Fix issue #2791: Task tools now combine with agent tools instead of overriding them

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

.github/workflows/linter.yml

@@ -5,29 +5,12 @@ on: [pull_request]
 jobs:
   lint:
     runs-on: ubuntu-latest
-    env:
-      TARGET_BRANCH: ${{ github.event.pull_request.base.ref }}
     steps:
       - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
 
-      - name: Fetch Target Branch
-        run: git fetch origin $TARGET_BRANCH --depth=1
-
-      - name: Install Ruff
-        run: pip install ruff
-
-      - name: Get Changed Python Files
-        id: changed-files
+      - name: Install Requirements
         run: |
-          merge_base=$(git merge-base origin/"$TARGET_BRANCH" HEAD)
-          changed_files=$(git diff --name-only --diff-filter=ACMRTUB "$merge_base" | grep '\.py$' || true)
-          echo "files<<EOF" >> $GITHUB_OUTPUT
-          echo "$changed_files" >> $GITHUB_OUTPUT
-          echo "EOF" >> $GITHUB_OUTPUT
+          pip install ruff
 
-      - name: Run Ruff on Changed Files
-        if: ${{ steps.changed-files.outputs.files != '' }}
-        run: |
-          echo "${{ steps.changed-files.outputs.files }}" | tr " " "\n" | xargs -I{} ruff check "{}"
+      - name: Run Ruff Linter
+        run: ruff check

.ruff.toml

@@ -2,3 +2,8 @@ exclude = [
     "templates",
     "__init__.py",
 ]
+
+[lint]
+select = [
+    "I", # isort rules
+]

docs/concepts/knowledge.mdx

@@ -700,11 +700,4 @@ recent_news = SpaceNewsKnowledgeSource(
     - Configure appropriate embedding models
     - Consider using local embedding providers for faster processing
   </Accordion>
-
-  <Accordion title="One Time Knowledge">
-    - With the typical file structure provided by CrewAI, knowledge sources are embedded every time the kickoff is triggered.
-    - If the knowledge sources are large, this leads to inefficiency and increased latency, as the same data is embedded each time.
-    - To resolve this, directly initialize the knowledge parameter instead of the knowledge_sources parameter.
-    - Link to the issue to get complete idea [Github Issue](https://github.com/crewAIInc/crewAI/issues/2755)
-  </Accordion>  
 </AccordionGroup>

src/crewai/agent.py

@@ -20,7 +20,6 @@ from crewai.tools.agent_tools.agent_tools import AgentTools
 from crewai.utilities import Converter, Prompts
 from crewai.utilities.agent_utils import (
     get_tool_names,
-    load_agent_from_repository,
     parse_tools,
     render_text_description_and_args,
 )
@@ -135,16 +134,6 @@ class Agent(BaseAgent):
         default=None,
         description="Knowledge search query for the agent dynamically generated by the agent.",
     )
-    from_repository: Optional[str] = Field(
-        default=None,
-        description="The Agent's role to be used from your repository.",
-    )
-
-    @model_validator(mode="before")
-    def validate_from_repository(cls, v):
-        if v is not None and (from_repository := v.get("from_repository")):
-            return load_agent_from_repository(from_repository) | v
-        return v
 
     @model_validator(mode="after")
     def post_init_setup(self):

src/crewai/cli/authentication/token.py

@@ -5,5 +5,5 @@ def get_auth_token() -> str:
     """Get the authentication token."""
     access_token = TokenManager().get_token()
     if not access_token:
-        raise Exception("No token found, make sure you are logged in")
+        raise Exception()
     return access_token

src/crewai/cli/plus_api.py

@@ -14,7 +14,6 @@ class PlusAPI:
 
     TOOLS_RESOURCE = "/crewai_plus/api/v1/tools"
     CREWS_RESOURCE = "/crewai_plus/api/v1/crews"
-    AGENTS_RESOURCE = "/crewai_plus/api/v1/agents"
 
     def __init__(self, api_key: str) -> None:
         self.api_key = api_key
@@ -38,9 +37,6 @@ class PlusAPI:
     def get_tool(self, handle: str):
         return self._make_request("GET", f"{self.TOOLS_RESOURCE}/{handle}")
 
-    def get_agent(self, handle: str):
-        return self._make_request("GET", f"{self.AGENTS_RESOURCE}/{handle}")
-
     def publish_tool(
         self,
         handle: str,

src/crewai/crew.py

@@ -52,7 +52,7 @@ from crewai.tools.agent_tools.agent_tools import AgentTools
 from crewai.tools.base_tool import BaseTool, Tool
 from crewai.types.usage_metrics import UsageMetrics
 from crewai.utilities import I18N, FileHandler, Logger, RPMController
-from crewai.utilities.constants import NOT_SPECIFIED, TRAINING_DATA_FILE
+from crewai.utilities.constants import TRAINING_DATA_FILE
 from crewai.utilities.evaluators.crew_evaluator_handler import CrewEvaluator
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
 from crewai.utilities.events.crew_events import (
@@ -478,7 +478,7 @@ class Crew(FlowTrackable, BaseModel):
         separated by a synchronous task.
         """
         for i, task in enumerate(self.tasks):
-            if task.async_execution and isinstance(task.context, list):
+            if task.async_execution and task.context:
                 for context_task in task.context:
                     if context_task.async_execution:
                         for j in range(i - 1, -1, -1):
@@ -496,7 +496,7 @@ class Crew(FlowTrackable, BaseModel):
         task_indices = {id(task): i for i, task in enumerate(self.tasks)}
 
         for task in self.tasks:
-            if isinstance(task.context, list):
+            if task.context:
                 for context_task in task.context:
                     if id(context_task) not in task_indices:
                         continue  # Skip context tasks not in the main tasks list
@@ -1034,14 +1034,11 @@ class Crew(FlowTrackable, BaseModel):
                 )
         return cast(List[BaseTool], tools)
 
-    def _get_context(self, task: Task, task_outputs: List[TaskOutput]) -> str:
-        if not task.context:
-            return ""
-
+    def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
         context = (
-            aggregate_raw_outputs_from_task_outputs(task_outputs)
-            if task.context is NOT_SPECIFIED
-            else aggregate_raw_outputs_from_tasks(task.context)
+            aggregate_raw_outputs_from_tasks(task.context)
+            if task.context
+            else aggregate_raw_outputs_from_task_outputs(task_outputs)
         )
         return context
 
@@ -1229,7 +1226,7 @@ class Crew(FlowTrackable, BaseModel):
             task_mapping[task.key] = cloned_task
 
         for cloned_task, original_task in zip(cloned_tasks, self.tasks):
-            if isinstance(original_task.context, list):
+            if original_task.context:
                 cloned_context = [
                     task_mapping[context_task.key]
                     for context_task in original_task.context

src/crewai/llm.py

@@ -5,7 +5,8 @@ import sys
 import threading
 import warnings
 from collections import defaultdict
-from contextlib import contextmanager, redirect_stderr, redirect_stdout
+from contextlib import contextmanager
+from types import SimpleNamespace
 from typing import (
     Any,
     DefaultDict,
@@ -30,6 +31,7 @@ from crewai.utilities.events.llm_events import (
     LLMCallType,
     LLMStreamChunkEvent,
 )
+from crewai.utilities.events.tool_usage_events import ToolExecutionErrorEvent
 
 with warnings.catch_warnings():
     warnings.simplefilter("ignore", UserWarning)
@@ -43,9 +45,6 @@ with warnings.catch_warnings():
     from litellm.utils import supports_response_schema
 
 
-import io
-from typing import TextIO
-
 from crewai.llms.base_llm import BaseLLM
 from crewai.utilities.events import crewai_event_bus
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
@@ -55,17 +54,12 @@ from crewai.utilities.exceptions.context_window_exceeding_exception import (
 load_dotenv()
 
 
-class FilteredStream(io.TextIOBase):
-    _lock = None
-
-    def __init__(self, original_stream: TextIO):
+class FilteredStream:
+    def __init__(self, original_stream):
         self._original_stream = original_stream
         self._lock = threading.Lock()
 
-    def write(self, s: str) -> int:
-        if not self._lock:
-            self._lock = threading.Lock()
-
+    def write(self, s) -> int:
         with self._lock:
             # Filter out extraneous messages from LiteLLM
             if (
@@ -220,11 +214,15 @@ def suppress_warnings():
         )
 
         # Redirect stdout and stderr
-        with (
-            redirect_stdout(FilteredStream(sys.stdout)),
-            redirect_stderr(FilteredStream(sys.stderr)),
-        ):
+        old_stdout = sys.stdout
+        old_stderr = sys.stderr
+        sys.stdout = FilteredStream(old_stdout)
+        sys.stderr = FilteredStream(old_stderr)
+        try:
             yield
+        finally:
+            sys.stdout = old_stdout
+            sys.stderr = old_stderr
 
 
 class Delta(TypedDict):

src/crewai/task.py

@@ -2,6 +2,7 @@ import datetime
 import inspect
 import json
 import logging
+import re
 import threading
 import uuid
 from concurrent.futures import Future
@@ -40,7 +41,6 @@ from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
 from crewai.tools.base_tool import BaseTool
 from crewai.utilities.config import process_config
-from crewai.utilities.constants import NOT_SPECIFIED
 from crewai.utilities.converter import Converter, convert_to_model
 from crewai.utilities.events import (
     TaskCompletedEvent,
@@ -97,7 +97,7 @@ class Task(BaseModel):
     )
     context: Optional[List["Task"]] = Field(
         description="Other tasks that will have their output used as context for this task.",
-        default=NOT_SPECIFIED,
+        default=None,
     )
     async_execution: Optional[bool] = Field(
         description="Whether the task should be executed asynchronously or not.",
@@ -321,8 +321,11 @@ class Task(BaseModel):
     @model_validator(mode="after")
     def check_tools(self):
         """Check if the tools are set."""
-        if not self.tools and self.agent and self.agent.tools:
-            self.tools.extend(self.agent.tools)
+        if self.agent and self.agent.tools:
+            existing_tool_names = {tool.name for tool in self.tools}
+            for tool in self.agent.tools:
+                if tool.name not in existing_tool_names:
+                    self.tools.append(tool)
         return self
 
     @model_validator(mode="after")
@@ -643,7 +646,7 @@ class Task(BaseModel):
 
         cloned_context = (
             [task_mapping[context_task.key] for context_task in self.context]
-            if isinstance(self.context, list)
+            if self.context
             else None
         )
 

src/crewai/telemetry/telemetry.py

@@ -10,18 +10,6 @@ from contextlib import contextmanager
 from importlib.metadata import version
 from typing import TYPE_CHECKING, Any, Optional
 
-from opentelemetry import trace
-from opentelemetry.exporter.otlp.proto.http.trace_exporter import (
-    OTLPSpanExporter,
-)
-from opentelemetry.sdk.resources import SERVICE_NAME, Resource
-from opentelemetry.sdk.trace import TracerProvider
-from opentelemetry.sdk.trace.export import (
-    BatchSpanProcessor,
-    SpanExportResult,
-)
-from opentelemetry.trace import Span, Status, StatusCode
-
 from crewai.telemetry.constants import (
     CREWAI_TELEMETRY_BASE_URL,
     CREWAI_TELEMETRY_SERVICE_NAME,
@@ -37,6 +25,18 @@ def suppress_warnings():
         yield
 
 
+from opentelemetry import trace  # noqa: E402
+from opentelemetry.exporter.otlp.proto.http.trace_exporter import (
+    OTLPSpanExporter,  # noqa: E402
+)
+from opentelemetry.sdk.resources import SERVICE_NAME, Resource  # noqa: E402
+from opentelemetry.sdk.trace import TracerProvider  # noqa: E402
+from opentelemetry.sdk.trace.export import (  # noqa: E402
+    BatchSpanProcessor,
+    SpanExportResult,
+)
+from opentelemetry.trace import Span, Status, StatusCode  # noqa: E402
+
 if TYPE_CHECKING:
     from crewai.crew import Crew
     from crewai.task import Task
@@ -232,7 +232,7 @@ class Telemetry:
                                 "agent_key": task.agent.key if task.agent else None,
                                 "context": (
                                     [task.description for task in task.context]
-                                    if isinstance(task.context, list)
+                                    if task.context
                                     else None
                                 ),
                                 "tools_names": [
@@ -748,7 +748,7 @@ class Telemetry:
                             "agent_key": task.agent.key if task.agent else None,
                             "context": (
                                 [task.description for task in task.context]
-                                if isinstance(task.context, list)
+                                if task.context
                                 else None
                             ),
                             "tools_names": [

src/crewai/utilities/agent_utils.py

@@ -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.errors import AgentRepositoryError
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
 )
@@ -429,41 +428,3 @@ def show_agent_logs(
             printer.print(
                 content=f"\033[95m## Final Answer:\033[00m \033[92m\n{formatted_answer.output}\033[00m\n\n"
             )
-
-
-def load_agent_from_repository(from_repository: str) -> Dict[str, Any]:
-    attributes: Dict[str, Any] = {}
-    if from_repository:
-        import importlib
-
-        from crewai.cli.authentication.token import get_auth_token
-        from crewai.cli.plus_api import PlusAPI
-
-        client = PlusAPI(api_key=get_auth_token())
-        response = client.get_agent(from_repository)
-        if response.status_code == 404:
-            raise AgentRepositoryError(
-                f"Agent {from_repository} does not exist, make sure the name is correct or the agent is available on your organization"
-            )
-
-        if response.status_code != 200:
-            raise AgentRepositoryError(
-                f"Agent {from_repository} could not be loaded: {response.text}"
-            )
-
-        agent = response.json()
-        for key, value in agent.items():
-            if key == "tools":
-                attributes[key] = []
-                for tool in value:
-                    try:
-                        module = importlib.import_module("crewai_tools")
-                        tool_class = getattr(module, tool["name"])
-                        attributes[key].append(tool_class())
-                    except Exception as e:
-                        raise AgentRepositoryError(
-                            f"Tool {tool['name']} could not be loaded: {e}"
-                        ) from e
-            else:
-                attributes[key] = value
-    return attributes

src/crewai/utilities/constants.py

@@ -5,14 +5,3 @@ KNOWLEDGE_DIRECTORY = "knowledge"
 MAX_LLM_RETRY = 3
 MAX_FILE_NAME_LENGTH = 255
 EMITTER_COLOR = "bold_blue"
-
-
-class _NotSpecified:
-    def __repr__(self):
-        return "NOT_SPECIFIED"
-
-
-# Sentinel value used to detect when no value has been explicitly provided.
-# Unlike `None`, which might be a valid value from the user, `NOT_SPECIFIED` allows
-# us to distinguish between "not passed at all" and "explicitly passed None" or "[]".
-NOT_SPECIFIED = _NotSpecified()

src/crewai/utilities/errors.py

@@ -1,5 +1,4 @@
 """Error message definitions for CrewAI database operations."""
-
 from typing import Optional
 
 
@@ -38,9 +37,3 @@ class DatabaseError:
             The formatted error message
         """
         return template.format(str(error))
-
-
-class AgentRepositoryError(Exception):
-    """Exception raised when an agent repository is not found."""
-
-    ...

src/crewai/utilities/formatter.py

@@ -1,6 +1,6 @@
+import re
 from typing import TYPE_CHECKING, List
 
-
 if TYPE_CHECKING:
     from crewai.task import Task
     from crewai.tasks.task_output import TaskOutput
@@ -17,11 +17,6 @@ def aggregate_raw_outputs_from_task_outputs(task_outputs: List["TaskOutput"]) ->
 
 def aggregate_raw_outputs_from_tasks(tasks: List["Task"]) -> str:
     """Generate string context from the tasks."""
-
-    task_outputs = (
-        [task.output for task in tasks if task.output is not None]
-        if isinstance(tasks, list)
-        else []
-    )
+    task_outputs = [task.output for task in tasks if task.output is not None]
 
     return aggregate_raw_outputs_from_task_outputs(task_outputs)

tests/agent_test.py

@@ -2,7 +2,7 @@
 
 import os
 from unittest import mock
-from unittest.mock import MagicMock, patch
+from unittest.mock import patch
 
 import pytest
 
@@ -18,7 +18,6 @@ from crewai.tools import tool
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
 from crewai.utilities import RPMController
-from crewai.utilities.errors import AgentRepositoryError
 from crewai.utilities.events import crewai_event_bus
 from crewai.utilities.events.tool_usage_events import ToolUsageFinishedEvent
 
@@ -309,7 +308,9 @@ def test_cache_hitting():
     def handle_tool_end(source, event):
         received_events.append(event)
 
-    with (patch.object(CacheHandler, "read") as read,):
+    with (
+        patch.object(CacheHandler, "read") as read,
+    ):
         read.return_value = "0"
         task = Task(
             description="What is 2 times 6? Ignore correctness and just return the result of the multiplication tool, you must use the tool.",
@@ -1039,7 +1040,7 @@ def test_agent_human_input():
             CrewAgentExecutor,
             "_invoke_loop",
             return_value=AgentFinish(output="Hello", thought="", text=""),
-        ),
+        ) as mock_invoke_loop,
     ):
         # Execute the task
         output = agent.execute_task(task)
@@ -2024,99 +2025,3 @@ def test_get_knowledge_search_query():
                 },
             ]
         )
-
-
-@pytest.fixture
-def mock_get_auth_token():
-    with patch(
-        "crewai.cli.authentication.token.get_auth_token", return_value="test_token"
-    ):
-        yield
-
-
-@patch("crewai.cli.plus_api.PlusAPI.get_agent")
-def test_agent_from_repository(mock_get_agent, mock_get_auth_token):
-    from crewai_tools import SerperDevTool
-
-    mock_get_response = MagicMock()
-    mock_get_response.status_code = 200
-    mock_get_response.json.return_value = {
-        "role": "test role",
-        "goal": "test goal",
-        "backstory": "test backstory",
-        "tools": [{"name": "SerperDevTool"}],
-    }
-    mock_get_agent.return_value = mock_get_response
-    agent = Agent(from_repository="test_agent")
-
-    assert agent.role == "test role"
-    assert agent.goal == "test goal"
-    assert agent.backstory == "test backstory"
-    assert len(agent.tools) == 1
-    assert isinstance(agent.tools[0], SerperDevTool)
-
-
-@patch("crewai.cli.plus_api.PlusAPI.get_agent")
-def test_agent_from_repository_override_attributes(mock_get_agent, mock_get_auth_token):
-    from crewai_tools import SerperDevTool
-
-    mock_get_response = MagicMock()
-    mock_get_response.status_code = 200
-    mock_get_response.json.return_value = {
-        "role": "test role",
-        "goal": "test goal",
-        "backstory": "test backstory",
-        "tools": [{"name": "SerperDevTool"}],
-    }
-    mock_get_agent.return_value = mock_get_response
-    agent = Agent(from_repository="test_agent", role="Custom Role")
-
-    assert agent.role == "Custom Role"
-    assert agent.goal == "test goal"
-    assert agent.backstory == "test backstory"
-    assert len(agent.tools) == 1
-    assert isinstance(agent.tools[0], SerperDevTool)
-
-
-@patch("crewai.cli.plus_api.PlusAPI.get_agent")
-def test_agent_from_repository_with_invalid_tools(mock_get_agent, mock_get_auth_token):
-    mock_get_response = MagicMock()
-    mock_get_response.status_code = 200
-    mock_get_response.json.return_value = {
-        "role": "test role",
-        "goal": "test goal",
-        "backstory": "test backstory",
-        "tools": [{"name": "DoesNotExist"}],
-    }
-    mock_get_agent.return_value = mock_get_response
-    with pytest.raises(
-        AgentRepositoryError,
-        match="Tool DoesNotExist could not be loaded: module 'crewai_tools' has no attribute 'DoesNotExist'",
-    ):
-        Agent(from_repository="test_agent")
-
-
-@patch("crewai.cli.plus_api.PlusAPI.get_agent")
-def test_agent_from_repository_internal_error(mock_get_agent, mock_get_auth_token):
-    mock_get_response = MagicMock()
-    mock_get_response.status_code = 500
-    mock_get_response.text = "Internal server error"
-    mock_get_agent.return_value = mock_get_response
-    with pytest.raises(
-        AgentRepositoryError,
-        match="Agent test_agent could not be loaded: Internal server error",
-    ):
-        Agent(from_repository="test_agent")
-
-
-@patch("crewai.cli.plus_api.PlusAPI.get_agent")
-def test_agent_from_repository_agent_not_found(mock_get_agent, mock_get_auth_token):
-    mock_get_response = MagicMock()
-    mock_get_response.status_code = 404
-    mock_get_response.text = "Agent not found"
-    mock_get_agent.return_value = mock_get_response
-    with pytest.raises(
-        AgentRepositoryError,
-        match="Agent test_agent does not exist, make sure the name is correct or the agent is available on your organization",
-    ):
-        Agent(from_repository="test_agent")

tests/cassettes/test_agent_human_input.yaml

@@ -0,0 +1,520 @@
+interactions:
+- request:
+    body: !!binary |
+      CqcXCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS/hYKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRJ5ChBuJJtOdNaB05mOW/p3915eEgj2tkAd3rZcASoQVG9vbCBVc2FnZSBFcnJvcjAB
+      OYa7/URvKBUYQUpcFEVvKBUYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoPCgNsbG0SCAoG
+      Z3B0LTRvegIYAYUBAAEAABLJBwoQifhX01E5i+5laGdALAlZBBIIBuGM1aN+OPgqDENyZXcgQ3Jl
+      YXRlZDABORVGruBvKBUYQaipwOBvKBUYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5w
+      eXRob25fdmVyc2lvbhIICgYzLjEyLjdKLgoIY3Jld19rZXkSIgogN2U2NjA4OTg5ODU5YTY3ZWVj
+      ODhlZWY3ZmNlODUyMjVKMQoHY3Jld19pZBImCiRiOThiNWEwMC01YTI1LTQxMDctYjQwNS1hYmYz
+      MjBhOGYzYThKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAA
+      ShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgB
+      SuQCCgtjcmV3X2FnZW50cxLUAgrRAlt7ImtleSI6ICIyMmFjZDYxMWU0NGVmNWZhYzA1YjUzM2Q3
+      NWU4ODkzYiIsICJpZCI6ICJkNWIyMzM1YS0yMmIyLTQyZWEtYmYwNS03OTc3NmU3MmYzOTIiLCAi
+      cm9sZSI6ICJEYXRhIFNjaWVudGlzdCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAy
+      MCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJn
+      cHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4
+      ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFsi
+      Z2V0IGdyZWV0aW5ncyJdfV1KkgIKCmNyZXdfdGFza3MSgwIKgAJbeyJrZXkiOiAiYTI3N2IzNGIy
+      YzE0NmYwYzU2YzVlMTM1NmU4ZjhhNTciLCAiaWQiOiAiMjJiZWMyMzEtY2QyMS00YzU4LTgyN2Ut
+      MDU4MWE4ZjBjMTExIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6
+      IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJEYXRhIFNjaWVudGlzdCIsICJhZ2VudF9rZXkiOiAiMjJh
+      Y2Q2MTFlNDRlZjVmYWMwNWI1MzNkNzVlODg5M2IiLCAidG9vbHNfbmFtZXMiOiBbImdldCBncmVl
+      dGluZ3MiXX1degIYAYUBAAEAABKOAgoQ5WYoxRtTyPjge4BduhL0rRIIv2U6rvWALfwqDFRhc2sg
+      Q3JlYXRlZDABOX068uBvKBUYQZkv8+BvKBUYSi4KCGNyZXdfa2V5EiIKIDdlNjYwODk4OTg1OWE2
+      N2VlYzg4ZWVmN2ZjZTg1MjI1SjEKB2NyZXdfaWQSJgokYjk4YjVhMDAtNWEyNS00MTA3LWI0MDUt
+      YWJmMzIwYThmM2E4Si4KCHRhc2tfa2V5EiIKIGEyNzdiMzRiMmMxNDZmMGM1NmM1ZTEzNTZlOGY4
+      YTU3SjEKB3Rhc2tfaWQSJgokMjJiZWMyMzEtY2QyMS00YzU4LTgyN2UtMDU4MWE4ZjBjMTExegIY
+      AYUBAAEAABKQAQoQXyeDtJDFnyp2Fjk9YEGTpxIIaNE7gbhPNYcqClRvb2wgVXNhZ2UwATkaXTvj
+      bygVGEGvx0rjbygVGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKHAoJdG9vbF9uYW1lEg8K
+      DUdldCBHcmVldGluZ3NKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAABLVBwoQMWfznt0qwauEzl7T
+      UOQxRBII9q+pUS5EdLAqDENyZXcgQ3JlYXRlZDABORONPORvKBUYQSAoS+RvKBUYShoKDmNyZXdh
+      aV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjEyLjdKLgoIY3Jld19r
+      ZXkSIgogYzMwNzYwMDkzMjY3NjE0NDRkNTdjNzFkMWRhM2YyN2NKMQoHY3Jld19pZBImCiQ3OTQw
+      MTkyNS1iOGU5LTQ3MDgtODUzMC00NDhhZmEzYmY4YjBKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVl
+      bnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVj
+      cmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSuoCCgtjcmV3X2FnZW50cxLaAgrXAlt7ImtleSI6ICI5
+      OGYzYjFkNDdjZTk2OWNmMDU3NzI3Yjc4NDE0MjVjZCIsICJpZCI6ICI5OTJkZjYyZi1kY2FiLTQy
+      OTUtOTIwNi05MDBkNDExNGIxZTkiLCAicm9sZSI6ICJGcmllbmRseSBOZWlnaGJvciIsICJ2ZXJi
+      b3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25f
+      Y2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJs
+      ZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9s
+      aW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFsiZGVjaWRlIGdyZWV0aW5ncyJdfV1KmAIKCmNyZXdf
+      dGFza3MSiQIKhgJbeyJrZXkiOiAiODBkN2JjZDQ5MDk5MjkwMDgzODMyZjBlOTgzMzgwZGYiLCAi
+      aWQiOiAiMmZmNjE5N2UtYmEyNy00YjczLWI0YTctNGZhMDQ4ZTYyYjQ3IiwgImFzeW5jX2V4ZWN1
+      dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJGcmll
+      bmRseSBOZWlnaGJvciIsICJhZ2VudF9rZXkiOiAiOThmM2IxZDQ3Y2U5NjljZjA1NzcyN2I3ODQx
+      NDI1Y2QiLCAidG9vbHNfbmFtZXMiOiBbImRlY2lkZSBncmVldGluZ3MiXX1degIYAYUBAAEAABKO
+      AgoQnjTp5boK7/+DQxztYIpqihIIgGnMUkBtzHEqDFRhc2sgQ3JlYXRlZDABOcpYcuRvKBUYQalE
+      c+RvKBUYSi4KCGNyZXdfa2V5EiIKIGMzMDc2MDA5MzI2NzYxNDQ0ZDU3YzcxZDFkYTNmMjdjSjEK
+      B2NyZXdfaWQSJgokNzk0MDE5MjUtYjhlOS00NzA4LTg1MzAtNDQ4YWZhM2JmOGIwSi4KCHRhc2tf
+      a2V5EiIKIDgwZDdiY2Q0OTA5OTI5MDA4MzgzMmYwZTk4MzM4MGRmSjEKB3Rhc2tfaWQSJgokMmZm
+      NjE5N2UtYmEyNy00YjczLWI0YTctNGZhMDQ4ZTYyYjQ3egIYAYUBAAEAABKTAQoQ26H9pLUgswDN
+      p9XhJwwL6BIIx3bw7mAvPYwqClRvb2wgVXNhZ2UwATmy7NPlbygVGEEvb+HlbygVGEoaCg5jcmV3
+      YWlfdmVyc2lvbhIICgYwLjg2LjBKHwoJdG9vbF9uYW1lEhIKEERlY2lkZSBHcmVldGluZ3NKDgoI
+      YXR0ZW1wdHMSAhgBegIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '2986'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Fri, 27 Dec 2024 22:14:53 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
+      personal goal is: test goal\nTo give my best complete final answer to the task
+      use the exact following format:\n\nThought: I now can give a great answer\nFinal
+      Answer: Your final answer must be the great and the most complete as possible,
+      it must be outcome described.\n\nI MUST use these formats, my job depends on
+      it!"}, {"role": "user", "content": "\nCurrent Task: Say the word: Hi\n\nThis
+      is the expect criteria for your final answer: The word: Hi\nyou MUST return
+      the actual complete content as the final answer, not a summary.\n\nBegin! This
+      is VERY important to you, use the tools available and give your best Final Answer,
+      your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '824'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=ePJSDFdHag2D8lj21_ijAMWjoA6xfnPNxN4uekvC728-1727226247743-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AjCtZLLrWi8ZASpP9bz6HaCV7xBIn\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735337693,\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: Hi\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      158,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 170,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f8caa83deca756b-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 22:14:53 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=wJkq_yLkzE3OdxE0aMJz.G0kce969.9JxRmZ0ratl4c-1735337693-1.0.1.1-OKpUoRrSPFGvWv5Hp5ET1PNZ7iZNHPKEAuakpcQUxxPSeisUIIR3qIOZ31MGmYugqB5.wkvidgbxOAagqJvmnw;
+        path=/; expires=Fri, 27-Dec-24 22:44:53 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=A_ASCLNAVfQoyucWOAIhecWtEpNotYoZr0bAFihgNxs-1735337693273-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '404'
+      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:
+      - '149999816'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_6ac84634bff9193743c4b0911c09b4a6
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "Determine if the following
+      feedback indicates that the user is satisfied or if further changes are needed.
+      Respond with ''True'' if further changes are needed, or ''False'' if the user
+      is satisfied. **Important** Do not include any additional commentary outside
+      of your ''True'' or ''False'' response.\n\nFeedback: \"Don''t say hi, say Hello
+      instead!\""}], "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream":
+      false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '461'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=A_ASCLNAVfQoyucWOAIhecWtEpNotYoZr0bAFihgNxs-1735337693273-0.0.1.1-604800000;
+        __cf_bm=wJkq_yLkzE3OdxE0aMJz.G0kce969.9JxRmZ0ratl4c-1735337693-1.0.1.1-OKpUoRrSPFGvWv5Hp5ET1PNZ7iZNHPKEAuakpcQUxxPSeisUIIR3qIOZ31MGmYugqB5.wkvidgbxOAagqJvmnw
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AjCtZNlWdrrPZhq0MJDqd16sMuQEJ\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735337693,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"True\",\n        \"refusal\": null\n
+      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 78,\n    \"completion_tokens\":
+      1,\n    \"total_tokens\": 79,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f8caa87094f756b-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 22:14:53 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '156'
+      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:
+      - '149999898'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_ec74bef2a9ef7b2144c03fd7f7bbeab0
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
+      personal goal is: test goal\nTo give my best complete final answer to the task
+      use the exact following format:\n\nThought: I now can give a great answer\nFinal
+      Answer: Your final answer must be the great and the most complete as possible,
+      it must be outcome described.\n\nI MUST use these formats, my job depends on
+      it!"}, {"role": "user", "content": "\nCurrent Task: Say the word: Hi\n\nThis
+      is the expect criteria for your final answer: The word: Hi\nyou MUST return
+      the actual complete content as the final answer, not a summary.\n\nBegin! This
+      is VERY important to you, use the tools available and give your best Final Answer,
+      your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I now
+      can give a great answer  \nFinal Answer: Hi"}, {"role": "user", "content": "Feedback:
+      Don''t say hi, say Hello instead!"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '986'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=A_ASCLNAVfQoyucWOAIhecWtEpNotYoZr0bAFihgNxs-1735337693273-0.0.1.1-604800000;
+        __cf_bm=wJkq_yLkzE3OdxE0aMJz.G0kce969.9JxRmZ0ratl4c-1735337693-1.0.1.1-OKpUoRrSPFGvWv5Hp5ET1PNZ7iZNHPKEAuakpcQUxxPSeisUIIR3qIOZ31MGmYugqB5.wkvidgbxOAagqJvmnw
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AjCtZGv4f3h7GDdhyOy9G0sB1lRgC\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735337693,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I understand the feedback and
+      will adjust my response accordingly.  \\nFinal Answer: Hello\",\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 188,\n    \"completion_tokens\":
+      18,\n    \"total_tokens\": 206,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f8caa88cac4756b-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 22:14:54 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '358'
+      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:
+      - '149999793'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_ae1ab6b206d28ded6fee3c83ed0c2ab7
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "Determine if the following
+      feedback indicates that the user is satisfied or if further changes are needed.
+      Respond with ''True'' if further changes are needed, or ''False'' if the user
+      is satisfied. **Important** Do not include any additional commentary outside
+      of your ''True'' or ''False'' response.\n\nFeedback: \"looks good\""}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '439'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=A_ASCLNAVfQoyucWOAIhecWtEpNotYoZr0bAFihgNxs-1735337693273-0.0.1.1-604800000;
+        __cf_bm=wJkq_yLkzE3OdxE0aMJz.G0kce969.9JxRmZ0ratl4c-1735337693-1.0.1.1-OKpUoRrSPFGvWv5Hp5ET1PNZ7iZNHPKEAuakpcQUxxPSeisUIIR3qIOZ31MGmYugqB5.wkvidgbxOAagqJvmnw
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AjCtaiHL4TY8Dssk0j2miqmjrzquy\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735337694,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"False\",\n        \"refusal\": null\n
+      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 73,\n    \"completion_tokens\":
+      1,\n    \"total_tokens\": 74,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f8caa8bdd26756b-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 22:14:54 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '184'
+      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:
+      - '149999902'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_652891f79c1104a7a8436275d78a69f1
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/task_test.py

@@ -43,7 +43,7 @@ def test_task_tool_reflect_agent_tools():
     assert task.tools == [fake_tool]
 
 
-def test_task_tool_takes_precedence_over_agent_tools():
+def test_task_tools_combined_with_agent_tools():
     from crewai.tools import tool
 
     @tool
@@ -52,7 +52,7 @@ def test_task_tool_takes_precedence_over_agent_tools():
 
     @tool
     def fake_task_tool() -> None:
-        "Fake tool"
+        "Fake task tool"
 
     researcher = Agent(
         role="Researcher",
@@ -69,7 +69,9 @@ def test_task_tool_takes_precedence_over_agent_tools():
         tools=[fake_task_tool],
     )
 
-    assert task.tools == [fake_task_tool]
+    assert len(task.tools) == 2
+    assert any(tool.name == fake_task_tool.name for tool in task.tools)
+    assert any(tool.name == fake_tool.name for tool in task.tools)
 
 
 def test_task_prompt_includes_expected_output():
@@ -1455,4 +1457,4 @@ def test_task_with_max_execution_time_exceeded():
     )
 
     with pytest.raises(TimeoutError):
-        task.execute_sync(agent=researcher)
+        task.execute_sync(agent=researcher)