quick fix for mike

docs/concepts/agents.mdx

@@ -43,7 +43,7 @@ Think of an agent as a specialized team member with specific skills, expertise,
 | **Max Retry Limit** _(optional)_        | `max_retry_limit`        | `int`                         | Maximum number of retries when an error occurs. Default is 2.                                                         |
 | **Respect Context Window** _(optional)_ | `respect_context_window` | `bool`                        | Keep messages under context window size by summarizing. Default is True.                                              |
 | **Code Execution Mode** _(optional)_    | `code_execution_mode`    | `Literal["safe", "unsafe"]`   | Mode for code execution: 'safe' (using Docker) or 'unsafe' (direct). Default is 'safe'.                               |
-| **Embedder** _(optional)_               | `embedder`               | `Optional[Dict[str, Any]]`    | Configuration for the embedder used by the agent.                                                                     |
+| **Embedder Config** _(optional)_        | `embedder_config`        | `Optional[Dict[str, Any]]`    | Configuration for the embedder used by the agent.                                                                     |
 | **Knowledge Sources** _(optional)_      | `knowledge_sources`      | `Optional[List[BaseKnowledgeSource]]` | Knowledge sources available to the agent.                                                                     |
 | **Use System Prompt** _(optional)_      | `use_system_prompt`      | `Optional[bool]`              | Whether to use system prompt (for o1 model support). Default is True.                                                 |
 
@@ -152,7 +152,7 @@ agent = Agent(
     use_system_prompt=True,  # Default: True
     tools=[SerperDevTool()],  # Optional: List of tools
     knowledge_sources=None,  # Optional: List of knowledge sources
-    embedder=None,  # Optional: Custom embedder configuration
+    embedder_config=None,  # Optional: Custom embedder configuration
     system_template=None,  # Optional: Custom system prompt template
     prompt_template=None,  # Optional: Custom prompt template
     response_template=None,  # Optional: Custom response template

docs/concepts/knowledge.mdx

@@ -324,13 +324,6 @@ agent = Agent(
     verbose=True,
     allow_delegation=False,
     llm=gemini_llm,
-    embedder={
-        "provider": "google",
-        "config": {
-            "model": "models/text-embedding-004",
-            "api_key": GEMINI_API_KEY,
-        }
-    }
 )
 
 task = Task(

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.100.0"
+version = "0.98.0"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
@@ -11,7 +11,7 @@ dependencies = [
     # Core Dependencies
     "pydantic>=2.4.2",
     "openai>=1.13.3",
-    "litellm==1.59.8",
+    "litellm==1.57.4",
     "instructor>=1.3.3",
     # Text Processing
     "pdfplumber>=0.11.4",

src/crewai/__init__.py

@@ -14,7 +14,7 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.100.0"
+__version__ = "0.98.0"
 __all__ = [
     "Agent",
     "Crew",

src/crewai/agent.py

@@ -61,7 +61,6 @@ class Agent(BaseAgent):
             tools: Tools at agents disposal
             step_callback: Callback to be executed after each step of the agent execution.
             knowledge_sources: Knowledge sources for the agent.
-            embedder: Embedder configuration for the agent.
     """
 
     _times_executed: int = PrivateAttr(default=0)
@@ -123,10 +122,17 @@ class Agent(BaseAgent):
         default="safe",
         description="Mode for code execution: 'safe' (using Docker) or 'unsafe' (direct execution).",
     )
-    embedder: Optional[Dict[str, Any]] = Field(
+    embedder_config: Optional[Dict[str, Any]] = Field(
         default=None,
         description="Embedder configuration for the agent.",
     )
+    knowledge_sources: Optional[List[BaseKnowledgeSource]] = Field(
+        default=None,
+        description="Knowledge sources for the agent.",
+    )
+    _knowledge: Optional[Knowledge] = PrivateAttr(
+        default=None,
+    )
 
     @model_validator(mode="after")
     def post_init_setup(self):
@@ -157,11 +163,10 @@ class Agent(BaseAgent):
                 if isinstance(self.knowledge_sources, list) and all(
                     isinstance(k, BaseKnowledgeSource) for k in self.knowledge_sources
                 ):
-                    self.knowledge = Knowledge(
+                    self._knowledge = Knowledge(
                         sources=self.knowledge_sources,
-                        embedder=self.embedder,
+                        embedder_config=self.embedder_config,
                         collection_name=knowledge_agent_name,
-                        storage=self.knowledge_storage or None,
                     )
         except (TypeError, ValueError) as e:
             raise ValueError(f"Invalid Knowledge Configuration: {str(e)}")
@@ -220,8 +225,8 @@ class Agent(BaseAgent):
             if memory.strip() != "":
                 task_prompt += self.i18n.slice("memory").format(memory=memory)
 
-        if self.knowledge:
-            agent_knowledge_snippets = self.knowledge.query([task.prompt()])
+        if self._knowledge:
+            agent_knowledge_snippets = self._knowledge.query([task.prompt()])
             if agent_knowledge_snippets:
                 agent_knowledge_context = extract_knowledge_context(
                     agent_knowledge_snippets

src/crewai/agents/agent_builder/base_agent.py

@@ -18,8 +18,6 @@ from pydantic_core import PydanticCustomError
 from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
 from crewai.agents.cache.cache_handler import CacheHandler
 from crewai.agents.tools_handler import ToolsHandler
-from crewai.knowledge.knowledge import Knowledge
-from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.tools import BaseTool
 from crewai.tools.base_tool import Tool
 from crewai.utilities import I18N, Logger, RPMController
@@ -50,8 +48,6 @@ class BaseAgent(ABC, BaseModel):
         cache_handler (InstanceOf[CacheHandler]): An instance of the CacheHandler class.
         tools_handler (InstanceOf[ToolsHandler]): An instance of the ToolsHandler class.
         max_tokens: Maximum number of tokens for the agent to generate in a response.
-        knowledge_sources: Knowledge sources for the agent.
-        knowledge_storage: Custom knowledge storage for the agent.
 
 
     Methods:
@@ -134,17 +130,6 @@ class BaseAgent(ABC, BaseModel):
     max_tokens: Optional[int] = Field(
         default=None, description="Maximum number of tokens for the agent's execution."
     )
-    knowledge: Optional[Knowledge] = Field(
-        default=None, description="Knowledge for the agent."
-    )
-    knowledge_sources: Optional[List[BaseKnowledgeSource]] = Field(
-        default=None,
-        description="Knowledge sources for the agent.",
-    )
-    knowledge_storage: Optional[Any] = Field(
-        default=None,
-        description="Custom knowledge storage for the agent.",
-    )
 
     @model_validator(mode="before")
     @classmethod
@@ -271,44 +256,13 @@ class BaseAgent(ABC, BaseModel):
             "tools_handler",
             "cache_handler",
             "llm",
-            "knowledge_sources",
-            "knowledge_storage",
-            "knowledge",
         }
 
-        # Copy llm
+        # Copy llm and clear callbacks
         existing_llm = shallow_copy(self.llm)
-        copied_knowledge = shallow_copy(self.knowledge)
-        copied_knowledge_storage = shallow_copy(self.knowledge_storage)
-        # Properly copy knowledge sources if they exist
-        existing_knowledge_sources = None
-        if self.knowledge_sources:
-            # Create a shared storage instance for all knowledge sources
-            shared_storage = (
-                self.knowledge_sources[0].storage if self.knowledge_sources else None
-            )
-
-            existing_knowledge_sources = []
-            for source in self.knowledge_sources:
-                copied_source = (
-                    source.model_copy()
-                    if hasattr(source, "model_copy")
-                    else shallow_copy(source)
-                )
-                # Ensure all copied sources use the same storage instance
-                copied_source.storage = shared_storage
-                existing_knowledge_sources.append(copied_source)
-
         copied_data = self.model_dump(exclude=exclude)
         copied_data = {k: v for k, v in copied_data.items() if v is not None}
-        copied_agent = type(self)(
-            **copied_data,
-            llm=existing_llm,
-            tools=self.tools,
-            knowledge_sources=existing_knowledge_sources,
-            knowledge=copied_knowledge,
-            knowledge_storage=copied_knowledge_storage,
-        )
+        copied_agent = type(self)(**copied_data, llm=existing_llm, tools=self.tools)
 
         return copied_agent
 

src/crewai/cli/templates/crew/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.100.0,<1.0.0"
+    "crewai[tools]>=0.98.0,<1.0.0"
 ]
 
 [project.scripts]

src/crewai/cli/templates/flow/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.100.0,<1.0.0",
+    "crewai[tools]>=0.98.0,<1.0.0",
 ]
 
 [project.scripts]

src/crewai/cli/templates/tool/pyproject.toml

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.100.0"
+    "crewai[tools]>=0.98.0"
 ]
 
 [tool.crewai]

src/crewai/crew.py

@@ -4,7 +4,6 @@ import re
 import uuid
 import warnings
 from concurrent.futures import Future
-from copy import copy as shallow_copy
 from hashlib import md5
 from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Union
 
@@ -211,9 +210,8 @@ class Crew(BaseModel):
         default=None,
         description="LLM used to handle chatting with the crew.",
     )
-    knowledge: Optional[Knowledge] = Field(
+    _knowledge: Optional[Knowledge] = PrivateAttr(
         default=None,
-        description="Knowledge for the crew.",
     )
 
     @field_validator("id", mode="before")
@@ -291,7 +289,7 @@ class Crew(BaseModel):
                 if isinstance(self.knowledge_sources, list) and all(
                     isinstance(k, BaseKnowledgeSource) for k in self.knowledge_sources
                 ):
-                    self.knowledge = Knowledge(
+                    self._knowledge = Knowledge(
                         sources=self.knowledge_sources,
                         embedder_config=self.embedder,
                         collection_name="crew",
@@ -993,8 +991,8 @@ class Crew(BaseModel):
         return result
 
     def query_knowledge(self, query: List[str]) -> Union[List[Dict[str, Any]], None]:
-        if self.knowledge:
-            return self.knowledge.query(query)
+        if self._knowledge:
+            return self._knowledge.query(query)
         return None
 
     def fetch_inputs(self) -> Set[str]:
@@ -1038,8 +1036,6 @@ class Crew(BaseModel):
             "_telemetry",
             "agents",
             "tasks",
-            "knowledge_sources",
-            "knowledge",
         }
 
         cloned_agents = [agent.copy() for agent in self.agents]
@@ -1047,9 +1043,6 @@ class Crew(BaseModel):
         task_mapping = {}
 
         cloned_tasks = []
-        existing_knowledge_sources = shallow_copy(self.knowledge_sources)
-        existing_knowledge = shallow_copy(self.knowledge)
-
         for task in self.tasks:
             cloned_task = task.copy(cloned_agents, task_mapping)
             cloned_tasks.append(cloned_task)
@@ -1069,13 +1062,7 @@ class Crew(BaseModel):
         copied_data.pop("agents", None)
         copied_data.pop("tasks", None)
 
-        copied_crew = Crew(
-            **copied_data,
-            agents=cloned_agents,
-            tasks=cloned_tasks,
-            knowledge_sources=existing_knowledge_sources,
-            knowledge=existing_knowledge,
-        )
+        copied_crew = Crew(**copied_data, agents=cloned_agents, tasks=cloned_tasks)
 
         return copied_crew
 

src/crewai/knowledge/knowledge.py

@@ -15,20 +15,20 @@ class Knowledge(BaseModel):
     Args:
         sources: List[BaseKnowledgeSource] = Field(default_factory=list)
         storage: Optional[KnowledgeStorage] = Field(default=None)
-        embedder: Optional[Dict[str, Any]] = None
+        embedder_config: Optional[Dict[str, Any]] = None
     """
 
     sources: List[BaseKnowledgeSource] = Field(default_factory=list)
     model_config = ConfigDict(arbitrary_types_allowed=True)
     storage: Optional[KnowledgeStorage] = Field(default=None)
-    embedder: Optional[Dict[str, Any]] = None
+    embedder_config: Optional[Dict[str, Any]] = None
     collection_name: Optional[str] = None
 
     def __init__(
         self,
         collection_name: str,
         sources: List[BaseKnowledgeSource],
-        embedder: Optional[Dict[str, Any]] = None,
+        embedder_config: Optional[Dict[str, Any]] = None,
         storage: Optional[KnowledgeStorage] = None,
         **data,
     ):
@@ -37,23 +37,25 @@ class Knowledge(BaseModel):
             self.storage = storage
         else:
             self.storage = KnowledgeStorage(
-                embedder=embedder, collection_name=collection_name
+                embedder_config=embedder_config, collection_name=collection_name
             )
         self.sources = sources
         self.storage.initialize_knowledge_storage()
-        self._add_sources()
+        for source in sources:
+            source.storage = self.storage
+            source.add()
 
     def query(self, query: List[str], limit: int = 3) -> List[Dict[str, Any]]:
         """
         Query across all knowledge sources to find the most relevant information.
         Returns the top_k most relevant chunks.
-
+        
         Raises:
             ValueError: If storage is not initialized.
         """
         if self.storage is None:
             raise ValueError("Storage is not initialized.")
-
+            
         results = self.storage.search(
             query,
             limit,
@@ -61,9 +63,6 @@ class Knowledge(BaseModel):
         return results
 
     def _add_sources(self):
-        try:
-            for source in self.sources:
-                source.storage = self.storage
-                source.add()
-        except Exception as e:
-            raise e
+        for source in self.sources:
+            source.storage = self.storage
+            source.add()

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -29,13 +29,7 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
     def validate_file_path(cls, v, info):
         """Validate that at least one of file_path or file_paths is provided."""
         # Single check if both are None, O(1) instead of nested conditions
-        if (
-            v is None
-            and info.data.get(
-                "file_path" if info.field_name == "file_paths" else "file_paths"
-            )
-            is None
-        ):
+        if v is None and info.data.get("file_path" if info.field_name == "file_paths" else "file_paths") is None:
             raise ValueError("Either file_path or file_paths must be provided")
         return v
 

src/crewai/knowledge/storage/knowledge_storage.py

@@ -48,11 +48,11 @@ class KnowledgeStorage(BaseKnowledgeStorage):
 
     def __init__(
         self,
-        embedder: Optional[Dict[str, Any]] = None,
+        embedder_config: Optional[Dict[str, Any]] = None,
         collection_name: Optional[str] = None,
     ):
         self.collection_name = collection_name
-        self._set_embedder_config(embedder)
+        self._set_embedder_config(embedder_config)
 
     def search(
         self,
@@ -99,7 +99,7 @@ class KnowledgeStorage(BaseKnowledgeStorage):
             )
             if self.app:
                 self.collection = self.app.get_or_create_collection(
-                    name=collection_name, embedding_function=self.embedder
+                    name=collection_name, embedding_function=self.embedder_config
                 )
             else:
                 raise Exception("Vector Database Client not initialized")
@@ -187,15 +187,17 @@ class KnowledgeStorage(BaseKnowledgeStorage):
             api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small"
         )
 
-    def _set_embedder_config(self, embedder: Optional[Dict[str, Any]] = None) -> None:
+    def _set_embedder_config(
+        self, embedder_config: Optional[Dict[str, Any]] = None
+    ) -> None:
         """Set the embedding configuration for the knowledge storage.
 
         Args:
             embedder_config (Optional[Dict[str, Any]]): Configuration dictionary for the embedder.
                 If None or empty, defaults to the default embedding function.
         """
-        self.embedder = (
-            EmbeddingConfigurator().configure_embedder(embedder)
-            if embedder
+        self.embedder_config = (
+            EmbeddingConfigurator().configure_embedder(embedder_config)
+            if embedder_config
             else self._create_default_embedding_function()
         )

src/crewai/utilities/embedding_configurator.py

@@ -43,6 +43,7 @@ class EmbeddingConfigurator:
             raise Exception(
                 f"Unsupported embedding provider: {provider}, supported providers: {list(self.embedding_functions.keys())}"
             )
+
         return self.embedding_functions[provider](config, model_name)
 
     @staticmethod

src/crewai/utilities/evaluators/task_evaluator.py

@@ -96,9 +96,9 @@ class TaskEvaluator:
         final_aggregated_data = ""
         for _, data in output_training_data.items():
             final_aggregated_data += (
-                f"Initial Output:\n{data.get('initial_output', '')}\n\n"
-                f"Human Feedback:\n{data.get('human_feedback', '')}\n\n"
-                f"Improved Output:\n{data.get('improved_output', '')}\n\n"
+                f"Initial Output:\n{data['initial_output']}\n\n"
+                f"Human Feedback:\n{data['human_feedback']}\n\n"
+                f"Improved Output:\n{data['improved_output']}\n\n"
             )
 
         evaluation_query = (

tests/agent_test.py

@@ -10,14 +10,13 @@ from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
 from crewai.agents.crew_agent_executor import CrewAgentExecutor
 from crewai.agents.parser import AgentAction, CrewAgentParser, OutputParserException
-from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.llm import LLM
 from crewai.tools import tool
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
 from crewai.tools.tool_usage_events import ToolUsageFinished
-from crewai.utilities import RPMController
+from crewai.utilities import Printer, RPMController
 from crewai.utilities.events import Emitter
 
 
@@ -1603,45 +1602,6 @@ def test_agent_with_knowledge_sources():
         assert "red" in result.raw.lower()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_agent_with_knowledge_sources_works_with_copy():
-    content = "Brandon's favorite color is red and he likes Mexican food."
-    string_source = StringKnowledgeSource(content=content)
-
-    with patch(
-        "crewai.knowledge.source.base_knowledge_source.BaseKnowledgeSource",
-        autospec=True,
-    ) as MockKnowledgeSource:
-        mock_knowledge_source_instance = MockKnowledgeSource.return_value
-        mock_knowledge_source_instance.__class__ = BaseKnowledgeSource
-        mock_knowledge_source_instance.sources = [string_source]
-
-        agent = Agent(
-            role="Information Agent",
-            goal="Provide information based on knowledge sources",
-            backstory="You have access to specific knowledge sources.",
-            llm=LLM(model="gpt-4o-mini"),
-            knowledge_sources=[string_source],
-        )
-
-        with patch(
-            "crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"
-        ) as MockKnowledgeStorage:
-            mock_knowledge_storage = MockKnowledgeStorage.return_value
-            agent.knowledge_storage = mock_knowledge_storage
-
-            agent_copy = agent.copy()
-
-            assert agent_copy.role == agent.role
-            assert agent_copy.goal == agent.goal
-            assert agent_copy.backstory == agent.backstory
-            assert agent_copy.knowledge_sources is not None
-            assert len(agent_copy.knowledge_sources) == 1
-            assert isinstance(agent_copy.knowledge_sources[0], StringKnowledgeSource)
-            assert agent_copy.knowledge_sources[0].content == content
-            assert isinstance(agent_copy.llm, LLM)
-
-
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_litellm_auth_error_handling():
     """Test that LiteLLM authentication errors are handled correctly and not retried."""

tests/cassettes/test_agent_tool_role_matching[ "Futel Official Infopoint" -True].yaml

@@ -0,0 +1,117 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
+      Futel Football Club info\nYour personal goal is: Answer questions about Futel\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: Test task\n\nThis is the expect criteria for your
+      final answer: Your best answer to your coworker asking you this, accounting
+      for the context shared.\nyou MUST return the actual complete content as the
+      final answer, not a summary.\n\nBegin! This is VERY important to you, use the
+      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
+      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '939'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
+        _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AnuRlxiTxduAVoXHHY58Fvfbll5IS\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736458417,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: This is a test task, and the context or question from the coworker is
+      not specified. Therefore, my best effort would be to affirm my readiness to
+      answer accurately and in detail any question about Futel Football Club based
+      on the context described. If provided with specific information or questions,
+      I will ensure to respond comprehensively as required by my job directives.\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 177,\n    \"completion_tokens\":
+      82,\n    \"total_tokens\": 259,\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_703d4ff298\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ff78bf7bd6cc002-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Jan 2025 21:33:40 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '2263'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_7c1a31da73cd103e9f410f908e59187f
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_tool_role_matching[ FUTEL\nOFFICIAL INFOPOINT -True].yaml

@@ -0,0 +1,119 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
+      Futel Football Club info\nYour personal goal is: Answer questions about Futel\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: Test task\n\nThis is the expect criteria for your
+      final answer: Your best answer to your coworker asking you this, accounting
+      for the context shared.\nyou MUST return the actual complete content as the
+      final answer, not a summary.\n\nBegin! This is VERY important to you, use the
+      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
+      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '939'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
+        _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AnuRrFJZGKw8cIEshvuW1PKwFZFKs\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736458423,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: Although you mentioned this being a \\\"Test task\\\" and haven't provided
+      a specific question regarding Futel Football Club, your request appears to involve
+      ensuring accuracy and detail in responses. For a proper answer about Futel,
+      I'd be ready to provide details about the club's history, management, players,
+      match schedules, and recent performance statistics. Remember to ask specific
+      questions to receive a targeted response. If this were a real context where
+      information was shared, I would respond precisely to what's been asked regarding
+      Futel Football Club.\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      177,\n    \"completion_tokens\": 113,\n    \"total_tokens\": 290,\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_703d4ff298\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ff78c1d0ecdc002-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Jan 2025 21:33:47 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:
+      - '3097'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_179e1d56e2b17303e40480baffbc7b08
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_tool_role_matching["Futel Official Infopoint"-True].yaml

@@ -0,0 +1,114 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
+      Futel Football Club info\nYour personal goal is: Answer questions about Futel\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: Test task\n\nThis is the expect criteria for your
+      final answer: Your best answer to your coworker asking you this, accounting
+      for the context shared.\nyou MUST return the actual complete content as the
+      final answer, not a summary.\n\nBegin! This is VERY important to you, use the
+      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
+      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '939'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
+        _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AnuRqgg7eiHnDi2DOqdk99fiqOboz\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736458422,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: Your best answer to your coworker asking you this, accounting for the
+      context shared. You MUST return the actual complete content as the final answer,
+      not a summary.\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      177,\n    \"completion_tokens\": 44,\n    \"total_tokens\": 221,\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_703d4ff298\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ff78c164ad2c002-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Jan 2025 21:33:43 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '899'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_9f5226208edb90a27987aaf7e0ca03d3
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_tool_role_matching[Futel Official Infopoint-True].yaml

@@ -0,0 +1,119 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
+      Futel Football Club info\nYour personal goal is: Answer questions about Futel\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: Test task\n\nThis is the expect criteria for your
+      final answer: Your best answer to your coworker asking you this, accounting
+      for the context shared.\nyou MUST return the actual complete content as the
+      final answer, not a summary.\n\nBegin! This is VERY important to you, use the
+      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
+      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '939'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AnuRjmwH5mrykLxQhFwTqqTiDtuTf\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736458415,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: As this is a test task, please note that Futel Football Club is fictional
+      and any specific details about it would not be available. However, if you have
+      specific questions or need information about a particular aspect of Futel or
+      any general football club inquiry, feel free to ask, and I'll do my best to
+      assist you with your query!\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      177,\n    \"completion_tokens\": 79,\n    \"total_tokens\": 256,\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_703d4ff298\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ff78be5eebfc002-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Jan 2025 21:33:37 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
+        path=/; expires=Thu, 09-Jan-25 22:03:37 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000;
+        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:
+      - '2730'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_014478ba748f860d10ac250ca0ba824a
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_tool_role_matching[Futel Official Infopoint\n-True].yaml

@@ -0,0 +1,119 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
+      Futel Football Club info\nYour personal goal is: Answer questions about Futel\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: Test task\n\nThis is the expect criteria for your
+      final answer: Your best answer to your coworker asking you this, accounting
+      for the context shared.\nyou MUST return the actual complete content as the
+      final answer, not a summary.\n\nBegin! This is VERY important to you, use the
+      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
+      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '939'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
+        _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AnuRofLgmzWcDya5LILqYwIJYgFoq\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736458420,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: As an official Futel Football Club infopoint, my responsibility is to
+      provide detailed and accurate information about the club. This includes answering
+      questions regarding team statistics, player performances, upcoming fixtures,
+      ticketing and fan zone details, club history, and community initiatives. Our
+      focus is to ensure that fans and stakeholders have access to the latest and
+      most precise information about the club's on and off-pitch activities. If there's
+      anything specific you need to know, just let me know, and I'll be more than
+      happy to assist!\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      177,\n    \"completion_tokens\": 115,\n    \"total_tokens\": 292,\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_703d4ff298\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ff78c066f37c002-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Jan 2025 21:33:42 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:
+      - '2459'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_a146dd27f040f39a576750970cca0f52
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/crew_test.py

@@ -14,7 +14,6 @@ from crewai.agent import Agent
 from crewai.agents.cache import CacheHandler
 from crewai.crew import Crew
 from crewai.crews.crew_output import CrewOutput
-from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.process import Process
 from crewai.project import crew
@@ -556,12 +555,12 @@ def test_crew_with_delegating_agents_should_not_override_task_tools():
         _, kwargs = mock_execute_sync.call_args
         tools = kwargs["tools"]
 
-        assert any(isinstance(tool, TestTool) for tool in tools), (
-            "TestTool should be present"
-        )
-        assert any("delegate" in tool.name.lower() for tool in tools), (
-            "Delegation tool should be present"
-        )
+        assert any(
+            isinstance(tool, TestTool) for tool in tools
+        ), "TestTool should be present"
+        assert any(
+            "delegate" in tool.name.lower() for tool in tools
+        ), "Delegation tool should be present"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -620,12 +619,12 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
         _, kwargs = mock_execute_sync.call_args
         tools = kwargs["tools"]
 
-        assert any(isinstance(tool, TestTool) for tool in new_ceo.tools), (
-            "TestTool should be present"
-        )
-        assert any("delegate" in tool.name.lower() for tool in tools), (
-            "Delegation tool should be present"
-        )
+        assert any(
+            isinstance(tool, TestTool) for tool in new_ceo.tools
+        ), "TestTool should be present"
+        assert any(
+            "delegate" in tool.name.lower() for tool in tools
+        ), "Delegation tool should be present"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -749,17 +748,17 @@ def test_task_tools_override_agent_tools_with_allow_delegation():
         used_tools = kwargs["tools"]
 
         # Confirm AnotherTestTool is present but TestTool is not
-        assert any(isinstance(tool, AnotherTestTool) for tool in used_tools), (
-            "AnotherTestTool should be present"
-        )
-        assert not any(isinstance(tool, TestTool) for tool in used_tools), (
-            "TestTool should not be present among used tools"
-        )
+        assert any(
+            isinstance(tool, AnotherTestTool) for tool in used_tools
+        ), "AnotherTestTool should be present"
+        assert not any(
+            isinstance(tool, TestTool) for tool in used_tools
+        ), "TestTool should not be present among used tools"
 
         # Confirm delegation tool(s) are present
-        assert any("delegate" in tool.name.lower() for tool in used_tools), (
-            "Delegation tool should be present"
-        )
+        assert any(
+            "delegate" in tool.name.lower() for tool in used_tools
+        ), "Delegation tool should be present"
 
     # Finally, make sure the agent's original tools remain unchanged
     assert len(researcher_with_delegation.tools) == 1
@@ -1467,6 +1466,7 @@ def test_dont_set_agents_step_callback_if_already_set():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_function_calling_llm():
+
     from crewai import LLM
     from crewai.tools import tool
 
@@ -1560,9 +1560,9 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
 
         # Verify that exactly one tool was used and it was a CodeInterpreterTool
         assert len(used_tools) == 1, "Should have exactly one tool"
-        assert isinstance(used_tools[0], CodeInterpreterTool), (
-            "Tool should be CodeInterpreterTool"
-        )
+        assert isinstance(
+            used_tools[0], CodeInterpreterTool
+        ), "Tool should be CodeInterpreterTool"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -3107,9 +3107,9 @@ def test_fetch_inputs():
     expected_placeholders = {"role_detail", "topic", "field"}
     actual_placeholders = crew.fetch_inputs()
 
-    assert actual_placeholders == expected_placeholders, (
-        f"Expected {expected_placeholders}, but got {actual_placeholders}"
-    )
+    assert (
+        actual_placeholders == expected_placeholders
+    ), f"Expected {expected_placeholders}, but got {actual_placeholders}"
 
 
 def test_task_tools_preserve_code_execution_tools():
@@ -3182,20 +3182,20 @@ def test_task_tools_preserve_code_execution_tools():
         used_tools = kwargs["tools"]
 
         # Verify all expected tools are present
-        assert any(isinstance(tool, TestTool) for tool in used_tools), (
-            "Task's TestTool should be present"
-        )
-        assert any(isinstance(tool, CodeInterpreterTool) for tool in used_tools), (
-            "CodeInterpreterTool should be present"
-        )
-        assert any("delegate" in tool.name.lower() for tool in used_tools), (
-            "Delegation tool should be present"
-        )
+        assert any(
+            isinstance(tool, TestTool) for tool in used_tools
+        ), "Task's TestTool should be present"
+        assert any(
+            isinstance(tool, CodeInterpreterTool) for tool in used_tools
+        ), "CodeInterpreterTool should be present"
+        assert any(
+            "delegate" in tool.name.lower() for tool in used_tools
+        ), "Delegation tool should be present"
 
         # Verify the total number of tools (TestTool + CodeInterpreter + 2 delegation tools)
-        assert len(used_tools) == 4, (
-            "Should have TestTool, CodeInterpreter, and 2 delegation tools"
-        )
+        assert (
+            len(used_tools) == 4
+        ), "Should have TestTool, CodeInterpreter, and 2 delegation tools"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -3239,9 +3239,9 @@ def test_multimodal_flag_adds_multimodal_tools():
         used_tools = kwargs["tools"]
 
         # Check that the multimodal tool was added
-        assert any(isinstance(tool, AddImageTool) for tool in used_tools), (
-            "AddImageTool should be present when agent is multimodal"
-        )
+        assert any(
+            isinstance(tool, AddImageTool) for tool in used_tools
+        ), "AddImageTool should be present when agent is multimodal"
 
         # Verify we have exactly one tool (just the AddImageTool)
         assert len(used_tools) == 1, "Should only have the AddImageTool"
@@ -3467,9 +3467,9 @@ def test_crew_guardrail_feedback_in_context():
     assert len(execution_contexts) > 1, "Task should have been executed multiple times"
 
     # Verify that the second execution included the guardrail feedback
-    assert "Output must contain the keyword 'IMPORTANT'" in execution_contexts[1], (
-        "Guardrail feedback should be included in retry context"
-    )
+    assert (
+        "Output must contain the keyword 'IMPORTANT'" in execution_contexts[1]
+    ), "Guardrail feedback should be included in retry context"
 
     # Verify final output meets guardrail requirements
     assert "IMPORTANT" in result.raw, "Final output should contain required keyword"
@@ -3494,6 +3494,7 @@ def test_before_kickoff_callback():
 
         @before_kickoff
         def modify_inputs(self, inputs):
+
             self.inputs_modified = True
             inputs["modified"] = True
             return inputs
@@ -3595,21 +3596,3 @@ def test_before_kickoff_without_inputs():
     # Verify that the inputs were initialized and modified inside the before_kickoff method
     assert test_crew_instance.received_inputs is not None
     assert test_crew_instance.received_inputs.get("modified") is True
-
-
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_with_knowledge_sources_works_with_copy():
-    content = "Brandon's favorite color is red and he likes Mexican food."
-    string_source = StringKnowledgeSource(content=content)
-
-    crew = Crew(
-        agents=[researcher, writer],
-        tasks=[Task(description="test", expected_output="test", agent=researcher)],
-        knowledge_sources=[string_source],
-    )
-
-    crew_copy = crew.copy()
-
-    assert crew_copy.knowledge_sources == crew.knowledge_sources
-    assert len(crew_copy.agents) == len(crew.agents)
-    assert len(crew_copy.tasks) == len(crew.tasks)

tests/test_manager_llm_delegation.py

@@ -0,0 +1,51 @@
+import pytest
+
+from crewai import Agent
+from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
+
+
+class InternalAgentTool(BaseAgentTool):
+    """Concrete implementation of BaseAgentTool for testing."""
+
+    def _run(self, *args, **kwargs):
+        """Implement required _run method."""
+        return "Test response"
+
+
+@pytest.mark.parametrize(
+    "role_name,should_match",
+    [
+        ("Futel Official Infopoint", True),  # exact match
+        ('  "Futel Official Infopoint"  ', True),  # extra quotes and spaces
+        ("Futel Official Infopoint\n", True),  # trailing newline
+        ('"Futel Official Infopoint"', True),  # embedded quotes
+        (" FUTEL\nOFFICIAL   INFOPOINT ", True),  # multiple whitespace and newline
+    ],
+)
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_tool_role_matching(role_name, should_match):
+    """Test that agent tools can match roles regardless of case, whitespace, and special characters."""
+    # Create test agent
+    test_agent = Agent(
+        role="Futel Official Infopoint",
+        goal="Answer questions about Futel",
+        backstory="Futel Football Club info",
+        allow_delegation=False,
+    )
+
+    # Create test agent tool
+    agent_tool = InternalAgentTool(
+        name="test_tool", description="Test tool", agents=[test_agent]
+    )
+
+    # Test role matching
+    result = agent_tool._execute(agent_name=role_name, task="Test task", context=None)
+
+    if should_match:
+        assert (
+            "coworker mentioned not found" not in result.lower()
+        ), f"Should find agent with role name: {role_name}"
+    else:
+        assert (
+            "coworker mentioned not found" in result.lower()
+        ), f"Should not find agent with role name: {role_name}"

uv.lock

@@ -649,7 +649,7 @@ wheels = [
 
 [[package]]
 name = "crewai"
-version = "0.100.0"
+version = "0.98.0"
 source = { editable = "." }
 dependencies = [
     { name = "appdirs" },
@@ -740,7 +740,7 @@ requires-dist = [
     { name = "json-repair", specifier = ">=0.25.2" },
     { name = "json5", specifier = ">=0.10.0" },
     { name = "jsonref", specifier = ">=1.1.0" },
-    { name = "litellm", specifier = "==1.59.8" },
+    { name = "litellm", specifier = "==1.57.4" },
     { name = "mem0ai", marker = "extra == 'mem0'", specifier = ">=0.1.29" },
     { name = "openai", specifier = ">=1.13.3" },
     { name = "openpyxl", specifier = ">=3.1.5" },
@@ -2374,7 +2374,7 @@ wheels = [
 
 [[package]]
 name = "litellm"
-version = "1.59.8"
+version = "1.57.4"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aiohttp" },
@@ -2389,9 +2389,9 @@ dependencies = [
     { name = "tiktoken" },
     { name = "tokenizers" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/86/b0/c8ec06bd1c87a92d6d824008982b3c82b450d7bd3be850a53913f1ac4907/litellm-1.59.8.tar.gz", hash = "sha256:9d645cc4460f6a9813061f07086648c4c3d22febc8e1f21c663f2b7750d90512", size = 6428607 }
+sdist = { url = "https://files.pythonhosted.org/packages/1a/9a/115bde058901b087e7fec1bed4be47baf8d5c78aff7dd2ffebcb922003ff/litellm-1.57.4.tar.gz", hash = "sha256:747a870ddee9c71f9560fc68ad02485bc1008fcad7d7a43e87867a59b8ed0669", size = 6304427 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/b9/38/889da058f566ef9ea321aafa25e423249492cf2a508dfdc0e5acfcf04526/litellm-1.59.8-py3-none-any.whl", hash = "sha256:2473914bd2343485a185dfe7eedb12ee5fda32da3c9d9a8b73f6966b9b20cf39", size = 6716233 },
+    { url = "https://files.pythonhosted.org/packages/9f/72/35c8509cb2a37343c213b794420405cbef2e1fdf8626ee981fcbba3d7c5c/litellm-1.57.4-py3-none-any.whl", hash = "sha256:afe48924d8a36db801018970a101622fce33d117fe9c54441c0095c491511abb", size = 6592126 },
 ]
 
 [[package]]