Merge branch 'main' into feature-isolated-memory

fix: Correctly copy memory objects during crew training (fixes #2593 ) (#2594 )
* fix: Correctly copy memory objects during crew training (#2593) Co-Authored-By: Joe Moura <joao@crewai.com> * style: Fix import order in tests/crew_test.py Co-Authored-By: Joe Moura <joao@crewai.com> * fix: Rely on validator for memory copy, update test assertions Removes manual deep copy of memory objects in Crew.copy(). The Pydantic model_validator 'create_crew_memory' handles the initialization of new memory instances for the copied crew. Updates test_crew_copy_with_memory assertions to verify that the private memory attributes (_short_term_memory, etc.) are correctly initialized as new instances in the copied crew. Co-Authored-By: Joe Moura <joao@crewai.com> * Revert "fix: Rely on validator for memory copy, update test assertions" This reverts commit 8702bf1e34. * fix: Re-add manual deep copy for all memory types in Crew.copy Addresses feedback on PR #2594 to ensure all memory objects (short_term, long_term, entity, external, user) are correctly deep copied using model_copy(deep=True). Also simplifies the test case to directly verify the copy behavior instead of relying on the train method. Co-Authored-By: Joe Moura <joao@crewai.com> --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Joe Moura <joao@crewai.com>
2026-10-19 16:35:10 +02:00 · 2025-04-14 16:37:08 -03:00 · 2025-04-14 14:59:12 -04:00 · 2025-04-14 14:15:07 -03:00 · 2025-04-14 14:15:07 -03:00 · 2025-04-14 14:15:07 -03:00
35 changed files with 5210 additions and 1799 deletions
@@ -12,6 +12,9 @@ jobs:
  tests:
    runs-on: ubuntu-latest
    timeout-minutes: 15
+    strategy:
+      matrix:
+        python-version: ['3.10', '3.11', '3.12']
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
@@ -21,9 +24,8 @@ jobs:
        with:
          enable-cache: true

-
-      - name: Set up Python
-        run: uv python install 3.12.8
+      - name: Set up Python ${{ matrix.python-version }}
+        run: uv python install ${{ matrix.python-version }}

      - name: Install the project
        run: uv sync --dev --all-extras
@@ -145,6 +145,7 @@ from crewai.memory import LongTermMemory
 # Simple memory configuration
 crew = Crew(memory=True)  # Uses default storage locations
 ```
+Note that External Memory won’t be defined when `memory=True` is set, as we can’t infer which external memory would be suitable for your case

 ### Custom Storage Configuration
 ```python
@@ -278,15 +279,19 @@ crew = Crew(
 ### Using External Memory

 External Memory is a powerful feature that allows you to integrate external memory systems with your CrewAI applications. This is particularly useful when you want to use specialized memory providers or maintain memory across different applications.
+Since it’s an external memory, we’re not able to add a default value to it - unlike with Long Term and Short Term memory. 

 #### Basic Usage with Mem0

 The most common way to use External Memory is with Mem0 as the provider:

 ```python
+import os
 from crewai import Agent, Crew, Process, Task
 from crewai.memory.external.external_memory import ExternalMemory

+os.environ["MEM0_API_KEY"] = "YOUR-API-KEY"
+
 agent = Agent(
    role="You are a helpful assistant",
    goal="Plan a vacation for the user",
@@ -304,7 +309,6 @@ crew = Crew(
    tasks=[task],
    verbose=True,
    process=Process.sequential,
-    memory=True,
    external_memory=ExternalMemory(
        embedder_config={"provider": "mem0", "config": {"user_id": "U-123"}} # you can provide an entire Mem0 configuration
    ),
@@ -363,7 +367,6 @@ crew = Crew(
    tasks=[task],
    verbose=True,
    process=Process.sequential,
-    memory=True,
    external_memory=external_memory,
 )

@@ -263,6 +263,7 @@ Let's create our flow in the `main.py` file:
 ```python
 #!/usr/bin/env python
 import json
+import os
 from typing import List, Dict
 from pydantic import BaseModel, Field
 from crewai import LLM
@@ -341,6 +342,9 @@ class GuideCreatorFlow(Flow[GuideCreatorState]):
        outline_dict = json.loads(response)
        self.state.guide_outline = GuideOutline(**outline_dict)

+        # Ensure output directory exists before saving
+        os.makedirs("output", exist_ok=True)
+
        # Save the outline to a file
        with open("output/guide_outline.json", "w") as f:
            json.dump(outline_dict, f, indent=2)
@@ -25,7 +25,7 @@ uv add weaviate-client
 To effectively use the `WeaviateVectorSearchTool`, follow these steps:

 1. **Package Installation**: Confirm that the `crewai[tools]` and `weaviate-client` packages are installed in your Python environment.
-2. **Weaviate Setup**: Set up a Weaviate cluster. You can follow the [Weaviate documentation](https://weaviate.io/developers/wcs/connect) for instructions.
+2. **Weaviate Setup**: Set up a Weaviate cluster. You can follow the [Weaviate documentation](https://weaviate.io/developers/wcs/manage-clusters/connect) for instructions.
 3. **API Keys**: Obtain your Weaviate cluster URL and API key.
 4. **OpenAI API Key**: Ensure you have an OpenAI API key set in your environment variables as `OPENAI_API_KEY`.

@@ -161,4 +161,4 @@ rag_agent = Agent(

 ## Conclusion

-The `WeaviateVectorSearchTool` provides a powerful way to search for semantically similar documents in a Weaviate vector database. By leveraging vector embeddings, it enables more accurate and contextually relevant search results compared to traditional keyword-based searches. This tool is particularly useful for applications that require finding information based on meaning rather than exact matches. 
+The `WeaviateVectorSearchTool` provides a powerful way to search for semantically similar documents in a Weaviate vector database. By leveraging vector embeddings, it enables more accurate and contextually relevant search results compared to traditional keyword-based searches. This tool is particularly useful for applications that require finding information based on meaning rather than exact matches. 
@@ -156,6 +156,23 @@ class Agent(BaseAgent):
        except (TypeError, ValueError) as e:
            raise ValueError(f"Invalid Knowledge Configuration: {str(e)}")

+    def _is_any_available_memory(self) -> bool:
+        """Check if any memory is available."""
+        if not self.crew:
+            return False
+
+        memory_attributes = [
+            "memory",
+            "memory_config",
+            "_short_term_memory",
+            "_long_term_memory",
+            "_entity_memory",
+            "_user_memory",
+            "_external_memory",
+        ]
+
+        return any(getattr(self.crew, attr) for attr in memory_attributes)
+
    def execute_task(
        self,
        task: Task,
@@ -200,7 +217,7 @@ class Agent(BaseAgent):
                task=task_prompt, context=context
            )

-        if self.crew and self.crew.memory:
+        if self._is_any_available_memory():
            contextual_memory = ContextualMemory(
                self.crew.memory_config,
                self.crew._short_term_memory,
@@ -482,6 +499,7 @@ class Agent(BaseAgent):
            verbose=self.verbose,
            response_format=response_format,
            i18n=self.i18n,
+            original_agent=self,
        )

        return lite_agent.kickoff(messages)
@@ -72,7 +72,6 @@ class CrewAgentExecutorMixin:
        """Create and save long-term and entity memory items based on evaluation."""
        if (
            self.crew
-            and self.crew.memory
            and self.crew._long_term_memory
            and self.crew._entity_memory
            and self.task
@@ -114,6 +113,15 @@ class CrewAgentExecutorMixin:
            except Exception as e:
                print(f"Failed to add to long term memory: {e}")
                pass
+        elif (
+            self.crew
+            and self.crew._long_term_memory
+            and self.crew._entity_memory is None
+        ):
+            self._printer.print(
+                content="Long term memory is enabled, but entity memory is not enabled. Please configure entity memory or set memory=True to automatically enable it.",
+                color="bold_yellow",
+            )

    def _ask_human_input(self, final_answer: str) -> str:
        """Prompt human input with mode-appropriate messaging."""
@@ -33,7 +33,8 @@ def train():
    Train the crew for a given number of iterations.
    """
    inputs = {
-        "topic": "AI LLMs"
+        "topic": "AI LLMs",
+        'current_year': str(datetime.now().year)
    }
    try:
        {{crew_name}}().crew().train(n_iterations=int(sys.argv[1]), filename=sys.argv[2], inputs=inputs)
@@ -59,6 +60,7 @@ def test():
        "topic": "AI LLMs",
        "current_year": str(datetime.now().year)
    }
+    
    try:
        {{crew_name}}().crew().test(n_iterations=int(sys.argv[1]), eval_llm=sys.argv[2], inputs=inputs)

@@ -275,46 +275,51 @@ class Crew(BaseModel):

        return self

+    def _initialize_user_memory(self):
+        if (
+            self.memory_config
+            and "user_memory" in self.memory_config
+            and self.memory_config.get("provider") == "mem0"
+        ):  # Check for user_memory in config
+            user_memory_config = self.memory_config["user_memory"]
+            if isinstance(
+                user_memory_config, dict
+            ):  # Check if it's a configuration dict
+                self._user_memory = UserMemory(crew=self)
+            else:
+                raise TypeError("user_memory must be a configuration dictionary")
+
+    def _initialize_default_memories(self):
+        self._long_term_memory = self._long_term_memory or LongTermMemory()
+        self._short_term_memory = self._short_term_memory or ShortTermMemory(
+            crew=self,
+            embedder_config=self.embedder,
+        )
+        self._entity_memory = self.entity_memory or EntityMemory(
+            crew=self, embedder_config=self.embedder
+        )
+
    @model_validator(mode="after")
    def create_crew_memory(self) -> "Crew":
-        """Set private attributes."""
+        """Initialize private memory attributes."""
+        self._external_memory = (
+            # External memory doesn’t support a default value since it was designed to be managed entirely externally
+            self.external_memory.set_crew(self)
+            if self.external_memory
+            else None
+        )
+
+        self._long_term_memory = self.long_term_memory
+        self._short_term_memory = self.short_term_memory
+        self._entity_memory = self.entity_memory
+
+        # UserMemory is gonna to be deprecated in the future, but we have to initialize a default value for now
+        self._user_memory = None
+
        if self.memory:
-            self._long_term_memory = (
-                self.long_term_memory if self.long_term_memory else LongTermMemory()
-            )
-            self._short_term_memory = (
-                self.short_term_memory
-                if self.short_term_memory
-                else ShortTermMemory(
-                    crew=self,
-                    embedder_config=self.embedder,
-                )
-            )
-            self._entity_memory = (
-                self.entity_memory
-                if self.entity_memory
-                else EntityMemory(crew=self, embedder_config=self.embedder)
-            )
-            self._external_memory = (
-                # External memory doesn’t support a default value since it was designed to be managed entirely externally
-                self.external_memory.set_crew(self)
-                if self.external_memory
-                else None
-            )
-            if (
-                self.memory_config
-                and "user_memory" in self.memory_config
-                and self.memory_config.get("provider") == "mem0"
-            ):  # Check for user_memory in config
-                user_memory_config = self.memory_config["user_memory"]
-                if isinstance(
-                    user_memory_config, dict
-                ):  # Check if it's a configuration dict
-                    self._user_memory = UserMemory(crew=self)
-                else:
-                    raise TypeError("user_memory must be a configuration dictionary")
-            else:
-                self._user_memory = None  # No user memory if not in config
+            self._initialize_default_memories()
+            self._initialize_user_memory()
+
        return self

    @model_validator(mode="after")
@@ -1214,6 +1219,17 @@ class Crew(BaseModel):

        copied_data = self.model_dump(exclude=exclude)
        copied_data = {k: v for k, v in copied_data.items() if v is not None}
+        if self.short_term_memory:
+            copied_data["short_term_memory"] = self.short_term_memory.model_copy(deep=True)
+        if self.long_term_memory:
+            copied_data["long_term_memory"] = self.long_term_memory.model_copy(deep=True)
+        if self.entity_memory:
+            copied_data["entity_memory"] = self.entity_memory.model_copy(deep=True)
+        if self.external_memory:
+            copied_data["external_memory"] = self.external_memory.model_copy(deep=True)
+        if self.user_memory:
+            copied_data["user_memory"] = self.user_memory.model_copy(deep=True)
+

        copied_data.pop("agents", None)
        copied_data.pop("tasks", None)
@@ -1043,6 +1043,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
            import traceback

            traceback.print_exc()
+            raise

    def _log_flow_event(
        self, message: str, color: str = "yellow", level: str = "info"
@@ -47,11 +47,6 @@ from crewai.utilities.events.llm_events import (
    LLMCallStartedEvent,
    LLMCallType,
 )
-from crewai.utilities.events.tool_usage_events import (
-    ToolUsageErrorEvent,
-    ToolUsageFinishedEvent,
-    ToolUsageStartedEvent,
-)
 from crewai.utilities.llm_utils import create_llm
 from crewai.utilities.printer import Printer
 from crewai.utilities.token_counter_callback import TokenCalcHandler
@@ -155,6 +150,10 @@ class LiteAgent(BaseModel):
        default=[], description="Results of the tools used by the agent."
    )

+    # Reference of Agent
+    original_agent: Optional[BaseAgent] = Field(
+        default=None, description="Reference to the agent that created this LiteAgent"
+    )
    # Private Attributes
    _parsed_tools: List[CrewStructuredTool] = PrivateAttr(default_factory=list)
    _token_process: TokenProcess = PrivateAttr(default_factory=TokenProcess)
@@ -163,7 +162,7 @@ class LiteAgent(BaseModel):
    _messages: List[Dict[str, str]] = PrivateAttr(default_factory=list)
    _iterations: int = PrivateAttr(default=0)
    _printer: Printer = PrivateAttr(default_factory=Printer)
-
+    
    @model_validator(mode="after")
    def setup_llm(self):
        """Set up the LLM and other components after initialization."""
@@ -412,18 +411,6 @@ class LiteAgent(BaseModel):
                formatted_answer = process_llm_response(answer, self.use_stop_words)

                if isinstance(formatted_answer, AgentAction):
-                    # Emit tool usage started event
-                    crewai_event_bus.emit(
-                        self,
-                        event=ToolUsageStartedEvent(
-                            agent_key=self.key,
-                            agent_role=self.role,
-                            tool_name=formatted_answer.tool,
-                            tool_args=formatted_answer.tool_input,
-                            tool_class=formatted_answer.tool,
-                        ),
-                    )
-
                    try:
                        tool_result = execute_tool_and_check_finality(
                            agent_action=formatted_answer,
@@ -431,34 +418,9 @@ class LiteAgent(BaseModel):
                            i18n=self.i18n,
                            agent_key=self.key,
                            agent_role=self.role,
-                        )
-                        # Emit tool usage finished event
-                        crewai_event_bus.emit(
-                            self,
-                            event=ToolUsageFinishedEvent(
-                                agent_key=self.key,
-                                agent_role=self.role,
-                                tool_name=formatted_answer.tool,
-                                tool_args=formatted_answer.tool_input,
-                                tool_class=formatted_answer.tool,
-                                started_at=datetime.now(),
-                                finished_at=datetime.now(),
-                                output=tool_result.result,
-                            ),
+                            agent=self.original_agent,
                        )
                    except Exception as e:
-                        # Emit tool usage error event
-                        crewai_event_bus.emit(
-                            self,
-                            event=ToolUsageErrorEvent(
-                                agent_key=self.key,
-                                agent_role=self.role,
-                                tool_name=formatted_answer.tool,
-                                tool_args=formatted_answer.tool_input,
-                                tool_class=formatted_answer.tool,
-                                error=str(e),
-                            ),
-                        )
                        raise e

                    formatted_answer = handle_agent_action_core(
@@ -707,15 +707,6 @@ class LLM(BaseLLM):
                    function_name, lambda: None
                )  # Ensure fn is always a callable
                logging.error(f"Error executing function '{function_name}': {e}")
-                crewai_event_bus.emit(
-                    self,
-                    event=ToolExecutionErrorEvent(
-                        tool_name=function_name,
-                        tool_args=function_args,
-                        tool_class=fn,
-                        error=str(e),
-                    ),
-                )
                crewai_event_bus.emit(
                    self,
                    event=LLMCallFailedEvent(error=f"Tool execution error: {str(e)}"),
@@ -53,6 +53,10 @@ class ContextualMemory:
        Fetches recent relevant insights from STM related to the task's description and expected_output,
        formatted as bullet points.
        """
+
+        if self.stm is None:
+            return ""
+
        stm_results = self.stm.search(query)
        formatted_results = "\n".join(
            [
@@ -67,6 +71,10 @@ class ContextualMemory:
        Fetches historical data or insights from LTM that are relevant to the task's description and expected_output,
        formatted as bullet points.
        """
+
+        if self.ltm is None:
+            return ""
+
        ltm_results = self.ltm.search(task, latest_n=2)
        if not ltm_results:
            return None
@@ -86,6 +94,9 @@ class ContextualMemory:
        Fetches relevant entity information from Entity Memory related to the task's description and expected_output,
        formatted as bullet points.
        """
+        if self.em is None:
+            return ""
+
        em_results = self.em.search(query)
        formatted_results = "\n".join(
            [
@@ -1,4 +1,4 @@
-from typing import TYPE_CHECKING, Any, Dict, Optional, Self
+from typing import TYPE_CHECKING, Any, Dict, Optional

 from crewai.memory.external.external_memory_item import ExternalMemoryItem
 from crewai.memory.memory import Memory
@@ -52,7 +52,7 @@ class ExternalMemory(Memory):
    def reset(self) -> None:
        self.storage.reset()

-    def set_crew(self, crew: Any) -> Self:
+    def set_crew(self, crew: Any) -> "ExternalMemory":
        super().set_crew(crew)

        if not self.storage:
@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Optional, Self
+from typing import Any, Dict, List, Optional

 from pydantic import BaseModel

@@ -38,6 +38,6 @@ class Memory(BaseModel):
            query=query, limit=limit, score_threshold=score_threshold
        )

-    def set_crew(self, crew: Any) -> Self:
+    def set_crew(self, crew: Any) -> "Memory":
        self.crew = crew
        return self
@@ -48,7 +48,7 @@ class Mem0Storage(Storage):
                self.memory = MemoryClient(api_key=mem0_api_key)
        else:
            if mem0_local_config and len(mem0_local_config):
-                self.memory = Memory.from_config(config)
+                self.memory = Memory.from_config(mem0_local_config)
            else:
                self.memory = Memory()

@@ -1,3 +1,4 @@
+import asyncio
 import warnings
 from abc import ABC, abstractmethod
 from inspect import signature
@@ -65,7 +66,13 @@ class BaseTool(BaseModel, ABC):
        **kwargs: Any,
    ) -> Any:
        print(f"Using Tool: {self.name}")
-        return self._run(*args, **kwargs)
+        result = self._run(*args, **kwargs)
+
+        # If _run is async, we safely run it
+        if asyncio.iscoroutine(result):
+            return asyncio.run(result)
+
+        return result

    @abstractmethod
    def _run(
@@ -2,7 +2,6 @@ import ast
 import datetime
 import json
 import time
-from dataclasses import dataclass
 from difflib import SequenceMatcher
 from json import JSONDecodeError
 from textwrap import dedent
@@ -26,6 +25,7 @@ from crewai.utilities.events.tool_usage_events import (
    ToolSelectionErrorEvent,
    ToolUsageErrorEvent,
    ToolUsageFinishedEvent,
+    ToolUsageStartedEvent,
    ToolValidateInputErrorEvent,
 )

@@ -166,6 +166,21 @@ class ToolUsage:
                if self.task:
                    self.task.increment_tools_errors()

+        if self.agent:
+            event_data = {
+                "agent_key": self.agent.key,
+                "agent_role": self.agent.role,
+                "tool_name": self.action.tool,
+                "tool_args": self.action.tool_input,
+                "tool_class": self.action.tool,
+                "agent": self.agent,
+            }
+
+            if self.agent.fingerprint:
+                event_data.update(self.agent.fingerprint)
+
+            crewai_event_bus.emit(self,ToolUsageStartedEvent(**event_data))
+            
        started_at = time.time()
        from_cache = False
        result = None  # type: ignore
@@ -16,7 +16,6 @@ from crewai.tools.base_tool import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.tools.tool_types import ToolResult
 from crewai.utilities import I18N, Printer
-from crewai.utilities.events.tool_usage_events import ToolUsageStartedEvent
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
    LLMContextLengthExceededException,
 )
@@ -5,11 +5,6 @@ from crewai.security import Fingerprint
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.tools.tool_types import ToolResult
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
-from crewai.utilities.events import crewai_event_bus
-from crewai.utilities.events.tool_usage_events import (
-    ToolUsageErrorEvent,
-    ToolUsageStartedEvent,
-)
 from crewai.utilities.i18n import I18N


@@ -42,10 +37,8 @@ def execute_tool_and_check_finality(
        ToolResult containing the execution result and whether it should be treated as a final answer
    """
    try:
-        # Create tool name to tool map
        tool_name_to_tool_map = {tool.name: tool for tool in tools}

-        # Emit tool usage event if agent info is available
        if agent_key and agent_role and agent:
            fingerprint_context = fingerprint_context or {}
            if agent:
@@ -59,22 +52,6 @@ def execute_tool_and_check_finality(
                        except Exception as e:
                            raise ValueError(f"Failed to set fingerprint: {e}")

-            event_data = {
-                "agent_key": agent_key,
-                "agent_role": agent_role,
-                "tool_name": agent_action.tool,
-                "tool_args": agent_action.tool_input,
-                "tool_class": agent_action.tool,
-                "agent": agent,
-            }
-            event_data.update(fingerprint_context)
-            crewai_event_bus.emit(
-                agent,
-                event=ToolUsageStartedEvent(
-                    **event_data,
-                ),
-            )
-
        # Create tool usage instance
        tool_usage = ToolUsage(
            tools_handler=tools_handler,
@@ -110,17 +87,4 @@ def execute_tool_and_check_finality(
        return ToolResult(tool_result, False)

    except Exception as e:
-        # Emit error event if agent info is available
-        if agent_key and agent_role and agent:
-            crewai_event_bus.emit(
-                agent,
-                event=ToolUsageErrorEvent(
-                    agent_key=agent_key,
-                    agent_role=agent_role,
-                    tool_name=agent_action.tool,
-                    tool_args=agent_action.tool_input,
-                    tool_class=agent_action.tool,
-                    error=str(e),
-                ),
-            )
        raise e
@@ -1,112 +0,0 @@
-interactions:
- request:
-    body: '{"messages": [{"role": "user", "content": "Use the failing tool"}], "model":
-      "gpt-4o-mini", "stop": [], "tools": [{"type": "function", "function": {"name":
-      "failing_tool", "description": "This tool always fails.", "parameters": {"type":
-      "object", "properties": {"param": {"type": "string", "description": "A test
-      parameter"}}, "required": ["param"]}}}]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '353'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.8
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-B2P4zoJZuES7Aom8ugEq1modz5Vsl\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1739912761,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
-      \           \"id\": \"call_F6fJxISpMKUBIGV6dd2vjRNG\",\n            \"type\":
-      \"function\",\n            \"function\": {\n              \"name\": \"failing_tool\",\n
-      \             \"arguments\": \"{\\\"param\\\":\\\"test\\\"}\"\n            }\n
-      \         }\n        ],\n        \"refusal\": null\n      },\n      \"logprobs\":
-      null,\n      \"finish_reason\": \"tool_calls\"\n    }\n  ],\n  \"usage\": {\n
-      \   \"prompt_tokens\": 51,\n    \"completion_tokens\": 15,\n    \"total_tokens\":
-      66,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\":
-      0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
-      0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\":
-      0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\":
-      \"fp_00428b782a\"\n}\n"
-    headers:
-      CF-RAY:
-      - 9140fa827f38eb1e-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 18 Feb 2025 21:06:02 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=xbuu3IQpCMh.43ZrqL1TRMECOc6QldgHV0hzOX1GrWI-1739912762-1.0.1.1-t7iyq5xMioPrwfeaHLvPT9rwRPp7Q9A9uIm69icH9dPxRD4xMA3cWqb1aXj1_e2IyAEQQWFe1UWjlmJ22aHh3Q;
-        path=/; expires=Tue, 18-Feb-25 21:36:02 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=x9l.Rhja8_wXDN.j8qcEU1PvvEqAwZp4Fd3s_aj4qwM-1739912762161-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '861'
-      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:
-      - '149999978'
-      x-ratelimit-reset-requests:
-      - 2ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_8666ec3aa6677cb346ba00993556051d
-    http_version: HTTP/1.1
-    status_code: 200
-version: 1
@@ -0,0 +1,209 @@
+interactions:
+- request:
+    body: !!binary |
+      CuAMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkStwwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKdCAoQe1SuF2c2xWX4juAv74oXphII/LGj/b5w49QqDENyZXcgQ3JlYXRlZDABOcCZ
+      B6F1rTUYQRhzEqF1rTUYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIGM5N2I1ZmViNWQxYjY2YmI1OTAwNmFhYTAx
+      YTI5Y2Q2SjEKB2NyZXdfaWQSJgokMDU1YWZhNGQtNWU5MS00YWU1LTg4ZTQtMGQ3N2I2OTZiODJl
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
+      X2ZpbmdlcnByaW50EiYKJGI3NzY4MjJlLTU4YzItNDg5Ni05NmVhLTlmNDQzNjc4NThjNko7Chtj
+      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xMlQxNzo1MjozMS4zOTkzMTdK
+      0QIKC2NyZXdfYWdlbnRzEsECCr4CW3sia2V5IjogIjA3ZDk5YjYzMDQxMWQzNWZkOTA0N2E1MzJk
+      NTNkZGE3IiwgImlkIjogIjI5MmZlMjI4LTNlYzEtNDE4Zi05NzQzLTFkNTI3ZGY5M2QwYyIsICJy
+      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJt
+      YXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRv
+      LW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRp
+      b24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSv8B
+      CgpjcmV3X3Rhc2tzEvABCu0BW3sia2V5IjogIjYzOTk2NTE3ZjNmM2YxYzk0ZDZiYjYxN2FhMGIx
+      YzRmIiwgImlkIjogIjhlY2E1NTQzLTc3MDEtNDhjMy1hODM1LWI4YWE2YmE3YTMzZSIsICJhc3lu
+      Y19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUi
+      OiAiUmVzZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiMDdkOTliNjMwNDExZDM1ZmQ5MDQ3YTUzMmQ1
+      M2RkYTciLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQmqGVrPp33uFfE2WlsNm/
+      phIIx0mZ95NGSyIqDFRhc2sgQ3JlYXRlZDABObBlHqF1rTUYQbi3HqF1rTUYSi4KCGNyZXdfa2V5
+      EiIKIGM5N2I1ZmViNWQxYjY2YmI1OTAwNmFhYTAxYTI5Y2Q2SjEKB2NyZXdfaWQSJgokMDU1YWZh
+      NGQtNWU5MS00YWU1LTg4ZTQtMGQ3N2I2OTZiODJlSi4KCHRhc2tfa2V5EiIKIDYzOTk2NTE3ZjNm
+      M2YxYzk0ZDZiYjYxN2FhMGIxYzRmSjEKB3Rhc2tfaWQSJgokOGVjYTU1NDMtNzcwMS00OGMzLWE4
+      MzUtYjhhYTZiYTdhMzNlSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokYjc3NjgyMmUtNThjMi00ODk2
+      LTk2ZWEtOWY0NDM2Nzg1OGM2SjoKEHRhc2tfZmluZ2VycHJpbnQSJgokYTk5NjE4ZTYtODFhZC00
+      N2YyLWE4ZGEtOTc1NjkzN2YxYmIwSjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoy
+      MDI1LTA0LTEyVDE3OjUyOjMxLjM5ODIxNEo7ChFhZ2VudF9maW5nZXJwcmludBImCiRlZjkxZGYx
+      NS0zNmNiLTQ0MDQtOWFkMi05MmM1OTQ1NGU2ZTZ6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1635'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.31.1
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Sat, 12 Apr 2025 20:52:35 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
+      an expert in research and you love to learn new things.\nYour personal goal
+      is: You research about math.\nTo give my best complete final answer to the task
+      respond using the exact following format:\n\nThought: I now can give a great
+      answer\nFinal Answer: Your final answer must be the great and the most complete
+      as possible, it must be outcome described.\n\nI MUST use these formats, my job
+      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Research a topic
+      to teach a kid aged 6 about math.\n\nThis is the expected criteria for your
+      final answer: A topic, explanation, angle, and examples.\nyou MUST return the
+      actual complete content as the final answer, not a summary.\n\n# Useful context:
+      \n<MagicMock name=''build_context_for_task()'' id=''13586043616''>\n\nBegin!
+      This is VERY important to you, use the tools available and give your best Final
+      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1031'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BLc7zvaXoFAArOIDK9TrMtdq8kKY0\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744491151,\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**Topic: Introduction to Addition with Fun Objects**\\n\\n**Explanation:**
+      \ \\nAt its core, addition is all about combining two or more groups of things
+      to find out how many there are in total. We can think of addition as a way to
+      bring friends together! Imagine if you have some apples and your friend brings
+      some more apples; together, you want to find out how many apples there are altogether.
+      This is the foundation of addition, and it can be made fun and engaging for
+      a 6-year-old.\\n\\n**Angle:**  \\nTo make this relatable and enjoyable, we can
+      use everyday objects that kids love, such as toys, fruits, or even drawings.
+      We can create little stories or scenarios that involve addition, turning it
+      into a game where they get to count and add things together. By using real items,
+      children can see and feel what addition means, making it easier to grasp the
+      concept.\\n\\n**Examples:**  \\n1. **Using Fruits:**  \\n   Let's say you have
+      3 oranges. You can say, \\\"I have 3 oranges.\\\" Then, if your friend brings
+      you 2 more oranges, you can introduce the addition by saying, \\\"Now, how many
+      do we have all together?\\\"  \\n   - So you would show it as: 3 (oranges you
+      have) + 2 (oranges your friend brought) = ?  \\n   To find the answer, you can
+      count all the oranges together: 1, 2, 3 (your oranges) and 4, 5 (your friend's
+      oranges).  \\n   - The answer is 5 oranges in total!\\n\\n2. **Using Toys:**
+      \ \\n   If a child has 4 toy cars and finds 3 more under the couch, we can ask,
+      \\\"How many cars do you have now?\\\"  \\n   - Write it down: 4 (toy cars)
+      + 3 (found cars) = ?  \\n   Then, count the toy cars together: 1, 2, 3, 4 (original
+      cars), 5, 6, 7.  \\n   - The answer is 7 toy cars!\\n\\n3. **Story Scenario:**
+      \ \\n   Create an engaging story: \\\"Once upon a time, there were 2 friendly
+      puppies. One day, 3 more puppies came to play. How many puppies are playing
+      now?\\\"  \\n   - Present it as: 2 (original puppies) + 3 (new puppies) = ?
+      \ \\n   Count the puppies: 1, 2 (the first two) and then 3, 4, 5 (the new ones).
+      \ \\n   - The answer is 5 puppies playing!\\n\\nBy presenting addition through
+      fun scenarios and interactive counting, a 6-year-old can learn and understand
+      addition while enjoying the process. They can even use crayons to draw the items
+      or fruit to count in a playful, hands-on approach. This makes math not just
+      a subject, but also a delightful adventure!\",\n        \"refusal\": null,\n
+      \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 206,\n    \"completion_tokens\":
+      609,\n    \"total_tokens\": 815,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_44added55e\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92f59ba1fa19572a-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 12 Apr 2025 20:52:44 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=C7ejNhC7vNTBO9VtBqzN_ce__mP2Dz8noDo2lIcNBn0-1744491164-1.0.1.1-kQgWk4d54JIGxg_yCJ.7uV9HkU8JXrhpfIth0WHDdqf9ESzAsQyDu0xKVLYnga.xswBnm5kePpuFCcnIqGKgyag31cEyuiFFf6JHTvQcvWI;
+        path=/; expires=Sat, 12-Apr-25 21:22:44 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=QuvcyYK0MZfY9dNclglrzesXcplWfoZN.rd4J57.xtY-1744491164641-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '12806'
+      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:
+      - '149999777'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_49f3c203229149ce08c0813ac4071355
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1
@@ -0,0 +1,335 @@
+interactions:
+- request:
+    body: !!binary |
+      CuAMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkStwwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKdCAoQ7xzvcCOT4PrOc8md0oeT3RIIOq+vIsGQam8qDENyZXcgQ3JlYXRlZDABOejV
+      5rl4rTUYQdAs7rl4rTUYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIGM5N2I1ZmViNWQxYjY2YmI1OTAwNmFhYTAx
+      YTI5Y2Q2SjEKB2NyZXdfaWQSJgokNzI2ZTU0NWEtNGEzZC00NzFiLWJiMmQtODM3ZGY4OGQ3ZWY5
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
+      X2ZpbmdlcnByaW50EiYKJGVhYWVhMmQxLTc4Y2EtNDk2Mi05MmI2LTA5Y2QyMzY1ZmZiMEo7Chtj
+      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xMlQxNzo1Mjo0NC43MDE3MjdK
+      0QIKC2NyZXdfYWdlbnRzEsECCr4CW3sia2V5IjogIjA3ZDk5YjYzMDQxMWQzNWZkOTA0N2E1MzJk
+      NTNkZGE3IiwgImlkIjogIjcwMjE0NzVhLTNlMzAtNGYzNS1hMzQxLTA2NjBlYzAwYTMyZiIsICJy
+      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJt
+      YXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRv
+      LW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRp
+      b24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSv8B
+      CgpjcmV3X3Rhc2tzEvABCu0BW3sia2V5IjogIjYzOTk2NTE3ZjNmM2YxYzk0ZDZiYjYxN2FhMGIx
+      YzRmIiwgImlkIjogIjQ0MTQ4YzM4LWI3NTMtNDIzNy1hOTFhLTI0MDllMzExNTFlYiIsICJhc3lu
+      Y19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUi
+      OiAiUmVzZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiMDdkOTliNjMwNDExZDM1ZmQ5MDQ3YTUzMmQ1
+      M2RkYTciLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQxWHt0ARtypIweXgPS3Mq
+      CBIIBl4bQnc1/j8qDFRhc2sgQ3JlYXRlZDABOQBs97l4rTUYQfDB97l4rTUYSi4KCGNyZXdfa2V5
+      EiIKIGM5N2I1ZmViNWQxYjY2YmI1OTAwNmFhYTAxYTI5Y2Q2SjEKB2NyZXdfaWQSJgokNzI2ZTU0
+      NWEtNGEzZC00NzFiLWJiMmQtODM3ZGY4OGQ3ZWY5Si4KCHRhc2tfa2V5EiIKIDYzOTk2NTE3ZjNm
+      M2YxYzk0ZDZiYjYxN2FhMGIxYzRmSjEKB3Rhc2tfaWQSJgokNDQxNDhjMzgtYjc1My00MjM3LWE5
+      MWEtMjQwOWUzMTE1MWViSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokZWFhZWEyZDEtNzhjYS00OTYy
+      LTkyYjYtMDljZDIzNjVmZmIwSjoKEHRhc2tfZmluZ2VycHJpbnQSJgokMzA5Y2M3NDgtMzliMS00
+      NzMyLWFkOWYtNjI4OGJiOTVkZTU4SjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoy
+      MDI1LTA0LTEyVDE3OjUyOjQ0LjU5ODAzNEo7ChFhZ2VudF9maW5nZXJwcmludBImCiQyMDA1ZWFj
+      Zi03Mzk4LTRiZjEtYjQxNS01NWZkZjE1MTg5ZDF6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1635'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.31.1
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Sat, 12 Apr 2025 20:52:45 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
+      an expert in research and you love to learn new things.\nYour personal goal
+      is: You research about math.\nTo give my best complete final answer to the task
+      respond using the exact following format:\n\nThought: I now can give a great
+      answer\nFinal Answer: Your final answer must be the great and the most complete
+      as possible, it must be outcome described.\n\nI MUST use these formats, my job
+      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Research a topic
+      to teach a kid aged 6 about math.\n\nThis is the expected criteria for your
+      final answer: A topic, explanation, angle, and examples.\nyou MUST return the
+      actual complete content as the final answer, not a summary.\n\n# Useful context:
+      \n<MagicMock name=''build_context_for_task()'' id=''6104248928''>\n\nBegin!
+      This is VERY important to you, use the tools available and give your best Final
+      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1030'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=C7ejNhC7vNTBO9VtBqzN_ce__mP2Dz8noDo2lIcNBn0-1744491164-1.0.1.1-kQgWk4d54JIGxg_yCJ.7uV9HkU8JXrhpfIth0WHDdqf9ESzAsQyDu0xKVLYnga.xswBnm5kePpuFCcnIqGKgyag31cEyuiFFf6JHTvQcvWI;
+        _cfuvid=QuvcyYK0MZfY9dNclglrzesXcplWfoZN.rd4J57.xtY-1744491164641-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BLc8DAj1Tept22jJPnWaYga9UPHGF\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744491165,\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**Topic: Introducing Basic Addition**\\n\\n**Explanation:**  \\nAddition
+      is one of the first fundamental concepts that children learn in math. It involves
+      combining two or more groups of objects or numbers to find a total. Teaching
+      addition helps kids understand how to solve everyday problems and builds the
+      foundation for more advanced math concepts later on.\\n\\n**Angle:**  \\nTo
+      make learning addition fun and engaging for a 6-year-old, we can use colorful
+      visuals and interactive methods. A playful approach, using everyday objects
+      they can relate to, will capture their attention and promote better understanding.\\n\\n**Examples:**\\n\\n1.
+      **Using Objects:**  \\n   Gather small items like toys, blocks, or fruits. For
+      instance, take 3 apples and add 2 more apples. Lay them out together and count
+      them:\\n   - Place 3 apples on a table.\\n   - Ask, \\\"If I add 2 more apples,
+      how many do we have now?\\\"\\n   - Count all the apples together to show that
+      3 + 2 = 5.\\n\\n2. **Story Problems:**  \\n   Create a simple story that involves
+      addition. For example:\\n   - \\\"You have 4 red balloons, and your friend gives
+      you 2 blue balloons. How many balloons do you have in total?\\\"\\n   - Help
+      them visualize it by drawing balloons and counting them.\\n\\n3. **Interactive
+      Games:**  \\n   Utilize fun games to practice addition. A game like \u201CAddition
+      Bingo\u201D can be exciting:\\n   - Create bingo cards with addition problems
+      (like 1 + 2, 3 + 1) in each square.\\n   - Call out the answers, and when a
+      child has the problem that matches the answer, they can cover that square.\\n\\n4.
+      **Visual Aids:**  \\n   Use a number line to show addition. Draw a number line
+      from 0 to 10.\\n   - Start at 3, and count 2 more jumps forward to reach 5,
+      explaining what happens when you add numbers on the number line.\\n\\n5. **Songs
+      and Rhymes:**  \\n   Incorporate catchy songs or rhymes that involve counting
+      and adding. For example, \u201CFive Little Ducks\u201D can be a fun way to introduce
+      subtraction in the context of counting forward.\\n\\nBy using these interactive
+      methods, children can grasp the concept of addition easily and enjoyably. Allowing
+      kids to make connections with real-life examples will nurture their love for
+      math and pave the way for future learning.\",\n        \"refusal\": null,\n
+      \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 206,\n    \"completion_tokens\":
+      504,\n    \"total_tokens\": 710,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_44added55e\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92f59bf4a822572a-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 12 Apr 2025 20:52:57 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '12719'
+      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:
+      - '149999777'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_82f6b628956f2f524b5a813c2248a92b
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"input": ["I now can give a great answer.   Final Answer:   **Topic: Introducing
+      Basic Addition**  **Explanation:**   Addition is one of the first fundamental
+      concepts that children learn in math. It involves combining two or more groups
+      of objects or numbers to find a total. Teaching addition helps kids understand
+      how to solve everyday problems and builds the foundation for more advanced math
+      concepts later on.  **Angle:**   To make learning addition fun and engaging
+      for a 6-year-old, we can use colorful visuals and interactive methods. A playful
+      approach, using everyday objects they can relate to, will capture their attention
+      and promote better understanding.  **Examples:**  1. **Using Objects:**      Gather
+      small items like toys, blocks, or fruits. For instance, take 3 apples and add
+      2 more apples. Lay them out together and count them:    - Place 3 apples on
+      a table.    - Ask, \"If I add 2 more apples, how many do we have now?\"    -
+      Count all the apples together to show that 3 + 2 = 5.  2. **Story Problems:**      Create
+      a simple story that involves addition. For example:    - \"You have 4 red balloons,
+      and your friend gives you 2 blue balloons. How many balloons do you have in
+      total?\"    - Help them visualize it by drawing balloons and counting them.  3.
+      **Interactive Games:**      Utilize fun games to practice addition. A game like
+      \u201cAddition Bingo\u201d can be exciting:    - Create bingo cards with addition
+      problems (like 1 + 2, 3 + 1) in each square.    - Call out the answers, and
+      when a child has the problem that matches the answer, they can cover that square.  4.
+      **Visual Aids:**      Use a number line to show addition. Draw a number line
+      from 0 to 10.    - Start at 3, and count 2 more jumps forward to reach 5, explaining
+      what happens when you add numbers on the number line.  5. **Songs and Rhymes:**      Incorporate
+      catchy songs or rhymes that involve counting and adding. For example, \u201cFive
+      Little Ducks\u201d can be a fun way to introduce subtraction in the context
+      of counting forward.  By using these interactive methods, children can grasp
+      the concept of addition easily and enjoyably. Allowing kids to make connections
+      with real-life examples will nurture their love for math and pave the way for
+      future learning."], "model": "text-embedding-3-small", "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2340'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
+      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
+      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
+      514,\n    \"total_tokens\": 514\n  }\n}\n"
+    headers:
+      CF-RAY:
+      - 92f59c45fe8a01a1-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 12 Apr 2025 20:52:58 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=.E5frVsbnouTvYCdMdv6xTsbxIKa0cGfieFpUdzLyFw-1744491178-1.0.1.1-9L_mO4kTLYQcsyPJH8VW8mKZaKxtUNmSQh1M3azRg6otw__XJkbU7PY2qLDoOoikow.Sk_XPc2STfYjPm9pY_m_ZE4j21.j1YLWFBrLRNY4;
+        path=/; expires=Sat, 12-Apr-25 21:22:58 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=pStEaD_yX5_0Hi8lDwa3XkSIXv1peylcsq05XdbvMg8-1744491178771-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '85'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-cbdb5c968-skgz8
+      x-envoy-upstream-service-time:
+      - '71'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999439'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 3ms
+      x-request-id:
+      - req_0dcb8cc2b2d67c7dbe8569da90cf498e
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1
@@ -0,0 +1,205 @@
+interactions:
+- request:
+    body: !!binary |
+      CuAMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkStwwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKdCAoQE1JYPHUcNy20EEB8E7lQKRIIeom6mAik9I0qDENyZXcgQ3JlYXRlZDABOdhP
+      ANFPrzUYQWCwCNFPrzUYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIGM5N2I1ZmViNWQxYjY2YmI1OTAwNmFhYTAx
+      YTI5Y2Q2SjEKB2NyZXdfaWQSJgokMjNmZDllZTktMWRiZC00M2FjLTlhZGYtNTQ5YWFhZTNkMTNj
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
+      X2ZpbmdlcnByaW50EiYKJDk2M2UyNDA4LTI3MzktNGU3ZS04ZTAzLTIxOGUzZjhmMTFhZEo7Chtj
+      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xMlQxODoyNjoyOC4wMTg1MzVK
+      0QIKC2NyZXdfYWdlbnRzEsECCr4CW3sia2V5IjogIjA3ZDk5YjYzMDQxMWQzNWZkOTA0N2E1MzJk
+      NTNkZGE3IiwgImlkIjogIjA3ZWIyOWYzLWE2OWQtNGQ1MC1iZGJiLTAwNjEzN2UzYjU4MiIsICJy
+      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJt
+      YXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRv
+      LW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRp
+      b24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSv8B
+      CgpjcmV3X3Rhc2tzEvABCu0BW3sia2V5IjogIjYzOTk2NTE3ZjNmM2YxYzk0ZDZiYjYxN2FhMGIx
+      YzRmIiwgImlkIjogImUwOWIzMzg1LThmNTAtNDIxYy1hYzE0LTdhZDU5NTU4YmY4NiIsICJhc3lu
+      Y19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUi
+      OiAiUmVzZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiMDdkOTliNjMwNDExZDM1ZmQ5MDQ3YTUzMmQ1
+      M2RkYTciLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQ/KSXqXcsLoGmHCaEWYIa
+      9xII/Ucae2PMp18qDFRhc2sgQ3JlYXRlZDABObAfF9FPrzUYQeCUF9FPrzUYSi4KCGNyZXdfa2V5
+      EiIKIGM5N2I1ZmViNWQxYjY2YmI1OTAwNmFhYTAxYTI5Y2Q2SjEKB2NyZXdfaWQSJgokMjNmZDll
+      ZTktMWRiZC00M2FjLTlhZGYtNTQ5YWFhZTNkMTNjSi4KCHRhc2tfa2V5EiIKIDYzOTk2NTE3ZjNm
+      M2YxYzk0ZDZiYjYxN2FhMGIxYzRmSjEKB3Rhc2tfaWQSJgokZTA5YjMzODUtOGY1MC00MjFjLWFj
+      MTQtN2FkNTk1NThiZjg2SjoKEGNyZXdfZmluZ2VycHJpbnQSJgokOTYzZTI0MDgtMjczOS00ZTdl
+      LThlMDMtMjE4ZTNmOGYxMWFkSjoKEHRhc2tfZmluZ2VycHJpbnQSJgokN2FhMTE0NDAtYjNkYi00
+      Y2VmLTgzYjUtNTk3ZTMwMTIxZGZhSjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoy
+      MDI1LTA0LTEyVDE4OjI2OjI4LjAxNzMyNEo7ChFhZ2VudF9maW5nZXJwcmludBImCiQ0MDczMjdk
+      NC1hMzRjLTQyNTUtYWIxYy1iM2I1OTNiMmM4MTJ6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1635'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.31.1
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Sat, 12 Apr 2025 21:26:32 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
+      an expert in research and you love to learn new things.\nYour personal goal
+      is: You research about math.\nTo give my best complete final answer to the task
+      respond using the exact following format:\n\nThought: I now can give a great
+      answer\nFinal Answer: Your final answer must be the great and the most complete
+      as possible, it must be outcome described.\n\nI MUST use these formats, my job
+      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Research a topic
+      to teach a kid aged 6 about math.\n\nThis is the expected criteria for your
+      final answer: A topic, explanation, angle, and examples.\nyou MUST return the
+      actual complete content as the final answer, not a summary.\n\nBegin! This is
+      VERY important to you, use the tools available and give your best Final Answer,
+      your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '947'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BLceqFO97kLaTEPUSKGHkGlckpxLe\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744493188,\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**Topic:** Introduction to Addition\\n\\n**Explanation:**  \\nAddition
+      is a fundamental concept in math that means putting together two or more numbers
+      to find out how many there are in total. When we add, we combine quantities
+      to see the total amount we have. The symbol for addition is \\\"+\\\". \\n\\nLet's
+      break it down so it's easy to understand. If you have a small group of apples
+      and then you get more apples, to find out how many apples you have altogether,
+      you add them up! \\n\\n**Angle:**  \\nTo teach this concept to a 6-year-old,
+      we can use tangible objects they can relate to, such as fruits, toys, or stickers.
+      Kids learn best through play and visual representation, so using real-life examples
+      will make the concept of addition exciting and engaging!\\n\\n**Examples:**
+      \ \\n1. **Using Fruits:** \\n   - Start with 2 apples. \\n\\n     \U0001F34F\U0001F34F
+      (2 apples)\\n\\n   - Then, you receive 3 more apples. \\n\\n     \U0001F34F\U0001F34F\U0001F34F
+      (3 apples)\\n\\n   - To find out how many apples you have now, we add them together:
+      \\n\\n     2 + 3 = 5 \\n\\n   - Show them the total by counting all the apples
+      together: \\n\\n     \U0001F34F\U0001F34F\U0001F34F\U0001F34F\U0001F34F (5 apples)\\n\\n2.
+      **Using Toys:** \\n   - Let\u2019s say there are 4 toy cars. \\n\\n     \U0001F697\U0001F697\U0001F697\U0001F697
+      (4 toy cars)\\n\\n   - If you get 2 more toy cars. \\n\\n     \U0001F697\U0001F697
+      (2 toy cars)\\n\\n   - How many do we have in total? \\n\\n     4 + 2 = 6 \\n\\n
+      \  - Count them all together: \\n\\n     \U0001F697\U0001F697\U0001F697\U0001F697\U0001F697\U0001F697
+      (6 toy cars)\\n\\n3. **Using Stickers:**  \\n   - You have 5 stickers. \\n\\n
+      \    \U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F (5 stickers)\\n\\n   -
+      Your friend gives you 4 more stickers. \\n\\n     \U0001F31F\U0001F31F\U0001F31F\U0001F31F
+      (4 stickers)\\n\\n   - Now, let\u2019s see how many stickers you have in total:
+      \\n\\n     5 + 4 = 9 \\n\\n   - Count them together: \\n\\n     \U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F
+      (9 stickers)\\n\\n**Conclusion:**  \\nTry to make addition fun! Use snacks or
+      play time to practice addition. Ask questions during snack time, such as \u201CIf
+      you eat one of your 5 cookies, how many will you have left?\u201D This approach
+      makes learning relatable and enjoyable, enhancing their understanding of math
+      in everyday situations. Happy adding!\",\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 182,\n    \"completion_tokens\":
+      561,\n    \"total_tokens\": 743,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_44added55e\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92f5cd5a19257e0f-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 12 Apr 2025 21:26:36 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=RJADJOyAKqFS8232yM1dbM71E3ODRyiAty_s9rGvM0Y-1744493196-1.0.1.1-f4yxtdxM2DD78r7TOvv1J75SF6jkKDecDiDNH3cGysXRR3R.QycZfAzjKzWFkncqaQY4jeqGFYZlVR06qIdq2Gw178QxYpOC6MrJT1eqduw;
+        path=/; expires=Sat, 12-Apr-25 21:56:36 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=l0OvqELD24_KHHDhiAwih_bsqFrop1327mHak9Y_Ovk-1744493196966-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '8640'
+      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:
+      - '149999797'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_dda2c2217b856a9012403aeb7378a9e2
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1
@@ -3,6 +3,7 @@
 import hashlib
 import json
 import os
+import tempfile
 from concurrent.futures import Future
 from unittest import mock
 from unittest.mock import MagicMock, patch
@@ -19,6 +20,8 @@ from crewai.crews.crew_output import CrewOutput
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.llm import LLM
 from crewai.memory.contextual.contextual_memory import ContextualMemory
+from crewai.memory.long_term.long_term_memory import LongTermMemory
+from crewai.memory.short_term.short_term_memory import ShortTermMemory
 from crewai.process import Process
 from crewai.task import Task
 from crewai.tasks.conditional_task import ConditionalTask
@@ -2405,6 +2408,136 @@ def test_using_contextual_memory():
        contextual_mem.assert_called_once()


+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_using_contextual_memory_with_long_term_memory():
+    from unittest.mock import patch
+
+    math_researcher = Agent(
+        role="Researcher",
+        goal="You research about math.",
+        backstory="You're an expert in research and you love to learn new things.",
+        allow_delegation=False,
+    )
+
+    task1 = Task(
+        description="Research a topic to teach a kid aged 6 about math.",
+        expected_output="A topic, explanation, angle, and examples.",
+        agent=math_researcher,
+    )
+
+    crew = Crew(
+        agents=[math_researcher],
+        tasks=[task1],
+        long_term_memory=LongTermMemory(),
+    )
+
+    with patch.object(ContextualMemory, "build_context_for_task") as contextual_mem:
+        crew.kickoff()
+        contextual_mem.assert_called_once()
+        assert crew.memory is False
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_warning_long_term_memory_without_entity_memory():
+    from unittest.mock import patch
+
+    math_researcher = Agent(
+        role="Researcher",
+        goal="You research about math.",
+        backstory="You're an expert in research and you love to learn new things.",
+        allow_delegation=False,
+    )
+
+    task1 = Task(
+        description="Research a topic to teach a kid aged 6 about math.",
+        expected_output="A topic, explanation, angle, and examples.",
+        agent=math_researcher,
+    )
+
+    crew = Crew(
+        agents=[math_researcher],
+        tasks=[task1],
+        long_term_memory=LongTermMemory(),
+    )
+
+    with (
+        patch("crewai.utilities.printer.Printer.print") as mock_print,
+        patch(
+            "crewai.memory.long_term.long_term_memory.LongTermMemory.save"
+        ) as save_memory,
+    ):
+        crew.kickoff()
+        mock_print.assert_called_with(
+            content="Long term memory is enabled, but entity memory is not enabled. Please configure entity memory or set memory=True to automatically enable it.",
+            color="bold_yellow",
+        )
+        save_memory.assert_not_called()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_long_term_memory_with_memory_flag():
+    from unittest.mock import patch
+
+    math_researcher = Agent(
+        role="Researcher",
+        goal="You research about math.",
+        backstory="You're an expert in research and you love to learn new things.",
+        allow_delegation=False,
+    )
+
+    task1 = Task(
+        description="Research a topic to teach a kid aged 6 about math.",
+        expected_output="A topic, explanation, angle, and examples.",
+        agent=math_researcher,
+    )
+
+    crew = Crew(
+        agents=[math_researcher],
+        tasks=[task1],
+        memory=True,
+        long_term_memory=LongTermMemory(),
+    )
+
+    with (
+        patch("crewai.utilities.printer.Printer.print") as mock_print,
+        patch(
+            "crewai.memory.long_term.long_term_memory.LongTermMemory.save"
+        ) as save_memory,
+    ):
+        crew.kickoff()
+        mock_print.assert_not_called()
+        save_memory.assert_called_once()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_using_contextual_memory_with_short_term_memory():
+    from unittest.mock import patch
+
+    math_researcher = Agent(
+        role="Researcher",
+        goal="You research about math.",
+        backstory="You're an expert in research and you love to learn new things.",
+        allow_delegation=False,
+    )
+
+    task1 = Task(
+        description="Research a topic to teach a kid aged 6 about math.",
+        expected_output="A topic, explanation, angle, and examples.",
+        agent=math_researcher,
+    )
+
+    crew = Crew(
+        agents=[math_researcher],
+        tasks=[task1],
+        short_term_memory=ShortTermMemory(),
+    )
+
+    with patch.object(ContextualMemory, "build_context_for_task") as contextual_mem:
+        crew.kickoff()
+        contextual_mem.assert_called_once()
+        assert crew.memory is False
+
+
@pytest.mark.vcr(filter_headers=["authorization"])
 def test_disabled_memory_using_contextual_memory():
    from unittest.mock import patch
@@ -4116,6 +4249,54 @@ def test_crew_kickoff_for_each_works_with_manager_agent_copy():
    assert crew_copy.manager_agent.id != crew.manager_agent.id
    assert crew_copy.manager_agent.role == crew.manager_agent.role
    assert crew_copy.manager_agent.goal == crew.manager_agent.goal
-    assert crew_copy.manager_agent.backstory == crew.manager_agent.backstory
-    assert isinstance(crew_copy.manager_agent.agent_executor, CrewAgentExecutor)
-    assert isinstance(crew_copy.manager_agent.cache_handler, CacheHandler)
+
+def test_crew_copy_with_memory():
+    """Test that copying a crew with memory enabled does not raise validation errors and copies memory correctly."""
+    agent = Agent(role="Test Agent", goal="Test Goal", backstory="Test Backstory")
+    task = Task(description="Test Task", expected_output="Test Output", agent=agent)
+    crew = Crew(agents=[agent], tasks=[task], memory=True)
+
+    original_short_term_id = id(crew._short_term_memory) if crew._short_term_memory else None
+    original_long_term_id = id(crew._long_term_memory) if crew._long_term_memory else None
+    original_entity_id = id(crew._entity_memory) if crew._entity_memory else None
+    original_external_id = id(crew._external_memory) if crew._external_memory else None
+    original_user_id = id(crew._user_memory) if crew._user_memory else None
+
+
+    try:
+        crew_copy = crew.copy()
+
+        assert hasattr(crew_copy, "_short_term_memory"), "Copied crew should have _short_term_memory"
+        assert crew_copy._short_term_memory is not None, "Copied _short_term_memory should not be None"
+        assert id(crew_copy._short_term_memory) != original_short_term_id, "Copied _short_term_memory should be a new object"
+
+        assert hasattr(crew_copy, "_long_term_memory"), "Copied crew should have _long_term_memory"
+        assert crew_copy._long_term_memory is not None, "Copied _long_term_memory should not be None"
+        assert id(crew_copy._long_term_memory) != original_long_term_id, "Copied _long_term_memory should be a new object"
+
+        assert hasattr(crew_copy, "_entity_memory"), "Copied crew should have _entity_memory"
+        assert crew_copy._entity_memory is not None, "Copied _entity_memory should not be None"
+        assert id(crew_copy._entity_memory) != original_entity_id, "Copied _entity_memory should be a new object"
+
+        if original_external_id:
+             assert hasattr(crew_copy, "_external_memory"), "Copied crew should have _external_memory"
+             assert crew_copy._external_memory is not None, "Copied _external_memory should not be None"
+             assert id(crew_copy._external_memory) != original_external_id, "Copied _external_memory should be a new object"
+        else:
+             assert not hasattr(crew_copy, "_external_memory") or crew_copy._external_memory is None, "Copied _external_memory should be None if not originally present"
+
+        if original_user_id:
+             assert hasattr(crew_copy, "_user_memory"), "Copied crew should have _user_memory"
+             assert crew_copy._user_memory is not None, "Copied _user_memory should not be None"
+             assert id(crew_copy._user_memory) != original_user_id, "Copied _user_memory should be a new object"
+        else:
+             assert not hasattr(crew_copy, "_user_memory") or crew_copy._user_memory is None, "Copied _user_memory should be None if not originally present"
+
+
+    except pydantic_core.ValidationError as e:
+         if "Input should be an instance of" in str(e) and ("Memory" in str(e)):
+              pytest.fail(f"Copying with memory raised Pydantic ValidationError, likely due to incorrect memory copy: {e}")
+         else:
+              raise e # Re-raise other validation errors
+    except Exception as e:
+        pytest.fail(f"Copying crew raised an unexpected exception: {e}")
@@ -395,51 +395,3 @@ def test_deepseek_r1_with_open_router():
    result = llm.call("What is the capital of France?")
    assert isinstance(result, str)
    assert "Paris" in result
-
-
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_tool_execution_error_event():
-    llm = LLM(model="gpt-4o-mini")
-
-    def failing_tool(param: str) -> str:
-        """This tool always fails."""
-        raise Exception("Tool execution failed!")
-
-    tool_schema = {
-        "type": "function",
-        "function": {
-            "name": "failing_tool",
-            "description": "This tool always fails.",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "param": {"type": "string", "description": "A test parameter"}
-                },
-                "required": ["param"],
-            },
-        },
-    }
-
-    received_events = []
-
-    @crewai_event_bus.on(ToolExecutionErrorEvent)
-    def event_handler(source, event):
-        received_events.append(event)
-
-    available_functions = {"failing_tool": failing_tool}
-
-    messages = [{"role": "user", "content": "Use the failing tool"}]
-
-    llm.call(
-        messages,
-        tools=[tool_schema],
-        available_functions=available_functions,
-    )
-
-    assert len(received_events) == 1
-    event = received_events[0]
-    assert isinstance(event, ToolExecutionErrorEvent)
-    assert event.tool_name == "failing_tool"
-    assert event.tool_args == {"param": "test"}
-    assert event.tool_class == failing_tool
-    assert "Tool execution failed!" in event.error
@@ -1,650 +0,0 @@
-interactions:
- request:
-    body: '{"input": ["Perform a search on specific topics."], "model": "text-embedding-3-small",
-      "encoding_format": "base64"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '115'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.68.2
-      x-stainless-read-timeout:
-      - '600'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
-      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
-      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
-      7,\n    \"total_tokens\": 7\n  }\n}\n"
-    headers:
-      CF-RAY:
-      - 929abaf15acd7df9-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 01 Apr 2025 20:10:30 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=JcjzeNadYektCKxz.qAt_Iu9W82BXw8zXu9IzahTzL4-1743538230-1.0.1.1-zltiq2Kl.WZlrShHKUBPQrPv0dX2jM_mrIEDEv58Na6s2GSfEgAQbiffMTPHtElo6HoDyJX5g8sjIacSnLyZSswTCjtL4C75K1IK09Or9mo;
-        path=/; expires=Tue, 01-Apr-25 20:40:30 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=cqy59cJ9.MxM3ogPzubxDJvueA5vj1ZPlpD5x5e3hdA-1743538230508-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-allow-origin:
-      - '*'
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-model:
-      - text-embedding-3-small
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '66'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      via:
-      - envoy-router-7c6fb6444f-cxmk8
-      x-envoy-upstream-service-time:
-      - '32'
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '10000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '9999991'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_8ec9a4a21a4dda1d560d7002327e9bf5
-    http_version: HTTP/1.1
-    status_code: 200
- request:
-    body: '{"input": ["Perform a search on specific topics."], "model": "text-embedding-3-small",
-      "encoding_format": "base64"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '115'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.68.2
-      x-stainless-read-timeout:
-      - '600'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
-      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
-      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
-      7,\n    \"total_tokens\": 7\n  }\n}\n"
-    headers:
-      CF-RAY:
-      - 929abaf509b47deb-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 01 Apr 2025 20:10:30 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=xm0wOFZcQAyJrMSiOz3MZOr_g5T3TyUhPvPR4mQpdeA-1743538230-1.0.1.1-kOKoGCRupMuPeKOGl9Uu0Gwt07QZKWJwMBg7JzariAfNaVs.AnqEQ__712GZsReNyqiOzUE0Qeykvt11gEEyFHX9VyyvNJcb6uHADLpyLLI;
-        path=/; expires=Tue, 01-Apr-25 20:40:30 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=.x6X1bgu02i.2_qawj3TiVXv0.G8azhdA2QeTcj83tY-1743538230900-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-allow-origin:
-      - '*'
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-model:
-      - text-embedding-3-small
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '108'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      via:
-      - envoy-router-8486ff7cdd-dskkc
-      x-envoy-upstream-service-time:
-      - '93'
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '10000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '9999991'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_7570e7930cbf7583a5c482bc9a9829cd
-    http_version: HTTP/1.1
-    status_code: 200
- request:
-    body: !!binary |
-      CtoMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSsQwKEgoQY3Jld2FpLnRl
-      bGVtZXRyeRKXCAoQoIk4ztsSW1VcQBoGyvUEwRII42yueEHaLpkqDENyZXcgQ3JlYXRlZDABOaDB
-      SlvCSjIYQai+bVvCSjIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTA4LjBKGgoOcHl0aG9uX3Zl
-      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIDA3YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhk
-      MjgzMmM2SjEKB2NyZXdfaWQSJgokMWI2YjUxZGEtMzgxMy00YjI1LTljN2EtOGM1ODkwM2NkMjk1
-      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAUoaChRjcmV3
-      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
-      X2ZpbmdlcnByaW50EiYKJDFjNGQ3MTZhLTA3YjktNDFjNi05NTk0LWI2ZDJmZmJiNDMxZEo7Chtj
-      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0wMVQxNzoxMDowMy45NTQwNjRK
-      ywIKC2NyZXdfYWdlbnRzErsCCrgCW3sia2V5IjogIjAyZGYxM2UzNjcxMmFiZjUxZDIzOGZlZWJh
-      YjFjYTI2IiwgImlkIjogIjFmNzNlM2ZiLThmMWEtNGVjYy05ZWY0LWMxZjgxMWU3ZGQ1MyIsICJy
-      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAyNSwgIm1h
-      eF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8i
-      LCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/Ijog
-      ZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSv8BCgpjcmV3
-      X3Rhc2tzEvABCu0BW3sia2V5IjogIjdiNDJkZjNjM2M3NGMyMWM4OTQ4MGUwYzA3MDUzODVmIiwg
-      ImlkIjogImU0OGY1MDYwLWM5MjYtNGQ3ZC04M2NhLTk4MzQ0ZDU5OGJmMyIsICJhc3luY19leGVj
-      dXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiUmVz
-      ZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiMDJkZjEzZTM2NzEyYWJmNTFkMjM4ZmVlYmFiMWNhMjYi
-      LCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQWFKbmOfdsTZ4sp84HAkrQRIIQ5oa
-      A8zScp4qDFRhc2sgQ3JlYXRlZDABOaiGoFvCSjIYQbBPolvCSjIYSi4KCGNyZXdfa2V5EiIKIDA3
-      YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhkMjgzMmM2SjEKB2NyZXdfaWQSJgokMWI2YjUxZGEtMzgx
-      My00YjI1LTljN2EtOGM1ODkwM2NkMjk1Si4KCHRhc2tfa2V5EiIKIDdiNDJkZjNjM2M3NGMyMWM4
-      OTQ4MGUwYzA3MDUzODVmSjEKB3Rhc2tfaWQSJgokZTQ4ZjUwNjAtYzkyNi00ZDdkLTgzY2EtOTgz
-      NDRkNTk4YmYzSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokMWM0ZDcxNmEtMDdiOS00MWM2LTk1OTQt
-      YjZkMmZmYmI0MzFkSjoKEHRhc2tfZmluZ2VycHJpbnQSJgokNDY1NmIwOTctMDdkMy00Zjg2LWE1
-      OTgtYWQ1YmJiN2YwM2JlSjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0
-      LTAxVDE3OjEwOjAzLjk1MjM3NUo7ChFhZ2VudF9maW5nZXJwcmludBImCiRkNGQyYzEzMy1hNmE4
-      LTQ5YjktYTI0OS1iNzcwNDlkZjZlZWV6AhgBhQEAAQAA
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '1629'
-      Content-Type:
-      - application/x-protobuf
-      User-Agent:
-      - OTel-OTLP-Exporter-Python/1.31.1
-    method: POST
-    uri: https://telemetry.crewai.com:4319/v1/traces
-  response:
-    body:
-      string: "\n\0"
-    headers:
-      Content-Length:
-      - '2'
-      Content-Type:
-      - application/x-protobuf
-      Date:
-      - Tue, 01 Apr 2025 20:10:32 GMT
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "system", "content": "You are Researcher. You are
-      a researcher at a leading tech think tank.\nYour personal goal is: Search relevant
-      data and provide results\nTo give my best complete final answer to the task
-      respond using the exact following format:\n\nThought: I now can give a great
-      answer\nFinal Answer: Your final answer must be the great and the most complete
-      as possible, it must be outcome described.\n\nI MUST use these formats, my job
-      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Perform a search
-      on specific topics.\n\nThis is the expected criteria for your final answer:
-      A list of relevant URLs based on the search query.\nyou MUST return the actual
-      complete content as the final answer, not a summary.\n\n# Useful context: \nExternal
-      memories:\n\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:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '984'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=26AntG8LjHgDcgN0MYB7TgUTXmoUsQqg8yChWws9CAE-1743538222-1.0.1.1-jo5QRov4A_6L5CaGwhXx2I2aGHzSN6wvrS5Lt2yDpcV5vfTu3FlroYl2d4LBq.ySrtNMDxGQgpsA6fMg0z4iEOXpD5DT7CrJKWRNr4H7Y_k;
-        _cfuvid=.HNP7WFC.O40eZMPSJZ4USQu9SYczq5v794aRx34sZg-1743538222787-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.68.2
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-read-timeout:
-      - '600.0'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-BHcEJeQt9RxZ492mqpQIcZVupQH1c\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1743538231,\n  \"model\": \"gpt-4o-2024-08-06\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"My current task is to perform a search
-      on specific topics and return a list of relevant URLs. I don't have access to
-      external internet tools to fetch live data, but I can guide on how to find information
-      based on specific search queries.\\n\\n1. Identify the specific topics or keywords
-      for the search.\\n2. Use a search engine like Google to input these keywords.\\n3.
-      Look for credible sources, such as academic publications, news outlets, or specialized
-      websites, that provide relevant and reliable information.\\n4. Compile the URLs
-      from credible sources that directly relate to your search query.\\n\\nThought:
-      I now can give a great answer\\nFinal Answer: To obtain a list of relevant URLs,
-      you would need to perform a live search on a search engine using the specific
-      keywords related to your topics of interest and collect URLs from credible sources
-      such as academic journals, government websites, or reputable news outlets.\",\n
-      \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-      185,\n    \"completion_tokens\": 177,\n    \"total_tokens\": 362,\n    \"prompt_tokens_details\":
-      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
-      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-      \"default\",\n  \"system_fingerprint\": \"fp_898ac29719\"\n}\n"
-    headers:
-      CF-RAY:
-      - 929abaf84c1a7dfa-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 01 Apr 2025 20:10:34 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '2937'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '50000'
-      x-ratelimit-limit-tokens:
-      - '150000000'
-      x-ratelimit-remaining-requests:
-      - '49999'
-      x-ratelimit-remaining-tokens:
-      - '149999788'
-      x-ratelimit-reset-requests:
-      - 1ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_c8e37cceac4fcca65da1c883d29cd816
-    http_version: HTTP/1.1
-    status_code: 200
- request:
-    body: '{"input": ["My current task is to perform a search on specific topics and
-      return a list of relevant URLs. I don''t have access to external internet tools
-      to fetch live data, but I can guide on how to find information based on specific
-      search queries.  1. Identify the specific topics or keywords for the search.
-      2. Use a search engine like Google to input these keywords. 3. Look for credible
-      sources, such as academic publications, news outlets, or specialized websites,
-      that provide relevant and reliable information. 4. Compile the URLs from credible
-      sources that directly relate to your search query.  Thought: I now can give
-      a great answer Final Answer: To obtain a list of relevant URLs, you would need
-      to perform a live search on a search engine using the specific keywords related
-      to your topics of interest and collect URLs from credible sources such as academic
-      journals, government websites, or reputable news outlets."], "model": "text-embedding-3-small",
-      "encoding_format": "base64"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '995'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=JcjzeNadYektCKxz.qAt_Iu9W82BXw8zXu9IzahTzL4-1743538230-1.0.1.1-zltiq2Kl.WZlrShHKUBPQrPv0dX2jM_mrIEDEv58Na6s2GSfEgAQbiffMTPHtElo6HoDyJX5g8sjIacSnLyZSswTCjtL4C75K1IK09Or9mo;
-        _cfuvid=cqy59cJ9.MxM3ogPzubxDJvueA5vj1ZPlpD5x5e3hdA-1743538230508-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.68.2
-      x-stainless-read-timeout:
-      - '600'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
-      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
-      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
-      182,\n    \"total_tokens\": 182\n  }\n}\n"
-    headers:
-      CF-RAY:
-      - 929abb0bee737df9-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 01 Apr 2025 20:10:34 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-allow-origin:
-      - '*'
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-model:
-      - text-embedding-3-small
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '86'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      via:
-      - envoy-router-bbb94bf85-txxsl
-      x-envoy-upstream-service-time:
-      - '78'
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '10000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '9999770'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 1ms
-      x-request-id:
-      - req_7ea6db6200478758c413eeb853e93f15
-    http_version: HTTP/1.1
-    status_code: 200
- request:
-    body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
-      completed based on the description, expected output, and actual results.\n\nTask
-      Description:\nPerform a search on specific topics.\n\nExpected Output:\nA list
-      of relevant URLs based on the search query.\n\nActual Output:\nMy current task
-      is to perform a search on specific topics and return a list of relevant URLs.
-      I don''t have access to external internet tools to fetch live data, but I can
-      guide on how to find information based on specific search queries.\n\n1. Identify
-      the specific topics or keywords for the search.\n2. Use a search engine like
-      Google to input these keywords.\n3. Look for credible sources, such as academic
-      publications, news outlets, or specialized websites, that provide relevant and
-      reliable information.\n4. Compile the URLs from credible sources that directly
-      relate to your search query.\n\nThought: I now can give a great answer\nFinal
-      Answer: To obtain a list of relevant URLs, you would need to perform a live
-      search on a search engine using the specific keywords related to your topics
-      of interest and collect URLs from credible sources such as academic journals,
-      government websites, or reputable news outlets.\n\nPlease provide:\n- Bullet
-      points suggestions to improve future similar tasks\n- A score from 0 to 10 evaluating
-      on completion, quality, and overall performance- Entities extracted from the
-      task output, if any, their type, description, and relationships"}], "model":
-      "gpt-4o", "tool_choice": {"type": "function", "function": {"name": "TaskEvaluation"}},
-      "tools": [{"type": "function", "function": {"name": "TaskEvaluation", "description":
-      "Correctly extracted `TaskEvaluation` with all the required parameters with
-      correct types", "parameters": {"$defs": {"Entity": {"properties": {"name": {"description":
-      "The name of the entity.", "title": "Name", "type": "string"}, "type": {"description":
-      "The type of the entity.", "title": "Type", "type": "string"}, "description":
-      {"description": "Description of the entity.", "title": "Description", "type":
-      "string"}, "relationships": {"description": "Relationships of the entity.",
-      "items": {"type": "string"}, "title": "Relationships", "type": "array"}}, "required":
-      ["name", "type", "description", "relationships"], "title": "Entity", "type":
-      "object"}}, "properties": {"suggestions": {"description": "Suggestions to improve
-      future similar tasks.", "items": {"type": "string"}, "title": "Suggestions",
-      "type": "array"}, "quality": {"description": "A score from 0 to 10 evaluating
-      on completion, quality, and overall performance, all taking into account the
-      task description, expected output, and the result of the task.", "title": "Quality",
-      "type": "number"}, "entities": {"description": "Entities extracted from the
-      task output.", "items": {"$ref": "#/$defs/Entity"}, "title": "Entities", "type":
-      "array"}}, "required": ["entities", "quality", "suggestions"], "type": "object"}}}]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2952'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=26AntG8LjHgDcgN0MYB7TgUTXmoUsQqg8yChWws9CAE-1743538222-1.0.1.1-jo5QRov4A_6L5CaGwhXx2I2aGHzSN6wvrS5Lt2yDpcV5vfTu3FlroYl2d4LBq.ySrtNMDxGQgpsA6fMg0z4iEOXpD5DT7CrJKWRNr4H7Y_k;
-        _cfuvid=.HNP7WFC.O40eZMPSJZ4USQu9SYczq5v794aRx34sZg-1743538222787-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.68.2
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-read-timeout:
-      - '600.0'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-BHcEMcdhPRL3gLo2olJ4aUutrNfLv\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1743538234,\n  \"model\": \"gpt-4o-2024-08-06\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
-      \           \"id\": \"call_rzy02tsLLurMdGuEiul9lHF8\",\n            \"type\":
-      \"function\",\n            \"function\": {\n              \"name\": \"TaskEvaluation\",\n
-      \             \"arguments\": \"{\\\"suggestions\\\":[\\\"Ensure access to the
-      internet or appropriate APIs to perform live searches in future tasks.\\\",\\\"Consider
-      simulating a response with example URLs if live search capability is unavailable.\\\",\\\"Provide
-      a disclaimer regarding the unavailability of live data retrieval.\\\",\\\"Indicate
-      clearly that the task cannot be completed as expected due to limitations.\\\"],\\\"quality\\\":3,\\\"entities\\\":[]}\"\n
-      \           }\n          }\n        ],\n        \"refusal\": null,\n        \"annotations\":
-      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
-      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 459,\n    \"completion_tokens\":
-      71,\n    \"total_tokens\": 530,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
-      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
-      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-      \"default\",\n  \"system_fingerprint\": \"fp_898ac29719\"\n}\n"
-    headers:
-      CF-RAY:
-      - 929abb0f2d587dfa-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 01 Apr 2025 20:10:36 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '1657'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '50000'
-      x-ratelimit-limit-tokens:
-      - '150000000'
-      x-ratelimit-remaining-requests:
-      - '49999'
-      x-ratelimit-remaining-tokens:
-      - '149999644'
-      x-ratelimit-reset-requests:
-      - 1ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_ff90eb4514605cbdd86933a230691b6b
-    http_version: HTTP/1.1
-    status_code: 200
-version: 1
@@ -1,836 +0,0 @@
-interactions:
- request:
-    body: '{"input": ["Perform a search on specific topics."], "model": "text-embedding-3-small",
-      "encoding_format": "base64"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '115'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.68.2
-      x-stainless-read-timeout:
-      - '600'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
-      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
-      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
-      7,\n    \"total_tokens\": 7\n  }\n}\n"
-    headers:
-      CF-RAY:
-      - 929abab459817e07-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 01 Apr 2025 20:10:20 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=wQNqc3BNcaCzhFR4owoCJRMIvs7PWqvy7xmWaIr4k.A-1743538220-1.0.1.1-AIxSGyU_kRiSsc4DYqsunqMwAlAn0fhT.P.7_bBBWTyHeVrexxOSRpm5yj6QmiIVcYwEgdJqk9EsHBy9LfadhgMJ5w8LIrHF_sxBFAXOOxc;
-        path=/; expires=Tue, 01-Apr-25 20:40:20 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=g5w7.LJsKZSYhPzW6M1n.OyrMWQSUF5zX.cFK1vZrQI-1743538220809-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-allow-origin:
-      - '*'
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-model:
-      - text-embedding-3-small
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '308'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      via:
-      - envoy-router-68459c4c98-bfmcm
-      x-envoy-upstream-service-time:
-      - '243'
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '10000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '9999991'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_51cfe3e45d22af953af55f6708e77623
-    http_version: HTTP/1.1
-    status_code: 200
- request:
-    body: '{"input": ["Perform a search on specific topics."], "model": "text-embedding-3-small",
-      "encoding_format": "base64"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '115'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.68.2
-      x-stainless-read-timeout:
-      - '600'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
-      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
-      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
-      7,\n    \"total_tokens\": 7\n  }\n}\n"
-    headers:
-      CF-RAY:
-      - 929abab86d4a7e1b-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 01 Apr 2025 20:10:21 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=MCDkRAmvHC26iz7BEoKzXwq4j5v_FEX5IQepnW5ARp4-1743538221-1.0.1.1-GXJkwk8HCFy9W0tA9R.s3NWzCNJ7wCiaUFu4YCbra4nQNVJa_mN3jdnmfREeET4QfWbYGCQXuM5GHffwtQZ_W1EV3mUC4JFa3w5CCDqO41Y;
-        path=/; expires=Tue, 01-Apr-25 20:40:21 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=mRF3.ZghYObsvTKqmSfcqSbJFV0SBPVk2Psc.9DVGlE-1743538221434-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-allow-origin:
-      - '*'
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-model:
-      - text-embedding-3-small
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '156'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      via:
-      - envoy-router-7c6fb6444f-m8b65
-      x-envoy-upstream-service-time:
-      - '132'
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '10000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '9999991'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_463b788a4cc327763e9544976b2fe7ce
-    http_version: HTTP/1.1
-    status_code: 200
- request:
-    body: !!binary |
-      CtoMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSsQwKEgoQY3Jld2FpLnRl
-      bGVtZXRyeRKXCAoQllrSJs4siWPoysCAkdyzdhIIeP9LvWGg1D0qDENyZXcgQ3JlYXRlZDABOeAu
-      xRLASjIYQUh77RLASjIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTA4LjBKGgoOcHl0aG9uX3Zl
-      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIDA3YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhk
-      MjgzMmM2SjEKB2NyZXdfaWQSJgokOWUwNDE3NDgtZTg2MS00M2YzLWE4ZTYtMTA4N2I3NjA1MTE1
-      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAUoaChRjcmV3
-      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
-      X2ZpbmdlcnByaW50EiYKJDlhODQwMjI3LTQwY2UtNDU4OC1iYTAzLTBlYzZlMjQzMDdjMUo7Chtj
-      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0wMVQxNzowOTo1NC4xMzIwMzlK
-      ywIKC2NyZXdfYWdlbnRzErsCCrgCW3sia2V5IjogIjAyZGYxM2UzNjcxMmFiZjUxZDIzOGZlZWJh
-      YjFjYTI2IiwgImlkIjogImNlMjE2ZTU4LTY1MDgtNDQ0My1iZTY0LWUwNzVhNTQ5YzMzZCIsICJy
-      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAyNSwgIm1h
-      eF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8i
-      LCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/Ijog
-      ZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSv8BCgpjcmV3
-      X3Rhc2tzEvABCu0BW3sia2V5IjogIjdiNDJkZjNjM2M3NGMyMWM4OTQ4MGUwYzA3MDUzODVmIiwg
-      ImlkIjogImVmMDNjMDliLTIwNGQtNGU2Yy04NDIwLTQyNmNmOWM4OGFmYyIsICJhc3luY19leGVj
-      dXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiUmVz
-      ZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiMDJkZjEzZTM2NzEyYWJmNTFkMjM4ZmVlYmFiMWNhMjYi
-      LCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQZo4JZzOQlEm7ZP/lMPxN9hIIymaC
-      IpHXF4cqDFRhc2sgQ3JlYXRlZDABObhUIRPASjIYQQgSIxPASjIYSi4KCGNyZXdfa2V5EiIKIDA3
-      YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhkMjgzMmM2SjEKB2NyZXdfaWQSJgokOWUwNDE3NDgtZTg2
-      MS00M2YzLWE4ZTYtMTA4N2I3NjA1MTE1Si4KCHRhc2tfa2V5EiIKIDdiNDJkZjNjM2M3NGMyMWM4
-      OTQ4MGUwYzA3MDUzODVmSjEKB3Rhc2tfaWQSJgokZWYwM2MwOWItMjA0ZC00ZTZjLTg0MjAtNDI2
-      Y2Y5Yzg4YWZjSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokOWE4NDAyMjctNDBjZS00NTg4LWJhMDMt
-      MGVjNmUyNDMwN2MxSjoKEHRhc2tfZmluZ2VycHJpbnQSJgokNzcwMDBjZjktZjVlNC00MDJhLTg1
-      MTgtNzFhMzZhZTc2MmQwSjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0
-      LTAxVDE3OjA5OjU0LjEzMTE4NUo7ChFhZ2VudF9maW5nZXJwcmludBImCiQ0Y2Y4OTc4Yy1iN2M4
-      LTRiMjUtODYxMC1lNWE4NmMxOTYwNzB6AhgBhQEAAQAA
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '1629'
-      Content-Type:
-      - application/x-protobuf
-      User-Agent:
-      - OTel-OTLP-Exporter-Python/1.31.1
-    method: POST
-    uri: https://telemetry.crewai.com:4319/v1/traces
-  response:
-    body:
-      string: "\n\0"
-    headers:
-      Content-Length:
-      - '2'
-      Content-Type:
-      - application/x-protobuf
-      Date:
-      - Tue, 01 Apr 2025 20:10:22 GMT
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "system", "content": "You are Researcher. You are
-      a researcher at a leading tech think tank.\nYour personal goal is: Search relevant
-      data and provide results\nTo give my best complete final answer to the task
-      respond using the exact following format:\n\nThought: I now can give a great
-      answer\nFinal Answer: Your final answer must be the great and the most complete
-      as possible, it must be outcome described.\n\nI MUST use these formats, my job
-      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Perform a search
-      on specific topics.\n\nThis is the expected criteria for your final answer:
-      A list of relevant URLs based on the search query.\nyou MUST return the actual
-      complete content as the final answer, not a summary.\n\n# Useful context: \nExternal
-      memories:\n\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:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '984'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.68.2
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-read-timeout:
-      - '600.0'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-BHcE9342OpU72PR82mknhgcVzhK5H\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1743538221,\n  \"model\": \"gpt-4o-2024-08-06\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Thought: I need to gather relevant URLs
-      based on the search query provided in order to fulfill the task requirements.\\n\\nFinal
-      Answer: The search query or topics were not specified. Please provide specific
-      topics or search query to perform a search for relevant URLs.\",\n        \"refusal\":
-      null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 185,\n    \"completion_tokens\":
-      50,\n    \"total_tokens\": 235,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
-      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
-      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-      \"default\",\n  \"system_fingerprint\": \"fp_898ac29719\"\n}\n"
-    headers:
-      CF-RAY:
-      - 929ababcdf9c7dfa-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 01 Apr 2025 20:10:22 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=26AntG8LjHgDcgN0MYB7TgUTXmoUsQqg8yChWws9CAE-1743538222-1.0.1.1-jo5QRov4A_6L5CaGwhXx2I2aGHzSN6wvrS5Lt2yDpcV5vfTu3FlroYl2d4LBq.ySrtNMDxGQgpsA6fMg0z4iEOXpD5DT7CrJKWRNr4H7Y_k;
-        path=/; expires=Tue, 01-Apr-25 20:40:22 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=.HNP7WFC.O40eZMPSJZ4USQu9SYczq5v794aRx34sZg-1743538222787-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '860'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '50000'
-      x-ratelimit-limit-tokens:
-      - '150000000'
-      x-ratelimit-remaining-requests:
-      - '49999'
-      x-ratelimit-remaining-tokens:
-      - '149999788'
-      x-ratelimit-reset-requests:
-      - 1ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_bf03af6c68765e4393cb60521c5d99ec
-    http_version: HTTP/1.1
-    status_code: 200
- request:
-    body: '{"input": ["Thought: I need to gather relevant URLs based on the search
-      query provided in order to fulfill the task requirements.  Final Answer: The
-      search query or topics were not specified. Please provide specific topics or
-      search query to perform a search for relevant URLs."], "model": "text-embedding-3-small",
-      "encoding_format": "base64"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '344'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=wQNqc3BNcaCzhFR4owoCJRMIvs7PWqvy7xmWaIr4k.A-1743538220-1.0.1.1-AIxSGyU_kRiSsc4DYqsunqMwAlAn0fhT.P.7_bBBWTyHeVrexxOSRpm5yj6QmiIVcYwEgdJqk9EsHBy9LfadhgMJ5w8LIrHF_sxBFAXOOxc;
-        _cfuvid=g5w7.LJsKZSYhPzW6M1n.OyrMWQSUF5zX.cFK1vZrQI-1743538220809-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.68.2
-      x-stainless-read-timeout:
-      - '600'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
-      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
-      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
-      50,\n    \"total_tokens\": 50\n  }\n}\n"
-    headers:
-      CF-RAY:
-      - 929abac4a8fc7e07-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 01 Apr 2025 20:10:24 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-allow-origin:
-      - '*'
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-model:
-      - text-embedding-3-small
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '1403'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      via:
-      - envoy-router-69ff67f767-88tkx
-      x-envoy-upstream-service-time:
-      - '1369'
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '10000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '9999934'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_5a1b9f49c2d200641e58e8cd95ef063a
-    http_version: HTTP/1.1
-    status_code: 200
- request:
-    body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
-      completed based on the description, expected output, and actual results.\n\nTask
-      Description:\nPerform a search on specific topics.\n\nExpected Output:\nA list
-      of relevant URLs based on the search query.\n\nActual Output:\nThought: I need
-      to gather relevant URLs based on the search query provided in order to fulfill
-      the task requirements.\n\nFinal Answer: The search query or topics were not
-      specified. Please provide specific topics or search query to perform a search
-      for relevant URLs.\n\nPlease provide:\n- Bullet points suggestions to improve
-      future similar tasks\n- A score from 0 to 10 evaluating on completion, quality,
-      and overall performance- Entities extracted from the task output, if any, their
-      type, description, and relationships"}], "model": "gpt-4o", "tool_choice": {"type":
-      "function", "function": {"name": "TaskEvaluation"}}, "tools": [{"type": "function",
-      "function": {"name": "TaskEvaluation", "description": "Correctly extracted `TaskEvaluation`
-      with all the required parameters with correct types", "parameters": {"$defs":
-      {"Entity": {"properties": {"name": {"description": "The name of the entity.",
-      "title": "Name", "type": "string"}, "type": {"description": "The type of the
-      entity.", "title": "Type", "type": "string"}, "description": {"description":
-      "Description of the entity.", "title": "Description", "type": "string"}, "relationships":
-      {"description": "Relationships of the entity.", "items": {"type": "string"},
-      "title": "Relationships", "type": "array"}}, "required": ["name", "type", "description",
-      "relationships"], "title": "Entity", "type": "object"}}, "properties": {"suggestions":
-      {"description": "Suggestions to improve future similar tasks.", "items": {"type":
-      "string"}, "title": "Suggestions", "type": "array"}, "quality": {"description":
-      "A score from 0 to 10 evaluating on completion, quality, and overall performance,
-      all taking into account the task description, expected output, and the result
-      of the task.", "title": "Quality", "type": "number"}, "entities": {"description":
-      "Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
-      "title": "Entities", "type": "array"}}, "required": ["entities", "quality",
-      "suggestions"], "type": "object"}}}]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2295'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=26AntG8LjHgDcgN0MYB7TgUTXmoUsQqg8yChWws9CAE-1743538222-1.0.1.1-jo5QRov4A_6L5CaGwhXx2I2aGHzSN6wvrS5Lt2yDpcV5vfTu3FlroYl2d4LBq.ySrtNMDxGQgpsA6fMg0z4iEOXpD5DT7CrJKWRNr4H7Y_k;
-        _cfuvid=.HNP7WFC.O40eZMPSJZ4USQu9SYczq5v794aRx34sZg-1743538222787-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.68.2
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-read-timeout:
-      - '600.0'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-BHcEDk89V0nWfSxs0BaUsqqVYrVxj\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1743538225,\n  \"model\": \"gpt-4o-2024-08-06\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
-      \           \"id\": \"call_39zVeoea7WZ0hceVZTcAut7Z\",\n            \"type\":
-      \"function\",\n            \"function\": {\n              \"name\": \"TaskEvaluation\",\n
-      \             \"arguments\": \"{\\\"suggestions\\\":[\\\"Ensure that the search
-      query or specific topics are provided before starting the task.\\\",\\\"Implement
-      error handling to provide more useful output or alternatives when input is insufficient.\\\",\\\"Provide
-      a fallback or a default set of topics in case none are provided.\\\",\\\"Clarify
-      task requirements with stakeholders if the input parameters are unclear.\\\"],\\\"quality\\\":2,\\\"entities\\\":[{\\\"name\\\":\\\"search
-      query\\\",\\\"type\\\":\\\"Requirement\\\",\\\"description\\\":\\\"A parameter
-      needed to perform the search operation.\\\",\\\"relationships\\\":[\\\"Without
-      this entity, the task cannot be completed.\\\"]},{\\\"name\\\":\\\"URLs\\\",\\\"type\\\":\\\"Output\\\",\\\"description\\\":\\\"The
-      expected result from executing the search.\\\",\\\"relationships\\\":[\\\"Expected
-      output when the search query is provided.\\\"]}]}\"\n            }\n          }\n
-      \       ],\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
-      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
-      \ \"usage\": {\n    \"prompt_tokens\": 332,\n    \"completion_tokens\": 137,\n
-      \   \"total_tokens\": 469,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
-      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
-      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-      \"default\",\n  \"system_fingerprint\": \"fp_898ac29719\"\n}\n"
-    headers:
-      CF-RAY:
-      - 929abad21a6b7dfa-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 01 Apr 2025 20:10:27 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '2597'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '50000'
-      x-ratelimit-limit-tokens:
-      - '150000000'
-      x-ratelimit-remaining-requests:
-      - '49999'
-      x-ratelimit-remaining-tokens:
-      - '149999807'
-      x-ratelimit-reset-requests:
-      - 1ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_a5c36be883759cbc3fec575604f8746e
-    http_version: HTTP/1.1
-    status_code: 200
- request:
-    body: '{"input": ["search query(Requirement): A parameter needed to perform the
-      search operation."], "model": "text-embedding-3-small", "encoding_format": "base64"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '157'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=MCDkRAmvHC26iz7BEoKzXwq4j5v_FEX5IQepnW5ARp4-1743538221-1.0.1.1-GXJkwk8HCFy9W0tA9R.s3NWzCNJ7wCiaUFu4YCbra4nQNVJa_mN3jdnmfREeET4QfWbYGCQXuM5GHffwtQZ_W1EV3mUC4JFa3w5CCDqO41Y;
-        _cfuvid=mRF3.ZghYObsvTKqmSfcqSbJFV0SBPVk2Psc.9DVGlE-1743538221434-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.68.2
-      x-stainless-read-timeout:
-      - '600'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
-      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
-      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
-      14,\n    \"total_tokens\": 14\n  }\n}\n"
-    headers:
-      CF-RAY:
-      - 929abae38c117df4-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 01 Apr 2025 20:10:28 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-allow-origin:
-      - '*'
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-model:
-      - text-embedding-3-small
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '557'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      via:
-      - envoy-router-d44cf9799-vc45q
-      x-envoy-upstream-service-time:
-      - '531'
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '10000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '9999980'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_91c495419e7c55b5f7396854da1588bc
-    http_version: HTTP/1.1
-    status_code: 200
- request:
-    body: '{"input": ["URLs(Output): The expected result from executing the search."],
-      "model": "text-embedding-3-small", "encoding_format": "base64"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '139'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=MCDkRAmvHC26iz7BEoKzXwq4j5v_FEX5IQepnW5ARp4-1743538221-1.0.1.1-GXJkwk8HCFy9W0tA9R.s3NWzCNJ7wCiaUFu4YCbra4nQNVJa_mN3jdnmfREeET4QfWbYGCQXuM5GHffwtQZ_W1EV3mUC4JFa3w5CCDqO41Y;
-        _cfuvid=mRF3.ZghYObsvTKqmSfcqSbJFV0SBPVk2Psc.9DVGlE-1743538221434-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.68.2
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.68.2
-      x-stainless-read-timeout:
-      - '600'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    content: "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\":
-      \"embedding\",\n      \"index\": 0,\n      \"embedding\": \"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 truncated
-      \   }\n  ],\n  \"model\": \"text-embedding-3-small\",\n  \"usage\": {\n    \"prompt_tokens\":
-      12,\n    \"total_tokens\": 12\n  }\n}\n"
-    headers:
-      CF-RAY:
-      - 929abae938887df4-GRU
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 01 Apr 2025 20:10:29 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-allow-origin:
-      - '*'
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-model:
-      - text-embedding-3-small
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '199'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      via:
-      - envoy-router-f47df6cdf-hhnd7
-      x-envoy-upstream-service-time:
-      - '105'
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '10000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '9999984'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_cfdd836532f45e9c2f03d332153438f6
-    http_version: HTTP/1.1
-    status_code: 200
-version: 1
@@ -0,0 +1,182 @@
+interactions:
+- request:
+    body: !!binary |
+      Ct8MCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkStgwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKcCAoQfm0pqVSMD2d8x7Z0oecKIRIIgWppMg8y3GoqDENyZXcgQ3JlYXRlZDABORAN
+      KtAWrDUYQagXMtAWrDUYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIDA3YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhk
+      MjgzMmM2SjEKB2NyZXdfaWQSJgokNGY1NjNkN2MtYmYyOC00ZWM2LTgzNzQtMDZlMjZiYzA1NWU0
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
+      X2ZpbmdlcnByaW50EiYKJGU4MGY4MDFmLWViZmQtNDlkOS1iNTEwLTM0NmVjN2VlNzAzZko7Chtj
+      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xMlQxNzoyNzoyNC42NTU4NzhK
+      0AIKC2NyZXdfYWdlbnRzEsACCr0CW3sia2V5IjogIjAyZGYxM2UzNjcxMmFiZjUxZDIzOGZlZWJh
+      YjFjYTI2IiwgImlkIjogIjg5MjdlNzQ1LWNkNWQtNDJkMy1hMjA2LTEyYTUxOWRlMDY1OCIsICJy
+      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAyNSwgIm1h
+      eF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8t
+      bWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlv
+      bj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/wEK
+      CmNyZXdfdGFza3MS8AEK7QFbeyJrZXkiOiAiN2I0MmRmM2MzYzc0YzIxYzg5NDgwZTBjMDcwNTM4
+      NWYiLCAiaWQiOiAiNDM0MDgzNDYtMjA5OC00M2I1LWE0NWUtMmU2MWY4ZmYxZTliIiwgImFzeW5j
+      X2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6
+      ICJSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6ICIwMmRmMTNlMzY3MTJhYmY1MWQyMzhmZWViYWIx
+      Y2EyNiIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChDv1iM8ejIY7tezTF4KBssA
+      Eghn2bJnw2f60SoMVGFzayBDcmVhdGVkMAE58LFA0BasNRhB4AdB0BasNRhKLgoIY3Jld19rZXkS
+      IgogMDdhNzE3NjhjYzRjOTNlYWIzYjMxZTNjOGQyODMyYzZKMQoHY3Jld19pZBImCiQ0ZjU2M2Q3
+      Yy1iZjI4LTRlYzYtODM3NC0wNmUyNmJjMDU1ZTRKLgoIdGFza19rZXkSIgogN2I0MmRmM2MzYzc0
+      YzIxYzg5NDgwZTBjMDcwNTM4NWZKMQoHdGFza19pZBImCiQ0MzQwODM0Ni0yMDk4LTQzYjUtYTQ1
+      ZS0yZTYxZjhmZjFlOWJKOgoQY3Jld19maW5nZXJwcmludBImCiRlODBmODAxZi1lYmZkLTQ5ZDkt
+      YjUxMC0zNDZlYzdlZTcwM2ZKOgoQdGFza19maW5nZXJwcmludBImCiQ2YjgzODVkYS0yYWJjLTRm
+      NWEtOTk3NC0xNjhiMzVhNDBlOTlKOwobdGFza19maW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIw
+      MjUtMDQtMTJUMTc6Mjc6MjQuNjU1ODQ4SjsKEWFnZW50X2ZpbmdlcnByaW50EiYKJDIyNTI4NDRl
+      LWNlMTYtNDYyZi04NDI4LTYwYzZmMWYyNGE3N3oCGAGFAQABAAA=
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1634'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.31.1
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Sat, 12 Apr 2025 20:27:26 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You are
+      a researcher at a leading tech think tank.\nYour personal goal is: Search relevant
+      data and provide results\nTo give my best complete final answer to the task
+      respond using the exact following format:\n\nThought: I now can give a great
+      answer\nFinal Answer: Your final answer must be the great and the most complete
+      as possible, it must be outcome described.\n\nI MUST use these formats, my job
+      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Perform a search
+      on specific topics.\n\nThis is the expected criteria for your final answer:
+      A list of relevant URLs based on the search query.\nyou MUST return the actual
+      complete content as the final answer, not a summary.\n\n# Useful context: \nExternal
+      memories:\n\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '989'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=nSje5Zn_Lk69BDG85XIauC2hrZjGl0pR2sel9__KWGw-1744489610-1.0.1.1-CPlAgcgTAE30uWrbi_2wiCWrbRDRWiaa.YuQMgST42DLDVg_wdNlJMDQT3Lsqk.g.BO68A66TTirWA0blQaQw.9xdBbPwKO609_ftjdwi5U;
+        _cfuvid=XLC52GLAWCOeWn2vI379CnSGKjPa7f.qr2vSAQ_R66M-1744489610542-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BLbjg0OfADWdrLsZxrjKHEeVVbWle\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744489644,\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: Here is a list of relevant URLs based on the specified search query:
+      \ \\n\\n1. https://www.forbes.com/technology/  \\n2. https://www.sciencedirect.com/
+      \ \\n3. https://www.techcrunch.com/  \\n4. https://www.wired.com/  \\n5. https://www.researchgate.net/
+      \ \\n6. https://www.springer.com/  \\n7. https://www.jstor.org/  \\n8. https://www.statista.com/
+      \ \\n9. https://www.pwc.com/gx/en/services/consulting/technology.html  \\n10.
+      https://www.gartner.com/en/information-technology  \\n\\nThese URLs provide
+      access to a wealth of information on various technology-related topics, including
+      articles, research papers, and analytics.\",\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 185,\n    \"completion_tokens\":
+      169,\n    \"total_tokens\": 354,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_80cf447eee\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92f576d83a447e05-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 12 Apr 2025 20:27:27 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '2273'
+      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:
+      - '149999788'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_38f6879956c29e6c61c844d1906fa2e8
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1
@@ -0,0 +1,190 @@
+interactions:
+- request:
+    body: !!binary |
+      Ct8MCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkStgwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKcCAoQjin/Su47zAwLq3Hv6yv8GhIImRMfAPs+FOMqDENyZXcgQ3JlYXRlZDABOYCY
+      xbgUrDUYQVie07gUrDUYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIDA3YTcxNzY4Y2M0YzkzZWFiM2IzMWUzYzhk
+      MjgzMmM2SjEKB2NyZXdfaWQSJgokY2UyMGFlNWYtZmMyNy00YWJhLWExYWMtNzUwY2ZhZmMwMTE4
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
+      X2ZpbmdlcnByaW50EiYKJDQ4NGFmZDhjLTczMmEtNGM1Ni1hZjk2LTU2MzkwMjNmYjhjOUo7Chtj
+      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xMlQxNzoyNzoxNS42NzMyMjNK
+      0AIKC2NyZXdfYWdlbnRzEsACCr0CW3sia2V5IjogIjAyZGYxM2UzNjcxMmFiZjUxZDIzOGZlZWJh
+      YjFjYTI2IiwgImlkIjogImYyYjZkYTU1LTNiMGItNDZiNy05Mzk5LWE5NDJmYjQ4YzU2OSIsICJy
+      b2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAyNSwgIm1h
+      eF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8t
+      bWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlv
+      bj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/wEK
+      CmNyZXdfdGFza3MS8AEK7QFbeyJrZXkiOiAiN2I0MmRmM2MzYzc0YzIxYzg5NDgwZTBjMDcwNTM4
+      NWYiLCAiaWQiOiAiYmE1MjFjNDgtYzcwNS00MDRlLWE5MDktMjkwZGM0NTlkOThkIiwgImFzeW5j
+      X2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6
+      ICJSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6ICIwMmRmMTNlMzY3MTJhYmY1MWQyMzhmZWViYWIx
+      Y2EyNiIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChAmCOpHN6fX3l0shQvTLjrB
+      EgjLTyt4A1p7wyoMVGFzayBDcmVhdGVkMAE5gN7juBSsNRhBmFfkuBSsNRhKLgoIY3Jld19rZXkS
+      IgogMDdhNzE3NjhjYzRjOTNlYWIzYjMxZTNjOGQyODMyYzZKMQoHY3Jld19pZBImCiRjZTIwYWU1
+      Zi1mYzI3LTRhYmEtYTFhYy03NTBjZmFmYzAxMThKLgoIdGFza19rZXkSIgogN2I0MmRmM2MzYzc0
+      YzIxYzg5NDgwZTBjMDcwNTM4NWZKMQoHdGFza19pZBImCiRiYTUyMWM0OC1jNzA1LTQwNGUtYTkw
+      OS0yOTBkYzQ1OWQ5OGRKOgoQY3Jld19maW5nZXJwcmludBImCiQ0ODRhZmQ4Yy03MzJhLTRjNTYt
+      YWY5Ni01NjM5MDIzZmI4YzlKOgoQdGFza19maW5nZXJwcmludBImCiRhMDcyNjgwNC05ZjIwLTQw
+      ODgtYWFmOC1iNzhkYTUyNmM3NjlKOwobdGFza19maW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIw
+      MjUtMDQtMTJUMTc6Mjc6MTUuNjczMTgxSjsKEWFnZW50X2ZpbmdlcnByaW50EiYKJDNiZDE2MmNm
+      LWNmMWQtNGUwZi04ZmIzLTk3MDljMDkyNmM4ZHoCGAGFAQABAAA=
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1634'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.31.1
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Sat, 12 Apr 2025 20:27:16 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You are
+      a researcher at a leading tech think tank.\nYour personal goal is: Search relevant
+      data and provide results\nTo give my best complete final answer to the task
+      respond using the exact following format:\n\nThought: I now can give a great
+      answer\nFinal Answer: Your final answer must be the great and the most complete
+      as possible, it must be outcome described.\n\nI MUST use these formats, my job
+      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Perform a search
+      on specific topics.\n\nThis is the expected criteria for your final answer:
+      A list of relevant URLs based on the search query.\nyou MUST return the actual
+      complete content as the final answer, not a summary.\n\n# Useful context: \nExternal
+      memories:\n\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '989'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=nSje5Zn_Lk69BDG85XIauC2hrZjGl0pR2sel9__KWGw-1744489610-1.0.1.1-CPlAgcgTAE30uWrbi_2wiCWrbRDRWiaa.YuQMgST42DLDVg_wdNlJMDQT3Lsqk.g.BO68A66TTirWA0blQaQw.9xdBbPwKO609_ftjdwi5U;
+        _cfuvid=XLC52GLAWCOeWn2vI379CnSGKjPa7f.qr2vSAQ_R66M-1744489610542-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BLbjXyMvmR8ctf0sqhp7F1ePskveM\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744489635,\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: Here is a list of relevant URLs based on the search query:\\n\\n1. **Artificial
+      Intelligence in Healthcare**\\n   - https://www.healthit.gov/topic/scientific-initiatives/ai-healthcare\\n
+      \  - https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7317789/\\n   - https://www.forbes.com/sites/bernardmarr/2021/10/18/the-top-5-ways-ai-is-being-used-in-healthcare/?sh=3edf5df51c9c\\n\\n2.
+      **Blockchain Technology in Supply Chain Management**\\n   - https://www.ibm.com/blockchain/supply-chain\\n
+      \  - https://www.gartner.com/en/newsroom/press-releases/2021-06-23-gartner-says-three-use-cases-for-blockchain-in-supply-chain-are-scaling\\n
+      \  - https://www2.deloitte.com/us/en/insights/industry/retail-distribution/blockchain-in-supply-chain.html\\n\\n3.
+      **Renewable Energy Innovations**\\n   - https://www.irena.org/publications/2020/Sep/Renewable-Power-Generation-Costs-in-2020\\n
+      \  - https://www.nrel.gov/docs/fy20osti/77021.pdf\\n   - https://www.cnbc.com/2021/11/03/renewable-energy-could-get-its-first-taste-of-markets-in-2021.html\\n\\n4.
+      **7G Technology Developments**\\n   - https://www.sciencedirect.com/science/article/pii/S1389128619308189\\n
+      \  - https://www.forbes.com/sites/bernardmarr/2021/11/01/what-is-7g-technology-a-beginners-guide-to-the-future-of-mobile-communications/?sh=51b8a7e1464a\\n
+      \  - https://www.ericsson.com/en/reports-and-research/reports/7g-networks-a-powerful-future-for-connected-society\\n\\n5.
+      **Impact of Quantum Computing on Cybersecurity**\\n   - https://www.ibm.com/blogs/research/2021/09/quantum-computing-cybersecurity/\\n
+      \  - https://www.sciencedirect.com/science/article/pii/S0167739X21000072\\n
+      \  - https://www.techrepublic.com/article/how-quantum-computing-will-change-cybersecurity/\\n\\nThese
+      URLs should provide comprehensive information on the topics searched, providing
+      valuable insights and data for your research needs.\",\n        \"refusal\":
+      null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 185,\n    \"completion_tokens\":
+      534,\n    \"total_tokens\": 719,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_80cf447eee\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92f576a01d3b7e05-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 12 Apr 2025 20:27:24 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '8805'
+      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:
+      - '149999788'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_7c2d313d0b5997e903553a782b2afa25
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1
@@ -61,6 +61,35 @@ def crew_with_external_memory(external_memory_with_mocked_config, patch_configur
    return crew


+@pytest.fixture
+def crew_with_external_memory_without_memory_flag(
+    external_memory_with_mocked_config, patch_configure_mem0
+):
+    agent = Agent(
+        role="Researcher",
+        goal="Search relevant data and provide results",
+        backstory="You are a researcher at a leading tech think tank.",
+        tools=[],
+        verbose=True,
+    )
+
+    task = Task(
+        description="Perform a search on specific topics.",
+        expected_output="A list of relevant URLs based on the search query.",
+        agent=agent,
+    )
+
+    crew = Crew(
+        agents=[agent],
+        tasks=[task],
+        verbose=True,
+        process=Process.sequential,
+        external_memory=external_memory_with_mocked_config,
+    )
+
+    return crew
+
+
 def test_external_memory_initialization(external_memory_with_mocked_config):
    assert external_memory_with_mocked_config is not None
    assert isinstance(external_memory_with_mocked_config, ExternalMemory)
@@ -137,7 +166,9 @@ def test_crew_external_memory_reset(mem_type, crew_with_external_memory):

@pytest.mark.parametrize("mem_method", ["search", "save"])
@pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_external_memory_save(mem_method, crew_with_external_memory):
+def test_crew_external_memory_save_with_memory_flag(
+    mem_method, crew_with_external_memory
+):
    with patch(
        f"crewai.memory.external.external_memory.ExternalMemory.{mem_method}"
    ) as mock_method:
@@ -145,6 +176,18 @@ def test_crew_external_memory_save(mem_method, crew_with_external_memory):
        assert mock_method.call_count > 0


+@pytest.mark.parametrize("mem_method", ["search", "save"])
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_external_memory_save_using_crew_without_memory_flag(
+    mem_method, crew_with_external_memory_without_memory_flag
+):
+    with patch(
+        f"crewai.memory.external.external_memory.ExternalMemory.{mem_method}"
+    ) as mock_method:
+        crew_with_external_memory_without_memory_flag.kickoff()
+        assert mock_method.call_count > 0
+
+
 def test_external_memory_custom_storage(crew_with_external_memory):
    class CustomStorage(Storage):
        def __init__(self):
@@ -29,7 +29,7 @@ def mem0_storage_with_mocked_config(mock_mem0_memory):
    """Fixture to create a Mem0Storage instance with mocked dependencies"""

    # Patch the Memory class to return our mock
-    with patch("mem0.memory.main.Memory.from_config", return_value=mock_mem0_memory):
+    with patch("mem0.memory.main.Memory.from_config", return_value=mock_mem0_memory) as mock_from_config:
        config = {
            "vector_store": {
                "provider": "mock_vector_store",
@@ -66,13 +66,15 @@ def mem0_storage_with_mocked_config(mock_mem0_memory):
        )

        mem0_storage = Mem0Storage(type="short_term", crew=crew)
-        return mem0_storage
+        return mem0_storage, mock_from_config, config


 def test_mem0_storage_initialization(mem0_storage_with_mocked_config, mock_mem0_memory):
    """Test that Mem0Storage initializes correctly with the mocked config"""
-    assert mem0_storage_with_mocked_config.memory_type == "short_term"
-    assert mem0_storage_with_mocked_config.memory is mock_mem0_memory
+    mem0_storage, mock_from_config, config = mem0_storage_with_mocked_config
+    assert mem0_storage.memory_type == "short_term"
+    assert mem0_storage.memory is mock_mem0_memory
+    mock_from_config.assert_called_once_with(config)


@pytest.fixture
@@ -1,4 +1,8 @@
-from typing import Callable
+import asyncio
+import inspect
+import unittest
+from typing import Any, Callable, Dict, List
+from unittest.mock import patch

 from crewai.tools import BaseTool, tool

@@ -122,3 +126,69 @@ def test_result_as_answer_in_tool_decorator():
    
    converted_tool = my_tool_with_default.to_structured_tool()
    assert converted_tool.result_as_answer is False
+
+
+class SyncTool(BaseTool):
+    """Test implementation with a synchronous _run method"""
+    name: str = "sync_tool"
+    description: str = "A synchronous tool for testing"
+
+    def _run(self, input_text: str) -> str:
+        """Process input text synchronously."""
+        return f"Processed {input_text} synchronously"
+
+
+class AsyncTool(BaseTool):
+    """Test implementation with an asynchronous _run method"""
+    name: str = "async_tool"
+    description: str = "An asynchronous tool for testing"
+
+    async def _run(self, input_text: str) -> str:
+        """Process input text asynchronously."""
+        await asyncio.sleep(0.1)  # Simulate async operation
+        return f"Processed {input_text} asynchronously"
+
+
+def test_sync_run_returns_direct_result():
+    """Test that _run in a synchronous tool returns a direct result, not a coroutine."""
+    tool = SyncTool()
+    result = tool._run(input_text="hello")
+
+    assert not asyncio.iscoroutine(result)
+    assert result == "Processed hello synchronously"
+
+    run_result = tool.run(input_text="hello")
+    assert run_result == "Processed hello synchronously"
+
+
+def test_async_run_returns_coroutine():
+    """Test that _run in an asynchronous tool returns a coroutine object."""
+    tool = AsyncTool()
+    result = tool._run(input_text="hello")
+
+    assert asyncio.iscoroutine(result)
+    result.close()  # Clean up the coroutine
+
+
+def test_run_calls_asyncio_run_for_async_tools():
+    """Test that asyncio.run is called when using async tools."""
+    async_tool = AsyncTool()
+
+    with patch('asyncio.run') as mock_run:
+        mock_run.return_value = "Processed test asynchronously"
+        async_result = async_tool.run(input_text="test")
+
+        mock_run.assert_called_once()
+        assert async_result == "Processed test asynchronously"
+
+
+def test_run_does_not_call_asyncio_run_for_sync_tools():
+    """Test that asyncio.run is NOT called when using sync tools."""
+    sync_tool = SyncTool()
+
+    with patch('asyncio.run') as mock_run:
+        sync_result = sync_tool.run(input_text="test")
+
+        mock_run.assert_not_called()
+        assert sync_result == "Processed test synchronously"
+
Author	SHA1	Message	Date
Lucas Gomide	aa4a54f059	Merge branch 'main' into feature-isolated-memory	2025-04-14 16:37:08 -03:00
devin-ai-integration[bot]andJoe Moura	88455cd52c	fix: Correctly copy memory objects during crew training (fixes #2593 ) (#2594 ) * fix: Correctly copy memory objects during crew training (#2593) Co-Authored-By: Joe Moura <joao@crewai.com> * style: Fix import order in tests/crew_test.py Co-Authored-By: Joe Moura <joao@crewai.com> * fix: Rely on validator for memory copy, update test assertions Removes manual deep copy of memory objects in Crew.copy(). The Pydantic model_validator 'create_crew_memory' handles the initialization of new memory instances for the copied crew. Updates test_crew_copy_with_memory assertions to verify that the private memory attributes (_short_term_memory, etc.) are correctly initialized as new instances in the copied crew. Co-Authored-By: Joe Moura <joao@crewai.com> * Revert "fix: Rely on validator for memory copy, update test assertions" This reverts commit `8702bf1e34`. * fix: Re-add manual deep copy for all memory types in Crew.copy Addresses feedback on PR #2594 to ensure all memory objects (short_term, long_term, entity, external, user) are correctly deep copied using model_copy(deep=True). Also simplifies the test case to directly verify the copy behavior instead of relying on the train method. Co-Authored-By: Joe Moura <joao@crewai.com> --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Joe Moura <joao@crewai.com>	2025-04-14 14:59:12 -04:00
Lucas Gomide	e346064c36	feat: warn when long-term memory is defined but entity memory is not	2025-04-14 14:15:07 -03:00
Lucas Gomide	4fcca4c486	docs: enhance memory documentation	2025-04-14 14:15:07 -03:00
Lucas Gomide	4e9e190661	feat: add tests to ensure we are able to use contextual memory by set individual memories	2025-04-14 14:15:07 -03:00
Lucas Gomide	9eeed380a8	feat: support defining any memory in an isolated way This change makes it easier to use a specific memory type without unintentionally enabling all others. Previously, setting memory=True would implicitly configure all available memories (like LTM and STM), which might not be ideal in all cases. For example, when building a chatbot that only needs an external memory, users were forced to also configure LTM and STM — which rely on default OpenAPI embeddings — even if they weren’t needed. With this update, users can now define a single memory in isolation, making the configuration process simpler and more flexible.	2025-04-14 14:15:07 -03:00
Alexandre Gindre	6a1eb10830	fix(crew template): fix wrong parameter name and missing input (#2387 )	2025-04-14 11:09:59 -04:00
devin-ai-integration[bot]andJoe Moura	10edde100e	Fix: Use mem0_local_config instead of config in Memory.from_config (#2588 ) * fix: use mem0_local_config instead of config in Memory.from_config (#2587) Co-Authored-By: Joe Moura <joao@crewai.com> * refactor: consolidate tests as per PR feedback Co-Authored-By: Joe Moura <joao@crewai.com> --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Joe Moura <joao@crewai.com>	2025-04-14 08:55:23 -04:00
Eduardo Chiarotti	40a441f30e	feat: remove unused code and change ToolUsageStarted event place (#2581 ) * feat: remove unused code and change ToolUsageStarted event place * feat: run lint * feat: add agent refernece inside liteagent * feat: remove unused logic * feat: Remove not needed event * feat: remove test from tool execution erro: * feat: remove cassete	2025-04-11 14:26:59 -04:00
Vidit Ostwal	ea5ae9086a	added condition to check whether _run function returns a coroutine ob… (#2570 ) * added condition to check whether _run function returns a coroutine object * Cleaned the code * Fixed the test modules, Class -> Functions	2025-04-11 12:56:37 -04:00
Cypher Pepe	0cd524af86	fixed broken link in `docs/tools/weaviatevectorsearchtool.mdx` (#2569 )	2025-04-11 11:58:01 -04:00
Jesse R Weigel	4bff5408d8	Create output folder if it doesn't exits (#2573 ) When running this project, I got an error because the output folder had not been created. I added a line to check if the output folder exists and create it if needed.	2025-04-11 09:14:05 -04:00
Lucas GomideandLorenze Jay	d2caf11191	Support Python 3.10+ (on CI) and remove redundant Self imports (#2553 ) * ci(workflows): add Python version matrix (3.10-3.12) for tests * refactor: remove explicit Self import from typing Python 3.10+ natively supports Self type annotation without explicit imports * chore: rename external_memory file test --------- Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>	2025-04-10 14:37:24 -04:00
Vini Brasil	37979a0ca1	Raise exception when flow fails (#2579 )	2025-04-10 13:08:32 -04:00