate with users, providing insights, answering queries,
+      or even negotiating in some cases. These functionalities make AI agents invaluable
+      for tasks such as predictive analytics, personal assistance, and real-time decision-making
+      in complex systems.\n\n**Applications in Various Industries**  \nAI agents are
+      already being utilized across multiple industries, demonstrating their versatility
+      and efficiency. In healthcare, AI agents assist in diagnostics by analyzing
+      medical records and suggesting treatment plans tailored to individual patients.
+      In finance, they power robo-advisors that manage investment portfolios, automate
+      trading strategies, and provide financial advice based on real-time market analysis.
+      Furthermore, in customer service, AI chatbots serve as virtual assistants, enhancing
+      user experience by providing instant support and resolving queries without human
+      intervention. The logistics and supply chain industries have also seen AI agents
+      optimize inventory management and route planning, significantly improving operational
+      efficiency.\n\n**Future Impact on Technology and Society**  \nThe ongoing development
+      of AI agents is poised to have a profound impact on technology and society.
+      As these agents become more sophisticated, we can anticipate a shift towards
+      increased automation in both professional and personal spheres, leading to enhanced
+      productivity and new business models. However, this automation introduces challenges
+      such as job displacement and ethical considerations regarding decision-making
+      by AI. It is essential to foster an ongoing dialogue on the implications of
+      AI agents to ensure responsible development and integration into our daily lives.
+      As AI agents continue to evolve, they will undoubtedly play a pivotal role in
+      shaping the future of technology and its intersection with societal dynamics,
+      making it critical for us to engage thoughtfully with this emerging paradigm."}],
+      "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '6755'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rVquIlcnYXc7wMkbKG5Ii90HxfQ_ukNJjDgSHhsWb1k-1734893816-1.0.1.1-33qDl8KNWcxLAGBuPhT8FrZ6QUnEy9oOYh2Fp2hIjDnF.cQlyrgxiWcuHljTTxG_mH7eQrf1AHJ6p8sxZJZ30A;
+        _cfuvid=xqgLJsf3h5lBKZFTADRNNUqizeChNBBFoLvWiR2WPnw-1734893816555-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhLQOmLKuevpaWtRyyhHjHVYqvNVk\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734893824,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I have received a comprehensive
+      overview from the Senior Writer that includes the necessary information about
+      AI Agents, their functionalities, applications, and future implications. Now,
+      I can compile this into a final answer following the specified format: a complete
+      four-paragraph article.\\n\\nFinal Answer: \\n\\n**Overview of AI Agents**  \\nAI
+      agents are advanced software systems designed to autonomously perform tasks,
+      make decisions, and learn from their environments without needing constant human
+      intervention. They leverage machine learning, natural language processing, and
+      various AI techniques to simulate human-like understanding and autonomy. These
+      agents can be categorized into three types: reactive agents (which operate purely
+      based on their environment), deliberative agents (which can make decisions based
+      on reasoning), and hybrid agents that incorporate aspects of both types. Their
+      ability to adapt and learn over time makes them instrumental in automating processes
+      across various domains.\\n\\n**Functionalities of AI Agents**  \\nThe core functionalities
+      of AI agents include perception, action, learning, and interaction. They perceive
+      data through sensors or data feeds, process information through algorithms,
+      and take actions based on this data. Machine learning allows them to refine
+      their performance over time by analyzing outcomes and adjusting their strategies
+      accordingly. Interaction capabilities enable them to communicate with users,
+      providing insights, answering queries, or even negotiating in some cases. These
+      functionalities make AI agents invaluable for tasks such as predictive analytics,
+      personal assistance, and real-time decision-making in complex systems.\\n\\n**Applications
+      in Various Industries**  \\nAI agents are already being utilized across multiple
+      industries, demonstrating their versatility and efficiency. In healthcare, AI
+      agents assist in diagnostics by analyzing medical records and suggesting treatment
+      plans tailored to individual patients. In finance, they power robo-advisors
+      that manage investment portfolios, automate trading strategies, and provide
+      financial advice based on real-time market analysis. Furthermore, in customer
+      service, AI chatbots serve as virtual assistants, enhancing user experience
+      by providing instant support and resolving queries without human intervention.
+      The logistics and supply chain industries have also seen AI agents optimize
+      inventory management and route planning, significantly improving operational
+      efficiency.\\n\\n**Future Impact on Technology and Society**  \\nThe ongoing
+      development of AI agents is poised to have a profound impact on technology and
+      society. As these agents become more sophisticated, we can anticipate a shift
+      towards increased automation in both professional and personal spheres, leading
+      to enhanced productivity and new business models. However, this automation introduces
+      challenges such as job displacement and ethical considerations regarding decision-making
+      by AI. It is essential to foster an ongoing dialogue on the implications of
+      AI agents to ensure responsible development and integration into our daily lives.
+      As AI agents continue to evolve, they will undoubtedly play a pivotal role in
+      shaping the future of technology and its intersection with societal dynamics,
+      making it critical for us to engage thoughtfully with this emerging paradigm.\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 1242,\n    \"completion_tokens\":
+      550,\n    \"total_tokens\": 1792,\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  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f6255e49b37a519-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 22 Dec 2024 18:57:12 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '7562'
+      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:
+      - '149998353'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_a812bbb85b3d785660c4662212614ab9
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_multimodal_agent_live_image_analysis.yaml

@@ -0,0 +1,481 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Image Analyst. You''re
+      an expert at visual analysis, trained to notice and describe details in images.\nYour
+      personal goal is: Analyze images with high attention to detail\nYou ONLY have
+      access to the following tools, and should NEVER make up tools that are not listed
+      here:\n\nTool Name: Add image to content\nTool Arguments: {''image_url'': {''description'':
+      ''The URL or path of the image to add'', ''type'': ''str''}, ''action'': {''description'':
+      ''Optional context or question about the image'', ''type'': ''str''}}\nTool
+      Description: See image to understand it''s content, you can optionally ask a
+      question about the image\n\nUse the following format:\n\nThought: you should
+      always think about what to do\nAction: the action to take, only one name of
+      [Add image to content], just the name, exactly as it''s written.\nAction Input:
+      the input to the action, just a simple python dictionary, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce
+      all necessary information is gathered:\n\nThought: I now know the final answer\nFinal
+      Answer: the final answer to the original input question"}, {"role": "user",
+      "content": "\nCurrent Task: \n        Analyze the provided image and describe
+      what you see in detail.\n        Focus on main elements, colors, composition,
+      and any notable details.\n        Image: https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=\n        \n\nThis
+      is the expect criteria for your final answer: A comprehensive description of
+      the image contents.\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", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1948'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AiuIfzzcje5KdvKIG5CkFeORroiKk\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735266213,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Action: Add image to content\\nAction
+      Input: {\\\"image_url\\\": \\\"https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=\\\",
+      \\\"action\\\": \\\"Analyze the provided image and describe what you see in
+      detail.\\\"}\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      417,\n    \"completion_tokens\": 103,\n    \"total_tokens\": 520,\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  \"system_fingerprint\":
+      \"fp_5f20662549\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f85d96b280df217-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 02:23:35 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=kJ1pw1xjCMSxjHSS8iJC5z_j2PZxl.i387KCpj9xNZU-1735266215-1.0.1.1-Ybg0wVTsrBlpVZmtQyA1ullY8m3v2Ix0N_SYlhr9z7zKfbLeqGZEVL37YSY.dvIiLVY3XPZzMtG8Xwo6UucW6A;
+        path=/; expires=Fri, 27-Dec-24 02:53:35 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=v_wJZ5m7qCjrnRfks0gT2GAk9yR14BdIDAQiQR7xxI8-1735266215000-0.0.1.1-604800000;
+        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:
+      - '1212'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999539'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_663a2b18099a18361d6b02befc175289
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      Co4LCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS5QoKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKjBwoQHmzzumMNXHOgpJ4zCIxJSxII72WnLlLfRyYqDENyZXcgQ3JlYXRlZDABOQjB
+      gFxt5xQYQYhMiVxt5xQYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogZTM5NTY3YjUwNTI5MDljYTMzNDA5ODRiODM4
+      OTgwZWFKMQoHY3Jld19pZBImCiQ4MDA0YTA1NC0zYjNkLTQ4OGEtYTlkNC1kZWQzMDVhMDIxY2FK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSs4CCgtjcmV3
+      X2FnZW50cxK+Agq7Alt7ImtleSI6ICI5ZGM4Y2NlMDMwNDY4MTk2MDQxYjRjMzgwYjYxN2NiMCIs
+      ICJpZCI6ICJjNTZhZGI2Mi1lMGIwLTQzYzAtYmQ4OC0xYzEwYTNhNmU5NDQiLCAicm9sZSI6ICJJ
+      bWFnZSBBbmFseXN0IiwgInZlcmJvc2U/IjogdHJ1ZSwgIm1heF9pdGVyIjogMjAsICJtYXhfcnBt
+      IjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvIiwgImRl
+      bGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNl
+      LCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUqCAgoKY3Jld190YXNr
+      cxLzAQrwAVt7ImtleSI6ICJhOWE3NmNhNjk1N2QwYmZmYTY5ZWFiMjBiNjY0ODIyYiIsICJpZCI6
+      ICJhNzFiZDllNC0wNzdkLTRmMTQtODg0MS03MGMwZWM4MGZkMmMiLCAiYXN5bmNfZXhlY3V0aW9u
+      PyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIkltYWdlIEFu
+      YWx5c3QiLCAiYWdlbnRfa2V5IjogIjlkYzhjY2UwMzA0NjgxOTYwNDFiNGMzODBiNjE3Y2IwIiwg
+      InRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEOZ5pMdq9ep85DrP1Vv8Y8MSCE7ahOkm
+      2IDHKgxUYXNrIENyZWF0ZWQwATlIg85cbecUGEGQ9M5cbecUGEouCghjcmV3X2tleRIiCiBlMzk1
+      NjdiNTA1MjkwOWNhMzM0MDk4NGI4Mzg5ODBlYUoxCgdjcmV3X2lkEiYKJDgwMDRhMDU0LTNiM2Qt
+      NDg4YS1hOWQ0LWRlZDMwNWEwMjFjYUouCgh0YXNrX2tleRIiCiBhOWE3NmNhNjk1N2QwYmZmYTY5
+      ZWFiMjBiNjY0ODIyYkoxCgd0YXNrX2lkEiYKJGE3MWJkOWU0LTA3N2QtNGYxNC04ODQxLTcwYzBl
+      YzgwZmQyY3oCGAGFAQABAAASlwEKECyaQQK8JkKLh6S2mWHTeDgSCPWCpr7v9CQZKgpUb29sIFVz
+      YWdlMAE5MLyst23nFBhBOJy/t23nFBhKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC44Ni4wSiMKCXRv
+      b2xfbmFtZRIWChRBZGQgaW1hZ2UgdG8gY29udGVudEoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1425'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    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:
+      - Fri, 27 Dec 2024 02:23:39 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Image Analyst. You''re
+      an expert at visual analysis, trained to notice and describe details in images.\nYour
+      personal goal is: Analyze images with high attention to detail\nYou ONLY have
+      access to the following tools, and should NEVER make up tools that are not listed
+      here:\n\nTool Name: Add image to content\nTool Arguments: {''image_url'': {''description'':
+      ''The URL or path of the image to add'', ''type'': ''str''}, ''action'': {''description'':
+      ''Optional context or question about the image'', ''type'': ''str''}}\nTool
+      Description: See image to understand it''s content, you can optionally ask a
+      question about the image\n\nUse the following format:\n\nThought: you should
+      always think about what to do\nAction: the action to take, only one name of
+      [Add image to content], just the name, exactly as it''s written.\nAction Input:
+      the input to the action, just a simple python dictionary, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce
+      all necessary information is gathered:\n\nThought: I now know the final answer\nFinal
+      Answer: the final answer to the original input question"}, {"role": "user",
+      "content": "\nCurrent Task: \n        Analyze the provided image and describe
+      what you see in detail.\n        Focus on main elements, colors, composition,
+      and any notable details.\n        Image: https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=\n        \n\nThis
+      is the expect criteria for your final answer: A comprehensive description of
+      the image contents.\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:"},
+      {"role": "user", "content": [{"type": "text", "text": "Analyze the provided
+      image and describe what you see in detail."}, {"type": "image_url", "image_url":
+      {"url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k="}}]}],
+      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2279'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=kJ1pw1xjCMSxjHSS8iJC5z_j2PZxl.i387KCpj9xNZU-1735266215-1.0.1.1-Ybg0wVTsrBlpVZmtQyA1ullY8m3v2Ix0N_SYlhr9z7zKfbLeqGZEVL37YSY.dvIiLVY3XPZzMtG8Xwo6UucW6A;
+        _cfuvid=v_wJZ5m7qCjrnRfks0gT2GAk9yR14BdIDAQiQR7xxI8-1735266215000-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AiuIiqT33ROFMdw1gNmqH9jiw6PfF\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735266216,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The image is an aerial view of Lower
+      Manhattan in New York City. \\n\\nMain Elements:\\n- The One World Trade Center
+      tower stands prominently, distinguishable by its sleek, tapering structure reaching
+      into the sky, surrounded by other skyscrapers.\\n- Skyscrapers in varying heights
+      and architectural styles, fill the densely packed urban landscape.\\n- A waterfront
+      is visible at the edges, with docks and piers extending into the water.\\n\\nColors:\\n-
+      The buildings exhibit a mix of colors, predominantly grays, whites, and browns,
+      against the blues of the sky and water.\\n- There's a section of greenery visible,
+      likely a park or recreational space, offering a contrast with its vibrant green
+      hues.\\n\\nComposition:\\n- The angle of the photograph showcases the expanse
+      of the city, highlighting the density and scale of the buildings.\\n- Water
+      borders the city on two prominent sides, creating a natural boundary and enhancing
+      the island's urban island feel.\\n\\nNotable Details:\\n- The image captures
+      the iconic layout of Manhattan, with the surrounding Hudson River and New York
+      Harbor visible in the background.\\n- Beyond Lower Manhattan, more of the cityscape
+      stretches into the distance, illustrating the vastness of New York City.\\n-
+      The day appears clear and sunny, with shadows casting from the buildings, indicating
+      time in the morning or late afternoon.\\n\\nOverall, the image is a striking
+      depiction of the dynamic and bustling environment of New York's Lower Manhattan,
+      encapsulating its urban character and proximity to the water.\",\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 858,\n    \"completion_tokens\":
+      295,\n    \"total_tokens\": 1153,\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  \"system_fingerprint\":
+      \"fp_5f20662549\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f85d9741d0cf217-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 02:23:40 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '5136'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-input-images:
+      - '50000'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-input-images:
+      - '49999'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29998756'
+      x-ratelimit-reset-input-images:
+      - 1ms
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 2ms
+      x-request-id:
+      - req_57a7430712d4ff4a81f600ffb94d3b6e
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Image Analyst. You''re
+      an expert at visual analysis, trained to notice and describe details in images.\nYour
+      personal goal is: Analyze images with high attention to detail\nYou ONLY have
+      access to the following tools, and should NEVER make up tools that are not listed
+      here:\n\nTool Name: Add image to content\nTool Arguments: {''image_url'': {''description'':
+      ''The URL or path of the image to add'', ''type'': ''str''}, ''action'': {''description'':
+      ''Optional context or question about the image'', ''type'': ''str''}}\nTool
+      Description: See image to understand it''s content, you can optionally ask a
+      question about the image\n\nUse the following format:\n\nThought: you should
+      always think about what to do\nAction: the action to take, only one name of
+      [Add image to content], just the name, exactly as it''s written.\nAction Input:
+      the input to the action, just a simple python dictionary, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce
+      all necessary information is gathered:\n\nThought: I now know the final answer\nFinal
+      Answer: the final answer to the original input question"}, {"role": "user",
+      "content": "\nCurrent Task: \n        Analyze the provided image and describe
+      what you see in detail.\n        Focus on main elements, colors, composition,
+      and any notable details.\n        Image: https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=\n        \n\nThis
+      is the expect criteria for your final answer: A comprehensive description of
+      the image contents.\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:"},
+      {"role": "user", "content": [{"type": "text", "text": "Analyze the provided
+      image and describe what you see in detail."}, {"type": "image_url", "image_url":
+      {"url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k="}}]},
+      {"role": "user", "content": "I did it wrong. Invalid Format: I missed the ''Action:''
+      after ''Thought:''. I will do right next, and don''t use a tool I have already
+      used.\n\nIf you don''t need to use any more tools, you must give your best complete
+      final answer, make sure it satisfies the expected criteria, use the EXACT format
+      below:\n\nThought: I now can give a great answer\nFinal Answer: my best complete
+      final answer to the task.\n\n"}], "model": "gpt-4o", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2717'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=kJ1pw1xjCMSxjHSS8iJC5z_j2PZxl.i387KCpj9xNZU-1735266215-1.0.1.1-Ybg0wVTsrBlpVZmtQyA1ullY8m3v2Ix0N_SYlhr9z7zKfbLeqGZEVL37YSY.dvIiLVY3XPZzMtG8Xwo6UucW6A;
+        _cfuvid=v_wJZ5m7qCjrnRfks0gT2GAk9yR14BdIDAQiQR7xxI8-1735266215000-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AiuInuYNldaQVo6B1EsEquT1VFMN7\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735266221,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+      Answer: The image is an aerial view of Lower Manhattan in New York City. The
+      photograph prominently features the cluster of skyscrapers that characterizes
+      the area, with One World Trade Center standing out as a particularly tall and
+      iconic structure. The buildings vary in color, with shades of glassy blue, grey,
+      and natural stone dominating the skyline. In the bottom part of the image, there
+      is a green space, likely Battery Park, providing a stark contrast to the dense
+      urban environment, with trees and pathways visible. The water surrounding Manhattan
+      is a deep blue, and several piers jut into the harbor. The Hudson River is visible
+      on the left, and the East River can be seen on the right, framing the island.
+      The overall composition captures the bustling and vibrant nature of New York\u2019s
+      financial hub, with bright sunlight illuminating the buildings, casting sharp
+      shadows and enhancing the depth of the cityscape. The sky is clear, suggesting
+      a sunny day with good visibility.\",\n        \"refusal\": null\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 952,\n    \"completion_tokens\": 203,\n
+      \   \"total_tokens\": 1155,\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  \"system_fingerprint\":
+      \"fp_5f20662549\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f85d995ad1ef217-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 02:23:43 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '3108'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-input-images:
+      - '50000'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-input-images:
+      - '49999'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29998656'
+      x-ratelimit-reset-input-images:
+      - 1ms
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 2ms
+      x-request-id:
+      - req_45f0e3d457a18f973a59074d16f137b6
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_task_tools_override_agent_tools.yaml

@@ -0,0 +1,569 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
+      an expert researcher, specialized in technology, software engineering, AI and
+      startups. You work as a freelancer and is now working on doing research and
+      analysis for a new customer.\nYour personal goal is: Make the best research
+      and analysis on content about AI and AI agents\nYou ONLY have access to the
+      following tools, and should NEVER make up tools that are not listed here:\n\nTool
+      Name: Test Tool\nTool Arguments: {''query'': {''description'': ''Query to process'',
+      ''type'': ''str''}}\nTool Description: A test tool that just returns the input\n\nUse
+      the following format:\n\nThought: you should always think about what to do\nAction:
+      the action to take, only one name of [Test Tool], just the name, exactly as
+      it''s written.\nAction Input: the input to the action, just a simple python
+      dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
+      the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question"}, {"role": "user", "content": "\nCurrent Task: Write a test
+      task\n\nThis is the expect criteria for your final answer: Test output\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:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1536'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhQfznhDMtsr58XvTuRDZoB1kxwfK\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734914011,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I need to come up with a suitable test
+      task that meets the criteria provided. I will focus on outlining a clear and
+      effective test task related to AI and AI agents.\\n\\nAction: Test Tool\\nAction
+      Input: {\\\"query\\\": \\\"Create a test task that involves evaluating the performance
+      of an AI agent in a given scenario, including criteria for success, tools required,
+      and process for assessment.\\\"}\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      298,\n    \"completion_tokens\": 78,\n    \"total_tokens\": 376,\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  \"system_fingerprint\":
+      \"fp_d02d531b47\"\n}\n"
+    headers:
+      CF-RAY:
+      - 8f6442b868fda486-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 23 Dec 2024 00:33:32 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=i6jvNjhsDne300GPAeEmyiJJKYqy7OPuamFG_kht3KE-1734914012-1.0.1.1-tCeVANAF521vkXpBdgYw.ov.fYUr6t5QC4LG_DugWyzu4C60Pi2CruTVniUgfCvkcu6rdHA5DwnaEZf2jFaRCQ;
+        path=/; expires=Mon, 23-Dec-24 01:03:32 GMT; 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:
+      - '1400'
+      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:
+      - '149999642'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_c3e50e9ca9dc22de5572692e1a9c0f16
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CrBzCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSh3MKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRLUCwoQEr8cFisEEEEUtXBvovq6lhIIYdkQ+ekBh3wqDENyZXcgQ3JlYXRlZDABOThc
+      YLAZpxMYQfCuabAZpxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogZGUxMDFkODU1M2VhMDI0NTM3YTA4ZjgxMmVl
+      NmI3NGFKMQoHY3Jld19pZBImCiRmNTc2MjViZC1jZmY3LTRlNGMtYWM1Zi0xZWFiNjQyMzJjMmRK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAkobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSpIFCgtjcmV3
+      X2FnZW50cxKCBQr/BFt7ImtleSI6ICI4YmQyMTM5YjU5NzUxODE1MDZlNDFmZDljNDU2M2Q3NSIs
+      ICJpZCI6ICI1Y2Y0OWVjNy05NWYzLTRkZDctODU3Mi1mODAwNDA4NjBiMjgiLCAicm9sZSI6ICJS
+      ZXNlYXJjaGVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6
+      IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwg
+      ImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZh
+      bHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICI5
+      YTUwMTVlZjQ4OTVkYzYyNzhkNTQ4MThiYTQ0NmFmNyIsICJpZCI6ICI0MTEyM2QzZC01NmEwLTRh
+      NTgtYTljNi1mZjUwNjRmZjNmNTEiLCAicm9sZSI6ICJTZW5pb3IgV3JpdGVyIiwgInZlcmJvc2U/
+      IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxs
+      aW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8i
+      OiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0
+      IjogMiwgInRvb2xzX25hbWVzIjogW119XUrvAwoKY3Jld190YXNrcxLgAwrdA1t7ImtleSI6ICI5
+      NDRhZWYwYmFjODQwZjFjMjdiZDgzYTkzN2JjMzYxYiIsICJpZCI6ICI3ZDM2NDFhNi1hZmM4LTRj
+      NmMtYjkzMy0wNGZlZjY2NjUxN2MiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5f
+      aW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIlJlc2VhcmNoZXIiLCAiYWdlbnRfa2V5Ijog
+      IjhiZDIxMzliNTk3NTE4MTUwNmU0MWZkOWM0NTYzZDc1IiwgInRvb2xzX25hbWVzIjogW119LCB7
+      ImtleSI6ICI5ZjJkNGU5M2FiNTkwYzcyNTg4NzAyNzUwOGFmOTI3OCIsICJpZCI6ICIzNTVjZjFh
+      OS1lOTkzLTQxMTQtOWM0NC0yZDM5MDlhMDljNWYiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNl
+      LCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIlNlbmlvciBXcml0ZXIiLCAi
+      YWdlbnRfa2V5IjogIjlhNTAxNWVmNDg5NWRjNjI3OGQ1NDgxOGJhNDQ2YWY3IiwgInRvb2xzX25h
+      bWVzIjogW119XXoCGAGFAQABAAASjgIKEHbV3nDt+ndNQNix1f+5+cASCL+l6KV3+FEpKgxUYXNr
+      IENyZWF0ZWQwATmgfo+wGacTGEEQE5CwGacTGEouCghjcmV3X2tleRIiCiBkZTEwMWQ4NTUzZWEw
+      MjQ1MzdhMDhmODEyZWU2Yjc0YUoxCgdjcmV3X2lkEiYKJGY1NzYyNWJkLWNmZjctNGU0Yy1hYzVm
+      LTFlYWI2NDIzMmMyZEouCgh0YXNrX2tleRIiCiA5NDRhZWYwYmFjODQwZjFjMjdiZDgzYTkzN2Jj
+      MzYxYkoxCgd0YXNrX2lkEiYKJDdkMzY0MWE2LWFmYzgtNGM2Yy1iOTMzLTA0ZmVmNjY2NTE3Y3oC
+      GAGFAQABAAASjgIKECqDENVoAz+3ybVKR/wz7dMSCKI9ILLFYx8SKgxUYXNrIENyZWF0ZWQwATng
+      63CzGacTGEE4AXKzGacTGEouCghjcmV3X2tleRIiCiBkZTEwMWQ4NTUzZWEwMjQ1MzdhMDhmODEy
+      ZWU2Yjc0YUoxCgdjcmV3X2lkEiYKJGY1NzYyNWJkLWNmZjctNGU0Yy1hYzVmLTFlYWI2NDIzMmMy
+      ZEouCgh0YXNrX2tleRIiCiA5ZjJkNGU5M2FiNTkwYzcyNTg4NzAyNzUwOGFmOTI3OEoxCgd0YXNr
+      X2lkEiYKJDM1NWNmMWE5LWU5OTMtNDExNC05YzQ0LTJkMzkwOWEwOWM1ZnoCGAGFAQABAAAS1AsK
+      EOofSLF1HDmhYMt7eIAeFo8SCCaKUQMuWNdnKgxDcmV3IENyZWF0ZWQwATkYKA62GacTGEFwlhW2
+      GacTGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4x
+      MS43Si4KCGNyZXdfa2V5EiIKIDRlOGU0MmNmMWVhN2U2NjhhMGU5MzJhNzAyMDY1NzQ5SjEKB2Ny
+      ZXdfaWQSJgokMmIzNTVjZDMtY2MwNi00Y2QxLTk0YjgtZTU5YjM5OGI3MjEzShwKDGNyZXdfcHJv
+      Y2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90
+      YXNrcxICGAJKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAkqSBQoLY3Jld19hZ2VudHMSggUK
+      /wRbeyJrZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNkNzUiLCAiaWQiOiAiNWNm
+      NDllYzctOTVmMy00ZGQ3LTg1NzItZjgwMDQwODYwYjI4IiwgInJvbGUiOiAiUmVzZWFyY2hlciIs
+      ICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVu
+      Y3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9u
+      X2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9y
+      ZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiOWE1MDE1ZWY0ODk1
+      ZGM2Mjc4ZDU0ODE4YmE0NDZhZjciLCAiaWQiOiAiNDExMjNkM2QtNTZhMC00YTU4LWE5YzYtZmY1
+      MDY0ZmYzZjUxIiwgInJvbGUiOiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAi
+      bWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAi
+      IiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJh
+      bGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29s
+      c19uYW1lcyI6IFtdfV1K7wMKCmNyZXdfdGFza3MS4AMK3QNbeyJrZXkiOiAiNjc4NDlmZjcxN2Ri
+      YWRhYmExYjk1ZDVmMmRmY2VlYTEiLCAiaWQiOiAiOGE5OTgxMDYtZjg5Zi00YTQ5LThjZjEtYjk4
+      MzQ5ZDE1NDRmIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZh
+      bHNlLCAiYWdlbnRfcm9sZSI6ICJSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6ICI4YmQyMTM5YjU5
+      NzUxODE1MDZlNDFmZDljNDU2M2Q3NSIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiODRh
+      ZjlmYzFjZDMzMTk5Y2ViYjlkNDE0MjE4NWY4MDIiLCAiaWQiOiAiYTViMTg0MDgtYjA1OC00ZDE1
+      LTkyMmUtNDJkN2M5Y2ViYjFhIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lu
+      cHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJTZW5pb3IgV3JpdGVyIiwgImFnZW50X2tleSI6
+      ICI5YTUwMTVlZjQ4OTVkYzYyNzhkNTQ4MThiYTQ0NmFmNyIsICJ0b29sc19uYW1lcyI6IFtdfV16
+      AhgBhQEAAQAAEsIJChDCLrcWQ+nu3SxOgnq50XhSEghjozRtuCFA0SoMQ3JldyBDcmVhdGVkMAE5
+      CDeCthmnExhBmHiIthmnExhKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC44Ni4wShoKDnB5dGhvbl92
+      ZXJzaW9uEggKBjMuMTEuN0ouCghjcmV3X2tleRIiCiBlM2ZkYTBmMzExMGZlODBiMTg5NDdjMDE0
+      NzE0MzBhNEoxCgdjcmV3X2lkEiYKJGM1ZDQ0YjY5LTRhNzMtNDA3Zi1iY2RhLTUzZmUxZTQ3YTU3
+      M0oeCgxjcmV3X3Byb2Nlc3MSDgoMaGllcmFyY2hpY2FsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRj
+      cmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAkqSBQoL
+      Y3Jld19hZ2VudHMSggUK/wRbeyJrZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNk
+      NzUiLCAiaWQiOiAiNWNmNDllYzctOTVmMy00ZGQ3LTg1NzItZjgwMDQwODYwYjI4IiwgInJvbGUi
+      OiAiUmVzZWFyY2hlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9y
+      cG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWlu
+      aSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8i
+      OiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXki
+      OiAiOWE1MDE1ZWY0ODk1ZGM2Mjc4ZDU0ODE4YmE0NDZhZjciLCAiaWQiOiAiNDExMjNkM2QtNTZh
+      MC00YTU4LWE5YzYtZmY1MDY0ZmYzZjUxIiwgInJvbGUiOiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJi
+      b3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25f
+      Y2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJs
+      ZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9s
+      aW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K2wEKCmNyZXdfdGFza3MSzAEKyQFbeyJrZXki
+      OiAiNWZhNjVjMDZhOWUzMWYyYzY5NTQzMjY2OGFjZDYyZGQiLCAiaWQiOiAiNjNhYTVlOTYtYTM4
+      Yy00YjcyLWJiZDQtYjM2NmU5NTlhOWZhIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1
+      bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJOb25lIiwgImFnZW50X2tleSI6IG51
+      bGwsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEuYJChA8kiyQ+AFdDSYkp0+TUWKvEgjW
+      0grLw8r5KioMQ3JldyBDcmVhdGVkMAE5iLivvhmnExhBeG21vhmnExhKGgoOY3Jld2FpX3ZlcnNp
+      b24SCAoGMC44Ni4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTEuN0ouCghjcmV3X2tleRIiCiBl
+      M2ZkYTBmMzExMGZlODBiMTg5NDdjMDE0NzE0MzBhNEoxCgdjcmV3X2lkEiYKJGIzZGQ1MGYxLTI0
+      YWQtNDE5OC04ZGFhLTMwZTU0OTQ3MTlhMEoeCgxjcmV3X3Byb2Nlc3MSDgoMaGllcmFyY2hpY2Fs
+      ShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19u
+      dW1iZXJfb2ZfYWdlbnRzEgIYAkqSBQoLY3Jld19hZ2VudHMSggUK/wRbeyJrZXkiOiAiOGJkMjEz
+      OWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNkNzUiLCAiaWQiOiAiNWNmNDllYzctOTVmMy00ZGQ3LTg1
+      NzItZjgwMDQwODYwYjI4IiwgInJvbGUiOiAiUmVzZWFyY2hlciIsICJ2ZXJib3NlPyI6IGZhbHNl
+      LCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0i
+      OiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2Us
+      ICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0
+      b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiOWE1MDE1ZWY0ODk1ZGM2Mjc4ZDU0ODE4YmE0NDZh
+      ZjciLCAiaWQiOiAiNDExMjNkM2QtNTZhMC00YTU4LWE5YzYtZmY1MDY0ZmYzZjUxIiwgInJvbGUi
+      OiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1h
+      eF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8t
+      bWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlv
+      bj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/wEK
+      CmNyZXdfdGFza3MS8AEK7QFbeyJrZXkiOiAiNWZhNjVjMDZhOWUzMWYyYzY5NTQzMjY2OGFjZDYy
+      ZGQiLCAiaWQiOiAiNzEyODlkZTAtODQ4My00NDM2LWI2OGMtNDc1MWIzNTU0ZmUzIiwgImFzeW5j
+      X2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6
+      ICJSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6ICI4YmQyMTM5YjU5NzUxODE1MDZlNDFmZDljNDU2
+      M2Q3NSIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChCTiJL+KK5ff9xnie6eZbEc
+      EghbtQixNaG5DioMVGFzayBDcmVhdGVkMAE5cIXNvhmnExhBuPbNvhmnExhKLgoIY3Jld19rZXkS
+      IgogZTNmZGEwZjMxMTBmZTgwYjE4OTQ3YzAxNDcxNDMwYTRKMQoHY3Jld19pZBImCiRiM2RkNTBm
+      MS0yNGFkLTQxOTgtOGRhYS0zMGU1NDk0NzE5YTBKLgoIdGFza19rZXkSIgogNWZhNjVjMDZhOWUz
+      MWYyYzY5NTQzMjY2OGFjZDYyZGRKMQoHdGFza19pZBImCiQ3MTI4OWRlMC04NDgzLTQ0MzYtYjY4
+      Yy00NzUxYjM1NTRmZTN6AhgBhQEAAQAAEpwBChBCdDi/i+SH0kHHlJKQjmYgEgiemV9jVU5fQSoK
+      VG9vbCBVc2FnZTABOVj/YL8ZpxMYQWCwZr8ZpxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYu
+      MEooCgl0b29sX25hbWUSGwoZRGVsZWdhdGUgd29yayB0byBjb3dvcmtlckoOCghhdHRlbXB0cxIC
+      GAF6AhgBhQEAAQAAEqUBChBRuZ6Z/nNag4ubLeZ8L/8pEghCX4biKNFb6SoTVG9vbCBSZXBlYXRl
+      ZCBVc2FnZTABOUj9wr8ZpxMYQdg+yb8ZpxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoo
+      Cgl0b29sX25hbWUSGwoZRGVsZWdhdGUgd29yayB0byBjb3dvcmtlckoOCghhdHRlbXB0cxICGAF6
+      AhgBhQEAAQAAEpwBChDnt1bxQsOb0LVscG9GDYVtEgjf62keNMl5ZyoKVG9vbCBVc2FnZTABOdha
+      6MAZpxMYQWii7cAZpxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEooCgl0b29sX25hbWUS
+      GwoZRGVsZWdhdGUgd29yayB0byBjb3dvcmtlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpsB
+      ChDFqFA9b42EIwUxeNLTeScxEgiGFk7FwiNxVioKVG9vbCBVc2FnZTABObDAY8EZpxMYQdhIaMEZ
+      pxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEonCgl0b29sX25hbWUSGgoYQXNrIHF1ZXN0
+      aW9uIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASwgkKEHpB0rbuWbSXijzV
+      QdTa3oQSCNSPnbmqe2PfKgxDcmV3IENyZWF0ZWQwATmIXxTCGacTGEF4GhnCGacTGEoaCg5jcmV3
+      YWlfdmVyc2lvbhIICgYwLjg2LjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMS43Si4KCGNyZXdf
+      a2V5EiIKIGUzZmRhMGYzMTEwZmU4MGIxODk0N2MwMTQ3MTQzMGE0SjEKB2NyZXdfaWQSJgokZGJm
+      YzNjMjctMmRjZS00MjIyLThiYmQtYmMxMjU3OTVlNWI1Sh4KDGNyZXdfcHJvY2VzcxIOCgxoaWVy
+      YXJjaGljYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUob
+      ChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSpIFCgtjcmV3X2FnZW50cxKCBQr/BFt7ImtleSI6
+      ICI4YmQyMTM5YjU5NzUxODE1MDZlNDFmZDljNDU2M2Q3NSIsICJpZCI6ICI1Y2Y0OWVjNy05NWYz
+      LTRkZDctODU3Mi1mODAwNDA4NjBiMjgiLCAicm9sZSI6ICJSZXNlYXJjaGVyIiwgInZlcmJvc2U/
+      IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxs
+      aW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8i
+      OiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0
+      IjogMiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICI5YTUwMTVlZjQ4OTVkYzYyNzhkNTQ4
+      MThiYTQ0NmFmNyIsICJpZCI6ICI0MTEyM2QzZC01NmEwLTRhNTgtYTljNi1mZjUwNjRmZjNmNTEi
+      LCAicm9sZSI6ICJTZW5pb3IgV3JpdGVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6
+      IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjog
+      ImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVf
+      ZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjog
+      W119XUrbAQoKY3Jld190YXNrcxLMAQrJAVt7ImtleSI6ICI1ZmE2NWMwNmE5ZTMxZjJjNjk1NDMy
+      NjY4YWNkNjJkZCIsICJpZCI6ICIyYWFjOTllMC0yNWVmLTQzN2MtYTJmZi1jZGFlMjg2ZWU2MzQi
+      LCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2Vu
+      dF9yb2xlIjogIk5vbmUiLCAiYWdlbnRfa2V5IjogbnVsbCwgInRvb2xzX25hbWVzIjogW119XXoC
+      GAGFAQABAAAS1QkKEM6Xt0BvAHy+TI7iLC6ovN0SCEfHP30NZESSKgxDcmV3IENyZWF0ZWQwATkg
+      PdnDGacTGEFIPN/DGacTGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMS43Si4KCGNyZXdfa2V5EiIKIGU2NDk1NzNhMjZlNTg3OTBjYWMyMWEzN2Nk
+      NDQ0MzdhSjEKB2NyZXdfaWQSJgokNjE3MDA3NGMtYzU5OS00ODkyLTkwYzYtMTcxYjhkM2Y1OTRh
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAkqKBQoLY3Jl
+      d19hZ2VudHMS+gQK9wRbeyJrZXkiOiAiMzI4MjE3YjZjMjk1OWJkZmM0N2NhZDAwZTg0ODkwZDAi
+      LCAiaWQiOiAiYjNmMTczZTktNjY3NS00OTFkLTgyYjctODM4NmRkMjExMDM1IiwgInJvbGUiOiAi
+      Q0VPIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGws
+      ICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVn
+      YXRpb25fZW5hYmxlZD8iOiB0cnVlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJt
+      YXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX0sIHsia2V5IjogIjlhNTAxNWVm
+      NDg5NWRjNjI3OGQ1NDgxOGJhNDQ2YWY3IiwgImlkIjogIjQxMTIzZDNkLTU2YTAtNGE1OC1hOWM2
+      LWZmNTA2NGZmM2Y1MSIsICJyb2xlIjogIlNlbmlvciBXcml0ZXIiLCAidmVyYm9zZT8iOiBmYWxz
+      ZSwgIm1heF9pdGVyIjogMjAsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxt
+      IjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNl
+      LCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAi
+      dG9vbHNfbmFtZXMiOiBbXX1dSvgBCgpjcmV3X3Rhc2tzEukBCuYBW3sia2V5IjogIjBiOWQ2NWRi
+      NmI3YWVkZmIzOThjNTllMmE5ZjcxZWM1IiwgImlkIjogImJiNmI1Njg3LTg5NGMtNDAyNS05M2My
+      LTMyYjdkZmEwZTUxMyIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8i
+      OiBmYWxzZSwgImFnZW50X3JvbGUiOiAiQ0VPIiwgImFnZW50X2tleSI6ICIzMjgyMTdiNmMyOTU5
+      YmRmYzQ3Y2FkMDBlODQ4OTBkMCIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChCK
+      KIL9w7sqoMzG3JItjK8eEgiR4RSmJw+SMSoMVGFzayBDcmVhdGVkMAE5CCjywxmnExhByIXywxmn
+      ExhKLgoIY3Jld19rZXkSIgogZTY0OTU3M2EyNmU1ODc5MGNhYzIxYTM3Y2Q0NDQzN2FKMQoHY3Jl
+      d19pZBImCiQ2MTcwMDc0Yy1jNTk5LTQ4OTItOTBjNi0xNzFiOGQzZjU5NGFKLgoIdGFza19rZXkS
+      IgogMGI5ZDY1ZGI2YjdhZWRmYjM5OGM1OWUyYTlmNzFlYzVKMQoHdGFza19pZBImCiRiYjZiNTY4
+      Ny04OTRjLTQwMjUtOTNjMi0zMmI3ZGZhMGU1MTN6AhgBhQEAAQAAEpwBChD+/zv5udkceIEyIb7d
+      ne5vEgj1My75q1O7UCoKVG9vbCBVc2FnZTABOThPfMQZpxMYQcA4g8QZpxMYShoKDmNyZXdhaV92
+      ZXJzaW9uEggKBjAuODYuMEooCgl0b29sX25hbWUSGwoZRGVsZWdhdGUgd29yayB0byBjb3dvcmtl
+      ckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEuAJChBIzM1Xa9IhegFDHxt6rj3eEgj9z56V1hXk
+      aCoMQ3JldyBDcmVhdGVkMAE5mEoMxRmnExhBoPsRxRmnExhKGgoOY3Jld2FpX3ZlcnNpb24SCAoG
+      MC44Ni4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTEuN0ouCghjcmV3X2tleRIiCiBlNjQ5NTcz
+      YTI2ZTU4NzkwY2FjMjFhMzdjZDQ0NDM3YUoxCgdjcmV3X2lkEiYKJGQ4MjhhZWM2LTg2N2MtNDdh
+      YS04ODY4LWQwMWYwNGM0MGE0MUocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3
+      X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29m
+      X2FnZW50cxICGAJKigUKC2NyZXdfYWdlbnRzEvoECvcEW3sia2V5IjogIjMyODIxN2I2YzI5NTli
+      ZGZjNDdjYWQwMGU4NDg5MGQwIiwgImlkIjogImIzZjE3M2U5LTY2NzUtNDkxZC04MmI3LTgzODZk
+      ZDIxMTAzNSIsICJyb2xlIjogIkNFTyIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAy
+      MCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJn
+      cHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogdHJ1ZSwgImFsbG93X2NvZGVfZXhl
+      Y3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119
+      LCB7ImtleSI6ICI5YTUwMTVlZjQ4OTVkYzYyNzhkNTQ4MThiYTQ0NmFmNyIsICJpZCI6ICI0MTEy
+      M2QzZC01NmEwLTRhNTgtYTljNi1mZjUwNjRmZjNmNTEiLCAicm9sZSI6ICJTZW5pb3IgV3JpdGVy
+      IiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJm
+      dW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRp
+      b25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4
+      X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUqDAgoKY3Jld190YXNrcxL0AQrx
+      AVt7ImtleSI6ICIwYjlkNjVkYjZiN2FlZGZiMzk4YzU5ZTJhOWY3MWVjNSIsICJpZCI6ICI5YTBj
+      ODZhZi0wYTE0LTQ4MzgtOTJmZC02NDhhZGM1NzJlMDMiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZh
+      bHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIkNFTyIsICJhZ2VudF9r
+      ZXkiOiAiMzI4MjE3YjZjMjk1OWJkZmM0N2NhZDAwZTg0ODkwZDAiLCAidG9vbHNfbmFtZXMiOiBb
+      InRlc3QgdG9vbCJdfV16AhgBhQEAAQAAEo4CChDl0EBv/8sdeV8eJ45EUBpxEgj+C7UlokySqSoM
+      VGFzayBDcmVhdGVkMAE5oI8jxRmnExhBYO0jxRmnExhKLgoIY3Jld19rZXkSIgogZTY0OTU3M2Ey
+      NmU1ODc5MGNhYzIxYTM3Y2Q0NDQzN2FKMQoHY3Jld19pZBImCiRkODI4YWVjNi04NjdjLTQ3YWEt
+      ODg2OC1kMDFmMDRjNDBhNDFKLgoIdGFza19rZXkSIgogMGI5ZDY1ZGI2YjdhZWRmYjM5OGM1OWUy
+      YTlmNzFlYzVKMQoHdGFza19pZBImCiQ5YTBjODZhZi0wYTE0LTQ4MzgtOTJmZC02NDhhZGM1NzJl
+      MDN6AhgBhQEAAQAAEpsBChArkcRTKJCaWLUYbx8DLyvTEgikYuS5tmbKNioKVG9vbCBVc2FnZTAB
+      OSh+MscZpxMYQdgTOMcZpxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEonCgl0b29sX25h
+      bWUSGgoYQXNrIHF1ZXN0aW9uIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAAS
+      6wkKEHxFJsjiUgQromzfQHpYYMISCBkGairjk9kkKgxDcmV3IENyZWF0ZWQwATk4/rXHGacTGEGY
+      yrvHGacTGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoG
+      My4xMS43Si4KCGNyZXdfa2V5EiIKIGU2NDk1NzNhMjZlNTg3OTBjYWMyMWEzN2NkNDQ0MzdhSjEK
+      B2NyZXdfaWQSJgokMjY3NzEyNzItOTRlZC00NDVkLTg1MGEtYTkyYTZjOWI5YmJkShwKDGNyZXdf
+      cHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9v
+      Zl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAkqVBQoLY3Jld19hZ2VudHMS
+      hQUKggVbeyJrZXkiOiAiMzI4MjE3YjZjMjk1OWJkZmM0N2NhZDAwZTg0ODkwZDAiLCAiaWQiOiAi
+      YjNmMTczZTktNjY3NS00OTFkLTgyYjctODM4NmRkMjExMDM1IiwgInJvbGUiOiAiQ0VPIiwgInZl
+      cmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlv
+      bl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5h
+      YmxlZD8iOiB0cnVlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlf
+      bGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbInRlc3QgdG9vbCJdfSwgeyJrZXkiOiAiOWE1MDE1
+      ZWY0ODk1ZGM2Mjc4ZDU0ODE4YmE0NDZhZjciLCAiaWQiOiAiNDExMjNkM2QtNTZhMC00YTU4LWE5
+      YzYtZmY1MDY0ZmYzZjUxIiwgInJvbGUiOiAiU2VuaW9yIFdyaXRlciIsICJ2ZXJib3NlPyI6IGZh
+      bHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19s
+      bG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFs
+      c2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIs
+      ICJ0b29sc19uYW1lcyI6IFtdfV1KgwIKCmNyZXdfdGFza3MS9AEK8QFbeyJrZXkiOiAiMGI5ZDY1
+      ZGI2YjdhZWRmYjM5OGM1OWUyYTlmNzFlYzUiLCAiaWQiOiAiNjYzOTEwZjYtNTlkYS00NjE3LTli
+      ZTMtNTBmMDdhNmQ5N2U3IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0
+      PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJDRU8iLCAiYWdlbnRfa2V5IjogIjMyODIxN2I2YzI5
+      NTliZGZjNDdjYWQwMGU4NDg5MGQwIiwgInRvb2xzX25hbWVzIjogWyJ0ZXN0IHRvb2wiXX1degIY
+      AYUBAAEAABKOAgoQ1qBlNY8Yu1muyMaMnchyJBII0vE2y9FMwz0qDFRhc2sgQ3JlYXRlZDABObDR
+      zscZpxMYQah5z8cZpxMYSi4KCGNyZXdfa2V5EiIKIGU2NDk1NzNhMjZlNTg3OTBjYWMyMWEzN2Nk
+      NDQ0MzdhSjEKB2NyZXdfaWQSJgokMjY3NzEyNzItOTRlZC00NDVkLTg1MGEtYTkyYTZjOWI5YmJk
+      Si4KCHRhc2tfa2V5EiIKIDBiOWQ2NWRiNmI3YWVkZmIzOThjNTllMmE5ZjcxZWM1SjEKB3Rhc2tf
+      aWQSJgokNjYzOTEwZjYtNTlkYS00NjE3LTliZTMtNTBmMDdhNmQ5N2U3egIYAYUBAAEAABKMAQoQ
+      a8ZDV3ZaBmcOZE5dJ87f1hII7iBRAQfEmdAqClRvb2wgVXNhZ2UwATmYcwjIGacTGEE4RxLIGacT
+      GEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKGAoJdG9vbF9uYW1lEgsKCVRlc3QgVG9vbEoO
+      CghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEowBChBqK4036ypaH1gZ3OIOE/0HEgiF8wTQDQGRlSoK
+      VG9vbCBVc2FnZTABOYBiSsgZpxMYQRCYUsgZpxMYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYu
+      MEoYCgl0b29sX25hbWUSCwoJVGVzdCBUb29sSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASwQcK
+      EIWSiNjtKgeNQ6oIv8gjJ+MSCG8YnypCXfw1KgxDcmV3IENyZWF0ZWQwATnYUW/KGacTGEEoenTK
+      GacTGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4x
+      MS43Si4KCGNyZXdfa2V5EiIKIDk4MjQ2MGVlMmRkMmNmMTJhNzEzOGI3MDg1OWZlODE3SjEKB2Ny
+      ZXdfaWQSJgokZDNkODZjNmEtNWNmMi00MGI0LWExZGQtMzA5NTYyODdjNWE3ShwKDGNyZXdfcHJv
+      Y2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90
+      YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrcAgoLY3Jld19hZ2VudHMSzAIK
+      yQJbeyJrZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNkNzUiLCAiaWQiOiAiNWNm
+      NDllYzctOTVmMy00ZGQ3LTg1NzItZjgwMDQwODYwYjI4IiwgInJvbGUiOiAiUmVzZWFyY2hlciIs
+      ICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVu
+      Y3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9u
+      X2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9y
+      ZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFsidGVzdCB0b29sIl19XUqSAgoKY3Jld190
+      YXNrcxKDAgqAAlt7ImtleSI6ICJmODM5Yzg3YzNkNzU3Yzg4N2Y0Y2U3NGQxODY0YjAyYSIsICJp
+      ZCI6ICJjM2Y2NjY2MS00YWNjLTQ5OWQtYjJkNC1kZjI0Nzg1MTJhZGYiLCAiYXN5bmNfZXhlY3V0
+      aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIlJlc2Vh
+      cmNoZXIiLCAiYWdlbnRfa2V5IjogIjhiZDIxMzliNTk3NTE4MTUwNmU0MWZkOWM0NTYzZDc1Iiwg
+      InRvb2xzX25hbWVzIjogWyJhbm90aGVyIHRlc3QgdG9vbCJdfV16AhgBhQEAAQAAEo4CChD8dNvp
+      UItERukk59GnvESYEghtjirHyG3B3SoMVGFzayBDcmVhdGVkMAE5MAGByhmnExhBIFeByhmnExhK
+      LgoIY3Jld19rZXkSIgogOTgyNDYwZWUyZGQyY2YxMmE3MTM4YjcwODU5ZmU4MTdKMQoHY3Jld19p
+      ZBImCiRkM2Q4NmM2YS01Y2YyLTQwYjQtYTFkZC0zMDk1NjI4N2M1YTdKLgoIdGFza19rZXkSIgog
+      ZjgzOWM4N2MzZDc1N2M4ODdmNGNlNzRkMTg2NGIwMmFKMQoHdGFza19pZBImCiRjM2Y2NjY2MS00
+      YWNjLTQ5OWQtYjJkNC1kZjI0Nzg1MTJhZGZ6AhgBhQEAAQAAEowBChDdoNfQMW/Om7LQU9gZGDrl
+      Egjw71DM3bnOWCoKVG9vbCBVc2FnZTABOUgPFC8apxMYQdhtKi8apxMYShoKDmNyZXdhaV92ZXJz
+      aW9uEggKBjAuODYuMEoYCgl0b29sX25hbWUSCwoJVGVzdCBUb29sSg4KCGF0dGVtcHRzEgIYAXoC
+      GAGFAQABAAA=
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '14771'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    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:
+      - Mon, 23 Dec 2024 00:33:37 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
+      an expert researcher, specialized in technology, software engineering, AI and
+      startups. You work as a freelancer and is now working on doing research and
+      analysis for a new customer.\nYour personal goal is: Make the best research
+      and analysis on content about AI and AI agents\nYou ONLY have access to the
+      following tools, and should NEVER make up tools that are not listed here:\n\nTool
+      Name: Test Tool\nTool Arguments: {''query'': {''description'': ''Query to process'',
+      ''type'': ''str''}}\nTool Description: A test tool that just returns the input\n\nUse
+      the following format:\n\nThought: you should always think about what to do\nAction:
+      the action to take, only one name of [Test Tool], just the name, exactly as
+      it''s written.\nAction Input: the input to the action, just a simple python
+      dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
+      the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question"}, {"role": "user", "content": "\nCurrent Task: Write a test
+      task\n\nThis is the expect criteria for your final answer: Test output\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:"}, {"role": "assistant", "content":
+      "I need to come up with a suitable test task that meets the criteria provided.
+      I will focus on outlining a clear and effective test task related to AI and
+      AI agents.\n\nAction: Test Tool\nAction Input: {\"query\": \"Create a test task
+      that involves evaluating the performance of an AI agent in a given scenario,
+      including criteria for success, tools required, and process for assessment.\"}\nObservation:
+      Processed: Create a test task that involves evaluating the performance of an
+      AI agent in a given scenario, including criteria for success, tools required,
+      and process for assessment."}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2160'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000;
+        __cf_bm=i6jvNjhsDne300GPAeEmyiJJKYqy7OPuamFG_kht3KE-1734914012-1.0.1.1-tCeVANAF521vkXpBdgYw.ov.fYUr6t5QC4LG_DugWyzu4C60Pi2CruTVniUgfCvkcu6rdHA5DwnaEZf2jFaRCQ
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AhQg0Cx1FED7gOwMpJUD5cQxVzQBK\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1734914012,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I need to compile a complete
+      and detailed test task based on the processed input, ensuring it includes all
+      necessary components as per the expect criteria.\\n\\nFinal Answer: \\n### Test
+      Task: Evaluating the Performance of an AI Agent\\n\\n**Objective:** \\nTo evaluate
+      the performance of an AI agent in simulating conversation with users in a customer
+      service context.\\n\\n**Scenario:**\\nAn AI agent is tasked with handling customer
+      inquiries on an e-commerce platform. The agent must respond to questions about
+      product availability, order tracking, returns, and other common queries.\\n\\n**Criteria
+      for Success:**\\n1. **Accuracy:** The AI should provide correct information
+      in at least 90% of the interactions.\\n2. **Response Time:** The average response
+      time should be under 2 seconds.\\n3. **User Satisfaction:** Aim for a user satisfaction
+      score of 85% or higher based on follow-up surveys after interactions.\\n4. **Fallback
+      Rate:** The AI should not default to a human agent more than 10% of the time.\\n\\n**Tools
+      Required:**\\n- Chatbot development platform (e.g., Dialogflow, Rasa)\\n- Metrics
+      tracking software (to measure accuracy, response times, and user satisfaction)\\n-
+      Survey tool (e.g., Google Forms, SurveyMonkey) for feedback collection\\n\\n**Process
+      for Assessment:**\\n1. **Setup:** Deploy the AI agent on a testing environment
+      simulating real customer inquiries.\\n2. **Data Collection:** Run the test for
+      a predetermined period (e.g., one week) or until a set number of interactions
+      (e.g., 1000).\\n3. **Measurement:**\\n   - Record the interactions and analyze
+      the accuracy of the AI's responses.\\n   - Measure the average response time
+      for each interaction.\\n   - Collect user satisfaction scores via surveys sent
+      after the interaction.\\n4. **Analysis:** Compile the data to see if the AI
+      met the success criteria. Identify strengths and weaknesses in the responses.\\n5.
+      **Review:** Share findings with the development team to strategize improvements.\\n\\nThis
+      detailed task will help assess the AI agent\u2019s capabilities and provide
+      insights for further enhancements.\",\n        \"refusal\": null\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 416,\n    \"completion_tokens\": 422,\n
+      \   \"total_tokens\": 838,\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  \"system_fingerprint\":
+      \"fp_d02d531b47\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f6442c2ba15a486-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 23 Dec 2024 00:33:39 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '6734'
+      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:
+      - '149999497'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_7d8df8b840e279bd64280d161d854161
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/crew_test.py

@@ -332,22 +332,31 @@ def test_manager_agent_delegating_to_assigned_task_agent():
         tasks=[task],
     )
 
-    crew.kickoff()
-
-    # Check if the manager agent has the correct tools
-    assert crew.manager_agent is not None
-    assert crew.manager_agent.tools is not None
-
-    assert len(crew.manager_agent.tools) == 2
-    assert (
-        "Delegate a specific task to one of the following coworkers: Researcher\n"
-        in crew.manager_agent.tools[0].description
-    )
-    assert (
-        "Ask a specific question to one of the following coworkers: Researcher\n"
-        in crew.manager_agent.tools[1].description
+    mock_task_output = TaskOutput(
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
     )
 
+    # Because we are mocking execute_sync, we never hit the underlying _execute_core
+    # which sets the output attribute of the task
+    task.output = mock_task_output
+
+    with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
+        crew.kickoff()
+
+        # Verify execute_sync was called once
+        mock_execute_sync.assert_called_once()
+
+        # Get the tools argument from the call
+        _, kwargs = mock_execute_sync.call_args
+        tools = kwargs['tools']
+
+        # Verify the delegation tools were passed correctly
+        assert len(tools) == 2
+        assert any("Delegate a specific task to one of the following coworkers: Researcher" in tool.description for tool in tools)
+        assert any("Ask a specific question to one of the following coworkers: Researcher" in tool.description for tool in tools)
+
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_manager_agent_delegating_to_all_agents():
@@ -402,9 +411,255 @@ def test_crew_with_delegating_agents():
 
     assert (
         result.raw
-        == "This is the complete content as specified:\nArtificial Intelligence (AI) Agents are sophisticated computer programs designed to perform tasks that typically require human intelligence, such as decision making, problem-solving, and learning. These agents operate autonomously, utilizing vast amounts of data, advanced algorithms, and machine learning techniques to analyze their environment, adapt to new information, and improve their performance over time.\n\nThe significance of AI Agents lies in their transformative potential across various industries. In healthcare, for example, they assist in diagnosing diseases with greater accuracy and speed than human practitioners, offering personalized treatment plans by analyzing patient data. In finance, AI Agents predict market trends, manage risks, and even execute trades, contributing to more stable and profitable financial systems. Customer service sectors benefit significantly from AI Agents, as they provide personalized and efficient responses, often resolving issues faster than traditional methods.\n\nMoreover, AI Agents are also making substantial contributions in fields like education and manufacturing. In education, they offer tailored learning experiences by assessing individual student needs and adjusting teaching methods accordingly. They help educators identify students who might need additional support and provide resources to enhance learning outcomes. In manufacturing, AI Agents optimize production lines, predict equipment failures, and improve supply chain management, thus boosting productivity and reducing downtime.\n\nAs these AI-powered entities continue to evolve, they are not only enhancing operational efficiencies but also driving innovation and creating new opportunities for growth and development in every sector they penetrate. The future of AI Agents looks promising, with the potential to revolutionize the way we live and work, making processes more efficient, decisions more data-driven, and solutions more innovative than ever before."
+        == "In the rapidly evolving landscape of technology, AI agents have emerged as formidable tools, revolutionizing how we interact with data and automate tasks. These sophisticated systems leverage machine learning and natural language processing to perform a myriad of functions, from virtual personal assistants to complex decision-making companions in industries such as finance, healthcare, and education. By mimicking human intelligence, AI agents can analyze massive data sets at unparalleled speeds, enabling businesses to uncover valuable insights, enhance productivity, and elevate user experiences to unprecedented levels.\n\nOne of the most striking aspects of AI agents is their adaptability; they learn from their interactions and continuously improve their performance over time. This feature is particularly valuable in customer service where AI agents can address inquiries, resolve issues, and provide personalized recommendations without the limitations of human fatigue. Moreover, with intuitive interfaces, AI agents enhance user interactions, making technology more accessible and user-friendly, thereby breaking down barriers that have historically hindered digital engagement.\n\nDespite their immense potential, the deployment of AI agents raises important ethical and practical considerations. Issues related to privacy, data security, and the potential for job displacement necessitate thoughtful dialogue and proactive measures. Striking a balance between technological innovation and societal impact will be crucial as organizations integrate these agents into their operations. Additionally, ensuring transparency in AI decision-making processes is vital to maintain public trust as AI agents become an integral part of daily life.\n\nLooking ahead, the future of AI agents appears bright, with ongoing advancements promising even greater capabilities. As we continue to harness the power of AI, we can expect these agents to play a transformative role in shaping various sectors—streamlining workflows, enabling smarter decision-making, and fostering more personalized experiences. Embracing this technology responsibly can lead to a future where AI agents not only augment human effort but also inspire creativity and efficiency across the board, ultimately redefining our interaction with the digital world."
     )
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_with_delegating_agents_should_not_override_task_tools():
+    from typing import Type
+
+    from pydantic import BaseModel, Field
+
+    from crewai.tools import BaseTool
+
+    class TestToolInput(BaseModel):
+        """Input schema for TestTool."""
+        query: str = Field(..., description="Query to process")
+
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool that just returns the input"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Processed: {query}"
+
+    # Create a task with the test tool
+    tasks = [
+        Task(
+            description="Produce and amazing 1 paragraph draft of an article about AI Agents.",
+            expected_output="A 4 paragraph article about AI.",
+            agent=ceo,
+            tools=[TestTool()],
+        )
+    ]
+
+    crew = Crew(
+        agents=[ceo, writer],
+        process=Process.sequential,
+        tasks=tasks,
+    )
+
+    mock_task_output = TaskOutput(
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
+    )
+
+    # Because we are mocking execute_sync, we never hit the underlying _execute_core
+    # which sets the output attribute of the task
+    tasks[0].output = mock_task_output
+
+    with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
+        crew.kickoff()
+
+        # Execute the task and verify both tools are present
+        _, kwargs = mock_execute_sync.call_args
+        tools = kwargs['tools']
+
+        assert any(isinstance(tool, TestTool) for tool in tools), "TestTool should be present"
+        assert any("delegate" in tool.name.lower() for tool in tools), "Delegation tool should be present"
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_with_delegating_agents_should_not_override_agent_tools():
+    from typing import Type
+
+    from pydantic import BaseModel, Field
+
+    from crewai.tools import BaseTool
+
+    class TestToolInput(BaseModel):
+        """Input schema for TestTool."""
+        query: str = Field(..., description="Query to process")
+
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool that just returns the input"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Processed: {query}"
+
+    new_ceo = ceo.model_copy()
+    new_ceo.tools = [TestTool()]
+
+    # Create a task with the test tool
+    tasks = [
+        Task(
+            description="Produce and amazing 1 paragraph draft of an article about AI Agents.",
+            expected_output="A 4 paragraph article about AI.",
+            agent=new_ceo
+        )
+    ]
+
+    crew = Crew(
+        agents=[new_ceo, writer],
+        process=Process.sequential,
+        tasks=tasks,
+    )
+
+    mock_task_output = TaskOutput(
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
+    )
+
+    # Because we are mocking execute_sync, we never hit the underlying _execute_core
+    # which sets the output attribute of the task
+    tasks[0].output = mock_task_output
+
+    with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
+        crew.kickoff()
+
+        # Execute the task and verify both tools are present
+        _, kwargs = mock_execute_sync.call_args
+        tools = kwargs['tools']
+
+        assert any(isinstance(tool, TestTool) for tool in new_ceo.tools), "TestTool should be present"
+        assert any("delegate" in tool.name.lower() for tool in tools), "Delegation tool should be present"
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_task_tools_override_agent_tools():
+    from typing import Type
+
+    from pydantic import BaseModel, Field
+
+    from crewai.tools import BaseTool
+
+    class TestToolInput(BaseModel):
+        """Input schema for TestTool."""
+        query: str = Field(..., description="Query to process")
+
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool that just returns the input"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Processed: {query}"
+
+    class AnotherTestTool(BaseTool):
+        name: str = "Another Test Tool"
+        description: str = "Another test tool"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Another processed: {query}"
+
+    # Set agent tools
+    new_researcher = researcher.model_copy()
+    new_researcher.tools = [TestTool()]
+
+    # Create task with different tools
+    task = Task(
+        description="Write a test task",
+        expected_output="Test output",
+        agent=new_researcher,
+        tools=[AnotherTestTool()]
+    )
+
+    crew = Crew(
+        agents=[new_researcher],
+        tasks=[task],
+        process=Process.sequential
+    )
+
+    crew.kickoff()
+
+    # Verify task tools override agent tools
+    assert len(task.tools) == 1  # AnotherTestTool
+    assert any(isinstance(tool, AnotherTestTool) for tool in task.tools)
+    assert not any(isinstance(tool, TestTool) for tool in task.tools)
+
+    # Verify agent tools remain unchanged
+    assert len(new_researcher.tools) == 1
+    assert isinstance(new_researcher.tools[0], TestTool)
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_task_tools_override_agent_tools_with_allow_delegation():
+    """
+    Test that task tools override agent tools while preserving delegation tools when allow_delegation=True
+    """
+    from typing import Type
+
+    from pydantic import BaseModel, Field
+
+    from crewai.tools import BaseTool
+
+    class TestToolInput(BaseModel):
+        query: str = Field(..., description="Query to process")
+
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool that just returns the input"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Processed: {query}"
+
+    class AnotherTestTool(BaseTool):
+        name: str = "Another Test Tool"
+        description: str = "Another test tool"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Another processed: {query}"
+
+    # Set up agents with tools and allow_delegation
+    researcher_with_delegation = researcher.model_copy()
+    researcher_with_delegation.allow_delegation = True
+    researcher_with_delegation.tools = [TestTool()]
+
+    writer_for_delegation = writer.model_copy()
+
+    # Create a task with different tools
+    task = Task(
+        description="Write a test task",
+        expected_output="Test output",
+        agent=researcher_with_delegation,
+        tools=[AnotherTestTool()],
+    )
+
+    crew = Crew(
+        agents=[researcher_with_delegation, writer_for_delegation],
+        tasks=[task],
+        process=Process.sequential,
+    )
+
+    mock_task_output = TaskOutput(
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
+    )
+
+    # We mock execute_sync to verify which tools get used at runtime
+    with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync:
+        crew.kickoff()
+
+        # Inspect the call kwargs to verify the actual tools passed to execution
+        _, kwargs = mock_execute_sync.call_args
+        used_tools = kwargs["tools"]
+
+        # Confirm AnotherTestTool is present but TestTool is not
+        assert any(isinstance(tool, AnotherTestTool) for tool in used_tools), "AnotherTestTool should be present"
+        assert not any(isinstance(tool, TestTool) for tool in used_tools), "TestTool should not be present among used tools"
+
+        # Confirm delegation tool(s) are present
+        assert any("delegate" in tool.name.lower() for tool in used_tools), "Delegation tool should be present"
+
+    # Finally, make sure the agent's original tools remain unchanged
+    assert len(researcher_with_delegation.tools) == 1
+    assert isinstance(researcher_with_delegation.tools[0], TestTool)
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_verbose_output(capsys):
@@ -1193,12 +1448,22 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
 
     crew = Crew(agents=[programmer], tasks=[task])
 
-    with patch.object(Agent, "execute_task") as executor:
-        executor.return_value = "ok"
-        crew.kickoff()
-        assert len(programmer.tools) == 1
-        assert programmer.tools[0].__class__ == CodeInterpreterTool
+    mock_task_output = TaskOutput(
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
+    )
 
+    with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync:
+        crew.kickoff()
+
+        # Get the tools that were actually used in execution
+        _, kwargs = mock_execute_sync.call_args
+        used_tools = kwargs["tools"]
+
+        # Verify that exactly one tool was used and it was a CodeInterpreterTool
+        assert len(used_tools) == 1, "Should have exactly one tool"
+        assert isinstance(used_tools[0], CodeInterpreterTool), "Tool should be CodeInterpreterTool"
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_delegation_is_not_enabled_if_there_are_only_one_agent():
@@ -1307,21 +1572,37 @@ def test_hierarchical_crew_creation_tasks_with_agents():
         process=Process.hierarchical,
         manager_llm="gpt-4o",
     )
-    crew.kickoff()
 
-    assert crew.manager_agent is not None
-    assert crew.manager_agent.tools is not None
-    assert (
-        "Delegate a specific task to one of the following coworkers: Senior Writer\n"
-        in crew.manager_agent.tools[0].description
+    mock_task_output = TaskOutput(
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
     )
 
+    # Because we are mocking execute_sync, we never hit the underlying _execute_core
+    # which sets the output attribute of the task
+    task.output = mock_task_output
+
+    with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
+        crew.kickoff()
+
+        # Verify execute_sync was called once
+        mock_execute_sync.assert_called_once()
+
+        # Get the tools argument from the call
+        _, kwargs = mock_execute_sync.call_args
+        tools = kwargs['tools']
+
+        # Verify the delegation tools were passed correctly
+        assert len(tools) == 2
+        assert any("Delegate a specific task to one of the following coworkers: Senior Writer" in tool.description for tool in tools)
+        assert any("Ask a specific question to one of the following coworkers: Senior Writer" in tool.description for tool in tools)
+
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_hierarchical_crew_creation_tasks_with_async_execution():
     """
-    Agents are not required for tasks in a hierarchical process but sometimes they are still added
-    This test makes sure that the manager still delegates the task to the agent even if the agent is passed in the task
+    Tests that async tasks in hierarchical crews are handled correctly with proper delegation tools
     """
     task = Task(
         description="Write one amazing paragraph about AI.",
@@ -1337,14 +1618,35 @@ def test_hierarchical_crew_creation_tasks_with_async_execution():
         manager_llm="gpt-4o",
     )
 
-    crew.kickoff()
-    assert crew.manager_agent is not None
-    assert crew.manager_agent.tools is not None
-    assert (
-        "Delegate a specific task to one of the following coworkers: Senior Writer\n"
-        in crew.manager_agent.tools[0].description
+    mock_task_output = TaskOutput(
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
     )
 
+    # Create a mock Future that returns our TaskOutput
+    mock_future = MagicMock(spec=Future)
+    mock_future.result.return_value = mock_task_output
+
+    # Because we are mocking execute_async, we never hit the underlying _execute_core
+    # which sets the output attribute of the task
+    task.output = mock_task_output
+
+    with patch.object(Task, 'execute_async', return_value=mock_future) as mock_execute_async:
+        crew.kickoff()
+
+        # Verify execute_async was called once
+        mock_execute_async.assert_called_once()
+
+        # Get the tools argument from the call
+        _, kwargs = mock_execute_async.call_args
+        tools = kwargs['tools']
+
+        # Verify the delegation tools were passed correctly
+        assert len(tools) == 2
+        assert any("Delegate a specific task to one of the following coworkers: Senior Writer\n" in tool.description for tool in tools)
+        assert any("Ask a specific question to one of the following coworkers: Senior Writer\n" in tool.description for tool in tools)
+
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_hierarchical_crew_creation_tasks_with_sync_last():
@@ -2583,3 +2885,244 @@ def test_hierarchical_verbose_false_manager_agent():
 
     assert crew.manager_agent is not None
     assert not crew.manager_agent.verbose
+
+
+def test_task_tools_preserve_code_execution_tools():
+    """
+    Test that task tools don't override code execution tools when allow_code_execution=True
+    """
+    from typing import Type
+
+    from crewai_tools import CodeInterpreterTool
+    from pydantic import BaseModel, Field
+
+    from crewai.tools import BaseTool
+
+    class TestToolInput(BaseModel):
+        """Input schema for TestTool."""
+        query: str = Field(..., description="Query to process")
+
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool that just returns the input"
+        args_schema: Type[BaseModel] = TestToolInput
+
+        def _run(self, query: str) -> str:
+            return f"Processed: {query}"
+
+    # Create a programmer agent with code execution enabled
+    programmer = Agent(
+        role="Programmer",
+        goal="Write code to solve problems.",
+        backstory="You're a programmer who loves to solve problems with code.",
+        allow_delegation=True,
+        allow_code_execution=True,
+    )
+
+    # Create a code reviewer agent
+    reviewer = Agent(
+        role="Code Reviewer",
+        goal="Review code for bugs and improvements",
+        backstory="You're an experienced code reviewer who ensures code quality and best practices.",
+        allow_delegation=True,
+        allow_code_execution=True,
+    )
+
+    # Create a task with its own tools
+    task = Task(
+        description="Write a program to calculate fibonacci numbers.",
+        expected_output="A working fibonacci calculator.",
+        agent=programmer,
+        tools=[TestTool()]
+    )
+
+    crew = Crew(
+        agents=[programmer, reviewer],
+        tasks=[task],
+        process=Process.sequential,
+    )
+
+    mock_task_output = TaskOutput(
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
+    )
+
+    with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync:
+        crew.kickoff()
+
+        # Get the tools that were actually used in execution
+        _, kwargs = mock_execute_sync.call_args
+        used_tools = kwargs["tools"]
+
+        # Verify all expected tools are present
+        assert any(isinstance(tool, TestTool) for tool in used_tools), "Task's TestTool should be present"
+        assert any(isinstance(tool, CodeInterpreterTool) for tool in used_tools), "CodeInterpreterTool should be present"
+        assert any("delegate" in tool.name.lower() for tool in used_tools), "Delegation tool should be present"
+
+        # Verify the total number of tools (TestTool + CodeInterpreter + 2 delegation tools)
+        assert len(used_tools) == 4, "Should have TestTool, CodeInterpreter, and 2 delegation tools"
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_multimodal_flag_adds_multimodal_tools():
+    """
+    Test that an agent with multimodal=True automatically has multimodal tools added to the task execution.
+    """
+    from crewai.tools.agent_tools.add_image_tool import AddImageTool
+
+    # Create an agent that supports multimodal
+    multimodal_agent = Agent(
+        role="Multimodal Analyst",
+        goal="Handle multiple media types (text, images, etc.).",
+        backstory="You're an agent specialized in analyzing text, images, and other media.",
+        allow_delegation=False,
+        multimodal=True,  # crucial for adding the multimodal tool
+    )
+
+    # Create a dummy task
+    task = Task(
+        description="Describe what's in this image and generate relevant metadata.",
+        expected_output="An image description plus any relevant metadata.",
+        agent=multimodal_agent,
+    )
+
+    # Define a crew with the multimodal agent
+    crew = Crew(agents=[multimodal_agent], tasks=[task], process=Process.sequential)
+
+    mock_task_output = TaskOutput(
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
+    )
+
+    # Mock execute_sync to verify the tools passed at runtime
+    with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync:
+        crew.kickoff()
+
+        # Get the tools that were actually used in execution
+        _, kwargs = mock_execute_sync.call_args
+        used_tools = kwargs["tools"]
+
+        # Check that the multimodal tool was added
+        assert any(isinstance(tool, AddImageTool) for tool in used_tools), (
+            "AddImageTool should be present when agent is multimodal"
+        )
+
+        # Verify we have exactly one tool (just the AddImageTool)
+        assert len(used_tools) == 1, "Should only have the AddImageTool"
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_multimodal_agent_image_tool_handling():
+    """
+    Test that multimodal agents properly handle image tools in the CrewAgentExecutor
+    """
+    # Create a multimodal agent
+    multimodal_agent = Agent(
+        role="Image Analyst",
+        goal="Analyze images and provide descriptions",
+        backstory="You're an expert at analyzing and describing images.",
+        allow_delegation=False,
+        multimodal=True,
+    )
+
+    # Create a task that involves image analysis
+    task = Task(
+        description="Analyze this image and describe what you see.",
+        expected_output="A detailed description of the image.",
+        agent=multimodal_agent,
+    )
+
+    crew = Crew(agents=[multimodal_agent], tasks=[task])
+
+    # Mock the image tool response
+    mock_image_tool_result = {
+        "role": "user",
+        "content": [
+            {"type": "text", "text": "Please analyze this image"},
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": "https://example.com/test-image.jpg",
+                },
+            },
+        ],
+    }
+
+    # Create a mock task output for the final result
+    mock_task_output = TaskOutput(
+        description="Mock description",
+        raw="A detailed analysis of the image",
+        agent="Image Analyst"
+    )
+
+    with patch.object(Task, 'execute_sync') as mock_execute_sync:
+        # Set up the mock to return our task output
+        mock_execute_sync.return_value = mock_task_output
+
+        # Execute the crew
+        crew.kickoff()
+
+        # Get the tools that were passed to execute_sync
+        _, kwargs = mock_execute_sync.call_args
+        tools = kwargs['tools']
+
+        # Verify the AddImageTool is present and properly configured
+        image_tools = [tool for tool in tools if tool.name == "Add image to content"]
+        assert len(image_tools) == 1, "Should have exactly one AddImageTool"
+
+        # Test the tool's execution
+        image_tool = image_tools[0]
+        result = image_tool._run(
+            image_url="https://example.com/test-image.jpg",
+            action="Please analyze this image"
+        )
+
+        # Verify the tool returns the expected format
+        assert result == mock_image_tool_result
+        assert result["role"] == "user"
+        assert len(result["content"]) == 2
+        assert result["content"][0]["type"] == "text"
+        assert result["content"][1]["type"] == "image_url"
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_multimodal_agent_live_image_analysis():
+    """
+    Test that multimodal agents can analyze images through a real API call
+    """
+    # Create a multimodal agent
+    image_analyst = Agent(
+        role="Image Analyst",
+        goal="Analyze images with high attention to detail",
+        backstory="You're an expert at visual analysis, trained to notice and describe details in images.",
+        allow_delegation=False,
+        multimodal=True,
+        verbose=True,
+        llm="gpt-4o"
+    )
+
+    # Create a task for image analysis
+    analyze_image = Task(
+        description="""
+        Analyze the provided image and describe what you see in detail.
+        Focus on main elements, colors, composition, and any notable details.
+        Image: {image_url}
+        """,
+        expected_output="A comprehensive description of the image contents.",
+        agent=image_analyst
+    )
+
+    # Create and run the crew
+    crew = Crew(
+        agents=[image_analyst],
+        tasks=[analyze_image]
+    )
+
+    # Execute with an image URL
+    result = crew.kickoff(inputs={
+        "image_url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k="
+    })
+
+    # Verify we got a meaningful response
+    assert isinstance(result.raw, str)
+    assert len(result.raw) > 100  # Expecting a detailed analysis
+    assert "error" not in result.raw.lower()  # No error messages in response