fix: fix and add comments for all type checking errors

docs/core-concepts/Memory.md

@@ -12,7 +12,7 @@ description: Leveraging memory systems in the crewAI framework to enhance agent
 | Component            | Description                                                  |
 | :------------------- | :----------------------------------------------------------- |
 | **Short-Term Memory**| Temporarily stores recent interactions and outcomes, enabling agents to recall and utilize information relevant to their current context during the current executions. |
-| **Long-Term Memory** | Preserves valuable insights and learnings from past executions, allowing agents to build and refine their knowledge over time. So Agents can remember what they did right and wrong across multiple executions |
+| **Long-Term Memory** | Preserves valuable insights and learnings from past executions, allowing agents to build and refine their knowledge over time. So Agents can remeber what they did right and wrong across multiple executions |
 | **Entity Memory**    | Captures and organizes information about entities (people, places, concepts) encountered during tasks, facilitating deeper understanding and relationship mapping. |
 | **Contextual Memory**| Maintains the context of interactions by combining `ShortTermMemory`, `LongTermMemory`, and `EntityMemory`, aiding in the coherence and relevance of agent responses over a sequence of tasks or a conversation. |
 

docs/how-to/Create-Custom-Tools.md

@@ -51,7 +51,7 @@ To optimize tool performance with caching, define custom caching strategies usin
 @tool("Tool with Caching")
 def cached_tool(argument: str) -> str:
     """Tool functionality description."""
-    return "Cacheable result"
+    return "Cachable result"
 
 def my_cache_strategy(arguments: dict, result: str) -> bool:
     # Define custom caching logic

docs/how-to/Creating-a-Crew-and-kick-it-off.md

@@ -79,4 +79,5 @@ manager = Agent(
 
 1. `allow_code_execution`: Enable or disable code execution capabilities for the agent (default is False).
 2. `max_execution_time`: Set a maximum execution time (in seconds) for the agent to complete a task.
-3. `function_calling_llm`: Specify a separate language model for function calling.
+3. `function_calling_llm`: Specify a separate language model for function calling.
+4

docs/tools/GitHubSearchTool.md

@@ -4,7 +4,7 @@
     We are still working on improving tools, so there might be unexpected behavior or changes in the future.
 
 ## Description
-The GithubSearchTool is a Retrieval-Augmented Generation (RAG) tool specifically designed for conducting semantic searches within GitHub repositories. Utilizing advanced semantic search capabilities, it sifts through code, pull requests, issues, and repositories, making it an essential tool for developers, researchers, or anyone in need of precise information from GitHub.
+The GithubSearchTool is a Read, Append, and Generate (RAG) tool specifically designed for conducting semantic searches within GitHub repositories. Utilizing advanced semantic search capabilities, it sifts through code, pull requests, issues, and repositories, making it an essential tool for developers, researchers, or anyone in need of precise information from GitHub.
 
 ## Installation
 To use the GithubSearchTool, first ensure the crewai_tools package is installed in your Python environment:

docs/tools/TXTSearchTool.md

@@ -31,7 +31,7 @@ tool = TXTSearchTool(txt='path/to/text/file.txt')
 ```
 
 ## Arguments
-- `txt` (str): **Optional**. The path to the text file you want to search. This argument is only required if the tool was not initialized with a specific text file; otherwise, the search will be conducted within the initially provided text file.
+- `txt` (str): **Optinal**. The path to the text file you want to search. This argument is only required if the tool was not initialized with a specific text file; otherwise, the search will be conducted within the initially provided text file.
 
 ## Custom model and embeddings
 

poetry.lock

@@ -343,17 +343,17 @@ lxml = ["lxml"]
 
 [[package]]
 name = "boto3"
-version = "1.34.140"
+version = "1.34.139"
 description = "The AWS SDK for Python"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "boto3-1.34.140-py3-none-any.whl", hash = "sha256:23ca8d8f7a30c3bbd989808056b5fc5d68ff5121c02c722c6167b6b1bb7f8726"},
-    {file = "boto3-1.34.140.tar.gz", hash = "sha256:578bbd5e356005719b6b610d03edff7ea1b0824d078afe62d3fb8bea72f83a87"},
+    {file = "boto3-1.34.139-py3-none-any.whl", hash = "sha256:98b2a12bcb30e679fa9f60fc74145a39db5ec2ca7b7c763f42896e3bd9b3a38d"},
+    {file = "boto3-1.34.139.tar.gz", hash = "sha256:32b99f0d76ec81fdca287ace2c9744a2eb8b92cb62bf4d26d52a4f516b63a6bf"},
 ]
 
 [package.dependencies]
-botocore = ">=1.34.140,<1.35.0"
+botocore = ">=1.34.139,<1.35.0"
 jmespath = ">=0.7.1,<2.0.0"
 s3transfer = ">=0.10.0,<0.11.0"
 
@@ -362,13 +362,13 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]
 
 [[package]]
 name = "botocore"
-version = "1.34.140"
+version = "1.34.139"
 description = "Low-level, data-driven core of boto 3."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "botocore-1.34.140-py3-none-any.whl", hash = "sha256:43940d3a67d946ba3301631ba4078476a75f1015d4fb0fb0272d0b754b2cf9de"},
-    {file = "botocore-1.34.140.tar.gz", hash = "sha256:86302b2226c743b9eec7915a4c6cfaffd338ae03989cd9ee181078ef39d1ab39"},
+    {file = "botocore-1.34.139-py3-none-any.whl", hash = "sha256:dd1e085d4caa2a4c1b7d83e3bc51416111c8238a35d498e9d3b04f3b63b086ba"},
+    {file = "botocore-1.34.139.tar.gz", hash = "sha256:df023d8cf8999d574214dad4645cb90f9d2ccd1494f6ee2b57b1ab7522f6be77"},
 ]
 
 [package.dependencies]
@@ -747,13 +747,13 @@ all = ["pycocotools (==2.0.6)"]
 
 [[package]]
 name = "clarifai-grpc"
-version = "10.6.1"
+version = "10.5.4"
 description = "Clarifai gRPC API Client"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "clarifai_grpc-10.6.1-py3-none-any.whl", hash = "sha256:7f07c262f46042995b11af10cdd552718c4487e955db1b3f1253fcb0c2ab1ce1"},
-    {file = "clarifai_grpc-10.6.1.tar.gz", hash = "sha256:f692e3d6a051a1228ca371c3a9dc705cc9a61334eecc454d056f7af0b6f4dbad"},
+    {file = "clarifai_grpc-10.5.4-py3-none-any.whl", hash = "sha256:ae4c4d8985fdd2bf326cec27ee834571e44d0e989fb12686dd681f9b553ae218"},
+    {file = "clarifai_grpc-10.5.4.tar.gz", hash = "sha256:c67ce0dde186e8bab0d42a9923d28ddb4a05017b826c8e52ac7a86ec6df5f12a"},
 ]
 
 [package.dependencies]
@@ -884,21 +884,6 @@ webencodings = "*"
 doc = ["sphinx", "sphinx_rtd_theme"]
 test = ["flake8", "isort", "pytest"]
 
-[[package]]
-name = "dataclasses-json"
-version = "0.6.7"
-description = "Easily serialize dataclasses to and from JSON."
-optional = false
-python-versions = "<4.0,>=3.7"
-files = [
-    {file = "dataclasses_json-0.6.7-py3-none-any.whl", hash = "sha256:0dbf33f26c8d5305befd61b39d2b3414e8a407bedc2834dea9b8d642666fb40a"},
-    {file = "dataclasses_json-0.6.7.tar.gz", hash = "sha256:b6b3e528266ea45b9535223bc53ca645f5208833c29229e847b3f26a1cc55fc0"},
-]
-
-[package.dependencies]
-marshmallow = ">=3.18.0,<4.0.0"
-typing-inspect = ">=0.4.0,<1"
-
 [[package]]
 name = "decorator"
 version = "5.1.1"
@@ -1054,13 +1039,13 @@ idna = ">=2.0.0"
 
 [[package]]
 name = "embedchain"
-version = "0.1.115"
+version = "0.1.114"
 description = "Simplest open source retrieval (RAG) framework"
 optional = false
 python-versions = "<=3.13,>=3.9"
 files = [
-    {file = "embedchain-0.1.115-py3-none-any.whl", hash = "sha256:6f1842edea7780e6b1d21d073b72b2c916f440411c32e758165c88141b2ac1ec"},
-    {file = "embedchain-0.1.115.tar.gz", hash = "sha256:8b259a3307e022924c99cf82b17789f141d157f11e53beb3bc82bf49efa2e31e"},
+    {file = "embedchain-0.1.114-py3-none-any.whl", hash = "sha256:ce1b16196bcf53c679cacead0551a5466c33a9080a82be63f973e4437b0823ca"},
+    {file = "embedchain-0.1.114.tar.gz", hash = "sha256:fa5c4a29dd3c6b1137c772e1bc3e2d7ca489c58f46f4c7f7de133b3b9fc56e72"},
 ]
 
 [package.dependencies]
@@ -1068,12 +1053,10 @@ alembic = ">=1.13.1,<2.0.0"
 beautifulsoup4 = ">=4.12.2,<5.0.0"
 chromadb = ">=0.4.24,<0.5.0"
 clarifai = ">=10.0.1,<11.0.0"
-cohere = ">=5.3,<6.0"
 google-cloud-aiplatform = ">=1.26.1,<2.0.0"
 gptcache = ">=0.1.43,<0.2.0"
 langchain = ">0.2,<=0.3"
 langchain-cohere = ">=0.1.4,<0.2.0"
-langchain-community = ">=0.2.6,<0.3.0"
 langchain-openai = ">=0.1.7,<0.2.0"
 openai = ">=1.1.1"
 posthog = ">=3.0.2,<4.0.0"
@@ -1087,6 +1070,7 @@ tiktoken = ">=0.7.0,<0.8.0"
 
 [package.extras]
 aws-bedrock = ["boto3 (>=1.34.20,<2.0.0)"]
+cohere = ["cohere (>=5.3,<6.0)"]
 dataloaders = ["docx2txt (>=0.8,<0.9)", "duckduckgo-search (>=6.1.5,<7.0.0)", "pytube (>=15.0.0,<16.0.0)", "sentence-transformers (>=2.2.2,<3.0.0)", "youtube-transcript-api (>=0.6.1,<0.7.0)"]
 discord = ["discord (>=2.3.2,<3.0.0)"]
 dropbox = ["dropbox (>=11.36.2,<12.0.0)"]
@@ -2418,32 +2402,6 @@ files = [
 cohere = ">=5.5.6,<6.0"
 langchain-core = ">=0.2.0,<0.3"
 
-[[package]]
-name = "langchain-community"
-version = "0.2.6"
-description = "Community contributed LangChain integrations."
-optional = false
-python-versions = "<4.0,>=3.8.1"
-files = [
-    {file = "langchain_community-0.2.6-py3-none-any.whl", hash = "sha256:758cc800acfe5dd396bf8ba1b57c4792639ead0eab48ed0367f0732ec6ee1f68"},
-    {file = "langchain_community-0.2.6.tar.gz", hash = "sha256:40ce09a50ed798aa651ddb34c8978200fa8589b9813c7a28ce8af027bbf249f0"},
-]
-
-[package.dependencies]
-aiohttp = ">=3.8.3,<4.0.0"
-dataclasses-json = ">=0.5.7,<0.7"
-langchain = ">=0.2.6,<0.3.0"
-langchain-core = ">=0.2.10,<0.3.0"
-langsmith = ">=0.1.0,<0.2.0"
-numpy = [
-    {version = ">=1.26.0,<2.0.0", markers = "python_version >= \"3.12\""},
-    {version = ">=1,<2", markers = "python_version < \"3.12\""},
-]
-PyYAML = ">=5.3"
-requests = ">=2,<3"
-SQLAlchemy = ">=1.4,<3"
-tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
-
 [[package]]
 name = "langchain-core"
 version = "0.2.11"
@@ -2642,25 +2600,6 @@ files = [
     {file = "MarkupSafe-2.1.5.tar.gz", hash = "sha256:d283d37a890ba4c1ae73ffadf8046435c76e7bc2247bbb63c00bd1a709c6544b"},
 ]
 
-[[package]]
-name = "marshmallow"
-version = "3.21.3"
-description = "A lightweight library for converting complex datatypes to and from native Python datatypes."
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "marshmallow-3.21.3-py3-none-any.whl", hash = "sha256:86ce7fb914aa865001a4b2092c4c2872d13bc347f3d42673272cabfdbad386f1"},
-    {file = "marshmallow-3.21.3.tar.gz", hash = "sha256:4f57c5e050a54d66361e826f94fba213eb10b67b2fdb02c3e0343ce207ba1662"},
-]
-
-[package.dependencies]
-packaging = ">=17.0"
-
-[package.extras]
-dev = ["marshmallow[tests]", "pre-commit (>=3.5,<4.0)", "tox"]
-docs = ["alabaster (==0.7.16)", "autodocsumm (==0.2.12)", "sphinx (==7.3.7)", "sphinx-issues (==4.1.0)", "sphinx-version-warning (==1.1.2)"]
-tests = ["pytest", "pytz", "simplejson"]
-
 [[package]]
 name = "mdurl"
 version = "0.1.2"
@@ -5033,13 +4972,13 @@ widechars = ["wcwidth"]
 
 [[package]]
 name = "tenacity"
-version = "8.5.0"
+version = "8.4.2"
 description = "Retry code until it succeeds"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "tenacity-8.5.0-py3-none-any.whl", hash = "sha256:b594c2a5945830c267ce6b79a166228323ed52718f30302c1359836112346687"},
-    {file = "tenacity-8.5.0.tar.gz", hash = "sha256:8bc6c0c8a09b31e6cad13c47afbed1a567518250a9a171418582ed8d9c20ca78"},
+    {file = "tenacity-8.4.2-py3-none-any.whl", hash = "sha256:9e6f7cf7da729125c7437222f8a522279751cdfbe6b67bfe64f75d3a348661b2"},
+    {file = "tenacity-8.4.2.tar.gz", hash = "sha256:cd80a53a79336edba8489e767f729e4f391c896956b57140b5d7511a64bbd3ef"},
 ]
 
 [package.extras]
@@ -5266,13 +5205,13 @@ telegram = ["requests"]
 
 [[package]]
 name = "trio"
-version = "0.26.0"
+version = "0.25.1"
 description = "A friendly Python library for async concurrency and I/O"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "trio-0.26.0-py3-none-any.whl", hash = "sha256:bb9c1b259591af941fccfbabbdc65bc7ed764bd2db76428454c894cd5e3d2032"},
-    {file = "trio-0.26.0.tar.gz", hash = "sha256:67c5ec3265dd4abc7b1d1ab9ca4fe4c25b896f9c93dac73713778adab487f9c4"},
+    {file = "trio-0.25.1-py3-none-any.whl", hash = "sha256:e42617ba091e7b2e50c899052e83a3c403101841de925187f61e7b7eaebdf3fb"},
+    {file = "trio-0.25.1.tar.gz", hash = "sha256:9f5314f014ea3af489e77b001861c535005c3858d38ec46b6b071ebfa339d7fb"},
 ]
 
 [package.dependencies]
@@ -5375,21 +5314,6 @@ files = [
     {file = "typing_extensions-4.12.2.tar.gz", hash = "sha256:1a7ead55c7e559dd4dee8856e3a88b41225abfe1ce8df57b7c13915fe121ffb8"},
 ]
 
-[[package]]
-name = "typing-inspect"
-version = "0.9.0"
-description = "Runtime inspection utilities for typing module."
-optional = false
-python-versions = "*"
-files = [
-    {file = "typing_inspect-0.9.0-py3-none-any.whl", hash = "sha256:9ee6fc59062311ef8547596ab6b955e1b8aa46242d854bfc78f4f6b0eff35f9f"},
-    {file = "typing_inspect-0.9.0.tar.gz", hash = "sha256:b23fc42ff6f6ef6954e4852c1fb512cdd18dbea03134f91f856a95ccc9461f78"},
-]
-
-[package.dependencies]
-mypy-extensions = ">=0.3.0"
-typing-extensions = ">=3.7.4"
-
 [[package]]
 name = "ujson"
 version = "5.10.0"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "crewai"
-version = "0.36.1"
+version = "0.35.8"
 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."
 authors = ["Joao Moura <joao@crewai.com>"]
 readme = "README.md"

src/crewai/agents/agent_builder/utilities/base_output_converter_base.py

@@ -27,7 +27,7 @@ class OutputConverter(BaseModel, ABC):
     model: Any = Field(description="The model to be used to convert the text.")
     instructions: str = Field(description="Conversion instructions to the LLM.")
     max_attempts: Optional[int] = Field(
-        description="Max number of attempts to try to get the output formated.",
+        description="Max number of attemps to try to get the output formated.",
         default=3,
     )
 

src/crewai/cli/templates/pyproject.toml

@@ -6,7 +6,7 @@ authors = ["Your Name <you@example.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
-crewai = { extras = ["tools"], version = "^0.36.1" }
+crewai = { extras = ["tools"], version = "^0.35.8" }
 
 [tool.poetry.scripts]
 {{folder_name}} = "{{folder_name}}.main:run"

src/crewai/crew.py

@@ -421,17 +421,17 @@ class Crew(BaseModel):
 
         return results
 
-    def _run_sequential_process(self) -> Union[str, Dict[str, Any]]:
+    def _run_sequential_process(self) -> str:
         """Executes tasks sequentially and returns the final output."""
-        task_output = None
+        task_output = ""
 
         for task in self.tasks:
-            if task.agent and task.agent.allow_delegation:
+            if task.agent.allow_delegation:  # type: ignore #  Item "None" of "Agent | None" has no attribute "allow_delegation"
                 agents_for_delegation = [
                     agent for agent in self.agents if agent != task.agent
                 ]
                 if len(self.agents) > 1 and len(agents_for_delegation) > 0:
-                    task.tools += task.agent.get_delegation_tools(agents_for_delegation)
+                    task.tools += task.agent.get_delegation_tools(agents_for_delegation)  # type: ignore # Item "None" of "BaseAgent | None" has no attribute "get_delegation_tools"
 
             role = task.agent.role if task.agent is not None else "None"
             self._logger.log("debug", f"== Working Agent: {role}", color="bold_purple")
@@ -458,7 +458,7 @@ class Crew(BaseModel):
 
         token_usage = self.calculate_usage_metrics()
 
-        return self._format_output(task_output if task_output else "", token_usage)
+        return self._format_output(task_output, token_usage)  # type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
 
     def _run_hierarchical_process(
         self,
@@ -483,7 +483,7 @@ class Crew(BaseModel):
             )
             self.manager_agent = manager
 
-        task_output = None
+        task_output = ""
 
         for task in self.tasks:
             self._logger.log("debug", f"Working Agent: {manager.role}")
@@ -510,11 +510,10 @@ class Crew(BaseModel):
 
         self._finish_execution(task_output)
 
+        # type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
         token_usage = self.calculate_usage_metrics()
 
-        return self._format_output(
-            task_output if task_output else "", token_usage
-        ), token_usage
+        return self._format_output(task_output, token_usage), token_usage
 
     def copy(self):
         """Create a deep copy of the Crew."""
@@ -575,7 +574,7 @@ class Crew(BaseModel):
         """
 
         if self.full_output:
-            return {
+            return {  # type: ignore # Incompatible return value type (got "dict[str, Sequence[str | TaskOutput | None]]", expected "str")
                 "final_output": output,
                 "tasks_outputs": [task.output for task in self.tasks if task],
                 "usage_metrics": token_usage,

src/crewai/task.py

@@ -1,7 +1,7 @@
 import os
 import re
+import threading
 import uuid
-from concurrent.futures import Future, ThreadPoolExecutor
 from copy import copy
 from typing import Any, Dict, List, Optional, Type, Union
 
@@ -14,7 +14,6 @@ from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry.telemetry import Telemetry
 from crewai.utilities.converter import ConverterError
-from crewai.utilities.converter import Converter
 from crewai.utilities.i18n import I18N
 from crewai.utilities.printer import Printer
 from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
@@ -98,16 +97,12 @@ class Task(BaseModel):
         description="Whether the task should have a human review the final answer of the agent",
         default=False,
     )
-    converter_cls: Optional[Type[Converter]] = Field(
-        description="A converter class used to export structured output",
-        default=None,
-    )
 
     _telemetry: Telemetry
     _execution_span: Span | None = None
     _original_description: str | None = None
     _original_expected_output: str | None = None
-    _future: Future | None = None
+    _thread: threading.Thread | None = None
 
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
@@ -166,20 +161,20 @@ class Task(BaseModel):
         """Wait for asynchronous task completion and return the output."""
         assert self.async_execution, "Task is not set to be executed asynchronously."
 
-        if self._future:
-            self._future.result()  # Wait for the future to complete
-            self._future = None
+        if self._thread:
+            self._thread.join()
+            self._thread = None
 
         assert self.output, "Task output is not set."
 
         return self.output.exported_output
 
-    def execute(
+    def execute(  # type: ignore # Missing return statement
         self,
         agent: BaseAgent | None = None,
         context: Optional[str] = None,
         tools: Optional[List[Any]] = None,
-    ) -> str | None:
+    ) -> str:
         """Execute the task.
 
         Returns:
@@ -191,28 +186,26 @@ class Task(BaseModel):
         agent = agent or self.agent
         if not agent:
             raise Exception(
-                f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly "
-                "and should be executed in a Crew using a specific process that support that, like hierarchical."
+                f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly and should be executed in a Crew using a specific process that support that, like hierarchical."
             )
 
         if self.context:
-            internal_context = []
+            context = []  # type: ignore # Incompatible types in assignment (expression has type "list[Never]", variable has type "str | None")
             for task in self.context:
                 if task.async_execution:
                     task.wait_for_completion()
                 if task.output:
-                    internal_context.append(task.output.raw_output)
-            context = "\n".join(internal_context)
+                    context.append(task.output.raw_output)  # type: ignore # Item "str" of "str | None" has no attribute "append"
+            context = "\n".join(context)  # type: ignore # Argument 1 to "join" of "str" has incompatible type "str | None"; expected "Iterable[str]"
 
         self.prompt_context = context
         tools = tools or self.tools
 
         if self.async_execution:
-            with ThreadPoolExecutor() as executor:
-                self._future = executor.submit(
-                    self._execute, agent, self, context, tools
-                )
-            return None
+            self._thread = threading.Thread(
+                target=self._execute, args=(agent, self, context, tools)
+            )
+            self._thread.start()
         else:
             result = self._execute(
                 task=self,
@@ -222,7 +215,7 @@ class Task(BaseModel):
             )
             return result
 
-    def _execute(self, agent: "BaseAgent", task, context, tools) -> str | None:
+    def _execute(self, agent: "BaseAgent", task, context, tools):
         result = agent.execute_task(
             task=task,
             context=context,
@@ -230,7 +223,7 @@ class Task(BaseModel):
         )
         exported_output = self._export_output(result)
 
-        self.output = TaskOutput(
+        self.output = TaskOutput(  # type: ignore # the responses are usually str but need to figure out a more elegant solution here
             description=self.description,
             exported_output=exported_output,
             raw_output=result,
@@ -310,16 +303,6 @@ class Task(BaseModel):
 
         return copied_task
 
-    def _create_converter(self, *args, **kwargs) -> Converter: # type: ignore
-      converter = self.agent.get_output_converter(  # type: ignore # Item "None" of "BaseAgent | None" has no attribute "get_output_converter"
-        *args, **kwargs
-      )
-      if self.converter_cls:
-        converter = self.converter_cls(  # type: ignore # Item "None" of "BaseAgent | None" has no attribute "get_output_converter"
-          *args, **kwargs
-        )          
-      return converter
-
     def _export_output(self, result: str) -> Any:
         exported_result = result
         instructions = "I'm gonna convert this raw text into valid JSON."
@@ -350,7 +333,7 @@ class Task(BaseModel):
                 model_schema = PydanticSchemaParser(model=model).get_schema()  # type: ignore # Argument "model" to "PydanticSchemaParser" has incompatible type "type[BaseModel] | None"; expected "type[BaseModel]"
                 instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
 
-            converter = self._create_converter( # type: ignore # Item "None" of "BaseAgent | None" has no attribute "get_output_converter"
+            converter = self.agent.get_output_converter(  # type: ignore # Item "None" of "BaseAgent | None" has no attribute "get_output_converter"
                 llm=llm, text=result, model=model, instructions=instructions
             )
 

src/crewai/tools/tool_usage.py

@@ -151,12 +151,16 @@ class ToolUsage:
                             for k, v in calling.arguments.items()
                             if k in acceptable_args
                         }
-                        result = tool.invoke(input=arguments)
+                        result = tool._run(**arguments)
                     except Exception:
-                        arguments = calling.arguments
-                        result = tool.invoke(input=arguments)
+                        if tool.args_schema:
+                            arguments = calling.arguments
+                            result = tool._run(**arguments)
+                        else:
+                            arguments = calling.arguments.values()  # type: ignore # Incompatible types in assignment (expression has type "dict_values[str, Any]", variable has type "dict[str, Any]")
+                            result = tool._run(*arguments)
                 else:
-                    result = tool.invoke(input={})
+                    result = tool._run()
             except Exception as e:
                 self._run_attempts += 1
                 if self._run_attempts > self._max_parsing_attempts:

tests/cassettes/test_custom_converter_cls.yaml

@@ -1,258 +0,0 @@
-interactions:
-- request:
-    body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
-      in scoring titles.\nYour personal goal is: Score the titleTo 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: my best complete final answer to the task.\nYour
-      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!\nCurrent
-      Task: Give me an integer score between 1-5 for the following title: ''The impact
-      of AI in the future of work''\n\nThis is the expect criteria for your final
-      answer: The score of the title. \n you 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:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
-      "stream": true, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '997'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.35.10
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.35.10
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: 'data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        I"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        now"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        can"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        give"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        a"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        great"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        answer"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        Answer"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        "},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
-
-
-        data: [DONE]
-
-
-        '
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 89ed0cf0dc05741a-MIA
-      Connection:
-      - keep-alive
-      Content-Type:
-      - text/event-stream; charset=utf-8
-      Date:
-      - Sat, 06 Jul 2024 05:03:50 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=JI76H4xxreAnMx1JJoPragplAdYdjbDNA68Hr3Cs_0k-1720242230-1.0.1.1-oHSrtm.ejkvCiAHC11lg0MnvmopYZayTZRq09IcH2yh5BA6FyyufGH7Rm59BAz.gdZHc0izmjElXfLiu2bZ_jQ;
-        path=/; expires=Sat, 06-Jul-24 05:33:50 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=X4.n0cNP9j1jseIPV4H1aDJu2xrsAwcUI8rY0tbLc40-1720242230210-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '71'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '16000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '15999772'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_8dc1d49d85fcf8e39601e32ca80abd6b
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
-      "I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
-      {"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
-      "function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
-      `ScoreOutput` with all the required parameters with correct types", "parameters":
-      {"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
-      ["score"], "type": "object"}}}]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '519'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=JI76H4xxreAnMx1JJoPragplAdYdjbDNA68Hr3Cs_0k-1720242230-1.0.1.1-oHSrtm.ejkvCiAHC11lg0MnvmopYZayTZRq09IcH2yh5BA6FyyufGH7Rm59BAz.gdZHc0izmjElXfLiu2bZ_jQ;
-        _cfuvid=X4.n0cNP9j1jseIPV4H1aDJu2xrsAwcUI8rY0tbLc40-1720242230210-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.35.10
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.35.10
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA2xSS2/bMAy++1cIPNeF81pT34YBG9A13aHAgL5gKArtKJVFTaKBtkH++yDFi91g
-        PggEP34PkN5nQoDeQClAbSWr1pn8euvD6id9OP3V3C6bzZ2qd7eT1f3DykgFF5FB6x0q/se6VNQ6
-        g6zJHmHlUTJG1cnVtJjOp9NZkYCWNmgirXGczymPYF4s8smsJ25JKwxQiqdMCCH26Y0R7QbfoBRJ
-        JnVaDEE2COVpSAjwZGIHZAg6sLQMFwOoyDLamNp2xowAJjKVksYMxsdvP6qHPUljqsI2duX13ePN
-        w2/7HT/+8Lfd45cfYeR3lH53KVDdWXXazwg/9cszMyHAyjZx7xV5/NWx6/iMLgRI33QtWo7RYf8M
-        IQ4/Qzk/wKfRQ/a/+qWvDqe1Gmqcp3U42xLU2uqwrTzKkNJCYHJHiyj3ks7XfboIOE+t44rpFW0U
-        XPbXg+F/GcBFjzGxNCPOIuvjQXgPjG1Va9ugd16nU0LtqnlRLHG2vppcQ3bI/gIAAP//AwCtLU45
-        0wIAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 89ed0cf40ebc741a-MIA
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 06 Jul 2024 05:03:50 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '186'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '16000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '15999969'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_5da164d15ccb331864aeb5d3562969aa
-    status:
-      code: 200
-      message: OK
-version: 1

tests/cassettes/test_save_task_pydantic_output.yaml

@@ -46,64 +46,64 @@ interactions:
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: 'data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+      string: 'data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
         I"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
         now"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
         can"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
         give"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
         a"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
         great"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
         answer"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
         Answer"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
         "},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hry2om1JBkreHpDHFbfD2YDtg2oA","object":"chat.completion.chunk","created":1720242582,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+        data: {"id":"chatcmpl-9hEBF5KduXR80dsfVx2VivLMxOk4w","object":"chat.completion.chunk","created":1720089641,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
 
 
         data: [DONE]
@@ -114,20 +114,20 @@ interactions:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 89ed158b8bf0a566-MIA
+      - 89de7fa17ed72878-MIA
       Connection:
       - keep-alive
       Content-Type:
       - text/event-stream; charset=utf-8
       Date:
-      - Sat, 06 Jul 2024 05:09:42 GMT
+      - Thu, 04 Jul 2024 10:40:41 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=5C3MG9ni0I5bZoHGzfXZq16obGaD1INR3_.wX4CRPAk-1720242582-1.0.1.1-fZiD6L1FdBiC0gqcmBK9_IaHhbHPQi4z04fxYQtoDc9KbYqPvxm_sxP_RkuZX_AyPkHgu85IRq9E6MUAZJGzwQ;
-        path=/; expires=Sat, 06-Jul-24 05:39:42 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=m9ZbE3d_dSMsckOHqfK8mMIzKxCRI4vqsIelidShwVc-1720089641-1.0.1.1-xigQSnpNWopswY4gNuGCIgc2MR64bcUc6bpFwdeThTINo0jBkROlwHpIGyjOBQo3goJboqk_kUa_XZby0or19g;
+        path=/; expires=Thu, 04-Jul-24 11:10:41 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=YP7Z3XnHPKQDU2nOhrLzkxr8InOv42HLWchJd1ogneQ-1720242582534-0.0.1.1-604800000;
+      - _cfuvid=NgRTBkQl5NRUhXSdkH3Y7qNaA.KrG7PvxiuoOp9ip8w-1720089641502-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -136,7 +136,7 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '90'
+      - '109'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -154,7 +154,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_36d283adbca77945609f0da658047ba0
+      - req_2d7ac1e1ca6d58559a236046b682021e
     status:
       code: 200
       message: OK
@@ -178,8 +178,8 @@ interactions:
       content-type:
       - application/json
       cookie:
-      - __cf_bm=5C3MG9ni0I5bZoHGzfXZq16obGaD1INR3_.wX4CRPAk-1720242582-1.0.1.1-fZiD6L1FdBiC0gqcmBK9_IaHhbHPQi4z04fxYQtoDc9KbYqPvxm_sxP_RkuZX_AyPkHgu85IRq9E6MUAZJGzwQ;
-        _cfuvid=YP7Z3XnHPKQDU2nOhrLzkxr8InOv42HLWchJd1ogneQ-1720242582534-0.0.1.1-604800000
+      - __cf_bm=m9ZbE3d_dSMsckOHqfK8mMIzKxCRI4vqsIelidShwVc-1720089641-1.0.1.1-xigQSnpNWopswY4gNuGCIgc2MR64bcUc6bpFwdeThTINo0jBkROlwHpIGyjOBQo3goJboqk_kUa_XZby0or19g;
+        _cfuvid=NgRTBkQl5NRUhXSdkH3Y7qNaA.KrG7PvxiuoOp9ip8w-1720089641502-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
@@ -203,19 +203,19 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA2xS30/bMBB+z19h3XMzhbShJW8wiW1MGogixDRQ5DpOanB8ln1hK1X/d+Q0NKFa
-        HqzTfff90F22EWOgSsgZiDUn0Vgdn63dJl3d3rSv5xuf/b7Di/PLq/JUVYub5wwmgYGrZynog/VF
-        YGO1JIVmDwsnOcmgejJPk3SWZou0AxospQ602lI8wziAcZLFJ9OeuEYlpIec/YkYY2zbvSGiKeU/
-        yFky+eg00nteS8gPQ4yBQx06wL1XnrghmAygQEPShNSm1XoEEKIuBNd6MN5/21E97IlrXdxePlzN
-        /s6/rpZv3x+WF9P7nz++vdz/8iO/vfTGdoGq1ojDfkb4oZ8fmTEGhjcddynQyeuWbEtHdMaAu7pt
-        pKEQHbaP4MPwI+SzHXwa3UX/q5/6andYq8baOlz5oy1BpYzy68JJ7ru04Ant3iLIPXXnaz9dBKzD
-        xlJB+CJNEFz014PhfxnArMcIiesRJ4v6eOA3nmRTVMrU0lmnulNCZYsym59Ok3l1lkC0i94BAAD/
-        /wMAylx2sdMCAAA=
+        H4sIAAAAAAAAA2xS32vbMBB+918h7jkuTuwktd/WkcCgI6zdRmEtRlVkR5usU6UzbQj534scN3bD
+        /CCO++77wZ0PEWOgtlAwEDtOorE6znermzXiPr+xv17vVtn++636PcNNmrw8/IRJYODzXynog3Ul
+        sLFakkJzgoWTnGRQnS5nSXKdL7JpBzS4lTrQaktxhvEsmWVxMo+naU/coRLSQ8H+RIwxdujeENFs
+        5RsULJl8dBrpPa8lFOchxsChDh3g3itP3BBMBlCgIWlCatNqPQIIUZeCaz0Yn77DqB72xLUuza3W
+        i1SuV8vNw2L18m2dp/buy4+vI7+T9N52garWiPN+Rvi5X1yYMQaGNx33XqCTm5ZsSxd0xoC7um2k
+        oRAdDo/gw/AjFNkRPo0eo//VT311PK9VY20dPvuLLUGljPK70knuu7TgCe3JIsg9dedrP10ErMPG
+        Ukn4T5ogeN1fD4b/ZQDnPUZIXI8486iPB37vSTZlpUwtnXWqOyVUthQyWeZpmiYVRMfoHQAA//8D
+        ADLpRvfTAgAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 89ed158dee46a566-MIA
+      - 89de7fa4e8742878-MIA
       Connection:
       - keep-alive
       Content-Encoding:
@@ -223,7 +223,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 06 Jul 2024 05:09:42 GMT
+      - Thu, 04 Jul 2024 10:40:42 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -233,7 +233,7 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '144'
+      - '209'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -251,7 +251,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_990566332b9b1851c581486c0a4da0e6
+      - req_a66f76bc016b3f8752bac8c393e60578
     status:
       code: 200
       message: OK

tests/crew_test.py

@@ -501,13 +501,13 @@ def test_agents_rpm_is_never_set_if_crew_max_RPM_is_not_set():
 
 
 def test_async_task_execution():
-    from concurrent.futures import ThreadPoolExecutor
-    from unittest.mock import MagicMock, patch
+    import threading
+    from unittest.mock import patch
 
     from crewai.tasks.task_output import TaskOutput
 
     list_ideas = Task(
-        description="Give me a list of 5 interesting ideas to explore for an article, what makes them unique and interesting.",
+        description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
         expected_output="Bullet point list of 5 important events.",
         agent=researcher,
         async_execution=True,
@@ -533,24 +533,23 @@ def test_async_task_execution():
 
     with patch.object(Agent, "execute_task") as execute:
         execute.return_value = "ok"
-        with patch.object(ThreadPoolExecutor, "submit") as submit:
-            future = MagicMock()
-            future.result.return_value = "ok"
-            submit.return_value = future
-
-            list_ideas.output = TaskOutput(
-                description="A 4 paragraph article about AI.",
-                raw_output="ok",
-                agent="writer",
-            )
-            list_important_history.output = TaskOutput(
-                description="A 4 paragraph article about AI.",
-                raw_output="ok",
-                agent="writer",
-            )
-            crew.kickoff()
-            submit.assert_called()
-            future.result.assert_called()
+        with patch.object(threading.Thread, "start") as start:
+            thread = threading.Thread(target=lambda: None, args=()).start()
+            start.return_value = thread
+            with patch.object(threading.Thread, "join", wraps=thread.join()) as join:
+                list_ideas.output = TaskOutput(
+                    description="A 4 paragraph article about AI.",
+                    raw_output="ok",
+                    agent="writer",
+                )
+                list_important_history.output = TaskOutput(
+                    description="A 4 paragraph article about AI.",
+                    raw_output="ok",
+                    agent="writer",
+                )
+                crew.kickoff()
+                start.assert_called()
+                join.assert_called()
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])

tests/task_test.py

@@ -9,7 +9,6 @@ from pydantic_core import ValidationError
 
 from crewai import Agent, Crew, Process, Task
 from crewai.tasks.task_output import TaskOutput
-from crewai.utilities.converter import Converter
 
 
 def test_task_tool_reflect_agent_tools():
@@ -394,38 +393,6 @@ def test_save_task_pydantic_output():
         save_file.assert_called_once_with('{"score":4}')
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_custom_converter_cls():
-    class ScoreOutput(BaseModel):
-        score: int
-
-    class ScoreConverter(Converter):
-        pass
-
-    scorer = Agent(
-        role="Scorer",
-        goal="Score the title",
-        backstory="You're an expert scorer, specialized in scoring titles.",
-        allow_delegation=False,
-    )
-
-    task = Task(
-        description="Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work'",
-        expected_output="The score of the title.",
-        output_pydantic=ScoreOutput,
-        converter_cls=ScoreConverter,
-        agent=scorer,
-    )
-
-    crew = Crew(agents=[scorer], tasks=[task])
-
-    with patch.object(
-        ScoreConverter, "to_pydantic", return_value=ScoreOutput(score=5)
-    ) as mock_to_pydantic:
-        crew.kickoff()
-        mock_to_pydantic.assert_called_once()
-
-
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_increment_delegations_for_hierarchical_process():
     from langchain_openai import ChatOpenAI