test: change tests and gh action file

* feat: add version command to cli with tools flag

* test: check output of version and tools flag

* fix: add version tool info to cli outputs

.github/workflows/black.yml

@@ -1,10 +0,0 @@
-name: Lint
-
-on: [pull_request]
-
-jobs:
-  lint:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - uses: psf/black@stable

.github/workflows/linter.yml

@@ -0,0 +1,16 @@
+name: Lint
+
+on: [pull_request]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Install Requirements
+        run: |
+          pip install ruff
+
+      - name: Run Ruff Linter
+        run: ruff check --exclude "templates","__init__.py"

.github/workflows/tests.yml

@@ -14,19 +14,18 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
 
       - name: Setup Python
         uses: actions/setup-python@v4
         with:
-          python-version: '3.10'
+          python-version: "3.11"
 
       - name: Install Requirements
         run: |
-          sudo apt-get update &&
-          pip install poetry &&
+          pip install poetry
           poetry lock &&
           poetry install
 
       - name: Run tests
-        run: poetry run pytest
+        run: poetry run pytest tests

.github/workflows/type-checker.yml

@@ -1,4 +1,3 @@
-
 name: Run Type Checks
 
 on: [pull_request]
@@ -12,19 +11,16 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
 
       - name: Setup Python
         uses: actions/setup-python@v4
         with:
-          python-version: '3.10'
+          python-version: "3.10"
 
       - name: Install Requirements
         run: |
-          sudo apt-get update &&
-          pip install poetry &&
-          poetry lock &&
-          poetry install
+          pip install mypy
 
       - name: Run type checks
-        run: poetry run pyright
+        run: mypy src

.pre-commit-config.yaml

@@ -1,21 +1,9 @@
 repos:
-  - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 23.12.1
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.4.4
     hooks:
-      - id: black
-        language_version: python3.11
-        files: \.(py)$
-        exclude: 'src/crewai/cli/templates/(crew|main)\.py'
-
-  - repo: https://github.com/pycqa/isort
-    rev: 5.13.2
-    hooks:
-      - id: isort
-        name: isort (python)
-        args: ["--profile", "black", "--filter-files"]
-
-  - repo: https://github.com/PyCQA/autoflake
-    rev: v2.2.1
-    hooks:
-      - id: autoflake
-        args: ['--in-place', '--remove-all-unused-imports', '--remove-unused-variables', '--ignore-init-module-imports']
+      - id: ruff
+        args: ["--fix"]
+        exclude: "templates"
+      - id: ruff-format
+        exclude: "templates"

README.md

@@ -231,7 +231,7 @@ poetry run pytest
 ### Running static type checks
 
 ```bash
-poetry run pyright
+poetry run mypy
 ```
 
 ### Packaging

docs/how-to/LLM-Connections.md

@@ -103,7 +103,8 @@ general_agent = Agent(role = "Math Professor",
                       verbose = True,
                       llm = llm)
 task = Task (description="""what is 3 + 5""",
-             agent = general_agent)
+             agent = general_agent,
+             expected_output="A numerical answer.")
 
 crew = Crew(
             agents=[general_agent],

docs/index.md

@@ -9,32 +9,32 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
         <h2>Core Concepts</h2>
         <ul>
             <li>
-                <a href="./core-concepts/Agents.md">
+                <a href="./core-concepts/Agents">
                     Agents
                 </a>
             </li>
             <li>
-                <a href="./core-concepts/Tasks.md">
+                <a href="./core-concepts/Tasks">
                     Tasks
                 </a>
             </li>
             <li>
-                <a href="./core-concepts/Tools.md">
+                <a href="./core-concepts/Tools">
                     Tools
                 </a>
             </li>
             <li>
-                <a href="./core-concepts/Processes.md">
+                <a href="./core-concepts/Processes">
                     Processes
                 </a>
             </li>
             <li>
-                <a href="./core-concepts/Crews.md">
+                <a href="./core-concepts/Crews">
                     Crews
                 </a>
             </li>
             <li>
-                <a href="./core-concepts/Memory.md">
+                <a href="./core-concepts/Memory">
                     Memory
                 </a>
             </li>
@@ -44,47 +44,47 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
         <h2>How-To Guides</h2>
         <ul>
             <li>
-                <a href="./how-to/Installing-CrewAI.md">
+                <a href="./how-to/Installing-CrewAI">
                     Installing crewAI
                 </a>
             </li>
             <li>
-                <a href="./how-to/Creating-a-Crew-and-kick-it-off.md">
+                <a href="./how-to/Creating-a-Crew-and-kick-it-off">
                     Getting Started
                 </a>
             </li>
             <li>
-                <a href="./how-to/Create-Custom-Tools.md">
+                <a href="./how-to/Create-Custom-Tools">
                     Create Custom Tools
                 </a>
             </li>
             <li>
-                <a href="./how-to/Sequential.md">
+                <a href="./how-to/Sequential">
                     Using Sequential Process
                 </a>
             </li>
             <li>
-                <a href="./how-to/Hierarchical.md">
+                <a href="./how-to/Hierarchical">
                     Using Hierarchical Process
                 </a>
             </li>
             <li>
-                <a href="./how-to/LLM-Connections.md">
+                <a href="./how-to/LLM-Connections">
                     Connecting to LLMs
                 </a>
             </li>
             <li>
-                <a href="./how-to/Customizing-Agents.md">
+                <a href="./how-to/Customizing-Agents">
                     Customizing Agents
                 </a>
             </li>
             <li>
-                <a href="./how-to/Human-Input-on-Execution.md">
+                <a href="./how-to/Human-Input-on-Execution">
                     Human Input on Execution
                 </a>
             </li>
             <li>
-                <a href="./how-to/AgentOps-Observability.md">
+                <a href="./how-to/AgentOps-Observability">
                     Agent Monitoring with AgentOps
                 </a>
             </li>

docs/tools/CSVSearchTool.md

@@ -50,7 +50,7 @@ tool = CSVSearchTool(
             ),
         ),
         embedder=dict(
-            provider="google",
+            provider="google", # or openai, ollama, ...
             config=dict(
                 model="models/embedding-001",
                 task_type="retrieval_document",

docs/tools/CodeDocsSearchTool.md

@@ -53,7 +53,7 @@ tool = CodeDocsSearchTool(
             ),
         ),
         embedder=dict(
-            provider="google",
+            provider="google", # or openai, ollama, ...
             config=dict(
                 model="models/embedding-001",
                 task_type="retrieval_document",

docs/tools/DOCXSearchTool.md

@@ -48,7 +48,7 @@ tool = DOCXSearchTool(
             ),
         ),
         embedder=dict(
-            provider="google",
+            provider="google", # or openai, ollama, ...
             config=dict(
                 model="models/embedding-001",
                 task_type="retrieval_document",

docs/tools/DirectorySearchTool.md

@@ -43,7 +43,7 @@ tool = DirectorySearchTool(
             ),
         ),
         embedder=dict(
-            provider="google",
+            provider="google", # or openai, ollama, ...
             config=dict(
                 model="models/embedding-001",
                 task_type="retrieval_document",

docs/tools/GitHubSearchTool.md

@@ -55,7 +55,7 @@ tool = GithubSearchTool(
             ),
         ),
         embedder=dict(
-            provider="google",
+            provider="google", # or openai, ollama, ...
             config=dict(
                 model="models/embedding-001",
                 task_type="retrieval_document",

docs/tools/JSONSearchTool.md

@@ -48,7 +48,7 @@ tool = JSONSearchTool(
             },
         },
         "embedder": {
-            "provider": "google",
+            "provider": "google", # or openai, ollama, ...
             "config": {
                 "model": "models/embedding-001",
                 "task_type": "retrieval_document",

docs/tools/MDXSearchTool.md

@@ -49,7 +49,7 @@ tool = MDXSearchTool(
             ),
         ),
         embedder=dict(
-            provider="google",
+            provider="google", # or openai, ollama, ...
             config=dict(
                 model="models/embedding-001",
                 task_type="retrieval_document",

docs/tools/PDFSearchTool.md

@@ -48,7 +48,7 @@ tool = PDFSearchTool(
             ),
         ),
         embedder=dict(
-            provider="google",
+            provider="google", # or openai, ollama, ...
             config=dict(
                 model="models/embedding-001",
                 task_type="retrieval_document",

docs/tools/PGSearchTool.md

@@ -48,7 +48,7 @@ tool = PGSearchTool(
             ),
         ),
         embedder=dict(
-            provider="google",
+            provider="google", # or openai, ollama, ...
             config=dict(
                 model="models/embedding-001",
                 task_type="retrieval_document",

docs/tools/TXTSearchTool.md

@@ -50,7 +50,7 @@ tool = TXTSearchTool(
             ),
         ),
         embedder=dict(
-            provider="google",
+            provider="google", # or openai, ollama, ...
             config=dict(
                 model="models/embedding-001",
                 task_type="retrieval_document",

docs/tools/WebsiteSearchTool.md

@@ -48,7 +48,7 @@ tool = WebsiteSearchTool(
             ),
         ),
         embedder=dict(
-            provider="google",
+            provider="google", # or openai, ollama, ...
             config=dict(
                 model="models/embedding-001",
                 task_type="retrieval_document",

docs/tools/XMLSearchTool.md

@@ -48,7 +48,7 @@ tool = XMLSearchTool(
             ),
         ),
         embedder=dict(
-            provider="google",
+            provider="google", # or openai, ollama, ...
             config=dict(
                 model="models/embedding-001",
                 task_type="retrieval_document",

docs/tools/YoutubeChannelSearchTool.md

@@ -48,7 +48,7 @@ tool = YoutubeChannelSearchTool(
             ),
         ),
         embedder=dict(
-            provider="google",
+            provider="google", # or openai, ollama, ...
             config=dict(
                 model="models/embedding-001",
                 task_type="retrieval_document",

docs/tools/YoutubeVideoSearchTool.md

@@ -52,7 +52,7 @@ tool = YoutubeVideoSearchTool(
             ),
         ),
         embedder=dict(
-            provider="google",
+            provider="google", # or openai, ollama, ...
             config=dict(
                 model="models/embedding-001",
                 task_type="retrieval_document",

pyproject.toml

@@ -1,12 +1,10 @@
 [tool.poetry]
 name = "crewai"
-version = "0.30.0rc6"
+version = "0.30.11"
 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"
-packages = [
-    { include = "crewai", from = "src" },
-]
+packages = [{ include = "crewai", from = "src" }]
 
 [tool.poetry.urls]
 Homepage = "https://crewai.com"
@@ -23,7 +21,7 @@ opentelemetry-sdk = "^1.22.0"
 opentelemetry-exporter-otlp-proto-http = "^1.22.0"
 instructor = "^0.5.2"
 regex = "^2023.12.25"
-crewai-tools = { version = "^0.2.3", optional = true }
+crewai-tools = { version = "^0.2.6", optional = true }
 click = "^8.1.7"
 python-dotenv = "^1.0.0"
 embedchain = "^0.1.98"
@@ -34,22 +32,17 @@ tools = ["crewai-tools"]
 
 [tool.poetry.group.dev.dependencies]
 isort = "^5.13.2"
-pyright = ">=1.1.350,<2.0.0"
+mypy = "1.10.0"
 autoflake = "^2.2.1"
 pre-commit = "^3.6.0"
 mkdocs = "^1.4.3"
 mkdocstrings = "^0.22.0"
 mkdocstrings-python = "^1.1.2"
-mkdocs-material = {extras = ["imaging"], version = "^9.5.7"}
+mkdocs-material = { extras = ["imaging"], version = "^9.5.7" }
 mkdocs-material-extensions = "^1.3.1"
 pillow = "^10.2.0"
 cairosvg = "^2.7.1"
-crewai-tools = "^0.2.3"
-
-[tool.isort]
-profile = "black"
-known_first_party = ["crewai"]
-
+crewai-tools = "^0.2.6"
 
 [tool.poetry.group.test.dependencies]
 pytest = "^8.0.0"
@@ -59,6 +52,11 @@ python-dotenv = "1.0.0"
 [tool.poetry.scripts]
 crewai = "crewai.cli.cli:crewai"
 
+[tool.mypy]
+ignore_missing_imports = true
+disable_error_code = 'import-untyped'
+exclude = ["cli/templates/main.py", "cli/templates/crew.py"]
+
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"

src/crewai/agent.py

@@ -204,7 +204,7 @@ class Agent(BaseModel):
             Output of the agent
         """
         if self.tools_handler:
-            self.tools_handler.last_used_tool = {}
+            self.tools_handler.last_used_tool = {}  # type: ignore # Incompatible types in assignment (expression has type "dict[Never, Never]", variable has type "ToolCalling")
 
         task_prompt = task.prompt()
 
@@ -224,7 +224,7 @@ class Agent(BaseModel):
                 task_prompt += self.i18n.slice("memory").format(memory=memory)
 
         tools = tools or self.tools
-        parsed_tools = self._parse_tools(tools)
+        parsed_tools = self._parse_tools(tools)  # type: ignore # Argument 1 to "_parse_tools" of "Agent" has incompatible type "list[Any] | None"; expected "list[Any]"
 
         self.create_agent_executor(tools=tools)
         self.agent_executor.tools = parsed_tools
@@ -303,9 +303,9 @@ class Agent(BaseModel):
         }
 
         if self._rpm_controller:
-            executor_args[
-                "request_within_rpm_limit"
-            ] = self._rpm_controller.check_or_wait
+            executor_args["request_within_rpm_limit"] = (
+                self._rpm_controller.check_or_wait
+            )
 
         prompt = Prompts(
             i18n=self.i18n,
@@ -364,7 +364,7 @@ class Agent(BaseModel):
             thoughts += f"\n{observation_prefix}{observation}\n{llm_prefix}"
         return thoughts
 
-    def _parse_tools(self, tools: List[Any]) -> List[LangChainTool]:
+    def _parse_tools(self, tools: List[Any]) -> List[LangChainTool]:  # type: ignore # Function "langchain_core.tools.tool" is not valid as a type
         """Parse tools to be used for the task."""
         # tentatively try to import from crewai_tools import BaseTool as CrewAITool
         tools_list = []

src/crewai/agents/executor.py

@@ -35,7 +35,7 @@ class CrewAgentExecutor(AgentExecutor):
     crew: Any = None
     function_calling_llm: Any = None
     request_within_rpm_limit: Any = None
-    tools_handler: InstanceOf[ToolsHandler] = None
+    tools_handler: Optional[InstanceOf[ToolsHandler]] = None
     max_iterations: Optional[int] = 15
     have_forced_answer: bool = False
     force_answer_max_iterations: Optional[int] = None
@@ -189,7 +189,7 @@ class CrewAgentExecutor(AgentExecutor):
             intermediate_steps = self._prepare_intermediate_steps(intermediate_steps)
 
             # Call the LLM to see what to do.
-            output = self.agent.plan(
+            output = self.agent.plan(  # type: ignore #  Incompatible types in assignment (expression has type "AgentAction | AgentFinish | list[AgentAction]", variable has type "AgentAction")
                 intermediate_steps,
                 callbacks=run_manager.get_child() if run_manager else None,
                 **inputs,
@@ -275,8 +275,8 @@ class CrewAgentExecutor(AgentExecutor):
                 run_manager.on_agent_action(agent_action, color="green")
 
             tool_usage = ToolUsage(
-                tools_handler=self.tools_handler,
-                tools=self.tools,
+                tools_handler=self.tools_handler,  # type: ignore # Argument "tools_handler" to "ToolUsage" has incompatible type "ToolsHandler | None"; expected "ToolsHandler"
+                tools=self.tools,  # type: ignore # Argument "tools" to "ToolUsage" has incompatible type "Sequence[BaseTool]"; expected "list[BaseTool]"
                 original_tools=self.original_tools,
                 tools_description=self.tools_description,
                 tools_names=self.tools_names,

src/crewai/agents/tools_handler.py

@@ -8,13 +8,13 @@ from .cache.cache_handler import CacheHandler
 class ToolsHandler:
     """Callback handler for tool usage."""
 
-    last_used_tool: ToolCalling = {}
-    cache: CacheHandler
+    last_used_tool: ToolCalling = {}  # type: ignore # BUG?: Incompatible types in assignment (expression has type "Dict[...]", variable has type "ToolCalling")
+    cache: Optional[CacheHandler]
 
     def __init__(self, cache: Optional[CacheHandler] = None):
         """Initialize the callback handler."""
         self.cache = cache
-        self.last_used_tool = {}
+        self.last_used_tool = {}  # type: ignore # BUG?: same as above
 
     def on_tool_use(
         self,
@@ -23,7 +23,7 @@ class ToolsHandler:
         should_cache: bool = True,
     ) -> Any:
         """Run when tool ends running."""
-        self.last_used_tool = calling
+        self.last_used_tool = calling  # type: ignore # BUG?: Incompatible types in assignment (expression has type "Union[ToolCalling, InstructorToolCalling]", variable has type "ToolCalling")
         if self.cache and should_cache and calling.tool_name != CacheTools().name:
             self.cache.add(
                 tool=calling.tool_name,

src/crewai/cli/cli.py

@@ -1,6 +1,8 @@
 import click
+import pkg_resources
 
 from .create_crew import create_crew
+from .train_crew import train_crew
 
 
 @click.group()
@@ -15,5 +17,36 @@ def create(project_name):
     create_crew(project_name)
 
 
+@crewai.command()
+@click.option(
+    "--tools", is_flag=True, help="Show the installed version of crewai tools"
+)
+def version(tools):
+    """Show the installed version of crewai."""
+    crewai_version = pkg_resources.get_distribution("crewai").version
+    click.echo(f"crewai version: {crewai_version}")
+
+    if tools:
+        try:
+            tools_version = pkg_resources.get_distribution("crewai-tools").version
+            click.echo(f"crewai tools version: {tools_version}")
+        except pkg_resources.DistributionNotFound:
+            click.echo("crewai tools not installed")
+
+
+@crewai.command()
+@click.option(
+    "-n",
+    "--n_iterations",
+    type=int,
+    default=5,
+    help="Number of iterations to train the crew",
+)
+def train(n_iterations: int):
+    """Train the crew."""
+    click.echo(f"Training the crew for {n_iterations} iterations")
+    train_crew(n_iterations)
+
+
 if __name__ == "__main__":
     crewai()

src/crewai/cli/templates/main.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+import sys
 from {{folder_name}}.crew import {{crew_name}}Crew
 
 
@@ -7,4 +8,15 @@ def run():
     inputs = {
         'topic': 'AI LLMs'
     }
-    {{crew_name}}Crew().crew().kickoff(inputs=inputs)
+    {{crew_name}}Crew().crew().kickoff(inputs=inputs)
+
+
+def train():
+    """
+    Train the crew for a given number of iterations.
+    """
+    try:
+        {{crew_name}}Crew().crew().train(n_iterations=int(sys.argv[1]))
+
+    except Exception as e:
+        raise Exception(f"An error occurred while training the crew: {e}")

src/crewai/cli/templates/pyproject.toml

@@ -6,11 +6,12 @@ authors = ["Your Name <you@example.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
-crewai = {extras = ["tools"], version = "^0.28.8"}
+crewai = { extras = ["tools"], version = "^0.30.11" }
 
 [tool.poetry.scripts]
 {{folder_name}} = "{{folder_name}}.main:run"
+train = "{{folder_name}}.main:train"
 
 [build-system]
 requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"
+build-backend = "poetry.core.masonry.api"

src/crewai/cli/templates/tools/custom_tool.py

@@ -3,7 +3,9 @@ from crewai_tools import BaseTool
 
 class MyCustomTool(BaseTool):
     name: str = "Name of my tool"
-    description: str = "Clear description for what this tool is useful for, you agent will need this information to use it."
+    description: str = (
+        "Clear description for what this tool is useful for, you agent will need this information to use it."
+    )
 
     def _run(self, argument: str) -> str:
         # Implementation goes here

src/crewai/cli/train_crew.py

@@ -0,0 +1,29 @@
+import subprocess
+
+import click
+
+
+def train_crew(n_iterations: int) -> None:
+    """
+    Train the crew by running a command in the Poetry environment.
+
+    Args:
+        n_iterations (int): The number of iterations to train the crew.
+    """
+    command = ["poetry", "run", "train", str(n_iterations)]
+
+    try:
+        if n_iterations <= 0:
+            raise ValueError("The number of iterations must be a positive integer.")
+
+        result = subprocess.run(command, capture_output=False, text=True, check=True)
+
+        if result.stderr:
+            click.echo(result.stderr, err=True)
+
+    except subprocess.CalledProcessError as e:
+        click.echo(f"An error occurred while training the crew: {e}", err=True)
+        click.echo(e.output, err=True)
+
+    except Exception as e:
+        click.echo(f"An unexpected error occurred: {e}", err=True)

src/crewai/crew.py

@@ -164,8 +164,10 @@ class Crew(BaseModel):
         """Set private attributes."""
         if self.memory:
             self._long_term_memory = LongTermMemory()
-            self._short_term_memory = ShortTermMemory(embedder_config=self.embedder)
-            self._entity_memory = EntityMemory(embedder_config=self.embedder)
+            self._short_term_memory = ShortTermMemory(
+                crew=self, embedder_config=self.embedder
+            )
+            self._entity_memory = EntityMemory(crew=self, embedder_config=self.embedder)
         return self
 
     @model_validator(mode="after")
@@ -242,7 +244,7 @@ class Crew(BaseModel):
     def kickoff(self, inputs: Optional[Dict[str, Any]] = {}) -> str:
         """Starts the crew to work on its assigned tasks."""
         self._execution_span = self._telemetry.crew_execution_span(self)
-        self._interpolate_inputs(inputs)
+        self._interpolate_inputs(inputs)  # type: ignore # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
         self._set_tasks_callbacks()
 
         i18n = I18N(prompt_file=self.prompt_file)
@@ -263,8 +265,8 @@ class Crew(BaseModel):
         if self.process == Process.sequential:
             result = self._run_sequential_process()
         elif self.process == Process.hierarchical:
-            result, manager_metrics = self._run_hierarchical_process()
-            metrics.append(manager_metrics)
+            result, manager_metrics = self._run_hierarchical_process()  # type: ignore # Unpacking a string is disallowed
+            metrics.append(manager_metrics)  # type: ignore # Cannot determine type of "manager_metrics"
 
         else:
             raise NotImplementedError(
@@ -280,11 +282,15 @@ class Crew(BaseModel):
 
         return result
 
+    def train(self, n_iterations: int) -> None:
+        # TODO: Implement training
+        pass
+
     def _run_sequential_process(self) -> str:
         """Executes tasks sequentially and returns the final output."""
         task_output = ""
         for task in self.tasks:
-            if 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
                 ]
@@ -357,23 +363,23 @@ class Crew(BaseModel):
                 )
 
         self._finish_execution(task_output)
-        return self._format_output(task_output), manager._token_process.get_summary()
+        return self._format_output(task_output), manager._token_process.get_summary()  # type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
 
-    def _set_tasks_callbacks(self) -> str:
+    def _set_tasks_callbacks(self) -> None:
         """Sets callback for every task suing task_callback"""
         for task in self.tasks:
             if not task.callback:
                 task.callback = self.task_callback
 
-    def _interpolate_inputs(self, inputs: Dict[str, Any]) -> str:
+    def _interpolate_inputs(self, inputs: Dict[str, Any]) -> None:
         """Interpolates the inputs in the tasks and agents."""
-        [task.interpolate_inputs(inputs) for task in self.tasks]
-        [agent.interpolate_inputs(inputs) for agent in self.agents]
+        [task.interpolate_inputs(inputs) for task in self.tasks]  # type: ignore # "interpolate_inputs" of "Task" does not return a value (it only ever returns None)
+        [agent.interpolate_inputs(inputs) for agent in self.agents]  # type: ignore # "interpolate_inputs" of "Agent" does not return a value (it only ever returns None)
 
     def _format_output(self, output: str) -> str:
         """Formats the output of the crew execution."""
         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],
             }

src/crewai/memory/contextual/contextual_memory.py

@@ -1,3 +1,5 @@
+from typing import Optional
+
 from crewai.memory import EntityMemory, LongTermMemory, ShortTermMemory
 
 
@@ -32,7 +34,7 @@ class ContextualMemory:
         formatted_results = "\n".join([f"- {result}" for result in stm_results])
         return f"Recent Insights:\n{formatted_results}" if stm_results else ""
 
-    def _fetch_ltm_context(self, task) -> str:
+    def _fetch_ltm_context(self, task) -> Optional[str]:
         """
         Fetches historical data or insights from LTM that are relevant to the task's description and expected_output,
         formatted as bullet points.
@@ -44,10 +46,10 @@ class ContextualMemory:
         formatted_results = [
             suggestion
             for result in ltm_results
-            for suggestion in result["metadata"]["suggestions"]
+            for suggestion in result["metadata"]["suggestions"]  # type: ignore # Invalid index type "str" for "str"; expected type "SupportsIndex | slice"
         ]
         formatted_results = list(dict.fromkeys(formatted_results))
-        formatted_results = "\n".join([f"- {result}" for result in formatted_results])
+        formatted_results = "\n".join([f"- {result}" for result in formatted_results])  # type: ignore # Incompatible types in assignment (expression has type "str", variable has type "list[str]")
 
         return f"Historical Data:\n{formatted_results}" if ltm_results else ""
 
@@ -58,6 +60,6 @@ class ContextualMemory:
         """
         em_results = self.em.search(query)
         formatted_results = "\n".join(
-            [f"- {result['context']}" for result in em_results]
+            [f"- {result['context']}" for result in em_results]  # type: ignore #  Invalid index type "str" for "str"; expected type "SupportsIndex | slice"
         )
         return f"Entities:\n{formatted_results}" if em_results else ""

src/crewai/memory/entity/entity_memory.py

@@ -10,13 +10,16 @@ class EntityMemory(Memory):
     Inherits from the Memory class.
     """
 
-    def __init__(self, embedder_config=None):
+    def __init__(self, crew=None, embedder_config=None):
         storage = RAGStorage(
-            type="entities", allow_reset=False, embedder_config=embedder_config
+            type="entities",
+            allow_reset=False,
+            embedder_config=embedder_config,
+            crew=crew,
         )
         super().__init__(storage)
 
-    def save(self, item: EntityMemoryItem) -> None:
+    def save(self, item: EntityMemoryItem) -> None:  # type: ignore # BUG?: Signature of "save" incompatible with supertype "Memory"
         """Saves an entity item into the SQLite storage."""
         data = f"{item.name}({item.type}): {item.description}"
         super().save(data, item.metadata)

src/crewai/memory/long_term/long_term_memory.py

@@ -18,10 +18,10 @@ class LongTermMemory(Memory):
         storage = LTMSQLiteStorage()
         super().__init__(storage)
 
-    def save(self, item: LongTermMemoryItem) -> None:
+    def save(self, item: LongTermMemoryItem) -> None:  # type: ignore # BUG?: Signature of "save" incompatible with supertype "Memory"
         metadata = item.metadata
         metadata.update({"agent": item.agent, "expected_output": item.expected_output})
-        self.storage.save(
+        self.storage.save(  # type: ignore # BUG?: Unexpected keyword argument "task_description","score","datetime" for "save" of "Storage"
             task_description=item.task,
             score=metadata["quality"],
             metadata=metadata,
@@ -29,4 +29,4 @@ class LongTermMemory(Memory):
         )
 
     def search(self, task: str, latest_n: int = 3) -> Dict[str, Any]:
-        return self.storage.load(task, latest_n)
+        return self.storage.load(task, latest_n)  # type: ignore # BUG?: "Storage" has no attribute "load"

src/crewai/memory/long_term/long_term_memory_item.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict, Union
+from typing import Any, Dict, Optional, Union
 
 
 class LongTermMemoryItem:
@@ -8,8 +8,8 @@ class LongTermMemoryItem:
         task: str,
         expected_output: str,
         datetime: str,
-        quality: Union[int, float] = None,
-        metadata: Dict[str, Any] = None,
+        quality: Optional[Union[int, float]] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ):
         self.task = task
         self.agent = agent

src/crewai/memory/memory.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict
+from typing import Any, Dict, Optional
 
 from crewai.memory.storage.interface import Storage
 
@@ -12,12 +12,16 @@ class Memory:
         self.storage = storage
 
     def save(
-        self, value: Any, metadata: Dict[str, Any] = None, agent: str = None
+        self,
+        value: Any,
+        metadata: Optional[Dict[str, Any]] = None,
+        agent: Optional[str] = None,
     ) -> None:
         metadata = metadata or {}
         if agent:
             metadata["agent"] = agent
-        self.storage.save(value, metadata)
+
+        self.storage.save(value, metadata)  # type: ignore # Maybe BUG? Should be self.storage.save(key, value, metadata)
 
     def search(self, query: str) -> Dict[str, Any]:
         return self.storage.search(query)

src/crewai/memory/short_term/short_term_memory.py

@@ -12,12 +12,14 @@ class ShortTermMemory(Memory):
     MemoryItem instances.
     """
 
-    def __init__(self, embedder_config=None):
-        storage = RAGStorage(type="short_term", embedder_config=embedder_config)
+    def __init__(self, crew=None, embedder_config=None):
+        storage = RAGStorage(
+            type="short_term", embedder_config=embedder_config, crew=crew
+        )
         super().__init__(storage)
 
-    def save(self, item: ShortTermMemoryItem) -> None:
+    def save(self, item: ShortTermMemoryItem) -> None:  # type: ignore # BUG?: Signature of "save" incompatible with supertype "Memory"
         super().save(item.data, item.metadata, item.agent)
 
     def search(self, query: str, score_threshold: float = 0.35):
-        return self.storage.search(query=query, score_threshold=score_threshold)
+        return self.storage.search(query=query, score_threshold=score_threshold)  # type: ignore # BUG? The reference is to the parent class, but the parent class does not have this parameters

src/crewai/memory/short_term/short_term_memory_item.py

@@ -1,8 +1,10 @@
-from typing import Any, Dict
+from typing import Any, Dict, Optional
 
 
 class ShortTermMemoryItem:
-    def __init__(self, data: Any, agent: str, metadata: Dict[str, Any] = None):
+    def __init__(
+        self, data: Any, agent: str, metadata: Optional[Dict[str, Any]] = None
+    ):
         self.data = data
         self.agent = agent
         self.metadata = metadata if metadata is not None else {}

src/crewai/memory/storage/interface.py

@@ -7,5 +7,5 @@ class Storage:
     def save(self, key: str, value: Any, metadata: Dict[str, Any]) -> None:
         pass
 
-    def search(self, key: str) -> Dict[str, Any]:
+    def search(self, key: str) -> Dict[str, Any]:  # type: ignore
         pass

src/crewai/memory/storage/ltm_sqlite_storage.py

@@ -1,6 +1,6 @@
 import json
 import sqlite3
-from typing import Any, Dict, Union
+from typing import Any, Dict, List, Optional, Union
 
 from crewai.utilities import Printer
 from crewai.utilities.paths import db_storage_path
@@ -11,7 +11,9 @@ class LTMSQLiteStorage:
     An updated SQLite storage class for LTM data storage.
     """
 
-    def __init__(self, db_path=f"{db_storage_path()}/long_term_memory_storage.db"):
+    def __init__(
+        self, db_path: str = f"{db_storage_path()}/long_term_memory_storage.db"
+    ) -> None:
         self.db_path = db_path
         self._printer: Printer = Printer()
         self._initialize_db()
@@ -67,7 +69,9 @@ class LTMSQLiteStorage:
                 color="red",
             )
 
-    def load(self, task_description: str, latest_n: int) -> Dict[str, Any]:
+    def load(
+        self, task_description: str, latest_n: int
+    ) -> Optional[List[Dict[str, Any]]]:
         """Queries the LTM table by task description with error handling."""
         try:
             with sqlite3.connect(self.db_path) as conn:

src/crewai/memory/storage/rag_storage.py

@@ -2,7 +2,7 @@ import contextlib
 import io
 import logging
 import os
-from typing import Any, Dict
+from typing import Any, Dict, List, Optional
 
 from embedchain import App
 from embedchain.llm.base import BaseLlm
@@ -37,13 +37,18 @@ class RAGStorage(Storage):
     search efficiency.
     """
 
-    def __init__(self, type, allow_reset=True, embedder_config=None):
+    def __init__(self, type, allow_reset=True, embedder_config=None, crew=None):
         super().__init__()
         if (
             not os.getenv("OPENAI_API_KEY")
             and not os.getenv("OPENAI_BASE_URL") == "https://api.openai.com/v1"
         ):
             os.environ["OPENAI_API_KEY"] = "fake"
+
+        agents = crew.agents if crew else []
+        agents = [agent.role for agent in agents]
+        agents = "_".join(agents)
+
         config = {
             "app": {
                 "config": {"name": type, "collect_metrics": False, "log_level": "ERROR"}
@@ -58,7 +63,7 @@ class RAGStorage(Storage):
                 "provider": "chroma",
                 "config": {
                     "collection_name": type,
-                    "dir": f"{db_storage_path()}/{type}",
+                    "dir": f"{db_storage_path()}/{type}/{agents}",
                     "allow_reset": allow_reset,
                 },
             },
@@ -72,16 +77,16 @@ class RAGStorage(Storage):
         if allow_reset:
             self.app.reset()
 
-    def save(self, value: Any, metadata: Dict[str, Any]) -> None:
+    def save(self, value: Any, metadata: Dict[str, Any]) -> None:  # type: ignore # BUG?: Should be save(key, value, metadata)  Signature of "save" incompatible with supertype "Storage"
         self._generate_embedding(value, metadata)
 
-    def search(
+    def search(  # type: ignore # BUG?: Signature of "search" incompatible with supertype "Storage"
         self,
         query: str,
         limit: int = 3,
-        filter: dict = None,
+        filter: Optional[dict] = None,
         score_threshold: float = 0.35,
-    ) -> Dict[str, Any]:
+    ) -> List[Any]:
         with suppress_logging():
             try:
                 results = (

src/crewai/project/crew_base.py

@@ -4,13 +4,15 @@ from pathlib import Path
 
 import yaml
 from dotenv import load_dotenv
+from pydantic import ConfigDict
 
 load_dotenv()
 
 
 def CrewBase(cls):
     class WrappedClass(cls):
-        is_crew_class = True
+        model_config = ConfigDict(arbitrary_types_allowed=True)
+        is_crew_class: bool = True  # type: ignore
 
         base_directory = None
         for frame_info in inspect.stack():
@@ -40,6 +42,7 @@ def CrewBase(cls):
         @staticmethod
         def load_yaml(config_path: str):
             with open(config_path, "r") as file:
+                # parsedContent = YamlParser.parse(file)  # type: ignore # Argument 1 to "parse" has incompatible type "TextIOWrapper"; expected "YamlParser"
                 return yaml.safe_load(file)
 
     return WrappedClass

src/crewai/task.py

@@ -1,8 +1,8 @@
+import os
 import re
 import threading
 import uuid
 from typing import Any, Dict, List, Optional, Type
-import os
 
 from langchain_openai import ChatOpenAI
 from pydantic import UUID4, BaseModel, Field, field_validator, model_validator
@@ -41,7 +41,7 @@ class Task(BaseModel):
     tools_errors: int = 0
     delegations: int = 0
     i18n: I18N = I18N()
-    thread: threading.Thread = None
+    thread: Optional[threading.Thread] = None
     prompt_context: Optional[str] = None
     description: str = Field(description="Description of the actual task.")
     expected_output: str = Field(
@@ -109,6 +109,14 @@ class Task(BaseModel):
                 "may_not_set_field", "This field is not to be set by the user.", {}
             )
 
+    @field_validator("output_file")
+    @classmethod
+    def output_file_validattion(cls, value: str) -> str:
+        """Validate the output file path by removing the / from the beginning of the path."""
+        if value.startswith("/"):
+            return value[1:]
+        return value
+
     @model_validator(mode="after")
     def set_attributes_based_on_config(self) -> "Task":
         """Set attributes based on the agent configuration."""
@@ -136,7 +144,7 @@ class Task(BaseModel):
             )
         return self
 
-    def execute(
+    def execute(  # type: ignore # Missing return statement
         self,
         agent: Agent | None = None,
         context: Optional[str] = None,
@@ -155,13 +163,13 @@ class Task(BaseModel):
             )
 
         if self.context:
-            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.thread.join()
+                    task.thread.join()  # type: ignore # Item "None" of "Thread | None" has no attribute "join"
                 if task and task.output:
-                    context.append(task.output.raw_output)
-            context = "\n".join(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
@@ -242,26 +250,26 @@ class Task(BaseModel):
 
             # try to convert task_output directly to pydantic/json
             try:
-                exported_result = model.model_validate_json(result)
+                exported_result = model.model_validate_json(result)  # type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "model_validate_json"
                 if self.output_json:
-                    return exported_result.model_dump()
+                    return exported_result.model_dump()  # type: ignore # "str" has no attribute "model_dump"
                 return exported_result
             except Exception:
-              # sometimes the response contains valid JSON in the middle of text
-              match = re.search(r"({.*})", result, re.DOTALL)
-              if match:
-                  try:
-                      exported_result = model.model_validate_json(match.group(0))
-                      if self.output_json:
-                          return exported_result.model_dump()
-                      return exported_result
-                  except Exception:
-                      pass
+                # sometimes the response contains valid JSON in the middle of text
+                match = re.search(r"({.*})", result, re.DOTALL)
+                if match:
+                    try:
+                        exported_result = model.model_validate_json(match.group(0))  # type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "model_validate_json"
+                        if self.output_json:
+                            return exported_result.model_dump()  # type: ignore # "str" has no attribute "model_dump"
+                        return exported_result
+                    except Exception:
+                        pass
 
-            llm = self.agent.function_calling_llm or self.agent.llm
+            llm = self.agent.function_calling_llm or self.agent.llm  # type: ignore # Item "None" of "Agent | None" has no attribute "function_calling_llm"
 
             if not self._is_gpt(llm):
-                model_schema = PydanticSchemaParser(model=model).get_schema()
+                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 = Converter(
@@ -282,22 +290,22 @@ class Task(BaseModel):
 
         if self.output_file:
             content = (
-                exported_result if not self.output_pydantic else exported_result.json()
+                exported_result if not self.output_pydantic else exported_result.json()  # type: ignore # "str" has no attribute "json"
             )
             self._save_file(content)
 
         return exported_result
 
     def _is_gpt(self, llm) -> bool:
-        return isinstance(llm, ChatOpenAI) and llm.openai_api_base == None
+        return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None
 
     def _save_file(self, result: Any) -> None:
-        directory = os.path.dirname(self.output_file)
+        directory = os.path.dirname(self.output_file)  # type: ignore # Value of type variable "AnyOrLiteralStr" of "dirname" cannot be "str | None"
 
-        if not os.path.exists(directory):
+        if directory and not os.path.exists(directory):
             os.makedirs(directory)
 
-        with open(self.output_file, "w") as file:
+        with open(self.output_file, "w", encoding="utf-8") as file:  # type: ignore # Argument 1 to "open" has incompatible type "str | None"; expected "int | str | bytes | PathLike[str] | PathLike[bytes]"
             file.write(result)
         return None
 

src/crewai/telemetry/telemetry.py

@@ -256,9 +256,11 @@ class Telemetry:
                                 "async_execution?": task.async_execution,
                                 "output": task.expected_output,
                                 "agent_role": task.agent.role if task.agent else "None",
-                                "context": [task.description for task in task.context]
-                                if task.context
-                                else "None",
+                                "context": (
+                                    [task.description for task in task.context]
+                                    if task.context
+                                    else "None"
+                                ),
                                 "tools_names": [
                                     tool.name.casefold() for tool in task.tools
                                 ],

src/crewai/tools/agent_tools.py

@@ -1,4 +1,4 @@
-from typing import List
+from typing import List, Union
 
 from langchain.tools import StructuredTool
 from pydantic import BaseModel, Field
@@ -33,12 +33,26 @@ class AgentTools(BaseModel):
         ]
         return tools
 
-    def delegate_work(self, coworker: str, task: str, context: str):
+    def delegate_work(
+        self, task: str, context: str, coworker: Union[str, None] = None, **kwargs
+    ):
         """Useful to delegate a specific task to a co-worker passing all necessary context and names."""
+        coworker = coworker or kwargs.get("co_worker") or kwargs.get("co-worker")
+        if coworker is not None:
+            is_list = coworker.startswith("[") and coworker.endswith("]")
+            if is_list:
+                coworker = coworker[1:-1].split(",")[0]
         return self._execute(coworker, task, context)
 
-    def ask_question(self, coworker: str, question: str, context: str):
+    def ask_question(
+        self, question: str, context: str, coworker: Union[str, None] = None, **kwargs
+    ):
         """Useful to ask a question, opinion or take from a co-worker passing all necessary context and names."""
+        coworker = coworker or kwargs.get("co_worker") or kwargs.get("co-worker")
+        if coworker is not None:
+            is_list = coworker.startswith("[") and coworker.endswith("]")
+            if is_list:
+                coworker = coworker[1:-1].split(",")[0]
         return self._execute(coworker, question, context)
 
     def _execute(self, agent, task, context):
@@ -49,7 +63,7 @@ class AgentTools(BaseModel):
                 for available_agent in self.agents
                 if available_agent.role.casefold().strip() == agent.casefold().strip()
             ]
-        except:
+        except Exception as _:
             return self.i18n.errors("agent_tool_unexsiting_coworker").format(
                 coworkers="\n".join(
                     [f"- {agent.role.casefold()}" for agent in self.agents]

src/crewai/tools/tool_usage.py

@@ -64,7 +64,7 @@ class ToolUsage:
 
         # Set the maximum parsing attempts for bigger models
         if (isinstance(self.function_calling_llm, ChatOpenAI)) and (
-            self.function_calling_llm.openai_api_base == None
+            self.function_calling_llm.openai_api_base is None
         ):
             if self.function_calling_llm.model_name in OPENAI_BIGGER_MODELS:
                 self._max_parsing_attempts = 2
@@ -82,6 +82,8 @@ class ToolUsage:
             self._printer.print(content=f"\n\n{error}\n", color="red")
             self.task.increment_tools_errors()
             return error
+
+        # BUG? The code below seems to be unreachable
         try:
             tool = self._select_tool(calling.tool_name)
         except Exception as e:
@@ -89,15 +91,15 @@ class ToolUsage:
             self.task.increment_tools_errors()
             self._printer.print(content=f"\n\n{error}\n", color="red")
             return error
-        return f"{self._use(tool_string=tool_string, tool=tool, calling=calling)}"
+        return f"{self._use(tool_string=tool_string, tool=tool, calling=calling)}"  # type: ignore # BUG?: "_use" of "ToolUsage" does not return a value (it only ever returns None)
 
     def _use(
         self,
         tool_string: str,
         tool: BaseTool,
         calling: Union[ToolCalling, InstructorToolCalling],
-    ) -> None:
-        if self._check_tool_repeated_usage(calling=calling):
+    ) -> None:  # TODO: Fix this return type
+        if self._check_tool_repeated_usage(calling=calling):  # type: ignore # _check_tool_repeated_usage of "ToolUsage" does not return a value (it only ever returns None)
             try:
                 result = self._i18n.errors("task_repeated_usage").format(
                     tool_names=self.tools_names
@@ -108,15 +110,16 @@ class ToolUsage:
                     tool_name=tool.name,
                     attempts=self._run_attempts,
                 )
-                result = self._format_result(result=result)
-                return result
+                result = self._format_result(result=result)  # type: ignore #  "_format_result" of "ToolUsage" does not return a value (it only ever returns None)
+                return result  # type: ignore # Fix the reutrn type of this function
+
             except Exception:
                 self.task.increment_tools_errors()
 
-        result = None
+        result = None  # type: ignore # Incompatible types in assignment (expression has type "None", variable has type "str")
 
         if self.tools_handler.cache:
-            result = self.tools_handler.cache.read(
+            result = self.tools_handler.cache.read(  # type: ignore # Incompatible types in assignment (expression has type "str | None", variable has type "str")
                 tool=calling.tool_name, input=calling.arguments
             )
 
@@ -130,7 +133,7 @@ class ToolUsage:
 
                 if calling.arguments:
                     try:
-                        acceptable_args = tool.args_schema.schema()["properties"].keys()
+                        acceptable_args = tool.args_schema.schema()["properties"].keys()  # type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "schema"
                         arguments = {
                             k: v
                             for k, v in calling.arguments.items()
@@ -142,7 +145,7 @@ class ToolUsage:
                             arguments = calling.arguments
                             result = tool._run(**arguments)
                         else:
-                            arguments = calling.arguments.values()
+                            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._run()
@@ -158,9 +161,10 @@ class ToolUsage:
                     ).message
                     self.task.increment_tools_errors()
                     self._printer.print(content=f"\n\n{error_message}\n", color="red")
-                    return error
+                    return error  # type: ignore # No return value expected
+
                 self.task.increment_tools_errors()
-                return self.use(calling=calling, tool_string=tool_string)
+                return self.use(calling=calling, tool_string=tool_string)  # type: ignore # No return value expected
 
             if self.tools_handler:
                 should_cache = True
@@ -169,9 +173,9 @@ class ToolUsage:
                 )
                 if (
                     hasattr(original_tool, "cache_function")
-                    and original_tool.cache_function
+                    and original_tool.cache_function  # type: ignore # Item "None" of "Any | None" has no attribute "cache_function"
                 ):
-                    should_cache = original_tool.cache_function(
+                    should_cache = original_tool.cache_function(  # type: ignore # Item "None" of "Any | None" has no attribute "cache_function"
                         calling.arguments, result
                     )
 
@@ -185,13 +189,13 @@ class ToolUsage:
             tool_name=tool.name,
             attempts=self._run_attempts,
         )
-        result = self._format_result(result=result)
-        return result
+        result = self._format_result(result=result)  # type: ignore # "_format_result" of "ToolUsage" does not return a value (it only ever returns None)
+        return result  # type: ignore # No return value expected
 
     def _format_result(self, result: Any) -> None:
         self.task.used_tools += 1
-        if self._should_remember_format():
-            result = self._remember_format(result=result)
+        if self._should_remember_format():  # type: ignore # "_should_remember_format" of "ToolUsage" does not return a value (it only ever returns None)
+            result = self._remember_format(result=result)  # type: ignore # "_remember_format" of "ToolUsage" does not return a value (it only ever returns None)
         return result
 
     def _should_remember_format(self) -> None:
@@ -202,26 +206,33 @@ class ToolUsage:
         result += "\n\n" + self._i18n.slice("tools").format(
             tools=self.tools_description, tool_names=self.tools_names
         )
-        return result
+        return result  # type: ignore # No return value expected
 
     def _check_tool_repeated_usage(
         self, calling: Union[ToolCalling, InstructorToolCalling]
     ) -> None:
         if not self.tools_handler:
-            return False
+            return False  # type: ignore # No return value expected
         if last_tool_usage := self.tools_handler.last_used_tool:
-            return (calling.tool_name == last_tool_usage.tool_name) and (
+            return (calling.tool_name == last_tool_usage.tool_name) and (  # type: ignore # No return value expected
                 calling.arguments == last_tool_usage.arguments
             )
 
     def _select_tool(self, tool_name: str) -> BaseTool:
-        for tool in self.tools:
+        order_tools = sorted(
+            self.tools,
+            key=lambda tool: SequenceMatcher(
+                None, tool.name.lower().strip(), tool_name.lower().strip()
+            ).ratio(),
+            reverse=True,
+        )
+        for tool in order_tools:
             if (
                 tool.name.lower().strip() == tool_name.lower().strip()
                 or SequenceMatcher(
                     None, tool.name.lower().strip(), tool_name.lower().strip()
                 ).ratio()
-                > 0.9
+                > 0.85
             ):
                 return tool
         self.task.increment_tools_errors()
@@ -254,7 +265,7 @@ class ToolUsage:
         return "\n--\n".join(descriptions)
 
     def _is_gpt(self, llm) -> bool:
-        return isinstance(llm, ChatOpenAI) and llm.openai_api_base == None
+        return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None
 
     def _tool_calling(
         self, tool_string: str
@@ -292,14 +303,14 @@ class ToolUsage:
                     tool_input = self._validate_tool_input(self.action.tool_input)
                     arguments = ast.literal_eval(tool_input)
                 except Exception:
-                    return ToolUsageErrorException(
+                    return ToolUsageErrorException(  # type: ignore # Incompatible return value type (got "ToolUsageErrorException", expected "ToolCalling | InstructorToolCalling")
                         f'{self._i18n.errors("tool_arguments_error")}'
                     )
                 if not isinstance(arguments, dict):
-                    return ToolUsageErrorException(
+                    return ToolUsageErrorException(  # type: ignore # Incompatible return value type (got "ToolUsageErrorException", expected "ToolCalling | InstructorToolCalling")
                         f'{self._i18n.errors("tool_arguments_error")}'
                     )
-                calling = ToolCalling(
+                calling = ToolCalling(  # type: ignore # Unexpected keyword argument "log" for "ToolCalling"
                     tool_name=tool.name,
                     arguments=arguments,
                     log=tool_string,
@@ -310,7 +321,7 @@ class ToolUsage:
                 self._telemetry.tool_usage_error(llm=self.function_calling_llm)
                 self.task.increment_tools_errors()
                 self._printer.print(content=f"\n\n{e}\n", color="red")
-                return ToolUsageErrorException(
+                return ToolUsageErrorException(  # type: ignore # Incompatible return value type (got "ToolUsageErrorException", expected "ToolCalling | InstructorToolCalling")
                     f'{self._i18n.errors("tool_usage_error").format(error=e)}\nMoving on then. {self._i18n.slice("format").format(tool_names=self.tools_names)}'
                 )
             return self._tool_calling(tool_string)

src/crewai/translations/en.json

@@ -29,7 +29,7 @@
     "tool_usage_exception": "I encountered an error while trying to use the tool. This was the error: {error}.\n Tool {tool} accepts these inputs: {tool_inputs}"
   },
   "tools": {
-    "delegate_work": "Delegate a specific task to one of the following co-workers: {coworkers}\nThe input to this tool should be the co-worker, the task you want them to do, and ALL necessary context to exectue the task, they know nothing about the task, so share absolute everything you know, don't reference things but instead explain them.",
+    "delegate_work": "Delegate a specific task to one of the following co-workers: {coworkers}\nThe input to this tool should be the co-worker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolute everything you know, don't reference things but instead explain them.",
     "ask_question": "Ask a specific question to one of the following co-workers: {coworkers}\nThe input to this tool should be the co-worker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolute everything you know, don't reference things but instead explain them."
   }
 }

src/crewai/utilities/__init__.py

@@ -6,3 +6,4 @@ from .printer import Printer
 from .prompts import Prompts
 from .rpm_controller import RPMController
 from .fileHandler import FileHandler
+from .parser import YamlParser

src/crewai/utilities/converter.py

@@ -83,5 +83,5 @@ class Converter(BaseModel):
         )
         return new_prompt | self.llm | parser
 
-    def _is_gpt(self, llm) -> bool:
-        return isinstance(llm, ChatOpenAI) and llm.openai_api_base == None
+    def _is_gpt(self, llm) -> bool:  # type: ignore # BUG? Name "_is_gpt" defined on line 20 hides name from outer scope
+        return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None

src/crewai/utilities/evaluators/task_evaluator.py

@@ -58,4 +58,4 @@ class TaskEvaluator:
         return converter.to_pydantic()
 
     def _is_gpt(self, llm) -> bool:
-        return isinstance(llm, ChatOpenAI) and llm.openai_api_base == None
+        return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None

src/crewai/utilities/i18n.py

@@ -21,14 +21,14 @@ class I18N(BaseModel):
                     self._prompts = json.load(f)
             else:
                 dir_path = os.path.dirname(os.path.realpath(__file__))
-                prompts_path = os.path.join(dir_path, f"../translations/en.json")
+                prompts_path = os.path.join(dir_path, "../translations/en.json")
 
                 with open(prompts_path, "r") as f:
                     self._prompts = json.load(f)
         except FileNotFoundError:
             raise Exception(f"Prompt file '{self.prompt_file}' not found.")
         except json.JSONDecodeError:
-            raise Exception(f"Error decoding JSON from the prompts file.")
+            raise Exception("Error decoding JSON from the prompts file.")
 
         if not self._prompts:
             self._prompts = {}
@@ -47,5 +47,5 @@ class I18N(BaseModel):
     def retrieve(self, kind, key) -> str:
         try:
             return self._prompts[kind][key]
-        except:
+        except Exception as _:
             raise Exception(f"Prompt for '{kind}':'{key}'  not found.")

src/crewai/utilities/parser.py

@@ -0,0 +1,17 @@
+import re
+
+
+class YamlParser:
+    def parse(file):
+        content = file.read()
+        # Replace single { and } with doubled ones, while leaving already doubled ones intact and the other special characters {# and {%
+        modified_content = re.sub(r"(?<!\{){(?!\{)(?!\#)(?!\%)", "{{", content)
+        modified_content = re.sub(
+            r"(?<!\})(?<!\%)(?<!\#)\}(?!})", "}}", modified_content
+        )
+        # Check for 'context:' not followed by '[' and raise an error
+        if re.search(r"context:(?!\s*\[)", modified_content):
+            raise ValueError(
+                "Context is currently only supported in code when creating a task. Please use the 'context' key in the task configuration."
+            )
+        return modified_content

src/crewai/utilities/token_counter_callback.py

@@ -22,7 +22,7 @@ class TokenProcess:
     def sum_successful_requests(self, requests: int):
         self.successful_requests = self.successful_requests + requests
 
-    def get_summary(self) -> str:
+    def get_summary(self) -> Dict[str, Any]:
         return {
             "total_tokens": self.total_tokens,
             "prompt_tokens": self.prompt_tokens,
@@ -42,12 +42,12 @@ class TokenCalcHandler(BaseCallbackHandler):
     def on_llm_start(
         self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
     ) -> None:
-        if "gpt" in self.model:
+        try:
             encoding = tiktoken.encoding_for_model(self.model)
-        else:
+        except KeyError:
             encoding = tiktoken.get_encoding("cl100k_base")
 
-        if self.token_cost_process == None:
+        if self.token_cost_process is None:
             return
 
         for prompt in prompts:

tests/agent_test.py

@@ -31,8 +31,8 @@ def test_agent_default_values():
     assert isinstance(agent.llm, ChatOpenAI)
     assert agent.llm.model_name == "gpt-4"
     assert agent.llm.temperature == 0.7
-    assert agent.llm.verbose == False
-    assert agent.allow_delegation == True
+    assert agent.llm.verbose is False
+    assert agent.allow_delegation is True
 
 
 def test_custom_llm():
@@ -751,7 +751,7 @@ def test_agent_definition_based_on_dict():
     assert agent.role == "test role"
     assert agent.goal == "test goal"
     assert agent.backstory == "test backstory"
-    assert agent.verbose == True
+    assert agent.verbose is True
     assert agent.tools == []
 
 

tests/agent_tools/agent_tools_test.py

@@ -28,6 +28,20 @@ def test_delegate_work():
     )
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_delegate_work_with_wrong_co_worker_variable():
+    result = tools.delegate_work(
+        co_worker="researcher",
+        task="share your take on AI Agents",
+        context="I heard you hate them",
+    )
+
+    assert (
+        result
+        == "AI Agents are essentially computer programs that are designed to perform tasks autonomously, with the ability to adapt and learn from their environment. These tasks range from simple ones such as setting alarms, to more complex ones like diagnosing diseases or driving cars. AI agents have the potential to revolutionize many industries, making processes more efficient and accurate. \n\nHowever, like any technology, AI agents have their downsides. They can be susceptible to biases based on the data they're trained on and they can also raise privacy concerns. Moreover, the widespread adoption of AI agents could result in significant job displacement in certain industries.\n\nDespite these concerns, it's important to note that the development and use of AI agents are heavily dependent on human decisions and policies. Therefore, the key to harnessing the benefits of AI agents while mitigating the risks lies in responsible and thoughtful development and implementation.\n\nWhether one 'loves' or 'hates' AI agents often comes down to individual perspectives and experiences. But as a researcher, it is my job to provide balanced and factual information, so I hope this explanation helps you understand better what AI Agents are and the implications they have."
+    )
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_ask_question():
     result = tools.ask_question(
@@ -41,6 +55,46 @@ def test_ask_question():
         == "As an AI researcher, I don't have personal feelings or emotions like love or hate. However, I recognize the importance of AI Agents in today's technological landscape. They have the potential to greatly enhance our lives and make tasks more efficient. At the same time, it is crucial to consider the ethical implications and societal impacts that come with their use. My role is to provide objective research and analysis on these topics."
     )
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_ask_question_with_wrong_co_worker_variable():
+    result = tools.ask_question(
+        co_worker="researcher",
+        question="do you hate AI Agents?",
+        context="I heard you LOVE them",
+    )
+
+    assert (
+        result
+        == "No, I don't hate AI agents. In fact, I find them quite fascinating. They are powerful tools that can greatly assist in various tasks, including my research. As a technology researcher, AI and AI agents are subjects of interest to me due to their potential in advancing our understanding and capabilities in various fields. My supposed love for them stems from this professional interest and the potential they hold."
+    )
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_delegate_work_withwith_coworker_as_array():
+    result = tools.delegate_work(
+        co_worker="[researcher]",
+        task="share your take on AI Agents",
+        context="I heard you hate them",
+    )
+
+    assert (
+        result
+        == "AI Agents are software entities which operate in an environment to achieve a particular goal. They can perceive their environment, reason about it, and take actions to fulfill their objectives. This includes everything from chatbots to self-driving cars. They are designed to act autonomously to a certain extent and are capable of learning from their experiences to improve their performance over time.\n\nDespite some people's fears or dislikes, AI Agents are not inherently good or bad. They are tools, and like any tool, their value depends on how they are used. For instance, AI Agents can be used to automate repetitive tasks, provide customer support, or analyze vast amounts of data far more quickly and accurately than a human could. They can also be used in ways that invade privacy or replace jobs, which is often where the apprehension comes from.\n\nThe key is to create regulations and ethical guidelines for the use of AI Agents, and to continue researching and developing them in a way that maximizes their benefits and minimizes their potential harm. From a research perspective, there's a lot of potential in AI Agents, and it's a fascinating field to be a part of."
+    )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_ask_question_with_coworker_as_array():
+    result = tools.ask_question(
+        co_worker="[researcher]",
+        question="do you hate AI Agents?",
+        context="I heard you LOVE them",
+    )
+
+    assert (
+        result
+        == "I don't hate or love AI agents. My passion lies in understanding them, researching about their capabilities, implications, and potential for development. As a researcher, my feelings toward AI are more of fascination and interest rather than personal love or hate."
+    )
+
 
 def test_delegate_work_to_wrong_agent():
     result = tools.ask_question(

tests/agent_tools/cassettes/test_ask_question_with_coworker_as_array.yaml

@@ -0,0 +1,427 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are researcher. You''re
+      an expert researcher, specialized in technology\nYour personal goal is: make
+      the best research and analysis on content about AI and AI agentsTo 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: do you hate AI Agents?\n\nThis is the expect criteria for
+      your final answer: Your best answer to your co-worker asking you this, accounting
+      for the context shared. \n you MUST return the actual complete content as the
+      final answer, not a summary.\n\nThis is the context you''re working with:\nI
+      heard you LOVE them\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"}], "model":
+      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '1103'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=r7d0l_hEOM639ffTY.owt.2ZeXQN7IgsM0JmFM6FEiE-1715576040584-0.0.1.1-604800000;
+        __cf_bm=bHXznnX6IEnPWC4UFqVw22jiTLBlLvClKsTW4F99UPc-1715613132-1.0.1.1-5k2TYkm6.lsjrA1MkQ4uD2GxUGKPmwNVeYL_sKTpAPJ_trVvN3.uNZS4HljKfVPlku1XDNCYfU4y43hlt3e.RQ
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.25.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.25.1
+      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-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"As"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        researcher"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        specialized"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        technology"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        specifically"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        agents"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        my"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        personal"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        feelings"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        towards"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        them"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        are"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        not"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        based"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        on"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        emotion"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        but"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        on"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        professional"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        interest"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        intellectual"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        curiosity"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        \n\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        don"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"''t"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        hate"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        or"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        love"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        agents"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        My"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        passion"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        lies"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        understanding"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        them"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        researching"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        about"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        their"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        capabilities"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        implications"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        potential"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        for"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        development"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        As"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        researcher"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        my"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        feelings"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        toward"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        are"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        more"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        of"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        fascination"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        interest"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        rather"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        than"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        personal"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        love"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        or"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        hate"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 883396429922624c-GRU
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Mon, 13 May 2024 15:12:29 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '514'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299745'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 50ms
+      x-request-id:
+      - req_5a62449ef9052c3a350f1b47f268bbcc
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_agent_usage_metrics_are_captured_for_hierarchical_process.yaml

@@ -11,7 +11,7 @@ interactions:
       are not listed here:\n\nDelegate work to co-worker: Delegate work to co-worker(coworker:
       str, task: str, context: str) - Delegate a specific task to one of the following
       co-workers: [Researcher]\nThe input to this tool should be the coworker, the
-      task you want them to do, and ALL necessary context to exectue the task, they
+      task you want them to do, and ALL necessary context to execute the task, they
       know nothing about the task, so share absolute everything you know, don''t reference
       things but instead explain them.\nAsk question to co-worker: Ask question to
       co-worker(coworker: str, question: str, context: str) - Ask a specific question
@@ -1030,7 +1030,7 @@ interactions:
       are not listed here:\n\nDelegate work to co-worker: Delegate work to co-worker(coworker:
       str, task: str, context: str) - Delegate a specific task to one of the following
       co-workers: [Researcher]\nThe input to this tool should be the coworker, the
-      task you want them to do, and ALL necessary context to exectue the task, they
+      task you want them to do, and ALL necessary context to execute the task, they
       know nothing about the task, so share absolute everything you know, don''t reference
       things but instead explain them.\nAsk question to co-worker: Ask question to
       co-worker(coworker: str, question: str, context: str) - Ask a specific question

tests/cassettes/test_agent_use_specific_tasks_output_as_context.yaml

@@ -6,7 +6,7 @@ interactions:
       co-worker: Delegate work to co-worker(coworker: str, task: str, context: str)
       - Delegate a specific task to one of the following co-workers: [''test role2'']\nThe
       input to this tool should be the coworker, the task you want them to do, and
-      ALL necessary context to exectue the task, they know nothing about the task,
+      ALL necessary context to execute the task, they know nothing about the task,
       so share absolute everything you know, don''t reference things but instead explain
       them.\nAsk question to co-worker: Ask question to co-worker(coworker: str, question:
       str, context: str) - Ask a specific question to one of the following co-workers:
@@ -326,7 +326,7 @@ interactions:
       co-worker: Delegate work to co-worker(coworker: str, task: str, context: str)
       - Delegate a specific task to one of the following co-workers: [''test role2'']\nThe
       input to this tool should be the coworker, the task you want them to do, and
-      ALL necessary context to exectue the task, they know nothing about the task,
+      ALL necessary context to execute the task, they know nothing about the task,
       so share absolute everything you know, don''t reference things but instead explain
       them.\nAsk question to co-worker: Ask question to co-worker(coworker: str, question:
       str, context: str) - Ask a specific question to one of the following co-workers:
@@ -351,7 +351,7 @@ interactions:
       Delegate work to co-worker(coworker: str, task: str, context: str) - Delegate
       a specific task to one of the following co-workers: [''test role2'']\nThe input
       to this tool should be the coworker, the task you want them to do, and ALL necessary
-      context to exectue the task, they know nothing about the task, so share absolute
+      context to execute the task, they know nothing about the task, so share absolute
       everything you know, don''t reference things but instead explain them.\nAsk
       question to co-worker: Ask question to co-worker(coworker: str, question: str,
       context: str) - Ask a specific question to one of the following co-workers:
@@ -1027,7 +1027,7 @@ interactions:
       co-worker: Delegate work to co-worker(coworker: str, task: str, context: str)
       - Delegate a specific task to one of the following co-workers: [''test role2'']\nThe
       input to this tool should be the coworker, the task you want them to do, and
-      ALL necessary context to exectue the task, they know nothing about the task,
+      ALL necessary context to execute the task, they know nothing about the task,
       so share absolute everything you know, don''t reference things but instead explain
       them.\nAsk question to co-worker: Ask question to co-worker(coworker: str, question:
       str, context: str) - Ask a specific question to one of the following co-workers:
@@ -1052,7 +1052,7 @@ interactions:
       Delegate work to co-worker(coworker: str, task: str, context: str) - Delegate
       a specific task to one of the following co-workers: [''test role2'']\nThe input
       to this tool should be the coworker, the task you want them to do, and ALL necessary
-      context to exectue the task, they know nothing about the task, so share absolute
+      context to execute the task, they know nothing about the task, so share absolute
       everything you know, don''t reference things but instead explain them.\nAsk
       question to co-worker: Ask question to co-worker(coworker: str, question: str,
       context: str) - Ask a specific question to one of the following co-workers:
@@ -1236,7 +1236,7 @@ interactions:
       co-worker: Delegate work to co-worker(coworker: str, task: str, context: str)
       - Delegate a specific task to one of the following co-workers: [''test role2'']\nThe
       input to this tool should be the coworker, the task you want them to do, and
-      ALL necessary context to exectue the task, they know nothing about the task,
+      ALL necessary context to execute the task, they know nothing about the task,
       so share absolute everything you know, don''t reference things but instead explain
       them.\nAsk question to co-worker: Ask question to co-worker(coworker: str, question:
       str, context: str) - Ask a specific question to one of the following co-workers:
@@ -1485,7 +1485,7 @@ interactions:
       co-worker: Delegate work to co-worker(coworker: str, task: str, context: str)
       - Delegate a specific task to one of the following co-workers: [''test role'']\nThe
       input to this tool should be the coworker, the task you want them to do, and
-      ALL necessary context to exectue the task, they know nothing about the task,
+      ALL necessary context to execute the task, they know nothing about the task,
       so share absolute everything you know, don''t reference things but instead explain
       them.\nAsk question to co-worker: Ask question to co-worker(coworker: str, question:
       str, context: str) - Ask a specific question to one of the following co-workers:
@@ -2490,7 +2490,7 @@ interactions:
       co-worker: Delegate work to co-worker(coworker: str, task: str, context: str)
       - Delegate a specific task to one of the following co-workers: [''test role'']\nThe
       input to this tool should be the coworker, the task you want them to do, and
-      ALL necessary context to exectue the task, they know nothing about the task,
+      ALL necessary context to execute the task, they know nothing about the task,
       so share absolute everything you know, don''t reference things but instead explain
       them.\nAsk question to co-worker: Ask question to co-worker(coworker: str, question:
       str, context: str) - Ask a specific question to one of the following co-workers:

tests/cassettes/test_cache_hitting_between_agents.yaml

@@ -67,7 +67,7 @@ interactions:
       work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
       str) - Delegate a specific task to one of the following co-workers: [''Researcher'']\nThe
       input to this tool should be the coworker, the task you want them to do, and
-      ALL necessary context to exectue the task, they know nothing about the task,
+      ALL necessary context to execute the task, they know nothing about the task,
       so share absolute everything you know, don''t reference things but instead explain
       them.\nAsk question to co-worker: Ask question to co-worker(coworker: str, question:
       str, context: str) - Ask a specific question to one of the following co-workers:
@@ -442,7 +442,7 @@ interactions:
       work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
       str) - Delegate a specific task to one of the following co-workers: [''Researcher'']\nThe
       input to this tool should be the coworker, the task you want them to do, and
-      ALL necessary context to exectue the task, they know nothing about the task,
+      ALL necessary context to execute the task, they know nothing about the task,
       so share absolute everything you know, don''t reference things but instead explain
       them.\nAsk question to co-worker: Ask question to co-worker(coworker: str, question:
       str, context: str) - Ask a specific question to one of the following co-workers:

tests/cassettes/test_crew_with_delegating_agents.yaml

@@ -86,7 +86,7 @@ interactions:
       are not listed here:\n\nDelegate work to co-worker: Delegate work to co-worker(coworker:
       str, task: str, context: str) - Delegate a specific task to one of the following
       co-workers: [''Senior Writer'']\nThe input to this tool should be the coworker,
-      the task you want them to do, and ALL necessary context to exectue the task,
+      the task you want them to do, and ALL necessary context to execute the task,
       they know nothing about the task, so share absolute everything you know, don''t
       reference things but instead explain them.\nAsk question to co-worker: Ask question
       to co-worker(coworker: str, question: str, context: str) - Ask a specific question
@@ -1716,7 +1716,7 @@ interactions:
       are not listed here:\n\nDelegate work to co-worker: Delegate work to co-worker(coworker:
       str, task: str, context: str) - Delegate a specific task to one of the following
       co-workers: [''Senior Writer'']\nThe input to this tool should be the coworker,
-      the task you want them to do, and ALL necessary context to exectue the task,
+      the task you want them to do, and ALL necessary context to execute the task,
       they know nothing about the task, so share absolute everything you know, don''t
       reference things but instead explain them.\nAsk question to co-worker: Ask question
       to co-worker(coworker: str, question: str, context: str) - Ask a specific question

tests/cassettes/test_hierarchical_process.yaml

@@ -67,7 +67,7 @@ interactions:
       str, task: str, context: str) - Delegate a specific task to one of the following
       co-workers: [''Researcher'', ''Senior Writer'']\nThe input to this tool should
       be the coworker, the task you want them to do, and ALL necessary context to
-      exectue the task, they know nothing about the task, so share absolute everything
+      execute the task, they know nothing about the task, so share absolute everything
       you know, don''t reference things but instead explain them.\nAsk question to
       co-worker: Ask question to co-worker(coworker: str, question: str, context:
       str) - Ask a specific question to one of the following co-workers: [''Researcher'',
@@ -2448,7 +2448,7 @@ interactions:
       str, task: str, context: str) - Delegate a specific task to one of the following
       co-workers: [''Researcher'', ''Senior Writer'']\nThe input to this tool should
       be the coworker, the task you want them to do, and ALL necessary context to
-      exectue the task, they know nothing about the task, so share absolute everything
+      execute the task, they know nothing about the task, so share absolute everything
       you know, don''t reference things but instead explain them.\nAsk question to
       co-worker: Ask question to co-worker(coworker: str, question: str, context:
       str) - Ask a specific question to one of the following co-workers: [''Researcher'',
@@ -5367,7 +5367,7 @@ interactions:
       str, task: str, context: str) - Delegate a specific task to one of the following
       co-workers: [''Researcher'', ''Senior Writer'']\nThe input to this tool should
       be the coworker, the task you want them to do, and ALL necessary context to
-      exectue the task, they know nothing about the task, so share absolute everything
+      execute the task, they know nothing about the task, so share absolute everything
       you know, don''t reference things but instead explain them.\nAsk question to
       co-worker: Ask question to co-worker(coworker: str, question: str, context:
       str) - Ask a specific question to one of the following co-workers: [''Researcher'',

tests/cassettes/test_increment_tool_errors.yaml

@@ -60,7 +60,7 @@ interactions:
       are not listed here:\n\nDelegate work to co-worker: Delegate work to co-worker(coworker:
       str, task: str, context: str) - Delegate a specific task to one of the following
       co-workers: [''Scorer'']\nThe input to this tool should be the coworker, the
-      task you want them to do, and ALL necessary context to exectue the task, they
+      task you want them to do, and ALL necessary context to execute the task, they
       know nothing about the task, so share absolute everything you know, don''t reference
       things but instead explain them.\nAsk question to co-worker: Ask question to
       co-worker(coworker: str, question: str, context: str) - Ask a specific question
@@ -3200,7 +3200,7 @@ interactions:
       are not listed here:\n\nDelegate work to co-worker: Delegate work to co-worker(coworker:
       str, task: str, context: str) - Delegate a specific task to one of the following
       co-workers: [''Scorer'']\nThe input to this tool should be the coworker, the
-      task you want them to do, and ALL necessary context to exectue the task, they
+      task you want them to do, and ALL necessary context to execute the task, they
       know nothing about the task, so share absolute everything you know, don''t reference
       things but instead explain them.\nAsk question to co-worker: Ask question to
       co-worker(coworker: str, question: str, context: str) - Ask a specific question

tests/cli/cli_test.py

@@ -0,0 +1,59 @@
+from unittest import mock
+
+import pytest
+from click.testing import CliRunner
+
+from crewai.cli.cli import train, version
+
+
+@pytest.fixture
+def runner():
+    return CliRunner()
+
+
+@mock.patch("crewai.cli.cli.train_crew")
+def test_train_default_iterations(train_crew, runner):
+    result = runner.invoke(train)
+
+    train_crew.assert_called_once_with(5)
+    assert result.exit_code == 0
+    assert "Training the crew for 5 iterations" in result.output
+
+
+@mock.patch("crewai.cli.cli.train_crew")
+def test_train_custom_iterations(train_crew, runner):
+    result = runner.invoke(train, ["--n_iterations", "10"])
+
+    train_crew.assert_called_once_with(10)
+    assert result.exit_code == 0
+    assert "Training the crew for 10 iterations" in result.output
+
+
+@mock.patch("crewai.cli.cli.train_crew")
+def test_train_invalid_string_iterations(train_crew, runner):
+    result = runner.invoke(train, ["--n_iterations", "invalid"])
+
+    train_crew.assert_not_called()
+    assert result.exit_code == 2
+    assert (
+        "Usage: train [OPTIONS]\nTry 'train --help' for help.\n\nError: Invalid value for '-n' / '--n_iterations': 'invalid' is not a valid integer.\n"
+        in result.output
+    )
+
+
+def test_version_command(runner):
+    result = runner.invoke(version)
+
+    assert result.exit_code == 0
+    assert "crewai version:" in result.output
+
+
+def test_version_command_with_tools(runner):
+    result = runner.invoke(version, ["--tools"])
+
+    assert result.exit_code == 0
+    assert "crewai version:" in result.output
+    assert (
+        "crewai tools version:" in result.output
+        or "crewai tools not installed" in result.output
+    )

tests/cli/train_crew_test.py

@@ -0,0 +1,87 @@
+import subprocess
+from unittest import mock
+
+from crewai.cli.train_crew import train_crew
+
+
+@mock.patch("crewai.cli.train_crew.subprocess.run")
+def test_train_crew_positive_iterations(mock_subprocess_run):
+    # Arrange
+    n_iterations = 5
+    mock_subprocess_run.return_value = subprocess.CompletedProcess(
+        args=["poetry", "run", "train", str(n_iterations)],
+        returncode=0,
+        stdout="Success",
+        stderr="",
+    )
+
+    # Act
+    train_crew(n_iterations)
+
+    # Assert
+    mock_subprocess_run.assert_called_once_with(
+        ["poetry", "run", "train", str(n_iterations)],
+        capture_output=False,
+        text=True,
+        check=True,
+    )
+
+
+@mock.patch("crewai.cli.train_crew.click")
+def test_train_crew_zero_iterations(click):
+    train_crew(0)
+    click.echo.assert_called_once_with(
+        "An unexpected error occurred: The number of iterations must be a positive integer.",
+        err=True,
+    )
+
+
+@mock.patch("crewai.cli.train_crew.click")
+def test_train_crew_negative_iterations(click):
+    train_crew(-2)
+    click.echo.assert_called_once_with(
+        "An unexpected error occurred: The number of iterations must be a positive integer.",
+        err=True,
+    )
+
+
+@mock.patch("crewai.cli.train_crew.click")
+@mock.patch("crewai.cli.train_crew.subprocess.run")
+def test_train_crew_called_process_error(mock_subprocess_run, click):
+    n_iterations = 5
+    mock_subprocess_run.side_effect = subprocess.CalledProcessError(
+        returncode=1,
+        cmd=["poetry", "run", "train", str(n_iterations)],
+        output="Error",
+        stderr="Some error occurred",
+    )
+    train_crew(n_iterations)
+
+    mock_subprocess_run.assert_called_once_with(
+        ["poetry", "run", "train", "5"], capture_output=False, text=True, check=True
+    )
+    click.echo.assert_has_calls(
+        [
+            mock.call.echo(
+                "An error occurred while training the crew: Command '['poetry', 'run', 'train', '5']' returned non-zero exit status 1.",
+                err=True,
+            ),
+            mock.call.echo("Error", err=True),
+        ]
+    )
+
+
+@mock.patch("crewai.cli.train_crew.click")
+@mock.patch("crewai.cli.train_crew.subprocess.run")
+def test_train_crew_unexpected_exception(mock_subprocess_run, click):
+    # Arrange
+    n_iterations = 5
+    mock_subprocess_run.side_effect = Exception("Unexpected error")
+    train_crew(n_iterations)
+
+    mock_subprocess_run.assert_called_once_with(
+        ["poetry", "run", "train", "5"], capture_output=False, text=True, check=True
+    )
+    click.echo.assert_called_once_with(
+        "An unexpected error occurred: Unexpected error", err=True
+    )

tests/crew_test.py

@@ -437,6 +437,7 @@ def test_async_task_execution():
         process=Process.sequential,
         tasks=[list_ideas, list_important_history, write_article],
     )
+    output = TaskOutput(description="A 4 paragraph article about AI.", raw_output="ok")
 
     with patch.object(Agent, "execute_task") as execute:
         execute.return_value = "ok"
@@ -444,13 +445,11 @@ def test_async_task_execution():
             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"
-                )
-                list_important_history.output = TaskOutput(
-                    description="A 4 paragraph article about AI.", raw_output="ok"
-                )
+                list_ideas.output = output
+                list_important_history.output = output
+
                 crew.kickoff()
+
                 start.assert_called()
                 join.assert_called()
 
@@ -678,8 +677,8 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
     result = crew.kickoff()
     assert result == '"Howdy!"'
     assert crew.usage_metrics == {
-        "total_tokens": 1650,
-        "prompt_tokens": 1367,
+        "total_tokens": 1666,
+        "prompt_tokens": 1383,
         "completion_tokens": 283,
         "successful_requests": 3,
     }
@@ -698,6 +697,8 @@ def test_crew_inputs_interpolate_both_agents_and_tasks():
     )
 
     crew = Crew(agents=[agent], tasks=[task], inputs={"topic": "AI", "points": 5})
+    inputs = {"topic": "AI", "points": 5}
+    crew._interpolate_inputs(inputs=inputs)  # Manual call for now
 
     assert crew.tasks[0].description == "Give me an analysis around AI."
     assert crew.tasks[0].expected_output == "5 bullet points about AI."
@@ -706,7 +707,7 @@ def test_crew_inputs_interpolate_both_agents_and_tasks():
     assert crew.agents[0].backstory == "You have a lot of experience with AI."
 
 
-def test_crew_inputs_interpolate_both_agents_and_tasks():
+def test_crew_inputs_interpolate_both_agents_and_tasks_diff():
     from unittest.mock import patch
 
     agent = Agent(
@@ -828,9 +829,7 @@ def test_tools_with_custom_caching():
     with patch.object(
         CacheHandler, "add", wraps=crew._cache_handler.add
     ) as add_to_cache:
-        with patch.object(
-            CacheHandler, "read", wraps=crew._cache_handler.read
-        ) as read_from_cache:
+        with patch.object(CacheHandler, "read", wraps=crew._cache_handler.read) as _:
             result = crew.kickoff()
             add_to_cache.assert_called_once_with(
                 tool="multiplcation_tool",
@@ -907,8 +906,6 @@ def test_crew_log_file_output(tmp_path):
         )
     ]
 
-    test_message = {"agent": "Researcher", "task": "Say Hi"}
-
     crew = Crew(agents=[researcher], tasks=tasks, output_log_file=str(test_file))
     crew.kickoff()
     assert test_file.exists()
@@ -939,13 +936,11 @@ def test_manager_agent():
 
     with patch.object(Task, "execute") as execute:
         crew.kickoff()
-        assert manager.allow_delegation == True
+        assert manager.allow_delegation is True
         execute.assert_called()
 
 
 def test_manager_agent_in_agents_raises_exception():
-    pass
-
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -959,7 +954,7 @@ def test_manager_agent_in_agents_raises_exception():
     )
 
     with pytest.raises(pydantic_core._pydantic_core.ValidationError):
-        crew = Crew(
+        Crew(
             agents=[researcher, writer, manager],
             process=Process.hierarchical,
             manager_agent=manager,
@@ -968,7 +963,12 @@ def test_manager_agent_in_agents_raises_exception():
 
 
 def test_manager_agent_with_tools_raises_exception():
-    pass
+    from crewai_tools import tool
+
+    @tool
+    def testing_tool(first_number: int, second_number: int) -> int:
+        """Useful for when you need to multiply two numbers together."""
+        return first_number * second_number
 
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
@@ -980,6 +980,7 @@ def test_manager_agent_with_tools_raises_exception():
         goal="Manage the crew and ensure the tasks are completed efficiently.",
         backstory="You're an experienced manager, skilled in overseeing complex projects and guiding teams to success. Your role is to coordinate the efforts of the crew members, ensuring that each task is completed on time and to the highest standard.",
         allow_delegation=False,
+        tools=[testing_tool],
     )
 
     crew = Crew(
@@ -991,3 +992,35 @@ def test_manager_agent_with_tools_raises_exception():
 
     with pytest.raises(Exception):
         crew.kickoff()
+
+
+def test_crew_train_success():
+    task = Task(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[task],
+    )
+
+    crew.train(n_iterations=2)
+
+
+def test_crew_train_error():
+    task = Task(
+        description="Come up with a list of 5 interesting ideas to explore for an article",
+        expected_output="5 bullet points with a paragraph for each idea.",
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[task],
+    )
+
+    with pytest.raises(TypeError) as e:
+        crew.train()
+        assert "train() missing 1 required positional argument: 'n_iterations'" in str(
+            e
+        )

tests/memory/cassettes/test_save_and_search.yaml

@@ -0,0 +1,405 @@
+interactions:
+- request:
+    body: '{"input": ["test value test value test value test value test value test
+      value         test value test value test value test value test value test value         test
+      value test value test value test value test value test value"], "model": "text-embedding-ada-002",
+      "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '292'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.25.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.25.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        YXyDACB/th//38/PZLRrT7ldIgJZnBmfn4CJAiq+LyCiIKJAAqSrdXLgkEHeFhU8w8wDSxSD5oc6
+        WflNKJzM7Iut//7nz5+/fdFU5fT33z9/369x+vuff/78+XvPp/zvv3/+1z9//vz5899R6Vh1RXW/
+        vz51iwDwor7+/fePmAWQRvTvn787bSEMK+stofY5z+A4vzmmFLXFYr0KgCU+lpRH0gctwh5hOJ+6
+        HYvObV7Q6fuREQhFifllnkK6uJ9cVo5fC0uvRuPrc9leAFNbInanzsWsykWOWutesQOUh2G7vg4V
+        aklssHCBapjux2yGNjkR9sju72au1duMYlZlhDC8onGvhisqFPvOyLUmDReMY4rq92QzXXxci/Hy
+        3ACMpx9hnvS7J9PozDV8TqZJDt/hhvjz3VIwPq5EtVyshsZS31jTLmZINwyvfClP+xGqIULkUC44
+        3JXfWABr6TbEWycvmYd1e4SyrlsSbOqlWbUqi+G8JR0LHts45GFaC9rvt7HxHO9wM27epxi66e2z
+        Qyae+DyzDSD2KUqs3ZdPM3/TAqCXnRML9nbV8CvcbWAs6/Gqf3XEydJncChMkdLa/hbTN9uPcPVP
+        PYWZdAOvpdRE8tbwyP449M0aGNOsnqfCwLNc8mGKyliFm1CMeHOuTT7Lez4i6j8JifLnbNFQBxFa
+        Sb4ST2vNZneqNy/4WUHNdKKGfFWepYnGbSzgXeS8i1lRogsIX0/ENDrKRVc4L139jFKEBe8SFfzh
+        hTk62UVAokflIL6ZawGEcywRwkNize/r7QjcFnTiFt93yJStH6AsaVz6zi5BSPfm8ahF6BYz++TG
+        zRJOAVZ1ndyp0Nhs4Dg5vKD+0h/dST8tWUZHrpUbFlaC80BrpgZGF0bl2BLsXaJieQoOwCS+TOYI
+        yC/WOEp1sKblQ6wTvxZDfDRWIMolJf7XPTbcUcIUaZUuMOdzEDhVljgHT+IPKqWjOXAafWtQ0XjC
+        y8M+D1x5GzP8YuGEP3sfis9l2mO4Hu2OmXFdhiwVniVkYR2zw3VXoPV0sAE+TjER6/us+frR0pe6
+        aEjAqUdm9NwooQQPNbkS53T7FGtSfEv4vVaTHYi2b7az1frwEXc6VoIFEI3HR4TkxXiywAiihB+f
+        L12rzygh1kEqwmW2Rh/t8OVMTBoaXDppbg15QHaMXGrJWmb+HuHxKjmLTh87YfNgSptbsInwZgnN
+        ZPldsxk1yQ5IwL/Ap6ZkKbwvz5ocOroLl/JkjNDYeksVdGisZS/8KvDCNGS4NZxmdMsiB+FQnoi7
+        5ErIxUz5Ie+3SYnf7p8hPx+0DK3vS8UcXNrNgsAIwIl+Bzo/h85iG6Oa0XnfWfRjYYkvZuK+4Gxw
+        l37D5ZJQXE0RXAwzIHkhn9FSHR8YlHEo6SAqXrPml1OqhdHTYcQbq2G+j10E+6U6YunRFeGq+7cU
+        DOtOial/dcT9C1rh1Jojc8fc4cu+mijSbWLRb/ZWEdv2h1ohyhmxSIxenJ8nNQBrmnXi+tuJz/rs
+        mzDN48CM3NugT1bUAsSszFhFji1nZKlzhPPkQdzvvbH444M7FLMyY54X8nB6IxPDfqmOLNjbVbN4
+        5CYCH7szMbP8g1ZL2pTIOm8sEmi1jfiCvF7dNiePeU8FELuO2RFMPIWUXg8qYoJxvCD7acZ4paHB
+        Fx/Xsvb8hi0xnW4upneo/8B6ryIxf9hpVsOrc6jCzw1r5YItLiw3Fe1NU6M/YkxouKk8AkNVD7gW
+        buUwkdy3gbGsx7Kq0oQ/nQ9A6auYGfOWoVn+CioIt7hk1pG34eLUqqugxs/Y+XT7JNS1Bxte/uLS
+        l9PNxdg7bo1KuFDii9rDWvS2T2H4RT6x9ZgmPd7hUomT75YdtPJjTeOli6F7t2cSYCMtFtbeRBCc
+        h8NC4LU1ObXqgjhaBK+yaQ2/lrxneNP0zgqBj4ieg32ELuPPwfPySoefKS06RJ82ZcfxLaC53+57
+        9MDbH/NeipRQq9tTuA7qjOFZsHBtybQiigSfufPVtNhm7gV4pe8T89/7NJmVmxFo/WxXzFi234LL
+        b5VCZWVXRnCjW2v601LE+1Vgrr898MVePhJAxVVm6t8azcvDxMiPiwIzwaEhO+lwkYe8EAj+CX3I
+        1fYaA1adI4ueBQmXG78dIbjbIZbryOYNLWkKrRdviVldj4j6iavDtXU4iR7Vo5m1jgcogCll9rB7
+        cLqLdy8Yp/LGrLFqhvlGuhkSqTawqAx3viDY+yh/ixG5pOOrWc5uUqLddi6JIbO+mBOr+qFr5t0Y
+        mXBnfVS7dOEpa2cs2iRoZq3jPkzteGLVJbCQJFlND1plClSOz5a13Pgp1iS1FvBuntJkKRZNRK9j
+        a1PBuGkhsxXxCGH0dIj1+hTD9PPyDFzeYNxeLD/Zpp6dwQNvf8wOoymcRL3OtL6OJ6IXiz6suxWO
+        YE38QyLYy5xPWmrClckXUj6qTbOyzMAgby0Py8ZTbpYuuAQgveqQOPsH5qO5KWQIWnkmTvDoi0WJ
+        5Bqy4fxjpL5eOf8eLxGyD7c9cQTUJ3yguxfck43Nwq3ytOZvm6dwe31exCeZnmzX2LOhcIYWP2vB
+        SL728sxAu1grZrJjJLP5yKiqRweJzpH6HlbRTjuob6qCN9/Tl3PByFLIiotFnDJxE340phixpKuI
+        4SW0GSfjJMGrvZl0Te/DMCdNkkGtvQyiN0PMZ5PEKcpz02CH68602p3aYZh/W2DeOnnJcnaLChXf
+        40gCM3AQb/nxCGb1AmLvqNgse9raYAbTm/jpebZmvV5bYE1GiJHZrFinL1ORdRcI3Wntq/kZn6GD
+        G21TEjlTyNfp+y1BRUzG0u8uFau8himS1ueK47gurXl+cB9u8RoQcwwpp8W2aSEwTj0xYLSH3dY3
+        UzVGccNI3Nz4Ui62rO00Toi3/f2sNiN1CnllYcpwU4dj+npVEDUdZVH2tIq1mZMKOGQuHS7YaBbW
+        nkT1eNjHLLgiZRgOlj4i4X40mdEKKFxFO23BUxeH2Dc9tHhKBxfpHzEkx0C7WOwykR7GU0+Ybuu8
+        mbaPtdfGb8XxdgiexTLziYKLXjnxtPbVLMrU/qC4VQjXbe9z6aj5LsiL9STeQ2F8GqTGBLaJboQI
+        Drbmzn0C7LF1YX6UJZy+lihDy8sRsbDKdTPHojlC1LSUWemsJzPXmheyvmvOMDm2aF6FskT5W4qI
+        kXsPxMlS5+BaqsOC52oM2+eUYXilnxMzs/zDx+B3yMGetz8WOVOIVt2/XZDUsQ+L1IgNc/8OYyCH
+        MWOGyrbh+g0VF0kXquP1ej9xHopjgJbgXtFnElgJl7yHhPrswegybxmaoCgq2L1hYDOYHrXgXDGR
+        vFhPLI7iFg0kTlsoI6Vg+21yHfiBm0dQsp4Q97Baw2RwwHD9KAFxtoYV8v7p1CCcY4kFnndOpvLp
+        1pDGYYsbfcNDdtYkgC9PGZZu39iav2kBMM3jQIzguCTLt9dtZAxuOanP1WjmX/ORwDneI+LlUBdj
+        rZ5WhD7hm0Swl/k0vdEIIYIMC6tcD7xbpxm1j6RnlrnZ8GVZxRkMSf3geq+9OF9vrw6sadVZ+DVj
+        vqQfrwVBVDPmHU2jmbnWvFBgJD1dLp4biuUhEZCm/FQs6WibrKKdduqxnQ2il3Qu+IyMCNZ3WpFD
+        rEYF319MEYRDeWIPYzyhnp4uPRyhfTM7cR/JYvLwiDotU9jhukNoWV5CjlaHAlXy94TWA7ldAKrW
+        Jnt9t2vW7KO0iJHFJda7bYe5EHQd0jyYGX54SbJUx0eEcH56MMd+3cLF2yQ5oE/4xuO1nRLu9qkO
+        SWinVK7IueC4CWXwVxKR/Wl4hXx/CUT0iAeTeYG/RVP3y2Vkds+ZBPftu5jtifeArumBXZVPV8yN
+        L85gCn5F1X6sm3W/nkQonG9LPBNbw9ZsbBXIYcyIJRVRQ32L/ND4vh+Yeb474Zb8IhUKzbbIrStf
+        w/i+PkbQKl3At3CRCqoseQ5PJ+3YfritIVe2ug/X1uP4+lQAzai/m7BufcKCC+qKydsUOWwiCliB
+        g9Rweau4IE/4hXda+xpmdzzNIBvthzhbownZdIhL7eRnMyG40S3JPseZhuPjyCJ7voSS8Wk6iHa3
+        kfLr7DZr5omidqvWhoTHU1ysWpXFwDjWib2P6mT1eTAjPTVFZm2LxJqR18twhPbNDIUVw2Ivzxxy
+        82CzZK2OCXu1fIaD1M/MV1QRLaes/SEtIB9m7puxmU+pXMHVjgvaqJnPx7W6xUD9JyHkkfcWy9Ug
+        huVlH1hYhgHnI9V9zRBQThf/aA/8sbMBpNcrxODNZbEan6FF+OXeMS2CnbXodtNpk2Mz5rivyJrC
+        g1PCoslXZipO3iy/XSFAYVQ+00s6F1z6lB3a33ce8eg8WHwNzoEq1qZEkZsfm+maSjl008efttdb
+        GnId/B78oJUYHoSiWDV8k6H4HkeqfMot70n38JHbTHfM1cznq+FREWqlLth5/6B8UUG14ej4DxZg
+        I02WzCY2IrdxZWaP12bsuslHrfWo2J5dcDF5jwxDYVQ+3Q28T+YgJyYAnhNyqJanNV3e04iuHxQQ
+        Szi/rWl5CTkc5y4i++oVhPScYxM867Khw/WUDUtTfi7IFPyKGOI6WuM+91tIzUvEoiW+D+tt51RQ
+        Zqyjl0dXWOPwmit4PoOFhXe/bli126owKnFLDlrphSts7Bxuv5ZSITk8rd6ibavWyqsgh1gdi/Vl
+        BJK6284lu5bKd6B92ecQJbPG9HiHG8aQ6sO3oDfiy6oxjFJ472A89YQFV6QMS1TGqlbqyMQMN7rF
+        Kw9SdYcvZxIp0SXkzt6YNV6uLcHKqiT0bm9ewAh36dCbt2QhqhXDgLuIBJnMhne8mysNPa4627uL
+        ZUnfcLHh0v8eJDp+fnwR9giDWOsSnqRXH87P769E8hPvqVYuNJwu515Vf+q6pZtrTYb5Kx4pZMP1
+        R2GJ78MySIMJhiR/sCaU9bAaXiehWqsNdpaMS/Gbvh8ZMU4+zPAS2lDmm5L6yHvM/MG1GlG9kRYN
+        guWSUL9/Bg4rn8FXzT3zrWfYjNlcVqi7zQFzFCEe1t8gxvDIhy1GVXgdFqJaMRiPk8wOT9qgVUxz
+        AS6GGRDd1nnDzTDtIM2DGb+u9xNafrtCQEGvXibZeMrDIlePCOH89KCyU6V8qeneh/tnLVgwjnmx
+        NCW7qD/Pd8nlsGoJrdJIULfW901+224saILGH3rkPSZ5aJ8aVl3VUe7e7ZmYP/xIRkHyW0g8lxLM
+        0LVZo2MQo8PDzLF072jRN764okAcn0Qv6Vzwx3W/grjb5izqzzRcdlU2q/Eu1uj2c6j49KCrC2X7
+        CrAcFMEwn9K5AppddSoMAkq4lb90oGjDmL/q5rAGS6+i0ZFsEtKNGYrn5/KCMkIF8X4c8ynQlBqc
+        /r5hWFmV5Ge6moruuy5izrFchjV3cwAeAcf8/ous/l4+cyTFNMcqas7JuNLKheJ0Z3SJDjXn71cP
+        UPoqJqRLPWt8DHaq4Tx5MDf/DgM7a3INaIU9w+5l5f1MYAXsVk8SzcQddv6Fr6qaeXsWLtCiqSl7
+        Gaxp+eDNtSbNlNmeC9GuGPE7vR3Q6iWSAJ2WK4w0VzsRsRfJwKx5wknX7vha2oqLklhWCKmvVzTu
+        AxNrsfXDzPq0S7EGSy3DZj6PzNTMC+L7iymqjW8tzM7009B/xUeASl/FzNkIj6Kr2jAFxsmHmOl9
+        aHgqPCvY2GhDY8lJrdn/CSk6KyTCryZ1m12shzmypuXD7GHnhi3XhhfaDnGC07tWo3X32sro/C0K
+        5uwMxn9S00lw3rcW3qzhdpiewgFQ6cuYldd2Sn5+E2XI9b0n2VuiXkzvwilR8U5cLBrxB434Y/TI
+        Cy8hwxMK+G+RfjUc5w9nOA+0gR7IdQXhnnyJZcKr4E1rSqCjYU9n6REU8yP0WtQZmwNzX01r9f5P
+        uKDZ0wXmsdluuP3VZGSfI49Z1c8Z5huhM3pX9cj8dv8MZ+0izoDC2mQ3dGjChRuPFbHhZjLnfYgt
+        iTtOrQy/yGelNZvDTh/No/Z7rSZeVLYNuQ56rxZG6ZNLtP7CWQrPHVjuPmZ+FkeF/MqQj+LrUBC3
+        radiNI5hjIwiHpgu3EwuFduhQ7/XarL9cikSpraPI7KULmSm5IghxdWE1euOIkzty4NToikmwC8n
+        RLf02qK7eFdDNLyfxIBRKCgWvgCu7zzxzwwctFxbcQXjcZKZHUYHa/44ioniXaxhyJ73cPZ/QooO
+        FtlhKR3NhvuSXEO9rbeEdKlnzV/xESDNjEQszdeXxbe9U4N1gy8p4pNTzIl1xNB+3I4FP7ZYq/3O
+        ZlDEOGS6peuWqGYZhsA49cSXtDhcNje/h8+ZVOxw2fkN18fgCE5/3zBDWjNEqaylYCSnBwnZ5lyw
+        RT3G8KiGAsMUW5xrL7tElvJZKRL4iLgq3nv4xcKJeZGzCcfyHl9U3LkWVZ/bhzVrrpCD8HVEclAe
+        AZrPJx7AoZM2BBs3q+CXycBIqkaO5/79ttatWPmonuiR+HVkI857WYfbr6VUtp5Ds9J+rtH3SjkW
+        RYqT3eO6XwEJ8GIEnCJcDkOfwlmLVkI+aV7w+pKJsDm+UgxjHBTzFvY/ABXrFH2c77Aqp3OPxoO0
+        I1YkeZy/+WWEQrHvpHDzueF3uc+Ayy1j8fn+tkZ6qnoYgq4j3skU+fdBVxtwcKfM/OIo3PqP6qdK
+        Mc2JzyylWVqEAqiKImA6UQe+I94jNP96l0Xafi3E1g8lAJd7xKmPZrM9fgsBlW2zEIfbfKCakJSa
+        aGcqiabY4ltxfgpw7BdMgkxmw+IcOUWRBysJoA6LFW22F6DZWcfNUl3QrLlCBtvkcaFLbQzDuot9
+        X7WUNmTpsNug1XQ1GZ2i7MJcWz41c+d+BcRt0Nn5cxDQJB+eFagNSklIUnOQ2k0vI7V0GZ3V0h1E
+        4hYCeGEakgKn35AbRQ7o6aQdKbV9XKybSKiQPe9+FNzJKXYMqT6iO+FFN/5XHMbUfFMYVKtmh/eg
+        h7MgeSaIvW4yO9pb1pxXgJGvmnuihxprFmeWSxid7UCwdZvDRlsDCfRI15mro3PCd13zA8N6UPoI
+        OgtJi/R7ASINIdbr8+RMiLGNlKwnGILfc+AJS3WId7HGQoGPfAnvoQRib5qMOF9sLZb5wKiJjCs7
+        xGpUcDBXDAP+cIZbw2nW6TbY0KflC8ujlRSz4Dqlqm5YxcxjTYrVcUodTq05EgtlZiGS7hqA5KqE
+        CqtcN9ztUxPeQoCJdeQaZ/DSckDWS2JeAcmw1ds61Q4/6U2VYCnReHnqrXLNnBsdi+e+meP0IKh6
+        I76ZwbeSNaVelKvbawkEh0k/rLeP36PutArM+AifgeHEqeEU5RfiyZ+I01F9YCRmB5no9RA161sQ
+        ctTPbsX8Il6HeVqKDNQdHejWe70bNmDxAvVJmdhhr3vW8rkNHdzA/6J14ruEDxguKACWYqV4e8Uo
+        jmKkGap6ILphzWjEO93Upr17Zu6jM5LZws9cu61FwgLXe4UsrUYKvd9fiRf4Zz5n9cUFULFOxatl
+        oKk4rT9w0Sun6pftms5LJAF0NOyJ3+0PfNYuMKO3SV9UOAdBIgVLraLutArEK5XvMIbfsoQ4+W6J
+        McmHcGlgdFXUBBnR6XtBK9EUE4rvcWQEOZ9m3Ea+Deza2cQwLo9kST+kU5K1LrAQH7xhceu9D4ak
+        frB4sfxkHX9xrn0MfCJ6/3astX20PqDk8mG4M+JipnqtIkNAOYUxDgppvmZHNKz6xMK7Xzc8xTRF
+        y8/T6cMbhWGSD98SZmIGeLvaeUifyzYFUb+llIfKwhmJyxa1H7ujAlqjZJXN/QrN7m4z3NismV5T
+        9VOjcN0T77z5DbM++6b6EjHHQu7poYSrKUKHwhSZ9fo8+XQ516omvN0PMWc/DCd7eeZQnB6MEMWX
+        C97yYwx+F60kkLrHsO7Xk6SdSuwRktbfhL6p0qIN+ISKytCGS3FaeySZ8pe5S34LF5wrOuqWrCae
+        9LMaujezo5bH5pbY6rAr1iHELSLbCyUGk/WQqW0mIjN+NYQcm4O1nPwuBi53jDjkUQzvXt5KKBre
+        TxY1hRlK2ZVHcHjtbtNG8k98xp/9D2bPFAgBp7C45N1y6LaZS3I2unw+npmE6hOacCZqG2tO49FV
+        5SfeM3Kuy2Fuer1Dfp59iMvyKNwuLykH8n01dNT2a8H2EtZRkisjfd8TpZmtqsNqobkWCaeN3+xc
+        Oc61OvB8Ru75NmTONwK1bJuFWfomCUcx2pXw958/f/78+Z9//vz5P//558+fv11/r95///3zd6qW
+        6b/sAum/8nv+X6IoWRE8HfO6+vuvC2H09zv03Xf6f1PfVp/x779/dvCfYpv6KX/L/vPnz//88z//
+        GAM=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 88142860ce7a82e2-GIG
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - br
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 May 2024 19:39:49 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=JUH9MsoOBdCquA9K9qOgVbrLUkBpuF4d2k7EvjnBOLg-1715283589-1.0.1.1-96.yHqUmYzRiWC7xZ4.TPKu5RqvB1EFecasHfb_ix62oXcsw_Sp.gz0gDk4Inl119IxRMINM613CI5HheoJM2A;
+        path=/; expires=Thu, 09-May-24 20:09:49 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=DPNTnqcoTitPoe12n1vvVltuYsIzavX_dftsSEhQQcc-1715283589489-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - text-embedding-ada-002
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '15'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999946'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_ace5babe6674a08d07fce90792eef7eb
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": ["test value"], "model": "text-embedding-ada-002", "encoding_format":
+      "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '89'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=JUH9MsoOBdCquA9K9qOgVbrLUkBpuF4d2k7EvjnBOLg-1715283589-1.0.1.1-96.yHqUmYzRiWC7xZ4.TPKu5RqvB1EFecasHfb_ix62oXcsw_Sp.gz0gDk4Inl119IxRMINM613CI5HheoJM2A;
+        _cfuvid=DPNTnqcoTitPoe12n1vvVltuYsIzavX_dftsSEhQQcc-1715283589489-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.25.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.25.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        YXSDACDztvb89z8/k9FeZ0rVEhBIuDPopTFBQMT3fiOISifSJEBqlQdcfLgwYYhq0ycWOOTwIO1h
+        81r/88/f379D0VTl8u9//v7t6nn597/++fv79/lYHv/+5+///PP39/f3P6StVV9Uz2f9fVcg2EV9
+        /vufPz418QbBf/7+TVtk0UC95xN7n/0a8PWNEcnICNjKbJqhe2gQ9Wr4Ayx1fzE8z0dC8Rr2gMLH
+        FcIu2zgCDvBbsI/U1ODVDA+MzOeXsVewcrAIswt25vo6rW2Gcinhp4bEvzc/bfr7kYK+dDWqR3IE
+        1ruc89CtpJLeh3xPyOkbRWA+zQG+nYE5bZoXxepzeYTUFCS7GW6dZQGJPC8UO20HmGwYqRrLTUm4
+        GHsNIec4h4P6OWLz6zRgsz8XAqtlMKjzDUtzAy1XQ8s0eBpeP0mzTtkvh0WYXtB+v61gu3O5AXdN
+        geiYPBW2mMc0hxUqFMInt7rZXHnJlCi57dQR2GnalFpHaujICvaAzwB15s8IKa0stGW+ybZ8NCP4
+        jBUJh8Jgsz3J5xUON0cnHPKbhF0KjVc/3sEna/oixfrVn7ESzsmLLJzTsf1sYAsG0VGjDrPbYuOF
+        HUJdH97YnC53ky2XkwHw8/bAzkKMYjGP6QNIZjTgsD7ObAHnOoIWi0aMlcMWzHeITqCSzwM6gsZK
+        xO4k1aA69SLVFtk2Se33FdwyG2Ebb12wnTvQw68RACTd42ewNt/VgHSkF3QctpptEbgoaq9/ZxyK
+        ij6x2y458KRMV7ROwZtNwqjx8O09ABHn27vY5W/cwvvX3vEJPeaEukYcqkpr+NQR2NCs1rqV0MPk
+        Q8+HXJ+O4Wr5sOJtmcjnOjEFv4Uh5Osbw37H6Q0rBc+AXHb9Yf/0aqfV3gMNZlS5U60d4oAJRj+D
+        Iswu+OxtXrP/hEiB3XZJkPQ9SAnzaLjCFPEVxl48BuQwoxGey+ZK1I4bwaYfSQsX7FbYFl6C+ZPP
+        fAmokl6x6yaoICD+VHC5HyiRw+hWEF4eWmDV3AWpx/Y1sSVRU/CuShdXjVAl+/KRU2C3WCCAfDOw
+        b60fQ2UMvhivsQBWiVkzJPLqUP325dnqbhIPL+qsYe0pfKepFHRN8bVpobrvOIl4zeNWjZsd4EDs
+        STDnzZCB72U/IPZyw2Y9em4Jiuf1QA0sGia/k2iA3zAVsdO4Avjxws4dmpHMNORL2Vw8OfGhey9T
+        XFEZMLb99FIt9iIkR2s9TNvunXJ472eRCPWwmJsS5gSO58Wn1ls9NsQdeANOpnHGVmb3gDn6aQAH
+        5/vCxrhHCbVmxsNXkun0nP6UZMkPbIczjxHZVEubWIM8BXagQkTUnE+zVNm9htETpeh1O9gFO5nT
+        CrOHcMZ5o+zBEiddDwE9dsgf0TNg/t2w1Iq3ZaofpGRiTf3mofvqNuy6CSr2w8HjFaqkV6wfydec
+        b/JkwDHvikXAWxcs83Z3oHf1RyRdzxn40mQ6Af0CZarxvdYI1R2J8HiOI+zi2G6ONz98gNq2L9Q3
+        vSn4HZEzQrNxb9Qev21CoenNgCivAhvbK2CTcP0psLbtC1Ln/h1QbRwVKDXIJoxFa7L7XJyqbJ54
+        bFyfB7Dp70cGeD2zsdv01UTUhBlw/3wINctWZcNGYQ7D7GRQ2/g8APtIzRvaSeiio6T0DTkfLrOa
+        WvEXIz+KE7ZcTgYIt2VAe734wTSCzwijJ0rRVsyFuR0/ugj9ydOpcb9FbLZ3U4Pn+XQnLZfZ0xJE
+        1whGquBgfzgCkxbhM4U2E2WqvZsJrHS5xPAOdoPanECKfQoLTbGG/E7Tcq+TldyGFX5eWkaYXb+n
+        fT63LcTG00diGBFzDYUiBV9HIeTNnSuTnq2Ig3GzA+rEXBz0+f3OQaFcW2yG1yAgfN/l8PmFFq1k
+        z0m2lY0G/O2igmBu1dP65G4WrG33Qi23UgoyN1cLEARzxBVdDbZzB1ooMvdK9ZQ7BtsROQPw/PiO
+        pC7oklVklQJDR1aoVXtWcRwjbYSTaZypN8RNsaltm4KYizE9a1c9YcJBzuCUV1eq94nbrMfSGME7
+        USIidJGRLI/Dp4em6Sn0fFeWZL7LkQhFt43pK/UVQL+tvMP4/j2QJ+fYbMXN660cE23HdtX0YE2l
+        aQQLvz2RUA9LsB9+90xxToqN9ubQgSn/oBKO8X7D3vtemEzTkhI0Fhdgb/l1RXf9BRI8XS8rdR6q
+        l+xqAgxoLlGMhK+sBZsbDi28Xj2MA9uCydKS0wpd1Js4FAabHYVZPEHffrwxcoIwILz87pXp3Fr0
+        Bog8/dLxO0It4D5IPpetyeahjABo2zuNr88D2GMDxsr1EXEkRdq72Xl4VUCD3waR19tvmiezR8Ac
+        mheSNmwA5uinAW7vwwuRB3qzOYuOKcjFl4ZWb9/Z6vrZDLcAqeTI2nOwKk9fg/ztVWPnkB6DqVNg
+        CdfumGPtKXyb9d7KCsxE84j9q9Ka223YCGgEOcOBnO7JmiHfgOHU+tgE2G32j1dKsIC9iy1AomL1
+        he4NR+as6GiiwSRhIs2gOB5TtIm3zmSvz6+C909M6Pld182+fOQUys2a4kc720xcpV8IldbwEddQ
+        Wiy7p+UQS96JekPcJO1OohHMjSKQY1HuATM0PYbTU3mS9QnEhjXSJQUogy6+/PSJjQYwNOhw3AG7
+        tXdu2HLRDCjk5kbPl1UDAvXmFZ4EfEarNDlsTyxbhMLiqNT0FgH88tGMoXMPK7TPZjPNSQ18wER+
+        xeGnuwTb9WdKsDqTDntfPTIZXO4nIJnRgANLdoMt+e4plJKDSqQN14BF+9OB71+aEw75ZsFu++qo
+        1fBO6Olsjsm6W14IN3sVsKWU6cSm1K3hKW0LUqPX21xfQ5rDJvpsVNu4IKEZn/DwJTs11p5AnPa5
+        uTrQX0NEz6N5MRfxJUVQtS0b3881M8mrrGMl82ueiKfsaRLrC0e4+iOhlngjCbsyPwL6fPRQa41u
+        sQ4G4UHwriyirGuTLFV2eUP2Pc9oAsdPsOpFcQKS585IUNaTuZvqIQUV78r4XA5bw85WBOF5vxyp
+        Zn1ebHfUB4RbZiOMnGAOFv7tV5BYjw8OtmthUik/GyCqORG9h9o0j44pcJDzdxOHsVwlM7+CHWRj
+        ecHa75Ca7H28Q9D1hUF4N7GDdbjWBvTH1cauGNbJHma9Bl3Um1TjZ9osz5saAxe1Jk3J+QM2X2kJ
+        iCXRxZ68GEDs3tYOP/wu0aBRQLG2P6+Hj0vdUof/AkbKrXjAblVu1BK0udjPVz8GnGNGNHiGx2Iv
+        t+IBC9i61ECjUGwKRgZ87vyVbNq6mFtphKt8IQ4kt1JSGmrpDxHkb/LCliXAqRjBb4T+uNsE9qIV
+        7IfkLcI2O1N8YtK7mXwHSQAdexl9T60+rXKxlrAWbi5aoCIHs8JXMQRppOFI2gTATvc0gkJubgRM
+        8t7Qm2/l8O44FpEavglW9RRJ8LnkIbnqlgeW2pAhfOhhQB1mW8l+mNGoSEmnox72zNzEY1hDfw0R
+        NvmPOW305Gnw2/MBtt19AUsELpLq3suUOlq4TjPy5RlG8fikesiPzf57vXPgot5EEt5IwgKr8RUt
+        43ckcWNdzJ+rq8EwOxnUbQov2X7PrIbsYmFyYJoM9mMU1Sqk5IUOoYaSFTevN1AEUyIM4O/ETvcy
+        gt85TqhnNwXYm4qFsA9fkPodp0/bsKkl7ETDoUZpC+bWl7cTEOLuR13ldpw2/SM68Pt5mPS8Tk4h
+        7vK+w/skdmhSJj5h+ySusICti9MDy6YV+dsMy9u+USeWTLMLlccbtFeeUcceJECCw6QA+JiSZfbi
+        N1tDoUhBQoCOxPM3MsmzhCVY5DrCzn1apvG+lhrIroZHA+0gBtMzNE/QTdMOqSxtg309ayGUmtCm
+        l58+AUrHQw7Dj5bQgDdfCYm0+wlUA8DYZL5eiBe9JiDshRs9/aJpWnhB4cC77TrqpZhMmyR/Rzjl
+        1RWbiDuBvTzRGT6l+Ek2J7wmmxX8ELwKzowEtQqLfa1XArP1SwmXwy7YXHHVwO0xu0TCGyrmmzwZ
+        MJIMA7uGAZK9/2QZvKizRrgqcYOtuiMehJlvYMzJtTm5Rhyqr9+zwucmcpojdqAFKxUWSEKPsBC8
+        s+LDNrhW1OAE26Tv4wWqVm5p+Ho5LxNbLpoBUQZdfKmRnmwz7+TghWKeyMxeJgKgJEGgLCLVLtsY
+        zOaTi8D3sh7o6+SoybJ6jx7kVxFRv7bWaX18vwiiYy9Ta48Hc/1loIe3B3Gxl2LSEKK8fDg3ioA9
+        yxkBtcith62wR0joF5ZQJ9tO6vnys+m540awvG6TpXBraVDTrt/TjkZlhViNjtQMC8XczioWoRCW
+        Aba4rGtovPsSKFU/I4CUn2bOomMGf7cxoo6h8NNmfy4zvEfcFetirSTduQO9onhvgTDmf4r5ezvv
+        wLiNR+o2PTdtfH1YQb8dazSrSxisXVoPwFuvKfracE6YM39GcJsWgQYvQTB38NVy9WBLPq2swyvZ
+        uvuHB9S3XhiFkjuxqGxbqMX2gXox64NdiMYZ1q/DhxqlfQ22o1Q5sMs2DgmlXSX7Ra8JxJJ3or4k
+        /KZZYtYMH1ulYzfWPEZO3ygGgVZ/se7o72CT5O8IPKXG5MDJddDtnpZDq4YXqlmfAyO/sAuhfmMq
+        DfrhMFGO8jHk6xtDwg1s0+8Cp0q5+j+FOp/RAhsLBAJ/7Cxib8jjZFV2pYbiTZlI0QVkYrH3QvBl
+        EhXB8+0bbJy0OfBDl4k65X1j++F3z2DjM0w9PXeaNQNohYJrmNijmpuMfKeP6sKzJ+Kt0S343dKR
+        ahzblBwr65tsu6flEPDSjiR3PwZ7ZKISvvgbRTdfj5s90u4+3AH5kd15nxgZRDhIRza1OBQVvdmN
+        AYlw2y4S4dyamNtUvFu4WM0XcZuPTcZZSQwFd8nJfNK6gJFDloI+WL/Y6WgQsIWzdsh1cKGGURjT
+        b3+XA+hEWlCzU27B3glqDN9V6aLve5+mPb9fIBCNk08rdM0n5pDzA6hX9qBWUt/A4jX1AE6twqPd
+        3K1GSGKdh3b1TLBh9EcwM/uxQovFI7VUXwKzZt0dMJ4Xnwbcqkz7tXAVeA/eIdZecT5tQXSNQUJq
+        mzoskifyDZIReBZ/wd7kiMl6l3MRrJ2QU1ucdLAVkzGCkzf72Hqrx+YbrtYJ1p5oIQYekM3olQ+w
+        THSOOvfpPO1VkRMAfNvCWll10zK6hQjIQW7w9zD40yCuvx5+9arH+OSoxcJJsgOO6tvBwQF+E7Iq
+        IQRh5hv4fOogY9+L2AJ/CnQEjEwy55WMPLiD3cCm1HtgO350EcqDZFJ/3sJg0z+cBWB3Gqivq1VC
+        63DNoPQzPRxK2RjM1iqX4E32N9WaG8fWi3h6QwrMkXpfPQrmgPdWOJ17C5/Tn1Ks1NRFaOcDxgjs
+        VrB2txeExfN2QEpKjgn5sDaDckVdMi2+Dfbw9wmhQ4Yen7WrngyMjgjOv0xFs51Ttp+vfgw5DYVE
+        UcKpYdD0ZgioH2HTOWzTb/XFVIWRW1KL5EeTqL+pVsB4f1JHb/aGSBwRYZmYHHbvBz0QnjchAqdW
+        4ak5XeRgSeA9AvAR3ait44O5/JhrAOPYpkjZz3wyyNWyw0ueFdT0ZaM5VudyhqfD44TPl1VjQqY5
+        BkjulYxmYbDBT6l1pF5UolEDhm4h1n5fgWu7JwThj52Q9/5YwQtFPPVZmxVs7GQfVsnLpbolsKSv
+        9hnCLkA52vYnbzLrFqTyhfke2TLfBJvduhqkvHJG+5ocTBYQpVW6AOWInfcyYNDqSuWu3y5oc/M6
+        WH8Z6BWusEp6EetHQd77Y4fBu7LQMbMjc/7q1xgogi5RhGeloTNkCNajsOMzv87T7O8SAqy8Fvhk
+        Liv7PbWfAWbUYOoOm8F+7xwOwM5HTB3N0aetNjYOikvGsKfnzsQ27boq9/L8odbDXwLmGnEI7o5l
+        0Zgcs2kKrOYEHxk3U4fZbbEgMFuSk74mImrOpyHgq+UqUKhIPuKtC1ZWfjWlrCeDGl1Bit35jhWU
+        GHgQ+dO5TBCCqQbW832i1+Wtgr2qkAb2goVkvcJDwaRFfSvGPJv4OffvYP0MPoL5xS6odioiIDms
+        bGEfPiH2BHYBu9AXIXjo4E0OTmsz3n65IizUpCSq9fg29IOPPCyN9EetpL6BPbHOoiJVvoSAWbeM
+        PWVXAr/zCSABb53J+mjRIE25FbvHX1LM5yCQwGavAhGMYgL04vwUADBi1E0JMren9tPA7N3fpE9x
+        V+wGMDR4pamPul9xbJZ8DCLgg9cD7ZzQmWuKUgRd1JtISsS0WbH4mKF5TgVclikXEMgZFbxd1ZSe
+        7rFqrrnCt9B/f33EOuVmbgm8x9Bf5QY75X0DdD1YJ+C/O59qidkx1nTZCdzBblDrVp7A+vh+Q3gu
+        eA2jUHKnzaqFCpo5dpAk33Eyj9Mpg4aqldQWXkKwtsnFgt9PbtLX0m4NXX/FCFbNOVK/uPQmW3/F
+        CD8vI8N6Lp2CjVQBgU8pfuKwF61gfz+ZCPrS1UijmArb5ZiNYGmfFsYn51kMKLyWMABZSlRIG7ad
+        VVcEj63UCQBH3eRprmQwOncR3fDOpeSQpRC0/R2fNlyD5XYV3xB/RYoO9TEL2KcGBgQKFYmcSXOx
+        QdmMYGRkFtasbGx2PnZKCNJIw8nvoCabEkYzbKJmo9rxwab5dFIg3KNawxbJj+ZSU26GW0diio2O
+        TNs1bTmo3AWE2lehmccX6mN46GtIrfY4NOswizEAvLQT9nLnSewENYbbdpHwWbvqCV8nTQQ8u+nx
+        qa+/CVOWJlWH+IbIgZMNU7jptx6iD59Tz6HDxPr+WkOJc67kfRWjYjBP9g6j5LpT3xP7aXcuG1Qf
+        u5eR9QoPBYO39wAprSx61ve9IEJUE6XVti91GldgzJzqCNz164VqVuY3K+RDB67+SLBxjcdpS75K
+        Cpa7SmlojMHEb/ngw7U75lg3qy0gl0k5wdUfCbbVai6W57hW8PY+duTdDnvAGuQpoPEfCXZgnwTr
+        R1UIhMJLp76uckmrBg4CE+l2bMcjNy2Lx3Hg/okJ9kekmvQVrBzwHu1ODj4FwfyGHx9+9bKnji8H
+        jOW8PsDfYuUY4Y9dHE8LQHBGfoJPDW8GZD7PvdJ0vYq4ojPAnlg2D50fYNQs2yfbwVd7qOTRcPT8
+        ro2JTGFhgK/hAWo3BxosF9hUUC/rlXox600m6gYHUAZd6m1kmn7guM3wG2Yi1Q8Sa1prlUsoPinF
+        56vgBnw7cQqE9jnAJ3F7mCsSdB+q17xCnNIfiwk70IFDCWxqSr0Hjqn7i+BYmQ3hcmgHLN4NBaCZ
+        DBiFXNas4vrrYZp2GmKHdAHtaygf8KY1IWK/g1qwpn7zAEZuSZEThAFjWtDCWri62JMlydxTY7SA
+        Z3967K4AF8yaGS/zYXeh5sbx04Yu6QD3oGTULy69uaqBg+CC7YoiwXqbzMlkH0buHtKgHw4NSyu1
+        Bvcsf1L99k3BJsl0gIfpYOHw3stg44Wdg+87Tal7P3zM+cm9HGgP3ECOvr43lPwWER704Eaa/HVr
+        1sN7fis+sCq0TlkWLGmSPGAjgIwo8xYGpPd9Bz6/0MIes8/NMm8XC9YHhUPNFPgmL9haD07XZMVB
+        lbfmfGnsFHTa8MFh6m8TvflhDub0smHzXRGwV0VEYCndG+pNTpasNFdS+EoyHWtT8GZL8qscwF3H
+        FKksbYOfgpEGbbLNaG3CX0NP9zRWtUs+Yudl4Gb1X6oGnst2ok6bewHb1HcORLeNkVhBbTryU9vC
+        63qTieRfHZO1cq1A8GpCtPlOn0xpqYXwZ3QW1o8yTAhrJAt+DQ/g0y8Kms2Rkh2Wg+sTbiL91E9h
+        YcATPsU0zWwHrKIrSPAOdgMjPCsTsaLhAWaJ03EQfKdgU8J8Bt/Pw6TOQuqEdMEiQmvI79gDVsto
+        uq0ERO4a4udZpICcD/cZHkB7IjC3jGbVrIujzr9MxdrhPjJyGu0W2AMcyFsf+oKpZCRQtS2bYgKS
+        aRsePwR+7CxirfwpgB5I/lbRsZfxySmuAVEToIEyVN6I659JszqsbMFzmO7YPH97MMjbm1PhashY
+        Ay+ZTbcXL8Hbg7hE0C0PiPWutWA+kQBtR/I1mXb7Emg96xPGMYmTfT1rCAbr+sQ5dJNmC6JrDHg9
+        tRHdfje2EmvpQbdKN8LsgU4rv4IVmPVcYFfrxmJVdqWG3vU0YuP35qfdjPYeBFlyoi5JHubmt3wI
+        OufVYWtMIrZ+R41TVV/2qC7YXrJb0fAANvdYqZXUN0aD4piDf//5+/v7+99//v7+n//65+/v3354
+        Vt2///n7d6m25b+rvqiez/r7/u/H8/HfPC/++1///P39S+bHu/r3P3//88/f39/fv79p6H/L/7cM
+        bfWd//3Pn/hf//z9/f39uwzLo/v/lqGtvvO///kT//n7+99//vcfAwM=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 88142862e9f182e2-GIG
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - br
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 May 2024 19:39:49 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - text-embedding-ada-002
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '22'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999998'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_834c84237ace9a79492cb9e8d1f68737
+    status:
+      code: 200
+      message: OK
+version: 1

tests/memory/short_term_memory_test.py

@@ -1,15 +1,35 @@
 import pytest
 
+from crewai.agent import Agent
+from crewai.crew import Crew
 from crewai.memory.short_term.short_term_memory import ShortTermMemory
 from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
+from crewai.task import Task
 
 
 @pytest.fixture
 def short_term_memory():
     """Fixture to create a ShortTermMemory instance"""
-    return ShortTermMemory()
+    agent = Agent(
+        role="Researcher",
+        goal="Search relevant data and provide results",
+        backstory="You are a researcher at a leading tech think tank.",
+        tools=[],
+        verbose=True,
+    )
+
+    task = Task(
+        description="Perform a search on specific topics.",
+        expected_output="A list of relevant URLs based on the search query.",
+        agent=agent,
+    )
+    return ShortTermMemory(crew=Crew(
+        agents=[agent],
+        tasks=[task]
+    ))
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_save_and_search(short_term_memory):
     memory = ShortTermMemoryItem(
         data="""test value test value test value test value test value test value
@@ -19,6 +39,7 @@ def test_save_and_search(short_term_memory):
         metadata={"task": "test_task"},
     )
     short_term_memory.save(memory)
+
     find = short_term_memory.search("test value", score_threshold=0.01)[0]
     assert find["context"] == memory.data, "Data value mismatch."
     assert find["metadata"]["agent"] == "test_agent", "Agent value mismatch."