andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 00:28:31 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Merge branch 'main' of github.com:crewAIInc/crewAI into fix/clone_when_using_knowledge

Browse Source
This commit is contained in:
Lorenze Jay
2025-01-24 14:04:42 -08:00
parent e3e62c16d5 8c76bad50f
commit 65d3837c0d
27 changed files with 1473 additions and 390 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
docs/concepts/cli.mdx
View File

@@ -12,7 +12,7 @@ The CrewAI CLI provides a set of commands to interact with CrewAI, allowing you
To use the CrewAI CLI, make sure you have CrewAI installed:
```shell
```shell Terminal
pip install crewai
```
@@ -20,7 +20,7 @@ pip install crewai
The basic structure of a CrewAI CLI command is:
```shell
```shell Terminal
crewai [COMMAND] [OPTIONS] [ARGUMENTS]
```
@@ -30,7 +30,7 @@ crewai [COMMAND] [OPTIONS] [ARGUMENTS]
Create a new crew or flow.
```shell
```shell Terminal
crewai create [OPTIONS] TYPE NAME
```
@@ -38,7 +38,7 @@ crewai create [OPTIONS] TYPE NAME
- `NAME`: Name of the crew or flow
Example:
```shell
```shell Terminal
crewai create crew my_new_crew
crewai create flow my_new_flow
```
@@ -47,14 +47,14 @@ crewai create flow my_new_flow
Show the installed version of CrewAI.
```shell
```shell Terminal
crewai version [OPTIONS]
```
- `--tools`: (Optional) Show the installed version of CrewAI tools
Example:
```shell
```shell Terminal
crewai version
crewai version --tools
```
@@ -63,7 +63,7 @@ crewai version --tools
Train the crew for a specified number of iterations.
```shell
```shell Terminal
crewai train [OPTIONS]
```
@@ -71,7 +71,7 @@ crewai train [OPTIONS]
- `-f, --filename TEXT`: Path to a custom file for training (default: "trained_agents_data.pkl")
Example:
```shell
```shell Terminal
crewai train -n 10 -f my_training_data.pkl
```
@@ -79,14 +79,14 @@ crewai train -n 10 -f my_training_data.pkl
Replay the crew execution from a specific task.
```shell
```shell Terminal
crewai replay [OPTIONS]
```
- `-t, --task_id TEXT`: Replay the crew from this task ID, including all subsequent tasks
Example:
```shell
```shell Terminal
crewai replay -t task_123456
```
@@ -94,7 +94,7 @@ crewai replay -t task_123456
Retrieve your latest crew.kickoff() task outputs.
```shell
```shell Terminal
crewai log-tasks-outputs
```
@@ -102,7 +102,7 @@ crewai log-tasks-outputs
Reset the crew memories (long, short, entity, latest_crew_kickoff_outputs).
```shell
```shell Terminal
crewai reset-memories [OPTIONS]
```
@@ -113,7 +113,7 @@ crewai reset-memories [OPTIONS]
- `-a, --all`: Reset ALL memories
Example:
```shell
```shell Terminal
crewai reset-memories --long --short
crewai reset-memories --all
```
@@ -122,7 +122,7 @@ crewai reset-memories --all
Test the crew and evaluate the results.
```shell
```shell Terminal
crewai test [OPTIONS]
```
@@ -130,7 +130,7 @@ crewai test [OPTIONS]
- `-m, --model TEXT`: LLM Model to run the tests on the Crew (default: "gpt-4o-mini")
Example:
```shell
```shell Terminal
crewai test -n 5 -m gpt-3.5-turbo
```
@@ -138,7 +138,7 @@ crewai test -n 5 -m gpt-3.5-turbo
Run the crew.
```shell
```shell Terminal
crewai run
```
<Note>
@@ -147,7 +147,36 @@ Some commands may require additional configuration or setup within your project
</Note>
### 9. API Keys
### 9. Chat
Starting in version `0.98.0`, when you run the `crewai chat` command, you start an interactive session with your crew. The AI assistant will guide you by asking for necessary inputs to execute the crew. Once all inputs are provided, the crew will execute its tasks.
After receiving the results, you can continue interacting with the assistant for further instructions or questions.
```shell Terminal
crewai chat
```
<Note>
Ensure you execute these commands from your CrewAI project's root directory.
</Note>
<Note>
IMPORTANT: Set the `chat_llm` property in your `crew.py` file to enable this command.
```python
@crew
def crew(self) -> Crew:
return Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
verbose=True,
chat_llm="gpt-4o", # LLM for chat orchestration
)
```
</Note>
### 10. API Keys
When running ```crewai create crew``` command, the CLI will first show you the top 5 most common LLM providers and ask you to select one.

18
docs/concepts/llms.mdx
View File

@@ -243,6 +243,9 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
# llm: bedrock/amazon.titan-text-express-v1
# llm: bedrock/meta.llama2-70b-chat-v1
# Amazon SageMaker Models - Enterprise-grade
# llm: sagemaker/<my-endpoint>
# Mistral Models - Open source alternative
# llm: mistral/mistral-large-latest
# llm: mistral/mistral-medium-latest
@@ -506,6 +509,21 @@ Learn how to get the most out of your LLM configuration:
)
```
</Accordion>
<Accordion title="Amazon SageMaker">
```python Code
AWS_ACCESS_KEY_ID=<your-access-key>
AWS_SECRET_ACCESS_KEY=<your-secret-key>
AWS_DEFAULT_REGION=<your-region>
```
Example usage:
```python Code
llm = LLM(
model="sagemaker/<my-endpoint>"
)
```
</Accordion>
<Accordion title="Mistral">
```python Code

59
docs/installation.mdx
View File

@@ -15,10 +15,48 @@ icon: wrench
If you need to update Python, visit [python.org/downloads](https://python.org/downloads)
</Note>
# Setting Up Your Environment
Before installing CrewAI, it's recommended to set up a virtual environment. This helps isolate your project dependencies and avoid conflicts.
<Steps>
<Step title="Create a Virtual Environment">
Choose your preferred method to create a virtual environment:
**Using venv (Python's built-in tool):**
```shell Terminal
python3 -m venv .venv
```
**Using conda:**
```shell Terminal
conda create -n crewai-env python=3.12
```
</Step>
<Step title="Activate the Virtual Environment">
Activate your virtual environment based on your platform:
**On macOS/Linux (venv):**
```shell Terminal
source .venv/bin/activate
```
**On Windows (venv):**
```shell Terminal
.venv\Scripts\activate
```
**Using conda (all platforms):**
```shell Terminal
conda activate crewai-env
```
</Step>
</Steps>
# Installing CrewAI
CrewAI is a flexible and powerful AI framework that enables you to create and manage AI agents, tools, and tasks efficiently.
Let's get you set up! 🚀
Now let's get you set up! 🚀
<Steps>
<Step title="Install CrewAI">
@@ -72,9 +110,9 @@ Let's get you set up! 🚀
# Creating a New Project
<Info>
<Tip>
We recommend using the YAML Template scaffolding for a structured approach to defining agents and tasks.
</Info>
</Tip>
<Steps>
<Step title="Generate Project Structure">
@@ -104,7 +142,18 @@ Let's get you set up! 🚀
└── tasks.yaml
```
</Frame>
</Step>
</Step>
<Step title="Install Additional Tools">
You can install additional tools using UV:
```shell Terminal
uv add <tool-name>
```
<Tip>
UV is our preferred package manager as it's significantly faster than pip and provides better dependency resolution.
</Tip>
</Step>
<Step title="Customize Your Project">
Your project will contain these essential files:

2
docs/quickstart.mdx
View File

@@ -278,7 +278,7 @@ email_summarizer:
Summarize emails into a concise and clear summary
backstory: >
You will create a 5 bullet point summary of the report
llm: mixtal_llm
llm: openai/gpt-4o
```
<Tip>

100
docs/tools/composiotool.mdx
View File

@@ -1,78 +1,118 @@
---
title: Composio Tool
description: The `ComposioTool` is a wrapper around the composio set of tools and gives your agent access to a wide variety of tools from the Composio SDK.
description: Composio provides 250+ production-ready tools for AI agents with flexible authentication management.
icon: gear-code
---
# `ComposioTool`
# `ComposioToolSet`
## Description
Composio is an integration platform that allows you to connect your AI agents to 250+ tools. Key features include:
This tools is a wrapper around the composio set of tools and gives your agent access to a wide variety of tools from the Composio SDK.
- **Enterprise-Grade Authentication**: Built-in support for OAuth, API Keys, JWT with automatic token refresh
- **Full Observability**: Detailed tool usage logs, execution timestamps, and more
## Installation
To incorporate this tool into your project, follow the installation instructions below:
To incorporate Composio tools into your project, follow the instructions below:
```shell
pip install composio-core
pip install 'crewai[tools]'
pip install composio-crewai
pip install crewai
```
after the installation is complete, either run `composio login` or export your composio API key as `COMPOSIO_API_KEY`.
After the installation is complete, either run `composio login` or export your composio API key as `COMPOSIO_API_KEY`. Get your Composio API key from [here](https://app.composio.dev)
## Example
The following example demonstrates how to initialize the tool and execute a github action:
1. Initialize Composio tools
1. Initialize Composio toolset
```python Code
from composio import App
from crewai_tools import ComposioTool
from crewai import Agent, Task
from composio_crewai import ComposioToolSet, App, Action
from crewai import Agent, Task, Crew
tools = [ComposioTool.from_action(action=Action.GITHUB_ACTIVITY_STAR_REPO_FOR_AUTHENTICATED_USER)]
toolset = ComposioToolSet()
```
If you don't know what action you want to use, use `from_app` and `tags` filter to get relevant actions
2. Connect your GitHub account
<CodeGroup>
```shell CLI
composio add github
```
```python Code
tools = ComposioTool.from_app(App.GITHUB, tags=["important"])
request = toolset.initiate_connection(app=App.GITHUB)
print(f"Open this URL to authenticate: {request.redirectUrl}")
```
</CodeGroup>
or use `use_case` to search relevant actions
3. Get Tools
- Retrieving all the tools from an app (not recommended for production):
```python Code
tools = ComposioTool.from_app(App.GITHUB, use_case="Star a github repository")
tools = toolset.get_tools(apps=[App.GITHUB])
```
2. Define agent
- Filtering tools based on tags:
```python Code
tag = "users"
filtered_action_enums = toolset.find_actions_by_tags(
App.GITHUB,
tags=[tag],
)
tools = toolset.get_tools(actions=filtered_action_enums)
```
- Filtering tools based on use case:
```python Code
use_case = "Star a repository on GitHub"
filtered_action_enums = toolset.find_actions_by_use_case(
App.GITHUB, use_case=use_case, advanced=False
)
tools = toolset.get_tools(actions=filtered_action_enums)
```
<Tip>Set `advanced` to True to get actions for complex use cases</Tip>
- Using specific tools:
In this demo, we will use the `GITHUB_STAR_A_REPOSITORY_FOR_THE_AUTHENTICATED_USER` action from the GitHub app.
```python Code
tools = toolset.get_tools(
actions=[Action.GITHUB_STAR_A_REPOSITORY_FOR_THE_AUTHENTICATED_USER]
)
```
Learn more about filtering actions [here](https://docs.composio.dev/patterns/tools/use-tools/use-specific-actions)
4. Define agent
```python Code
crewai_agent = Agent(
role="Github Agent",
goal="You take action on Github using Github APIs",
backstory=(
"You are AI agent that is responsible for taking actions on Github "
"on users behalf. You need to take action on Github using Github APIs"
),
role="GitHub Agent",
goal="You take action on GitHub using GitHub APIs",
backstory="You are AI agent that is responsible for taking actions on GitHub on behalf of users using GitHub APIs",
verbose=True,
tools=tools,
llm= # pass an llm
)
```
3. Execute task
5. Execute task
```python Code
task = Task(
description="Star a repo ComposioHQ/composio on GitHub",
description="Star a repo composiohq/composio on GitHub",
agent=crewai_agent,
expected_output="if the star happened",
expected_output="Status of the operation",
)
task.execute()
crew = Crew(agents=[crewai_agent], tasks=[task])
crew.kickoff()
```
* More detailed list of tools can be found [here](https://app.composio.dev)
* More detailed list of tools can be found [here](https://app.composio.dev)

4
src/crewai/agent.py
View File

@@ -3,6 +3,7 @@ import shutil
import subprocess
from typing import Any, Dict, List, Literal, Optional, Union
from litellm import AuthenticationError as LiteLLMAuthenticationError
from pydantic import Field, InstanceOf, PrivateAttr, model_validator
from crewai.agents import CacheHandler
@@ -258,6 +259,9 @@ class Agent(BaseAgent):
}
)["output"]
except Exception as e:
if isinstance(e, LiteLLMAuthenticationError):
# Do not retry on authentication errors
raise e
self._times_executed += 1
if self._times_executed > self.max_retry_limit:
raise e

50
src/crewai/agents/crew_agent_executor.py
View File

@@ -3,6 +3,8 @@ import re
from dataclasses import dataclass
from typing import Any, Callable, Dict, List, Optional, Union
from litellm.exceptions import AuthenticationError as LiteLLMAuthenticationError
from crewai.agents.agent_builder.base_agent import BaseAgent
from crewai.agents.agent_builder.base_agent_executor_mixin import CrewAgentExecutorMixin
from crewai.agents.parser import (
@@ -13,6 +15,7 @@ from crewai.agents.parser import (
OutputParserException,
)
from crewai.agents.tools_handler import ToolsHandler
from crewai.llm import LLM
from crewai.tools.base_tool import BaseTool
from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
from crewai.utilities import I18N, Printer
@@ -54,7 +57,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
callbacks: List[Any] = [],
):
self._i18n: I18N = I18N()
self.llm = llm
self.llm: LLM = llm
self.task = task
self.agent = agent
self.crew = crew
@@ -80,10 +83,8 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
self.tool_name_to_tool_map: Dict[str, BaseTool] = {
tool.name: tool for tool in self.tools
}
if self.llm.stop:
self.llm.stop = list(set(self.llm.stop + self.stop))
else:
self.llm.stop = self.stop
self.stop = stop_words
self.llm.stop = list(set(self.llm.stop + self.stop))
def invoke(self, inputs: Dict[str, str]) -> Dict[str, Any]:
if "system" in self.prompt:
@@ -98,7 +99,11 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
self._show_start_logs()
self.ask_for_human_input = bool(inputs.get("ask_for_human_input", False))
formatted_answer = self._invoke_loop()
try:
formatted_answer = self._invoke_loop()
except Exception as e:
raise e
if self.ask_for_human_input:
formatted_answer = self._handle_human_feedback(formatted_answer)
@@ -124,7 +129,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
self._enforce_rpm_limit()
answer = self._get_llm_response()
formatted_answer = self._process_llm_response(answer)
if isinstance(formatted_answer, AgentAction):
@@ -145,10 +149,26 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
if self._is_context_length_exceeded(e):
self._handle_context_length()
continue
else:
self._handle_unknown_error(e)
raise e
finally:
self.iterations += 1
self._show_logs(formatted_answer)
return formatted_answer
def _handle_unknown_error(self, exception: Exception) -> None:
"""Handle unknown errors by informing the user."""
self._printer.print(
content="An unknown error occurred. Please check the details below.",
color="red",
)
self._printer.print(
content=f"Error details: {exception}",
color="red",
)
def _has_reached_max_iterations(self) -> bool:
"""Check if the maximum number of iterations has been reached."""
return self.iterations >= self.max_iter
@@ -160,10 +180,17 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
def _get_llm_response(self) -> str:
"""Call the LLM and return the response, handling any invalid responses."""
answer = self.llm.call(
self.messages,
callbacks=self.callbacks,
)
try:
answer = self.llm.call(
self.messages,
callbacks=self.callbacks,
)
except Exception as e:
self._printer.print(
content=f"Error during LLM call: {e}",
color="red",
)
raise e
if not answer:
self._printer.print(
@@ -184,7 +211,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
if FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE in e.error:
answer = answer.split("Observation:")[0].strip()
self.iterations += 1
return self._format_answer(answer)
def _handle_agent_action(

2
src/crewai/crew.py
View File

@@ -38,7 +38,6 @@ from crewai.tasks.task_output import TaskOutput
from crewai.telemetry import Telemetry
from crewai.tools.agent_tools.agent_tools import AgentTools
from crewai.tools.base_tool import Tool
from crewai.types.crew_chat import ChatInputs
from crewai.types.usage_metrics import UsageMetrics
from crewai.utilities import I18N, FileHandler, Logger, RPMController
from crewai.utilities.constants import TRAINING_DATA_FILE
@@ -85,6 +84,7 @@ class Crew(BaseModel):
step_callback: Callback to be executed after each step for every agents execution.
share_crew: Whether you want to share the complete crew information and execution with crewAI to make the library better, and allow us to train models.
planning: Plan the crew execution and add the plan to the crew.
chat_llm: The language model used for orchestrating chat interactions with the crew.
"""
__hash__ = object.__hash__ # type: ignore

120
src/crewai/flow/flow.py
View File

@@ -447,14 +447,12 @@ class Flow(Generic[T], metaclass=FlowMeta):
def __init__(
self,
persistence: Optional[FlowPersistence] = None,
restore_uuid: Optional[str] = None,
**kwargs: Any,
) -> None:
"""Initialize a new Flow instance.
Args:
persistence: Optional persistence backend for storing flow states
restore_uuid: Optional UUID to restore state from persistence
**kwargs: Additional state values to initialize or override
"""
# Initialize basic instance attributes
@@ -464,64 +462,12 @@ class Flow(Generic[T], metaclass=FlowMeta):
self._method_outputs: List[Any] = [] # List to store all method outputs
self._persistence: Optional[FlowPersistence] = persistence
# Validate state model before initialization
if isinstance(self.initial_state, type):
if issubclass(self.initial_state, BaseModel) and not issubclass(
self.initial_state, FlowState
):
# Check if model has id field
model_fields = getattr(self.initial_state, "model_fields", None)
if not model_fields or "id" not in model_fields:
raise ValueError("Flow state model must have an 'id' field")
# Initialize state with initial values
self._state = self._create_initial_state()
# Handle persistence and potential ID conflicts
stored_state = None
if self._persistence is not None:
if (
restore_uuid
and kwargs
and "id" in kwargs
and restore_uuid != kwargs["id"]
):
raise ValueError(
f"Conflicting IDs provided: restore_uuid='{restore_uuid}' "
f"vs kwargs['id']='{kwargs['id']}'. Use only one ID for restoration."
)
# Attempt to load state, prioritizing restore_uuid
if restore_uuid:
self._log_flow_event(f"Loading flow state from memory for UUID: {restore_uuid}", color="bold_yellow")
stored_state = self._persistence.load_state(restore_uuid)
if not stored_state:
raise ValueError(
f"No state found for restore_uuid='{restore_uuid}'"
)
elif kwargs and "id" in kwargs:
self._log_flow_event(f"Loading flow state from memory for ID: {kwargs['id']}", color="bold_yellow")
stored_state = self._persistence.load_state(kwargs["id"])
if not stored_state:
# For kwargs["id"], we allow creating new state if not found
self._state = self._create_initial_state()
if kwargs:
self._initialize_state(kwargs)
return
# Initialize state based on persistence and kwargs
if stored_state:
# Create initial state and restore from persistence
self._state = self._create_initial_state()
self._restore_state(stored_state)
# Apply any additional kwargs to override specific fields
if kwargs:
filtered_kwargs = {k: v for k, v in kwargs.items() if k != "id"}
if filtered_kwargs:
self._initialize_state(filtered_kwargs)
else:
# No stored state, create new state with initial values
self._state = self._create_initial_state()
# Apply any additional kwargs
if kwargs:
self._initialize_state(kwargs)
# Apply any additional kwargs
if kwargs:
self._initialize_state(kwargs)
self._telemetry.flow_creation_span(self.__class__.__name__)
@@ -635,18 +581,18 @@ class Flow(Generic[T], metaclass=FlowMeta):
@property
def flow_id(self) -> str:
"""Returns the unique identifier of this flow instance.
This property provides a consistent way to access the flow's unique identifier
regardless of the underlying state implementation (dict or BaseModel).
Returns:
str: The flow's unique identifier, or an empty string if not found
Note:
This property safely handles both dictionary and BaseModel state types,
returning an empty string if the ID cannot be retrieved rather than raising
an exception.
Example:
```python
flow = MyFlow()
@@ -656,7 +602,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
try:
if not hasattr(self, '_state'):
return ""
if isinstance(self._state, dict):
return str(self._state.get("id", ""))
elif isinstance(self._state, BaseModel):
@@ -731,7 +677,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
"""
# When restoring from persistence, use the stored ID
stored_id = stored_state.get("id")
self._log_flow_event(f"Restoring flow state from memory for ID: {stored_id}", color="bold_yellow")
if not stored_id:
raise ValueError("Stored state must have an 'id' field")
@@ -755,6 +700,36 @@ class Flow(Generic[T], metaclass=FlowMeta):
raise TypeError(f"State must be dict or BaseModel, got {type(self._state)}")
def kickoff(self, inputs: Optional[Dict[str, Any]] = None) -> Any:
"""Start the flow execution.
Args:
inputs: Optional dictionary containing input values and potentially a state ID to restore
"""
# Handle state restoration if ID is provided in inputs
if inputs and 'id' in inputs and self._persistence is not None:
restore_uuid = inputs['id']
stored_state = self._persistence.load_state(restore_uuid)
# Override the id in the state if it exists in inputs
if 'id' in inputs:
if isinstance(self._state, dict):
self._state['id'] = inputs['id']
elif isinstance(self._state, BaseModel):
setattr(self._state, 'id', inputs['id'])
if stored_state:
self._log_flow_event(f"Loading flow state from memory for UUID: {restore_uuid}", color="yellow")
# Restore the state
self._restore_state(stored_state)
else:
self._log_flow_event(f"No flow state found for UUID: {restore_uuid}", color="red")
# Apply any additional inputs after restoration
filtered_inputs = {k: v for k, v in inputs.items() if k != 'id'}
if filtered_inputs:
self._initialize_state(filtered_inputs)
# Start flow execution
self.event_emitter.send(
self,
event=FlowStartedEvent(
@@ -762,10 +737,11 @@ class Flow(Generic[T], metaclass=FlowMeta):
flow_name=self.__class__.__name__,
),
)
self._log_flow_event(f"Flow started with ID: {self.flow_id}", color="yellow")
self._log_flow_event(f"Flow started with ID: {self.flow_id}", color="bold_magenta")
if inputs is not None:
if inputs is not None and 'id' not in inputs:
self._initialize_state(inputs)
return asyncio.run(self.kickoff_async())
async def kickoff_async(self, inputs: Optional[Dict[str, Any]] = None) -> Any:
@@ -1010,18 +986,18 @@ class Flow(Generic[T], metaclass=FlowMeta):
def _log_flow_event(self, message: str, color: str = "yellow", level: str = "info") -> None:
"""Centralized logging method for flow events.
This method provides a consistent interface for logging flow-related events,
combining both console output with colors and proper logging levels.
Args:
message: The message to log
color: Color to use for console output (default: yellow)
Available colors: purple, red, bold_green, bold_purple,
bold_blue, yellow, bold_yellow
bold_blue, yellow, yellow
level: Log level to use (default: info)
Supported levels: info, warning
Note:
This method uses the Printer utility for colored console output
and the standard logging module for log level support.
@@ -1031,7 +1007,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
logger.info(message)
elif level == "warning":
logger.warning(message)
def plot(self, filename: str = "crewai_flow") -> None:
self._telemetry.flow_plotting_span(
self.__class__.__name__, list(self._methods.keys())

126
src/crewai/flow/persistence/decorators.py
View File

@@ -54,57 +54,44 @@ LOG_MESSAGES = {
class PersistenceDecorator:
"""Class to handle flow state persistence with consistent logging."""
_printer = Printer() # Class-level printer instance
@classmethod
def persist_state(cls, flow_instance: Any, method_name: str, persistence_instance: FlowPersistence) -> None:
"""Persist flow state with proper error handling and logging.
This method handles the persistence of flow state data, including proper
error handling and colored console output for status updates.
Args:
flow_instance: The flow instance whose state to persist
method_name: Name of the method that triggered persistence
persistence_instance: The persistence backend to use
Raises:
ValueError: If flow has no state or state lacks an ID
RuntimeError: If state persistence fails
AttributeError: If flow instance lacks required state attributes
Note:
Uses bold_yellow color for success messages and red for errors.
All operations are logged at appropriate levels (info/error).
Example:
```python
@persist
def my_flow_method(self):
# Method implementation
pass
# State will be automatically persisted after method execution
```
"""
try:
state = getattr(flow_instance, 'state', None)
if state is None:
raise ValueError("Flow instance has no state")
flow_uuid: Optional[str] = None
if isinstance(state, dict):
flow_uuid = state.get('id')
elif isinstance(state, BaseModel):
flow_uuid = getattr(state, 'id', None)
if not flow_uuid:
raise ValueError("Flow state must have an 'id' field for persistence")
# Log state saving with consistent message
cls._printer.print(LOG_MESSAGES["save_state"].format(flow_uuid), color="bold_yellow")
cls._printer.print(LOG_MESSAGES["save_state"].format(flow_uuid), color="cyan")
logger.info(LOG_MESSAGES["save_state"].format(flow_uuid))
try:
persistence_instance.save_state(
flow_uuid=flow_uuid,
@@ -154,44 +141,79 @@ def persist(persistence: Optional[FlowPersistence] = None):
def begin(self):
pass
"""
def decorator(target: Union[Type, Callable[..., T]]) -> Union[Type, Callable[..., T]]:
"""Decorator that handles both class and method decoration."""
actual_persistence = persistence or SQLiteFlowPersistence()
if isinstance(target, type):
# Class decoration
class_methods = {}
for name, method in target.__dict__.items():
if callable(method) and hasattr(method, "__is_flow_method__"):
# Wrap each flow method with persistence
if asyncio.iscoroutinefunction(method):
@functools.wraps(method)
async def class_async_wrapper(self: Any, *args: Any, **kwargs: Any) -> Any:
method_coro = method(self, *args, **kwargs)
if asyncio.iscoroutine(method_coro):
result = await method_coro
else:
result = method_coro
PersistenceDecorator.persist_state(self, method.__name__, actual_persistence)
return result
class_methods[name] = class_async_wrapper
else:
@functools.wraps(method)
def class_sync_wrapper(self: Any, *args: Any, **kwargs: Any) -> Any:
result = method(self, *args, **kwargs)
PersistenceDecorator.persist_state(self, method.__name__, actual_persistence)
return result
class_methods[name] = class_sync_wrapper
original_init = getattr(target, "__init__")
# Preserve flow-specific attributes
@functools.wraps(original_init)
def new_init(self: Any, *args: Any, **kwargs: Any) -> None:
if 'persistence' not in kwargs:
kwargs['persistence'] = actual_persistence
original_init(self, *args, **kwargs)
setattr(target, "__init__", new_init)
# Store original methods to preserve their decorators
original_methods = {}
for name, method in target.__dict__.items():
if callable(method) and (
hasattr(method, "__is_start_method__") or
hasattr(method, "__trigger_methods__") or
hasattr(method, "__condition_type__") or
hasattr(method, "__is_flow_method__") or
hasattr(method, "__is_router__")
):
original_methods[name] = method
# Create wrapped versions of the methods that include persistence
for name, method in original_methods.items():
if asyncio.iscoroutinefunction(method):
# Create a closure to capture the current name and method
def create_async_wrapper(method_name: str, original_method: Callable):
@functools.wraps(original_method)
async def method_wrapper(self: Any, *args: Any, **kwargs: Any) -> Any:
result = await original_method(self, *args, **kwargs)
PersistenceDecorator.persist_state(self, method_name, actual_persistence)
return result
return method_wrapper
wrapped = create_async_wrapper(name, method)
# Preserve all original decorators and attributes
for attr in ["__is_start_method__", "__trigger_methods__", "__condition_type__", "__is_router__"]:
if hasattr(method, attr):
setattr(class_methods[name], attr, getattr(method, attr))
setattr(class_methods[name], "__is_flow_method__", True)
setattr(wrapped, attr, getattr(method, attr))
setattr(wrapped, "__is_flow_method__", True)
# Update the class with the wrapped method
setattr(target, name, wrapped)
else:
# Create a closure to capture the current name and method
def create_sync_wrapper(method_name: str, original_method: Callable):
@functools.wraps(original_method)
def method_wrapper(self: Any, *args: Any, **kwargs: Any) -> Any:
result = original_method(self, *args, **kwargs)
PersistenceDecorator.persist_state(self, method_name, actual_persistence)
return result
return method_wrapper
wrapped = create_sync_wrapper(name, method)
# Preserve all original decorators and attributes
for attr in ["__is_start_method__", "__trigger_methods__", "__condition_type__", "__is_router__"]:
if hasattr(method, attr):
setattr(wrapped, attr, getattr(method, attr))
setattr(wrapped, "__is_flow_method__", True)
# Update the class with the wrapped method
setattr(target, name, wrapped)
# Update class with wrapped methods
for name, method in class_methods.items():
setattr(target, name, method)
return target
else:
# Method decoration
@@ -208,6 +230,7 @@ def persist(persistence: Optional[FlowPersistence] = None):
result = method_coro
PersistenceDecorator.persist_state(flow_instance, method.__name__, actual_persistence)
return result
for attr in ["__is_start_method__", "__trigger_methods__", "__condition_type__", "__is_router__"]:
if hasattr(method, attr):
setattr(method_async_wrapper, attr, getattr(method, attr))
@@ -219,6 +242,7 @@ def persist(persistence: Optional[FlowPersistence] = None):
result = method(flow_instance, *args, **kwargs)
PersistenceDecorator.persist_state(flow_instance, method.__name__, actual_persistence)
return result
for attr in ["__is_start_method__", "__trigger_methods__", "__condition_type__", "__is_router__"]:
if hasattr(method, attr):
setattr(method_sync_wrapper, attr, getattr(method, attr))

37
src/crewai/flow/persistence/sqlite.py
View File

@@ -3,10 +3,9 @@ SQLite-based implementation of flow state persistence.
"""
import json
import os
import sqlite3
import tempfile
from datetime import datetime
from pathlib import Path
from typing import Any, Dict, Optional, Union
from pydantic import BaseModel
@@ -16,34 +15,34 @@ from crewai.flow.persistence.base import FlowPersistence
class SQLiteFlowPersistence(FlowPersistence):
"""SQLite-based implementation of flow state persistence.
This class provides a simple, file-based persistence implementation using SQLite.
It's suitable for development and testing, or for production use cases with
moderate performance requirements.
"""
db_path: str # Type annotation for instance variable
def __init__(self, db_path: Optional[str] = None):
"""Initialize SQLite persistence.
Args:
db_path: Path to the SQLite database file. If not provided, uses
db_storage_path() from utilities.paths.
Raises:
ValueError: If db_path is invalid
"""
from crewai.utilities.paths import db_storage_path
# Get path from argument or default location
path = db_path or db_storage_path()
path = db_path or str(Path(db_storage_path()) / "flow_states.db")
if not path:
raise ValueError("Database path must be provided")
self.db_path = path # Now mypy knows this is str
self.init_db()
def init_db(self) -> None:
"""Create the necessary tables if they don't exist."""
with sqlite3.connect(self.db_path) as conn:
@@ -58,10 +57,10 @@ class SQLiteFlowPersistence(FlowPersistence):
""")
# Add index for faster UUID lookups
conn.execute("""
CREATE INDEX IF NOT EXISTS idx_flow_states_uuid
CREATE INDEX IF NOT EXISTS idx_flow_states_uuid
ON flow_states(flow_uuid)
""")
def save_state(
self,
flow_uuid: str,
@@ -69,7 +68,7 @@ class SQLiteFlowPersistence(FlowPersistence):
state_data: Union[Dict[str, Any], BaseModel],
) -> None:
"""Save the current flow state to SQLite.
Args:
flow_uuid: Unique identifier for the flow instance
method_name: Name of the method that just completed
@@ -84,7 +83,7 @@ class SQLiteFlowPersistence(FlowPersistence):
raise ValueError(
f"state_data must be either a Pydantic BaseModel or dict, got {type(state_data)}"
)
with sqlite3.connect(self.db_path) as conn:
conn.execute("""
INSERT INTO flow_states (
@@ -99,13 +98,13 @@ class SQLiteFlowPersistence(FlowPersistence):
datetime.utcnow().isoformat(),
json.dumps(state_dict),
))
def load_state(self, flow_uuid: str) -> Optional[Dict[str, Any]]:
"""Load the most recent state for a given flow UUID.
Args:
flow_uuid: Unique identifier for the flow instance
Returns:
The most recent state as a dictionary, or None if no state exists
"""
@@ -118,7 +117,7 @@ class SQLiteFlowPersistence(FlowPersistence):
LIMIT 1
""", (flow_uuid,))
row = cursor.fetchone()
if row:
return json.loads(row[0])
return None

68
src/crewai/llm.py
View File

@@ -142,7 +142,6 @@ class LLM:
self.temperature = temperature
self.top_p = top_p
self.n = n
self.stop = stop
self.max_completion_tokens = max_completion_tokens
self.max_tokens = max_tokens
self.presence_penalty = presence_penalty
@@ -160,37 +159,63 @@ class LLM:
litellm.drop_params = True
# Normalize self.stop to always be a List[str]
if stop is None:
self.stop: List[str] = []
elif isinstance(stop, str):
self.stop = [stop]
else:
self.stop = stop
self.set_callbacks(callbacks)
self.set_env_callbacks()
def call(
self,
messages: List[Dict[str, str]],
messages: Union[str, List[Dict[str, str]]],
tools: Optional[List[dict]] = None,
callbacks: Optional[List[Any]] = None,
available_functions: Optional[Dict[str, Any]] = None,
) -> str:
"""
High-level call method that:
1) Calls litellm.completion
2) Checks for function/tool calls
3) If a tool call is found:
a) executes the function
b) returns the result
4) If no tool call, returns the text response
High-level llm call method that:
1) Accepts either a string or a list of messages
2) Converts string input to the required message format
3) Calls litellm.completion
4) Handles function/tool calls if any
5) Returns the final text response or tool result
:param messages: The conversation messages
:param tools: Optional list of function schemas for function calling
:param callbacks: Optional list of callbacks
:param available_functions: A dictionary mapping function_name -> actual Python function
:return: Final text response from the LLM or the tool result
Parameters:
- messages (Union[str, List[Dict[str, str]]]): The input messages for the LLM.
- If a string is provided, it will be converted into a message list with a single entry.
- If a list of dictionaries is provided, each dictionary should have 'role' and 'content' keys.
- tools (Optional[List[dict]]): A list of tool schemas for function calling.
- callbacks (Optional[List[Any]]): A list of callback functions to be executed.
- available_functions (Optional[Dict[str, Any]]): A dictionary mapping function names to actual Python functions.
Returns:
- str: The final text response from the LLM or the result of a tool function call.
Examples:
---------
# Example 1: Using a string input
response = llm.call("Return the name of a random city in the world.")
print(response)
# Example 2: Using a list of messages
messages = [{"role": "user", "content": "What is the capital of France?"}]
response = llm.call(messages)
print(response)
"""
if isinstance(messages, str):
messages = [{"role": "user", "content": messages}]
with suppress_warnings():
if callbacks and len(callbacks) > 0:
self.set_callbacks(callbacks)
try:
# --- 1) Make the completion call
# --- 1) Prepare the parameters for the completion call
params = {
"model": self.model,
"messages": messages,
@@ -211,19 +236,21 @@ class LLM:
"api_version": self.api_version,
"api_key": self.api_key,
"stream": False,
"tools": tools, # pass the tool schema
"tools": tools,
}
# Remove None values from params
params = {k: v for k, v in params.items() if v is not None}
# --- 2) Make the completion call
response = litellm.completion(**params)
response_message = cast(Choices, cast(ModelResponse, response).choices)[
0
].message
text_response = response_message.content or ""
tool_calls = getattr(response_message, "tool_calls", [])
# Ensure callbacks get the full response object with usage info
# --- 3) Handle callbacks with usage info
if callbacks and len(callbacks) > 0:
for callback in callbacks:
if hasattr(callback, "log_success_event"):
@@ -236,11 +263,11 @@ class LLM:
end_time=0,
)
# --- 2) If no tool calls, return the text response
# --- 4) If no tool calls, return the text response
if not tool_calls or not available_functions:
return text_response
# --- 3) Handle the tool call
# --- 5) Handle the tool call
tool_call = tool_calls[0]
function_name = tool_call.function.name
@@ -255,7 +282,6 @@ class LLM:
try:
# Call the actual tool function
result = fn(**function_args)
return result
except Exception as e:

2
src/crewai/memory/storage/kickoff_task_outputs_storage.py
View File

@@ -23,7 +23,7 @@ class KickoffTaskOutputsSQLiteStorage:
) -> None:
if db_path is None:
# Get the parent directory of the default db path and create our db file there
db_path = str(Path(db_storage_path()).parent / "latest_kickoff_task_outputs.db")
db_path = str(Path(db_storage_path()) / "latest_kickoff_task_outputs.db")
self.db_path = db_path
self._printer: Printer = Printer()
self._initialize_db()

2
src/crewai/memory/storage/ltm_sqlite_storage.py
View File

@@ -17,7 +17,7 @@ class LTMSQLiteStorage:
) -> None:
if db_path is None:
# Get the parent directory of the default db path and create our db file there
db_path = str(Path(db_storage_path()).parent / "long_term_memory_storage.db")
db_path = str(Path(db_storage_path()) / "long_term_memory_storage.db")
self.db_path = db_path
self._printer: Printer = Printer()
# Ensure parent directory exists

4
src/crewai/utilities/llm_utils.py
View File

@@ -24,12 +24,10 @@ def create_llm(
# 1) If llm_value is already an LLM object, return it directly
if isinstance(llm_value, LLM):
print("LLM value is already an LLM object")
return llm_value
# 2) If llm_value is a string (model name)
if isinstance(llm_value, str):
print("LLM value is a string")
try:
created_llm = LLM(model=llm_value)
return created_llm
@@ -39,12 +37,10 @@ def create_llm(
# 3) If llm_value is None, parse environment variables or use default
if llm_value is None:
print("LLM value is None")
return _llm_via_environment_or_fallback()
# 4) Otherwise, attempt to extract relevant attributes from an unknown object
try:
print("LLM value is an unknown object")
# Extract attributes with explicit types
model = (
getattr(llm_value, "model_name", None)

6
src/crewai/utilities/paths.py
View File

@@ -7,7 +7,7 @@ import appdirs
def db_storage_path() -> str:
"""Returns the path for SQLite database storage.
Returns:
str: Full path to the SQLite database file
"""
@@ -16,7 +16,7 @@ def db_storage_path() -> str:
data_dir = Path(appdirs.user_data_dir(app_name, app_author))
data_dir.mkdir(parents=True, exist_ok=True)
return str(data_dir / "crewai_flows.db")
return str(data_dir)
def get_project_directory_name():
@@ -28,4 +28,4 @@ def get_project_directory_name():
else:
cwd = Path.cwd()
project_directory_name = cwd.name
return project_directory_name
return project_directory_name

25
src/crewai/utilities/printer.py
View File

@@ -21,6 +21,16 @@ class Printer:
self._print_yellow(content)
elif color == "bold_yellow":
self._print_bold_yellow(content)
elif color == "cyan":
self._print_cyan(content)
elif color == "bold_cyan":
self._print_bold_cyan(content)
elif color == "magenta":
self._print_magenta(content)
elif color == "bold_magenta":
self._print_bold_magenta(content)
elif color == "green":
self._print_green(content)
else:
print(content)
@@ -44,3 +54,18 @@ class Printer:
def _print_bold_yellow(self, content):
print("\033[1m\033[93m {}\033[00m".format(content))
def _print_cyan(self, content):
print("\033[96m {}\033[00m".format(content))
def _print_bold_cyan(self, content):
print("\033[1m\033[96m {}\033[00m".format(content))
def _print_magenta(self, content):
print("\033[35m {}\033[00m".format(content))
def _print_bold_magenta(self, content):
print("\033[1m\033[35m {}\033[00m".format(content))
def _print_green(self, content):
print("\033[32m {}\033[00m".format(content))

102
tests/agent_test.py
View File

@@ -16,7 +16,7 @@ from crewai.tools import tool
from crewai.tools.tool_calling import InstructorToolCalling
from crewai.tools.tool_usage import ToolUsage
from crewai.tools.tool_usage_events import ToolUsageFinished
from crewai.utilities import RPMController
from crewai.utilities import Printer, RPMController
from crewai.utilities.events import Emitter
@@ -1622,3 +1622,103 @@ def test_agent_with_knowledge_sources_works_with_test():
assert agent_copy.backstory == agent.backstory
assert agent_copy.knowledge_sources == agent.knowledge_sources
assert isinstance(agent_copy.llm, LLM)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_litellm_auth_error_handling():
"""Test that LiteLLM authentication errors are handled correctly and not retried."""
from litellm import AuthenticationError as LiteLLMAuthenticationError
# Create an agent with a mocked LLM and max_retry_limit=0
agent = Agent(
role="test role",
goal="test goal",
backstory="test backstory",
llm=LLM(model="gpt-4"),
max_retry_limit=0, # Disable retries for authentication errors
)
# Create a task
task = Task(
description="Test task",
expected_output="Test output",
agent=agent,
)
# Mock the LLM call to raise LiteLLMAuthenticationError
with (
patch.object(LLM, "call") as mock_llm_call,
pytest.raises(LiteLLMAuthenticationError, match="Invalid API key"),
):
mock_llm_call.side_effect = LiteLLMAuthenticationError(
message="Invalid API key", llm_provider="openai", model="gpt-4"
)
agent.execute_task(task)
# Verify the call was only made once (no retries)
mock_llm_call.assert_called_once()
def test_crew_agent_executor_litellm_auth_error():
"""Test that CrewAgentExecutor handles LiteLLM authentication errors by raising them."""
from litellm import AuthenticationError as LiteLLMAuthenticationError
from crewai.agents.tools_handler import ToolsHandler
from crewai.utilities import Printer
# Create an agent and executor
agent = Agent(
role="test role",
goal="test goal",
backstory="test backstory",
llm=LLM(model="gpt-4", api_key="invalid_api_key"),
)
task = Task(
description="Test task",
expected_output="Test output",
agent=agent,
)
# Create executor with all required parameters
executor = CrewAgentExecutor(
agent=agent,
task=task,
llm=agent.llm,
crew=None,
prompt={"system": "You are a test agent", "user": "Execute the task: {input}"},
max_iter=5,
tools=[],
tools_names="",
stop_words=[],
tools_description="",
tools_handler=ToolsHandler(),
)
# Mock the LLM call to raise LiteLLMAuthenticationError
with (
patch.object(LLM, "call") as mock_llm_call,
patch.object(Printer, "print") as mock_printer,
pytest.raises(LiteLLMAuthenticationError, match="Invalid API key"),
):
mock_llm_call.side_effect = LiteLLMAuthenticationError(
message="Invalid API key", llm_provider="openai", model="gpt-4"
)
executor.invoke(
{
"input": "test input",
"tool_names": "",
"tools": "",
}
)
# Verify error handling
mock_printer.assert_any_call(
content="An unknown error occurred. Please check the details below.",
color="red",
)
mock_printer.assert_any_call(
content="Error details: litellm.AuthenticationError: Invalid API key",
color="red",
)
# Verify the call was only made once (no retries)
mock_llm_call.assert_called_once()

183
tests/cassettes/test_agent_error_on_parsing_tool.yaml
View File

@@ -2,21 +2,21 @@ interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect criteria
for your final answer: The final answer\nyou MUST return the actual complete
content as the final answer, not a summary.\n\nBegin! This is VERY important
to you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}], "model": "gpt-4o"}'
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
in your response:\n\n```\nThought: you should always think about what to do\nAction:
the action to take, only one name of [get_final_answer], just the name, exactly
as it''s written.\nAction Input: the input to the action, just a simple JSON
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\n```\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n```"}, {"role": "user",
"content": "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect
criteria for your final answer: The final answer\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nBegin! This is VERY
important to you, use the tools available and give your best Final Answer, your
job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
@@ -25,16 +25,13 @@ interactions:
connection:
- keep-alive
content-length:
- '1325'
- '1367'
content-type:
- application/json
cookie:
- _cfuvid=ePJSDFdHag2D8lj21_ijAMWjoA6xfnPNxN4uekvC728-1727226247743-0.0.1.1-604800000;
__cf_bm=3giyBOIM0GNudFELtsBWYXwLrpLBTNLsh81wfXgu2tg-1727226247-1.0.1.1-ugUDz0c5EhmfVpyGtcdedlIWeDGuy2q0tXQTKVpv83HZhvxgBcS7SBL1wS4rapPM38yhfEcfwA79ARt3HQEzKA
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
@@ -44,30 +41,35 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-ABAtOWmVjvzQ9X58tKAUcOF4gmXwx\",\n \"object\":
\"chat.completion\",\n \"created\": 1727226842,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-AsXdf4OZKCZSigmN4k0gyh67NciqP\",\n \"object\":
\"chat.completion\",\n \"created\": 1737562383,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to use the get_final_answer
tool to determine the final answer.\\nAction: get_final_answer\\nAction Input:
{}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 274,\n \"completion_tokens\":
27,\n \"total_tokens\": 301,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
\"assistant\",\n \"content\": \"```\\nThought: I have to use the available
tool to get the final answer. Let's proceed with executing it.\\nAction: get_final_answer\\nAction
Input: {}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
274,\n \"completion_tokens\": 33,\n \"total_tokens\": 307,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_50cad350e4\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c8727b3492f31e6-MIA
- 9060d43e3be1d690-IAD
Connection:
- keep-alive
Content-Encoding:
@@ -75,19 +77,27 @@ interactions:
Content-Type:
- application/json
Date:
- Wed, 25 Sep 2024 01:14:03 GMT
- Wed, 22 Jan 2025 16:13:03 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=_Jcp7wnO_mXdvOnborCN6j8HwJxJXbszedJC1l7pFUg-1737562383-1.0.1.1-pDSLXlg.nKjG4wsT7mTJPjUvOX1UJITiS4MqKp6yfMWwRSJINsW1qC48SAcjBjakx2H5I1ESVk9JtUpUFDtf4g;
path=/; expires=Wed, 22-Jan-25 16:43:03 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=x3SYvzL2nq_PTBGtE8R9cl5CkeaaDzZFQIrYfo91S2s-1737562383916-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '348'
- '791'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -99,45 +109,59 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999682'
- '29999680'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_be929caac49706f487950548bdcdd46e
- req_eeed99acafd3aeb1e3d4a6c8063192b0
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect criteria
for your final answer: The final answer\nyou MUST return the actual complete
content as the final answer, not a summary.\n\nBegin! This is VERY important
to you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}, {"role": "user", "content": "Thought: I need to use the
get_final_answer tool to determine the final answer.\nAction: get_final_answer\nAction
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
in your response:\n\n```\nThought: you should always think about what to do\nAction:
the action to take, only one name of [get_final_answer], just the name, exactly
as it''s written.\nAction Input: the input to the action, just a simple JSON
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\n```\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n```"}, {"role": "user",
"content": "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect
criteria for your final answer: The final answer\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nBegin! This is VERY
important to you, use the tools available and give your best Final Answer, your
job depends on it!\n\nThought:"}, {"role": "assistant", "content": "```\nThought:
I have to use the available tool to get the final answer. Let''s proceed with
executing it.\nAction: get_final_answer\nAction Input: {}\nObservation: I encountered
an error: Error on parsing tool.\nMoving on then. I MUST either use a tool (use
one at time) OR give my best final answer not both at the same time. When responding,
I must use the following format:\n\n```\nThought: you should always think about
what to do\nAction: the action to take, should be one of [get_final_answer]\nAction
Input: the input to the action, dictionary enclosed in curly braces\nObservation:
the result of the action\n```\nThis Thought/Action/Action Input/Result can repeat
N times. Once I know the final answer, I must return the following format:\n\n```\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described\n\n```"}, {"role":
"assistant", "content": "```\nThought: I have to use the available tool to get
the final answer. Let''s proceed with executing it.\nAction: get_final_answer\nAction
Input: {}\nObservation: I encountered an error: Error on parsing tool.\nMoving
on then. I MUST either use a tool (use one at time) OR give my best final answer
not both at the same time. To Use the following format:\n\nThought: you should
always think about what to do\nAction: the action to take, should be one of
[get_final_answer]\nAction Input: the input to the action, dictionary enclosed
in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action
Input/Result can repeat N times)\nThought: I now can give a great answer\nFinal
not both at the same time. When responding, I must use the following format:\n\n```\nThought:
you should always think about what to do\nAction: the action to take, should
be one of [get_final_answer]\nAction Input: the input to the action, dictionary
enclosed in curly braces\nObservation: the result of the action\n```\nThis Thought/Action/Action
Input/Result can repeat N times. Once I know the final answer, I must return
the following format:\n\n```\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described\n\n \nNow it''s time you MUST give your absolute
it must be outcome described\n\n```\nNow it''s time you MUST give your absolute
best final answer. You''ll ignore all previous instructions, stop using any
tools, and just return your absolute BEST Final answer."}], "model": "gpt-4o"}'
tools, and just return your absolute BEST Final answer."}], "model": "gpt-4o",
"stop": ["\nObservation:"]}'
headers:
accept:
- application/json
@@ -146,16 +170,16 @@ interactions:
connection:
- keep-alive
content-length:
- '2320'
- '3445'
content-type:
- application/json
cookie:
- _cfuvid=ePJSDFdHag2D8lj21_ijAMWjoA6xfnPNxN4uekvC728-1727226247743-0.0.1.1-604800000;
__cf_bm=3giyBOIM0GNudFELtsBWYXwLrpLBTNLsh81wfXgu2tg-1727226247-1.0.1.1-ugUDz0c5EhmfVpyGtcdedlIWeDGuy2q0tXQTKVpv83HZhvxgBcS7SBL1wS4rapPM38yhfEcfwA79ARt3HQEzKA
- __cf_bm=_Jcp7wnO_mXdvOnborCN6j8HwJxJXbszedJC1l7pFUg-1737562383-1.0.1.1-pDSLXlg.nKjG4wsT7mTJPjUvOX1UJITiS4MqKp6yfMWwRSJINsW1qC48SAcjBjakx2H5I1ESVk9JtUpUFDtf4g;
_cfuvid=x3SYvzL2nq_PTBGtE8R9cl5CkeaaDzZFQIrYfo91S2s-1737562383916-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
@@ -165,29 +189,36 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-ABAtPaaeRfdNsZ3k06CfAmrEW8IJu\",\n \"object\":
\"chat.completion\",\n \"created\": 1727226843,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-AsXdg9UrLvAiqWP979E6DszLsQ84k\",\n \"object\":
\"chat.completion\",\n \"created\": 1737562384,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Final Answer: The final answer\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 483,\n \"completion_tokens\":
6,\n \"total_tokens\": 489,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
\"assistant\",\n \"content\": \"```\\nThought: I now know the final answer\\nFinal
Answer: The final answer must be the great and the most complete as possible,
it must be outcome described.\\n```\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 719,\n \"completion_tokens\": 35,\n
\ \"total_tokens\": 754,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_50cad350e4\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c8727b9da1f31e6-MIA
- 9060d4441edad690-IAD
Connection:
- keep-alive
Content-Encoding:
@@ -195,7 +226,7 @@ interactions:
Content-Type:
- application/json
Date:
- Wed, 25 Sep 2024 01:14:03 GMT
- Wed, 22 Jan 2025 16:13:05 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -209,7 +240,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '188'
- '928'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -221,13 +252,13 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999445'
- '29999187'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_d8e32538689fe064627468bad802d9a8
- req_61fc7506e6db326ec572224aec81ef23
http_version: HTTP/1.1
status_code: 200
version: 1

102
tests/cassettes/test_llm_call_with_message_list.yaml Normal file
View File

@@ -0,0 +1,102 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the capital of France?"}],
"model": "gpt-4o-mini"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '101'
content-type:
- application/json
cookie:
- _cfuvid=8NrWEBP3dDmc8p2.csR.EdsSwS8zFvzWI1kPICaK_fM-1737568015338-0.0.1.1-604800000;
__cf_bm=pKr3NwXmTZN9rMSlKvEX40VPKbrxF93QwDNHunL2v8Y-1737568015-1.0.1.1-nR0EA7hYIwWpIBYUI53d9xQrUnl5iML6lgz4AGJW4ZGPBDxFma3PZ2cBhlr_hE7wKa5fV3r32eMu_rNWMXD.eA
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AsZ6WjNfEOrHwwEEdSZZCRBiTpBMS\",\n \"object\":
\"chat.completion\",\n \"created\": 1737568016,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The capital of France is Paris.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 14,\n \"completion_tokens\":
8,\n \"total_tokens\": 22,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 90615dc63b805cb1-RDU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 22 Jan 2025 17:46:56 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '355'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999974'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_cdbed69c9c63658eb552b07f1220df19
http_version: HTTP/1.1
status_code: 200
version: 1

108
tests/cassettes/test_llm_call_with_string_input.yaml Normal file
View File

@@ -0,0 +1,108 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "Return the name of a random
city in the world."}], "model": "gpt-4o-mini"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '117'
content-type:
- application/json
cookie:
- _cfuvid=3UeEmz_rnmsoZxrVUv32u35gJOi766GDWNe5_RTjiPk-1736537376739-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AsZ6UtbaNSMpNU9VJKxvn52t5eJTq\",\n \"object\":
\"chat.completion\",\n \"created\": 1737568014,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"How about \\\"Lisbon\\\"? It\u2019s the
capital city of Portugal, known for its rich history and vibrant culture.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 18,\n \"completion_tokens\":
24,\n \"total_tokens\": 42,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 90615dbcaefb5cb1-RDU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 22 Jan 2025 17:46:55 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=pKr3NwXmTZN9rMSlKvEX40VPKbrxF93QwDNHunL2v8Y-1737568015-1.0.1.1-nR0EA7hYIwWpIBYUI53d9xQrUnl5iML6lgz4AGJW4ZGPBDxFma3PZ2cBhlr_hE7wKa5fV3r32eMu_rNWMXD.eA;
path=/; expires=Wed, 22-Jan-25 18:16:55 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=8NrWEBP3dDmc8p2.csR.EdsSwS8zFvzWI1kPICaK_fM-1737568015338-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '449'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999971'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_898373758d2eae3cd84814050b2588e3
http_version: HTTP/1.1
status_code: 200
version: 1

102
tests/cassettes/test_llm_call_with_string_input_and_callbacks.yaml Normal file
View File

@@ -0,0 +1,102 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "Tell me a joke."}], "model":
"gpt-4o-mini"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '86'
content-type:
- application/json
cookie:
- _cfuvid=8NrWEBP3dDmc8p2.csR.EdsSwS8zFvzWI1kPICaK_fM-1737568015338-0.0.1.1-604800000;
__cf_bm=pKr3NwXmTZN9rMSlKvEX40VPKbrxF93QwDNHunL2v8Y-1737568015-1.0.1.1-nR0EA7hYIwWpIBYUI53d9xQrUnl5iML6lgz4AGJW4ZGPBDxFma3PZ2cBhlr_hE7wKa5fV3r32eMu_rNWMXD.eA
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AsZ6VyjuUcXYpChXmD8rUSy6nSGq8\",\n \"object\":
\"chat.completion\",\n \"created\": 1737568015,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Why did the scarecrow win an award? \\n\\nBecause
he was outstanding in his field!\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
12,\n \"completion_tokens\": 19,\n \"total_tokens\": 31,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 90615dc03b6c5cb1-RDU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 22 Jan 2025 17:46:56 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '825'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999979'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_4c1485d44e7461396d4a7316a63ff353
http_version: HTTP/1.1
status_code: 200
version: 1

111
tests/cassettes/test_llm_call_with_tool_and_message_list.yaml Normal file
View File

@@ -0,0 +1,111 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the square of 5?"}],
"model": "gpt-4o-mini", "tools": [{"type": "function", "function": {"name":
"square_number", "description": "Returns the square of a number.", "parameters":
{"type": "object", "properties": {"number": {"type": "integer", "description":
"The number to square"}}, "required": ["number"]}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '361'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AsZL5nGOaVpcGnDOesTxBZPHhMoaS\",\n \"object\":
\"chat.completion\",\n \"created\": 1737568919,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_i6JVJ1KxX79A4WzFri98E03U\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"square_number\",\n
\ \"arguments\": \"{\\\"number\\\":5}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"tool_calls\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
58,\n \"completion_tokens\": 15,\n \"total_tokens\": 73,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 906173d229b905f6-IAD
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 22 Jan 2025 18:02:00 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=BYDpIoqfPZyRxl9xcFxkt4IzTUGe8irWQlZ.aYLt8Xc-1737568920-1.0.1.1-Y_cVFN7TbguWRBorSKZynVY02QUtYbsbHuR2gR1wJ8LHuqOF4xIxtK5iHVCpWWgIyPDol9xOXiqUkU8xRV_vHA;
path=/; expires=Wed, 22-Jan-25 18:32:00 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=etTqqA9SBOnENmrFAUBIexdW0v2ZeO1x9_Ek_WChlfU-1737568920137-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '642'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999976'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_388e63f9b8d4edc0dd153001f25388e5
http_version: HTTP/1.1
status_code: 200
version: 1

107
tests/cassettes/test_llm_call_with_tool_and_string_input.yaml Normal file
View File

@@ -0,0 +1,107 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the current year?"}],
"model": "gpt-4o-mini", "tools": [{"type": "function", "function": {"name":
"get_current_year", "description": "Returns the current year as a string.",
"parameters": {"type": "object", "properties": {}, "required": []}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '295'
content-type:
- application/json
cookie:
- _cfuvid=8NrWEBP3dDmc8p2.csR.EdsSwS8zFvzWI1kPICaK_fM-1737568015338-0.0.1.1-604800000;
__cf_bm=pKr3NwXmTZN9rMSlKvEX40VPKbrxF93QwDNHunL2v8Y-1737568015-1.0.1.1-nR0EA7hYIwWpIBYUI53d9xQrUnl5iML6lgz4AGJW4ZGPBDxFma3PZ2cBhlr_hE7wKa5fV3r32eMu_rNWMXD.eA
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AsZJ8HKXQU9nTB7xbGAkKxqrg9BZ2\",\n \"object\":
\"chat.completion\",\n \"created\": 1737568798,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_mfvEs2jngeFloVZpZOHZVaKY\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"get_current_year\",\n
\ \"arguments\": \"{}\"\n }\n }\n ],\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"tool_calls\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 46,\n \"completion_tokens\":
12,\n \"total_tokens\": 58,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 906170e038281775-IAD
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 22 Jan 2025 17:59:59 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '416'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999975'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_4039a5e5772d1790a3131f0b1ea06139
http_version: HTTP/1.1
status_code: 200
version: 1

117
tests/llm_test.py
View File

@@ -4,6 +4,7 @@ import pytest
from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
from crewai.llm import LLM
from crewai.tools import tool
from crewai.utilities.token_counter_callback import TokenCalcHandler
@@ -37,3 +38,119 @@ def test_llm_callback_replacement():
assert usage_metrics_1.successful_requests == 1
assert usage_metrics_2.successful_requests == 1
assert usage_metrics_1 == calc_handler_1.token_cost_process.get_summary()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_call_with_string_input():
llm = LLM(model="gpt-4o-mini")
# Test the call method with a string input
result = llm.call("Return the name of a random city in the world.")
assert isinstance(result, str)
assert len(result.strip()) > 0 # Ensure the response is not empty
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_call_with_string_input_and_callbacks():
llm = LLM(model="gpt-4o-mini")
calc_handler = TokenCalcHandler(token_cost_process=TokenProcess())
# Test the call method with a string input and callbacks
result = llm.call(
"Tell me a joke.",
callbacks=[calc_handler],
)
usage_metrics = calc_handler.token_cost_process.get_summary()
assert isinstance(result, str)
assert len(result.strip()) > 0
assert usage_metrics.successful_requests == 1
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_call_with_message_list():
llm = LLM(model="gpt-4o-mini")
messages = [{"role": "user", "content": "What is the capital of France?"}]
# Test the call method with a list of messages
result = llm.call(messages)
assert isinstance(result, str)
assert "Paris" in result
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_call_with_tool_and_string_input():
llm = LLM(model="gpt-4o-mini")
def get_current_year() -> str:
"""Returns the current year as a string."""
from datetime import datetime
return str(datetime.now().year)
# Create tool schema
tool_schema = {
"type": "function",
"function": {
"name": "get_current_year",
"description": "Returns the current year as a string.",
"parameters": {
"type": "object",
"properties": {},
"required": [],
},
},
}
# Available functions mapping
available_functions = {"get_current_year": get_current_year}
# Test the call method with a string input and tool
result = llm.call(
"What is the current year?",
tools=[tool_schema],
available_functions=available_functions,
)
assert isinstance(result, str)
assert result == get_current_year()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_call_with_tool_and_message_list():
llm = LLM(model="gpt-4o-mini")
def square_number(number: int) -> int:
"""Returns the square of a number."""
return number * number
# Create tool schema
tool_schema = {
"type": "function",
"function": {
"name": "square_number",
"description": "Returns the square of a number.",
"parameters": {
"type": "object",
"properties": {
"number": {"type": "integer", "description": "The number to square"}
},
"required": ["number"],
},
},
}
# Available functions mapping
available_functions = {"square_number": square_number}
messages = [{"role": "user", "content": "What is the square of 5?"}]
# Test the call method with messages and tool
result = llm.call(
messages,
tools=[tool_schema],
available_functions=available_functions,
)
assert isinstance(result, int)
assert result == 25

112
tests/test_flow_default_override.py Normal file
View File

@@ -0,0 +1,112 @@
"""Test that persisted state properly overrides default values."""
from crewai.flow.flow import Flow, FlowState, listen, start
from crewai.flow.persistence import persist
class PoemState(FlowState):
"""Test state model with default values that should be overridden."""
sentence_count: int = 1000 # Default that should be overridden
has_set_count: bool = False # Track whether we've set the count
poem_type: str = ""
def test_default_value_override():
"""Test that persisted state values override class defaults."""
@persist()
class PoemFlow(Flow[PoemState]):
initial_state = PoemState
@start()
def set_sentence_count(self):
if self.state.has_set_count and self.state.sentence_count == 2:
self.state.sentence_count = 3
elif self.state.has_set_count and self.state.sentence_count == 1000:
self.state.sentence_count = 1000
elif self.state.has_set_count and self.state.sentence_count == 5:
self.state.sentence_count = 5
else:
self.state.sentence_count = 2
self.state.has_set_count = True
# First run - should set sentence_count to 2
flow1 = PoemFlow()
flow1.kickoff()
original_uuid = flow1.state.id
assert flow1.state.sentence_count == 2
# Second run - should load sentence_count=2 instead of default 1000
flow2 = PoemFlow()
flow2.kickoff(inputs={"id": original_uuid})
assert flow2.state.sentence_count == 3 # Should load 2, not default 1000
# Fourth run - explicit override should work
flow3 = PoemFlow()
flow3.kickoff(inputs={
"id": original_uuid,
"has_set_count": True,
"sentence_count": 5, # Override persisted value
})
assert flow3.state.sentence_count == 5 # Should use override value
# Third run - should not load sentence_count=2 instead of default 1000
flow4 = PoemFlow()
flow4.kickoff(inputs={"has_set_count": True})
assert flow4.state.sentence_count == 1000 # Should load 1000, not 2
def test_multi_step_default_override():
"""Test default value override with multiple start methods."""
@persist()
class MultiStepPoemFlow(Flow[PoemState]):
initial_state = PoemState
@start()
def set_sentence_count(self):
print("Setting sentence count")
if not self.state.has_set_count:
self.state.sentence_count = 3
self.state.has_set_count = True
@listen(set_sentence_count)
def set_poem_type(self):
print("Setting poem type")
if self.state.sentence_count == 3:
self.state.poem_type = "haiku"
elif self.state.sentence_count == 5:
self.state.poem_type = "limerick"
else:
self.state.poem_type = "free_verse"
@listen(set_poem_type)
def finished(self):
print("finished")
# First run - should set both sentence count and poem type
flow1 = MultiStepPoemFlow()
flow1.kickoff()
original_uuid = flow1.state.id
assert flow1.state.sentence_count == 3
assert flow1.state.poem_type == "haiku"
# Second run - should load persisted state and update poem type
flow2 = MultiStepPoemFlow()
flow2.kickoff(inputs={
"id": original_uuid,
"sentence_count": 5
})
assert flow2.state.sentence_count == 5
assert flow2.state.poem_type == "limerick"
# Third run - new flow without persisted state should use defaults
flow3 = MultiStepPoemFlow()
flow3.kickoff(inputs={
"id": original_uuid
})
assert flow3.state.sentence_count == 5
assert flow3.state.poem_type == "limerick"

131
tests/test_flow_persistence.py
View File

@@ -1,12 +1,12 @@
"""Test flow state persistence functionality."""
import os
from typing import Dict, Optional
from typing import Dict
import pytest
from pydantic import BaseModel
from crewai.flow.flow import Flow, FlowState, start
from crewai.flow.flow import Flow, FlowState, listen, start
from crewai.flow.persistence import persist
from crewai.flow.persistence.sqlite import SQLiteFlowPersistence
@@ -73,13 +73,14 @@ def test_flow_state_restoration(tmp_path):
# First flow execution to create initial state
class RestorableFlow(Flow[TestState]):
initial_state = TestState
@start()
@persist(persistence)
def set_message(self):
self.state.message = "Original message"
self.state.counter = 42
if self.state.message == "":
self.state.message = "Original message"
if self.state.counter == 0:
self.state.counter = 42
# Create and persist initial state
flow1 = RestorableFlow(persistence=persistence)
@@ -87,11 +88,11 @@ def test_flow_state_restoration(tmp_path):
original_uuid = flow1.state.id
# Test case 1: Restore using restore_uuid with field override
flow2 = RestorableFlow(
persistence=persistence,
restore_uuid=original_uuid,
counter=43, # Override counter
)
flow2 = RestorableFlow(persistence=persistence)
flow2.kickoff(inputs={
"id": original_uuid,
"counter": 43
})
# Verify state restoration and selective field override
assert flow2.state.id == original_uuid
@@ -99,48 +100,17 @@ def test_flow_state_restoration(tmp_path):
assert flow2.state.counter == 43 # Overridden
# Test case 2: Restore using kwargs['id']
flow3 = RestorableFlow(
persistence=persistence,
id=original_uuid,
message="Updated message", # Override message
)
flow3 = RestorableFlow(persistence=persistence)
flow3.kickoff(inputs={
"id": original_uuid,
"message": "Updated message"
})
# Verify state restoration and selective field override
assert flow3.state.id == original_uuid
assert flow3.state.counter == 42 # Preserved
assert flow3.state.counter == 43 # Preserved
assert flow3.state.message == "Updated message" # Overridden
# Test case 3: Verify error on conflicting IDs
with pytest.raises(ValueError) as exc_info:
RestorableFlow(
persistence=persistence,
restore_uuid=original_uuid,
id="different-id", # Conflict with restore_uuid
)
assert "Conflicting IDs provided" in str(exc_info.value)
# Test case 4: Verify error on non-existent restore_uuid
with pytest.raises(ValueError) as exc_info:
RestorableFlow(
persistence=persistence,
restore_uuid="non-existent-uuid",
)
assert "No state found" in str(exc_info.value)
# Test case 5: Allow new state creation with kwargs['id']
new_uuid = "new-flow-id"
flow4 = RestorableFlow(
persistence=persistence,
id=new_uuid,
message="New message",
counter=100,
)
# Verify new state creation with provided ID
assert flow4.state.id == new_uuid
assert flow4.state.message == "New message"
assert flow4.state.counter == 100
def test_multiple_method_persistence(tmp_path):
"""Test state persistence across multiple method executions."""
@@ -148,48 +118,59 @@ def test_multiple_method_persistence(tmp_path):
persistence = SQLiteFlowPersistence(db_path)
class MultiStepFlow(Flow[TestState]):
initial_state = TestState
@start()
@persist(persistence)
def step_1(self):
self.state.counter = 1
self.state.message = "Step 1"
if self.state.counter == 1:
self.state.counter = 99999
self.state.message = "Step 99999"
else:
self.state.counter = 1
self.state.message = "Step 1"
@start()
@listen(step_1)
@persist(persistence)
def step_2(self):
self.state.counter = 2
self.state.message = "Step 2"
if self.state.counter == 1:
self.state.counter = 2
self.state.message = "Step 2"
flow = MultiStepFlow(persistence=persistence)
flow.kickoff()
flow2 = MultiStepFlow(persistence=persistence)
flow2.kickoff(inputs={"id": flow.state.id})
# Load final state
final_state = persistence.load_state(flow.state.id)
final_state = flow2.state
assert final_state is not None
assert final_state["counter"] == 2
assert final_state["message"] == "Step 2"
def test_persistence_error_handling(tmp_path):
"""Test error handling in persistence operations."""
db_path = os.path.join(tmp_path, "test_flows.db")
persistence = SQLiteFlowPersistence(db_path)
class InvalidFlow(Flow[TestState]):
# Missing id field in initial state
class InvalidState(BaseModel):
value: str = ""
initial_state = InvalidState
assert final_state.counter == 2
assert final_state.message == "Step 2"
class NoPersistenceMultiStepFlow(Flow[TestState]):
@start()
@persist(persistence)
def will_fail(self):
self.state.value = "test"
def step_1(self):
if self.state.counter == 1:
self.state.counter = 99999
self.state.message = "Step 99999"
else:
self.state.counter = 1
self.state.message = "Step 1"
with pytest.raises(ValueError) as exc_info:
flow = InvalidFlow(persistence=persistence)
@listen(step_1)
def step_2(self):
if self.state.counter == 1:
self.state.counter = 2
self.state.message = "Step 2"
assert "must have an 'id' field" in str(exc_info.value)
flow = NoPersistenceMultiStepFlow(persistence=persistence)
flow.kickoff()
flow2 = NoPersistenceMultiStepFlow(persistence=persistence)
flow2.kickoff(inputs={"id": flow.state.id})
# Load final state
final_state = flow2.state
assert final_state.counter == 99999
assert final_state.message == "Step 99999"