Merge branch 'main' into feat/trace-ui-exec-3

* added condition to check whether _run function returns a coroutine object

* Cleaned the code

* Fixed the test modules, Class -> Functions

.github/workflows/tests.yml

@@ -12,6 +12,9 @@ jobs:
   tests:
     runs-on: ubuntu-latest
     timeout-minutes: 15
+    strategy:
+      matrix:
+        python-version: ['3.10', '3.11', '3.12']
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -21,9 +24,8 @@ jobs:
         with:
           enable-cache: true
 
-
-      - name: Set up Python
-        run: uv python install 3.12.8
+      - name: Set up Python ${{ matrix.python-version }}
+        run: uv python install ${{ matrix.python-version }}
 
       - name: Install the project
         run: uv sync --dev --all-extras

docs/concepts/flows.mdx

@@ -545,16 +545,20 @@ The `third_method` and `fourth_method` listen to the output of the `second_metho
 
 When you run this Flow, the output will change based on the random boolean value generated by the `start_method`.
 
-## Adding LiteAgent to Flows
+## Adding Agents to Flows
 
-LiteAgents can be seamlessly integrated into your flows, providing a lightweight alternative to full Crews when you need simpler, focused task execution. Here's an example of how to use a LiteAgent within a flow to perform market research:
+Agents can be seamlessly integrated into your flows, providing a lightweight alternative to full Crews when you need simpler, focused task execution. Here's an example of how to use an Agent within a flow to perform market research:
 
 ```python
-from typing import List, cast
-from crewai_tools.tools.website_search.website_search_tool import WebsiteSearchTool
+import asyncio
+from typing import Any, Dict, List
+
+from crewai_tools import SerperDevTool
 from pydantic import BaseModel, Field
+
+from crewai.agent import Agent
 from crewai.flow.flow import Flow, listen, start
-from crewai.lite_agent import LiteAgent
+
 
 # Define a structured output format
 class MarketAnalysis(BaseModel):
@@ -562,28 +566,30 @@ class MarketAnalysis(BaseModel):
     market_size: str = Field(description="Estimated market size")
     competitors: List[str] = Field(description="Major competitors in the space")
 
+
 # Define flow state
 class MarketResearchState(BaseModel):
     product: str = ""
     analysis: MarketAnalysis | None = None
 
+
+# Create a flow class
 class MarketResearchFlow(Flow[MarketResearchState]):
     @start()
-    def initialize_research(self):
+    def initialize_research(self) -> Dict[str, Any]:
         print(f"Starting market research for {self.state.product}")
+        return {"product": self.state.product}
 
     @listen(initialize_research)
-    def analyze_market(self):
-        # Create a LiteAgent for market research
-        analyst = LiteAgent(
+    async def analyze_market(self) -> Dict[str, Any]:
+        # Create an Agent for market research
+        analyst = Agent(
             role="Market Research Analyst",
             goal=f"Analyze the market for {self.state.product}",
             backstory="You are an experienced market analyst with expertise in "
             "identifying market trends and opportunities.",
-            llm="gpt-4o",
-            tools=[WebsiteSearchTool()],
+            tools=[SerperDevTool()],
             verbose=True,
-            response_format=MarketAnalysis,
         )
 
         # Define the research query
@@ -592,49 +598,65 @@ class MarketResearchFlow(Flow[MarketResearchState]):
         1. Key market trends
         2. Market size
         3. Major competitors
-        
+
         Format your response according to the specified structure.
         """
 
-        # Execute the analysis
-        result = analyst.kickoff(query)
-        self.state.analysis = cast(MarketAnalysis, result.pydantic)
-        return result.pydantic
+        # Execute the analysis with structured output format
+        result = await analyst.kickoff_async(query, response_format=MarketAnalysis)
+        if result.pydantic:
+            print("result", result.pydantic)
+        else:
+            print("result", result)
+
+        # Return the analysis to update the state
+        return {"analysis": result.pydantic}
 
     @listen(analyze_market)
-    def present_results(self):
-        analysis = self.state.analysis
-        if analysis is None:
-            print("No analysis results available")
-            return
-
+    def present_results(self, analysis) -> None:
         print("\nMarket Analysis Results")
         print("=====================")
 
-        print("\nKey Market Trends:")
-        for trend in analysis.key_trends:
-            print(f"- {trend}")
+        if isinstance(analysis, dict):
+            # If we got a dict with 'analysis' key, extract the actual analysis object
+            market_analysis = analysis.get("analysis")
+        else:
+            market_analysis = analysis
 
-        print(f"\nMarket Size: {analysis.market_size}")
+        if market_analysis and isinstance(market_analysis, MarketAnalysis):
+            print("\nKey Market Trends:")
+            for trend in market_analysis.key_trends:
+                print(f"- {trend}")
+
+            print(f"\nMarket Size: {market_analysis.market_size}")
+
+            print("\nMajor Competitors:")
+            for competitor in market_analysis.competitors:
+                print(f"- {competitor}")
+        else:
+            print("No structured analysis data available.")
+            print("Raw analysis:", analysis)
 
-        print("\nMajor Competitors:")
-        for competitor in analysis.competitors:
-            print(f"- {competitor}")
 
 # Usage example
-flow = MarketResearchFlow()
-result = flow.kickoff(inputs={"product": "AI-powered chatbots"})
+async def run_flow():
+    flow = MarketResearchFlow()
+    result = await flow.kickoff_async(inputs={"product": "AI-powered chatbots"})
+    return result
+
+
+# Run the flow
+if __name__ == "__main__":
+    asyncio.run(run_flow())
 ```
 
-This example demonstrates several key features of using LiteAgents in flows:
+This example demonstrates several key features of using Agents in flows:
 
 1. **Structured Output**: Using Pydantic models to define the expected output format (`MarketAnalysis`) ensures type safety and structured data throughout the flow.
 
 2. **State Management**: The flow state (`MarketResearchState`) maintains context between steps and stores both inputs and outputs.
 
-3. **Tool Integration**: LiteAgents can use tools (like `WebsiteSearchTool`) to enhance their capabilities.
-
-If you want to learn more about LiteAgents, check out the [LiteAgent](/concepts/lite-agent) page.
+3. **Tool Integration**: Agents can use tools (like `WebsiteSearchTool`) to enhance their capabilities.
 
 ## Adding Crews to Flows
 

docs/concepts/lite-agent.mdx

@@ -1,242 +0,0 @@
----
-title: LiteAgent
-description: A lightweight, single-purpose agent for simple autonomous tasks within the CrewAI framework.
-icon: feather
----
-
-## Overview
-
-A `LiteAgent` is a streamlined version of CrewAI's Agent, designed for simpler, standalone tasks that don't require the full complexity of a crew-based workflow. It's perfect for quick automations, single-purpose tasks, or when you need a lightweight solution.
-
-<Tip>
-  Think of a LiteAgent as a specialized worker that excels at individual tasks.
-  While regular Agents are team players in a crew, LiteAgents are solo
-  performers optimized for specific operations.
-</Tip>
-
-## LiteAgent Attributes
-
-| Attribute                        | Parameter         | Type                   | Description                                                     |
-| :------------------------------- | :---------------- | :--------------------- | :-------------------------------------------------------------- |
-| **Role**                         | `role`            | `str`                  | Defines the agent's function and expertise.                     |
-| **Goal**                         | `goal`            | `str`                  | The specific objective that guides the agent's actions.         |
-| **Backstory**                    | `backstory`       | `str`                  | Provides context and personality to the agent.                  |
-| **LLM** _(optional)_             | `llm`             | `Union[str, LLM, Any]` | Language model powering the agent. Defaults to "gpt-4".         |
-| **Tools** _(optional)_           | `tools`           | `List[BaseTool]`       | Capabilities available to the agent. Defaults to an empty list. |
-| **Verbose** _(optional)_         | `verbose`         | `bool`                 | Enable detailed execution logs. Default is False.               |
-| **Response Format** _(optional)_ | `response_format` | `Type[BaseModel]`      | Pydantic model for structured output. Optional.                 |
-
-## Creating a LiteAgent
-
-Here's a simple example of creating and using a standalone LiteAgent:
-
-```python
-from typing import List, cast
-
-from crewai_tools import SerperDevTool
-from pydantic import BaseModel, Field
-
-from crewai.lite_agent import LiteAgent
-
-
-# Define a structured output format
-class MovieReview(BaseModel):
-    title: str = Field(description="The title of the movie")
-    rating: float = Field(description="Rating out of 10")
-    pros: List[str] = Field(description="List of positive aspects")
-    cons: List[str] = Field(description="List of negative aspects")
-
-
-# Create a LiteAgent
-critic = LiteAgent(
-    role="Movie Critic",
-    goal="Provide insightful movie reviews",
-    backstory="You are an experienced film critic known for balanced, thoughtful reviews.",
-    tools=[SerperDevTool()],
-    verbose=True,
-    response_format=MovieReview,
-)
-
-# Use the agent
-query = """
-Review the movie 'Inception'. Include:
-1. Your rating out of 10
-2. Key positive aspects
-3. Areas that could be improved
-"""
-
-result = critic.kickoff(query)
-
-
-# Access the structured output
-review = cast(MovieReview, result.pydantic)
-print(f"\nMovie Review: {review.title}")
-print(f"Rating: {review.rating}/10")
-print("\nPros:")
-for pro in review.pros:
-    print(f"- {pro}")
-print("\nCons:")
-for con in review.cons:
-    print(f"- {con}")
-
-```
-
-This example demonstrates the core features of a LiteAgent:
-
-- Structured output using Pydantic models
-- Tool integration with WebSearchTool
-- Simple execution with `kickoff()`
-- Easy access to both raw and structured results
-
-## Using LiteAgent in a Flow
-
-For more complex scenarios, you can integrate LiteAgents into a Flow. Here's an example of a market research flow:
-
-````python
-from typing import List
-from pydantic import BaseModel, Field
-from crewai.flow.flow import Flow, start, listen
-from crewai.lite_agent import LiteAgent
-from crewai.tools import WebSearchTool
-
-# Define a structured output format
-class MarketAnalysis(BaseModel):
-    key_trends: List[str] = Field(description="List of identified market trends")
-    market_size: str = Field(description="Estimated market size")
-    competitors: List[str] = Field(description="Major competitors in the space")
-
-# Define flow state
-class MarketResearchState(BaseModel):
-    product: str = ""
-    analysis: MarketAnalysis = None
-
-# Create a flow class
-class MarketResearchFlow(Flow[MarketResearchState]):
-    @start()
-    def initialize_research(self, product: str):
-        print(f"Starting market research for {product}")
-        self.state.product = product
-
-    @listen(initialize_research)
-    async def analyze_market(self):
-        # Create a LiteAgent for market research
-        analyst = LiteAgent(
-            role="Market Research Analyst",
-            goal=f"Analyze the market for {self.state.product}",
-            backstory="You are an experienced market analyst with expertise in "
-                     "identifying market trends and opportunities.",
-            tools=[WebSearchTool()],
-            verbose=True,
-            response_format=MarketAnalysis
-        )
-
-        # Define the research query
-        query = f"""
-        Research the market for {self.state.product}. Include:
-        1. Key market trends
-        2. Market size
-        3. Major competitors
-
-        Format your response according to the specified structure.
-        """
-
-        # Execute the analysis
-        result = await analyst.kickoff_async(query)
-        self.state.analysis = result.pydantic
-        return result.pydantic
-
-    @listen(analyze_market)
-    def present_results(self):
-        analysis = self.state.analysis
-        print("\nMarket Analysis Results")
-        print("=====================")
-
-        print("\nKey Market Trends:")
-        for trend in analysis.key_trends:
-            print(f"- {trend}")
-
-        print(f"\nMarket Size: {analysis.market_size}")
-
-        print("\nMajor Competitors:")
-        for competitor in analysis.competitors:
-            print(f"- {competitor}")
-
-# Usage example
-import asyncio
-
-async def run_flow():
-    flow = MarketResearchFlow()
-    result = await flow.kickoff(inputs={"product": "AI-powered chatbots"})
-    return result
-
-# Run the flow
-if __name__ == "__main__":
-    asyncio.run(run_flow())
-
-## Key Features
-
-### 1. Simplified Setup
-Unlike regular Agents, LiteAgents are designed for quick setup and standalone operation. They don't require crew configuration or task management.
-
-### 2. Structured Output
-LiteAgents support Pydantic models for response formatting, making it easy to get structured, type-safe data from your agent's operations.
-
-### 3. Tool Integration
-Just like regular Agents, LiteAgents can use tools to enhance their capabilities:
-```python
-from crewai.tools import SerperDevTool, CalculatorTool
-
-agent = LiteAgent(
-    role="Research Assistant",
-    goal="Find and analyze information",
-    tools=[SerperDevTool(), CalculatorTool()],
-    verbose=True
-)
-````
-
-### 4. Async Support
-
-LiteAgents support asynchronous execution through the `kickoff_async` method, making them suitable for non-blocking operations in your application.
-
-## Response Formatting
-
-LiteAgents support structured output through Pydantic models using the `response_format` parameter. This feature ensures type safety and consistent output structure, making it easier to work with agent responses in your application.
-
-### Basic Usage
-
-```python
-from pydantic import BaseModel, Field
-
-class SearchResult(BaseModel):
-    title: str = Field(description="The title of the found content")
-    summary: str = Field(description="A brief summary of the content")
-    relevance_score: float = Field(description="Relevance score from 0 to 1")
-
-agent = LiteAgent(
-    role="Search Specialist",
-    goal="Find and summarize relevant information",
-    response_format=SearchResult
-)
-
-result = await agent.kickoff_async("Find information about quantum computing")
-print(f"Title: {result.pydantic.title}")
-print(f"Summary: {result.pydantic.summary}")
-print(f"Relevance: {result.pydantic.relevance_score}")
-```
-
-### Handling Responses
-
-When using `response_format`, the agent's response will be available in two forms:
-
-1. **Raw Response**: Access the unstructured string response
-
-   ```python
-   result = await agent.kickoff_async("Analyze the market")
-   print(result.raw)  # Original LLM response
-   ```
-
-2. **Structured Response**: Access the parsed Pydantic model
-   ```python
-   print(result.pydantic)  # Parsed response as Pydantic model
-   print(result.pydantic.dict())  # Convert to dictionary
-   ```

docs/docs.json

@@ -66,7 +66,6 @@
               "concepts/tasks",
               "concepts/crews",
               "concepts/flows",
-              "concepts/lite-agent",
               "concepts/knowledge",
               "concepts/llms",
               "concepts/processes",
@@ -77,9 +76,7 @@
               "concepts/testing",
               "concepts/cli",
               "concepts/tools",
-              "concepts/event-listener",
-              "concepts/langchain-tools",
-              "concepts/llamaindex-tools"
+              "concepts/event-listener"
             ]
           },
           {
@@ -98,7 +95,9 @@
               "how-to/kickoff-async",
               "how-to/kickoff-for-each",
               "how-to/replay-tasks-from-latest-crew-kickoff",
-              "how-to/conditional-tasks"
+              "how-to/conditional-tasks",
+              "how-to/langchain-tools",
+              "how-to/llamaindex-tools"
             ]
           },
           {
@@ -197,6 +196,11 @@
           "anchor": "Community",
           "href": "https://community.crewai.com",
           "icon": "discourse"
+        },
+        {
+          "anchor": "Tutorials",
+          "href": "https://www.youtube.com/@crewAIInc",
+          "icon": "youtube"
         }
       ]
     }
@@ -231,4 +235,4 @@
       "reddit": "https://www.reddit.com/r/crewAIInc/"
     }
   }
-}
+}

docs/guides/flows/first-flow.mdx

@@ -263,6 +263,7 @@ Let's create our flow in the `main.py` file:
 ```python
 #!/usr/bin/env python
 import json
+import os
 from typing import List, Dict
 from pydantic import BaseModel, Field
 from crewai import LLM
@@ -341,6 +342,9 @@ class GuideCreatorFlow(Flow[GuideCreatorState]):
         outline_dict = json.loads(response)
         self.state.guide_outline = GuideOutline(**outline_dict)
 
+        # Ensure output directory exists before saving
+        os.makedirs("output", exist_ok=True)
+
         # Save the outline to a file
         with open("output/guide_outline.json", "w") as f:
             json.dump(outline_dict, f, indent=2)

docs/installation.mdx

@@ -4,6 +4,21 @@ description: Get started with CrewAI - Install, configure, and build your first
 icon: wrench
 ---
 
+## Video Tutorial
+Watch this video tutorial for a step-by-step demonstration of the installation process:
+
+<iframe
+  width="100%"
+  height="400"
+  src="https://www.youtube.com/embed/-kSOTtYzgEw"
+  title="CrewAI Installation Guide"
+  frameborder="0"
+  style={{ borderRadius: '10px' }}
+  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
+  allowfullscreen
+></iframe>
+
+## Text Tutorial
 <Note>
   **Python Version Requirements**
 

docs/tools/weaviatevectorsearchtool.mdx

@@ -25,7 +25,7 @@ uv add weaviate-client
 To effectively use the `WeaviateVectorSearchTool`, follow these steps:
 
 1. **Package Installation**: Confirm that the `crewai[tools]` and `weaviate-client` packages are installed in your Python environment.
-2. **Weaviate Setup**: Set up a Weaviate cluster. You can follow the [Weaviate documentation](https://weaviate.io/developers/wcs/connect) for instructions.
+2. **Weaviate Setup**: Set up a Weaviate cluster. You can follow the [Weaviate documentation](https://weaviate.io/developers/wcs/manage-clusters/connect) for instructions.
 3. **API Keys**: Obtain your Weaviate cluster URL and API key.
 4. **OpenAI API Key**: Ensure you have an OpenAI API key set in your environment variables as `OPENAI_API_KEY`.
 
@@ -161,4 +161,4 @@ rag_agent = Agent(
 
 ## Conclusion
 
-The `WeaviateVectorSearchTool` provides a powerful way to search for semantically similar documents in a Weaviate vector database. By leveraging vector embeddings, it enables more accurate and contextually relevant search results compared to traditional keyword-based searches. This tool is particularly useful for applications that require finding information based on meaning rather than exact matches. 
+The `WeaviateVectorSearchTool` provides a powerful way to search for semantically similar documents in a Weaviate vector database. By leveraging vector embeddings, it enables more accurate and contextually relevant search results compared to traditional keyword-based searches. This tool is particularly useful for applications that require finding information based on meaning rather than exact matches. 

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.108.0"
+version = "0.114.0"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
 requires-python = ">=3.10,<3.13"

src/crewai/__init__.py

@@ -17,7 +17,7 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.108.0"
+__version__ = "0.114.0"
 __all__ = [
     "Agent",
     "Crew",

src/crewai/agent.py

@@ -1,7 +1,6 @@
-import re
 import shutil
 import subprocess
-from typing import Any, Dict, List, Literal, Optional, Sequence, Union
+from typing import Any, Dict, List, Literal, Optional, Sequence, Type, Union
 
 from pydantic import Field, InstanceOf, PrivateAttr, model_validator
 
@@ -11,6 +10,7 @@ from crewai.agents.crew_agent_executor import CrewAgentExecutor
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.utils.knowledge_utils import extract_knowledge_context
+from crewai.lite_agent import LiteAgent, LiteAgentOutput
 from crewai.llm import BaseLLM
 from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.security import Fingerprint
@@ -449,3 +449,75 @@ class Agent(BaseAgent):
 
     def set_fingerprint(self, fingerprint: Fingerprint):
         self.security_config.fingerprint = fingerprint
+
+    def kickoff(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        response_format: Optional[Type[Any]] = None,
+    ) -> LiteAgentOutput:
+        """
+        Execute the agent with the given messages using a LiteAgent instance.
+
+        This method is useful when you want to use the Agent configuration but
+        with the simpler and more direct execution flow of LiteAgent.
+
+        Args:
+            messages: Either a string query or a list of message dictionaries.
+                     If a string is provided, it will be converted to a user message.
+                     If a list is provided, each dict should have 'role' and 'content' keys.
+            response_format: Optional Pydantic model for structured output.
+
+        Returns:
+            LiteAgentOutput: The result of the agent execution.
+        """
+        lite_agent = LiteAgent(
+            role=self.role,
+            goal=self.goal,
+            backstory=self.backstory,
+            llm=self.llm,
+            tools=self.tools or [],
+            max_iterations=self.max_iter,
+            max_execution_time=self.max_execution_time,
+            respect_context_window=self.respect_context_window,
+            verbose=self.verbose,
+            response_format=response_format,
+            i18n=self.i18n,
+            original_agent=self,
+        )
+
+        return lite_agent.kickoff(messages)
+
+    async def kickoff_async(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        response_format: Optional[Type[Any]] = None,
+    ) -> LiteAgentOutput:
+        """
+        Execute the agent asynchronously with the given messages using a LiteAgent instance.
+
+        This is the async version of the kickoff method.
+
+        Args:
+            messages: Either a string query or a list of message dictionaries.
+                     If a string is provided, it will be converted to a user message.
+                     If a list is provided, each dict should have 'role' and 'content' keys.
+            response_format: Optional Pydantic model for structured output.
+
+        Returns:
+            LiteAgentOutput: The result of the agent execution.
+        """
+        lite_agent = LiteAgent(
+            role=self.role,
+            goal=self.goal,
+            backstory=self.backstory,
+            llm=self.llm,
+            tools=self.tools or [],
+            max_iterations=self.max_iter,
+            max_execution_time=self.max_execution_time,
+            respect_context_window=self.respect_context_window,
+            verbose=self.verbose,
+            response_format=response_format,
+            i18n=self.i18n,
+        )
+
+        return await lite_agent.kickoff_async(messages)

src/crewai/cli/templates/crew/main.py

@@ -60,7 +60,7 @@ def test():
         "current_year": str(datetime.now().year)
     }
     try:
-        {{crew_name}}().crew().test(n_iterations=int(sys.argv[1]), openai_model_name=sys.argv[2], inputs=inputs)
+        {{crew_name}}().crew().test(n_iterations=int(sys.argv[1]), eval_llm=sys.argv[2], inputs=inputs)
 
     except Exception as e:
         raise Exception(f"An error occurred while testing the crew: {e}")

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

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.108.0,<1.0.0"
+    "crewai[tools]>=0.114.0,<1.0.0"
 ]
 
 [project.scripts]

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

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.108.0,<1.0.0",
+    "crewai[tools]>=0.114.0,<1.0.0",
 ]
 
 [project.scripts]

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

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.108.0"
+    "crewai[tools]>=0.114.0"
 ]
 
 [tool.crewai]

src/crewai/flow/flow.py

@@ -1043,6 +1043,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
             import traceback
 
             traceback.print_exc()
+            raise
 
     def _log_flow_event(
         self, message: str, color: str = "yellow", level: str = "info"

src/crewai/lite_agent.py

@@ -1,6 +1,4 @@
 import asyncio
-import json
-import re
 import uuid
 from datetime import datetime
 from typing import Any, Callable, Dict, List, Optional, Type, Union, cast
@@ -49,11 +47,6 @@ from crewai.utilities.events.llm_events import (
     LLMCallStartedEvent,
     LLMCallType,
 )
-from crewai.utilities.events.tool_usage_events import (
-    ToolUsageErrorEvent,
-    ToolUsageFinishedEvent,
-    ToolUsageStartedEvent,
-)
 from crewai.utilities.llm_utils import create_llm
 from crewai.utilities.printer import Printer
 from crewai.utilities.token_counter_callback import TokenCalcHandler
@@ -157,6 +150,10 @@ class LiteAgent(BaseModel):
         default=[], description="Results of the tools used by the agent."
     )
 
+    # Reference of Agent
+    original_agent: Optional[BaseAgent] = Field(
+        default=None, description="Reference to the agent that created this LiteAgent"
+    )
     # Private Attributes
     _parsed_tools: List[CrewStructuredTool] = PrivateAttr(default_factory=list)
     _token_process: TokenProcess = PrivateAttr(default_factory=TokenProcess)
@@ -165,7 +162,7 @@ class LiteAgent(BaseModel):
     _messages: List[Dict[str, str]] = PrivateAttr(default_factory=list)
     _iterations: int = PrivateAttr(default=0)
     _printer: Printer = PrivateAttr(default_factory=Printer)
-
+    
     @model_validator(mode="after")
     def setup_llm(self):
         """Set up the LLM and other components after initialization."""
@@ -414,18 +411,6 @@ class LiteAgent(BaseModel):
                 formatted_answer = process_llm_response(answer, self.use_stop_words)
 
                 if isinstance(formatted_answer, AgentAction):
-                    # Emit tool usage started event
-                    crewai_event_bus.emit(
-                        self,
-                        event=ToolUsageStartedEvent(
-                            agent_key=self.key,
-                            agent_role=self.role,
-                            tool_name=formatted_answer.tool,
-                            tool_args=formatted_answer.tool_input,
-                            tool_class=formatted_answer.tool,
-                        ),
-                    )
-
                     try:
                         tool_result = execute_tool_and_check_finality(
                             agent_action=formatted_answer,
@@ -433,34 +418,9 @@ class LiteAgent(BaseModel):
                             i18n=self.i18n,
                             agent_key=self.key,
                             agent_role=self.role,
-                        )
-                        # Emit tool usage finished event
-                        crewai_event_bus.emit(
-                            self,
-                            event=ToolUsageFinishedEvent(
-                                agent_key=self.key,
-                                agent_role=self.role,
-                                tool_name=formatted_answer.tool,
-                                tool_args=formatted_answer.tool_input,
-                                tool_class=formatted_answer.tool,
-                                started_at=datetime.now(),
-                                finished_at=datetime.now(),
-                                output=tool_result.result,
-                            ),
+                            agent=self.original_agent,
                         )
                     except Exception as e:
-                        # Emit tool usage error event
-                        crewai_event_bus.emit(
-                            self,
-                            event=ToolUsageErrorEvent(
-                                agent_key=self.key,
-                                agent_role=self.role,
-                                tool_name=formatted_answer.tool,
-                                tool_args=formatted_answer.tool_input,
-                                tool_class=formatted_answer.tool,
-                                error=str(e),
-                            ),
-                        )
                         raise e
 
                     formatted_answer = handle_agent_action_core(

src/crewai/llm.py

@@ -707,15 +707,6 @@ class LLM(BaseLLM):
                     function_name, lambda: None
                 )  # Ensure fn is always a callable
                 logging.error(f"Error executing function '{function_name}': {e}")
-                crewai_event_bus.emit(
-                    self,
-                    event=ToolExecutionErrorEvent(
-                        tool_name=function_name,
-                        tool_args=function_args,
-                        tool_class=fn,
-                        error=str(e),
-                    ),
-                )
                 crewai_event_bus.emit(
                     self,
                     event=LLMCallFailedEvent(error=f"Tool execution error: {str(e)}"),

src/crewai/memory/external/external_memory.py

@@ -1,4 +1,4 @@
-from typing import TYPE_CHECKING, Any, Dict, Optional, Self
+from typing import TYPE_CHECKING, Any, Dict, Optional
 
 from crewai.memory.external.external_memory_item import ExternalMemoryItem
 from crewai.memory.memory import Memory
@@ -52,7 +52,7 @@ class ExternalMemory(Memory):
     def reset(self) -> None:
         self.storage.reset()
 
-    def set_crew(self, crew: Any) -> Self:
+    def set_crew(self, crew: Any) -> "ExternalMemory":
         super().set_crew(crew)
 
         if not self.storage:

src/crewai/memory/memory.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Optional, Self
+from typing import Any, Dict, List, Optional
 
 from pydantic import BaseModel
 
@@ -38,6 +38,6 @@ class Memory(BaseModel):
             query=query, limit=limit, score_threshold=score_threshold
         )
 
-    def set_crew(self, crew: Any) -> Self:
+    def set_crew(self, crew: Any) -> "Memory":
         self.crew = crew
         return self

src/crewai/tools/base_tool.py

@@ -1,3 +1,4 @@
+import asyncio
 import warnings
 from abc import ABC, abstractmethod
 from inspect import signature
@@ -65,7 +66,13 @@ class BaseTool(BaseModel, ABC):
         **kwargs: Any,
     ) -> Any:
         print(f"Using Tool: {self.name}")
-        return self._run(*args, **kwargs)
+        result = self._run(*args, **kwargs)
+
+        # If _run is async, we safely run it
+        if asyncio.iscoroutine(result):
+            return asyncio.run(result)
+
+        return result
 
     @abstractmethod
     def _run(
@@ -244,9 +251,13 @@ def to_langchain(
     return [t.to_structured_tool() if isinstance(t, BaseTool) else t for t in tools]
 
 
-def tool(*args):
+def tool(*args, result_as_answer=False):
     """
     Decorator to create a tool from a function.
+    
+    Args:
+        *args: Positional arguments, either the function to decorate or the tool name.
+        result_as_answer: Flag to indicate if the tool result should be used as the final agent answer.
     """
 
     def _make_with_name(tool_name: str) -> Callable:
@@ -272,6 +283,7 @@ def tool(*args):
                 description=f.__doc__,
                 func=f,
                 args_schema=args_schema,
+                result_as_answer=result_as_answer,
             )
 
         return _make_tool

src/crewai/tools/tool_usage.py

@@ -2,7 +2,6 @@ import ast
 import datetime
 import json
 import time
-from dataclasses import dataclass
 from difflib import SequenceMatcher
 from json import JSONDecodeError
 from textwrap import dedent
@@ -26,6 +25,7 @@ from crewai.utilities.events.tool_usage_events import (
     ToolSelectionErrorEvent,
     ToolUsageErrorEvent,
     ToolUsageFinishedEvent,
+    ToolUsageStartedEvent,
     ToolValidateInputErrorEvent,
 )
 
@@ -166,6 +166,21 @@ class ToolUsage:
                 if self.task:
                     self.task.increment_tools_errors()
 
+        if self.agent:
+            event_data = {
+                "agent_key": self.agent.key,
+                "agent_role": self.agent.role,
+                "tool_name": self.action.tool,
+                "tool_args": self.action.tool_input,
+                "tool_class": self.action.tool,
+                "agent": self.agent,
+            }
+
+            if self.agent.fingerprint:
+                event_data.update(self.agent.fingerprint)
+
+            crewai_event_bus.emit(self,ToolUsageStartedEvent(**event_data))
+            
         started_at = time.time()
         from_cache = False
         result = None  # type: ignore

src/crewai/utilities/agent_utils.py

@@ -16,7 +16,6 @@ from crewai.tools.base_tool import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.tools.tool_types import ToolResult
 from crewai.utilities import I18N, Printer
-from crewai.utilities.events.tool_usage_events import ToolUsageStartedEvent
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
 )

src/crewai/utilities/tool_utils.py

@@ -5,11 +5,6 @@ from crewai.security import Fingerprint
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.tools.tool_types import ToolResult
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
-from crewai.utilities.events import crewai_event_bus
-from crewai.utilities.events.tool_usage_events import (
-    ToolUsageErrorEvent,
-    ToolUsageStartedEvent,
-)
 from crewai.utilities.i18n import I18N
 
 
@@ -42,10 +37,8 @@ def execute_tool_and_check_finality(
         ToolResult containing the execution result and whether it should be treated as a final answer
     """
     try:
-        # Create tool name to tool map
         tool_name_to_tool_map = {tool.name: tool for tool in tools}
 
-        # Emit tool usage event if agent info is available
         if agent_key and agent_role and agent:
             fingerprint_context = fingerprint_context or {}
             if agent:
@@ -59,22 +52,6 @@ def execute_tool_and_check_finality(
                         except Exception as e:
                             raise ValueError(f"Failed to set fingerprint: {e}")
 
-            event_data = {
-                "agent_key": agent_key,
-                "agent_role": agent_role,
-                "tool_name": agent_action.tool,
-                "tool_args": agent_action.tool_input,
-                "tool_class": agent_action.tool,
-                "agent": agent,
-            }
-            event_data.update(fingerprint_context)
-            crewai_event_bus.emit(
-                agent,
-                event=ToolUsageStartedEvent(
-                    **event_data,
-                ),
-            )
-
         # Create tool usage instance
         tool_usage = ToolUsage(
             tools_handler=tools_handler,
@@ -110,17 +87,4 @@ def execute_tool_and_check_finality(
         return ToolResult(tool_result, False)
 
     except Exception as e:
-        # Emit error event if agent info is available
-        if agent_key and agent_role and agent:
-            crewai_event_bus.emit(
-                agent,
-                event=ToolUsageErrorEvent(
-                    agent_key=agent_key,
-                    agent_role=agent_role,
-                    tool_name=agent_action.tool,
-                    tool_args=agent_action.tool_input,
-                    tool_class=agent_action.tool,
-                    error=str(e),
-                ),
-            )
         raise e

tests/cassettes/test_lite_agent_created_with_correct_parameters[False].yaml

@@ -0,0 +1,486 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour
+      personal goal is: Test Goal\n\nYou ONLY have access to the following tools,
+      and should NEVER make up tools that are not listed here:\n\nTool Name: search_web\nTool
+      Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Search the web for information about a topic.\nTool Name: calculate\nTool Arguments:
+      {''expression'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Calculate the result of a mathematical expression.\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 [search_web, calculate],
+      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": "Test query"}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1220'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=skEg5DBE_nQ5gLAsfGzhjTetiNUJ_Y2bXWLMsvjIi7s-1744222695-1.0.1.1-qyjwnTgJKwF54pRhf0YHxW_BUw6p7SC60kwFsF9XTq4i2u2mnFKVq4WbsgvQDeuDEIxyaNb.ngWUVOU1GIX1O2Hcxcdn6TSaJ8NXTQw28F8;
+        _cfuvid=Hwvd7n4RVfOZLGiOKPaHmYJC7h8rCQmlmnBgBsKqy4Y-1744222695443-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BKUIMCbxAr4MO0Ku8tDYBgJ30LGXi\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744222714,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"```\\nThought: I need more information
+      to understand what specific query to search for.\\nAction: search_web\\nAction
+      Input: {\\\"query\\\":\\\"Test query\\\"}\",\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 242,\n    \"completion_tokens\":
+      31,\n    \"total_tokens\": 273,\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_b376dfbbd5\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92dc01f9bd96cf41-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 09 Apr 2025 18:18:34 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '749'
+      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:
+      - '149999732'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_99e3ad4ee98371cc1c55a2f5c6ae3962
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour
+      personal goal is: Test Goal\n\nYou ONLY have access to the following tools,
+      and should NEVER make up tools that are not listed here:\n\nTool Name: search_web\nTool
+      Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Search the web for information about a topic.\nTool Name: calculate\nTool Arguments:
+      {''expression'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Calculate the result of a mathematical expression.\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 [search_web, calculate],
+      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": "Test query"}, {"role": "assistant", "content":
+      "```\nThought: I need more information to understand what specific query to
+      search for.\nAction: search_web\nAction Input: {\"query\":\"Test query\"}\nObservation:
+      Found information about Test query: This is a simulated search result for demonstration
+      purposes."}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1518'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=skEg5DBE_nQ5gLAsfGzhjTetiNUJ_Y2bXWLMsvjIi7s-1744222695-1.0.1.1-qyjwnTgJKwF54pRhf0YHxW_BUw6p7SC60kwFsF9XTq4i2u2mnFKVq4WbsgvQDeuDEIxyaNb.ngWUVOU1GIX1O2Hcxcdn6TSaJ8NXTQw28F8;
+        _cfuvid=Hwvd7n4RVfOZLGiOKPaHmYJC7h8rCQmlmnBgBsKqy4Y-1744222695443-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BKUINDYiGwrVyJU7wUoXCw3hft7yF\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744222715,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"```\\nThought: I now know the final answer\\nFinal
+      Answer: This is a simulated search result for demonstration purposes.\\n```\",\n
+      \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      295,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 321,\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_b376dfbbd5\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92dc02003c9ecf41-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 09 Apr 2025 18:18:35 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '531'
+      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:
+      - '149999667'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_dd9052c40d5d61ecc5eb141f49df3abe
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour
+      personal goal is: Test Goal\n\nYou ONLY have access to the following tools,
+      and should NEVER make up tools that are not listed here:\n\nTool Name: search_web\nTool
+      Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Search the web for information about a topic.\nTool Name: calculate\nTool Arguments:
+      {''expression'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Calculate the result of a mathematical expression.\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 [search_web, calculate],
+      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```\nIMPORTANT:
+      Your final answer MUST contain all the information requested in the following
+      format: {\n  \"test_field\": str\n}\n\nIMPORTANT: Ensure the final output does
+      not include any code block markers like ```json or ```python."}, {"role": "user",
+      "content": "Test query"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1451'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=skEg5DBE_nQ5gLAsfGzhjTetiNUJ_Y2bXWLMsvjIi7s-1744222695-1.0.1.1-qyjwnTgJKwF54pRhf0YHxW_BUw6p7SC60kwFsF9XTq4i2u2mnFKVq4WbsgvQDeuDEIxyaNb.ngWUVOU1GIX1O2Hcxcdn6TSaJ8NXTQw28F8;
+        _cfuvid=Hwvd7n4RVfOZLGiOKPaHmYJC7h8rCQmlmnBgBsKqy4Y-1744222695443-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BKUIN3xeM6JBgLjV5HQA8MTI2Uuem\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744222715,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"```\\nThought: I need to clarify what
+      specific information or topic the test query is targeting.\\nAction: search_web\\nAction
+      Input: {\\\"query\\\":\\\"What is the purpose of a test query in data retrieval?\\\"}\",\n
+      \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      288,\n    \"completion_tokens\": 43,\n    \"total_tokens\": 331,\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_b376dfbbd5\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92dc0204d91ccf41-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 09 Apr 2025 18:18:36 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '728'
+      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:
+      - '149999675'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_e792e993009ddfe84cfbb503560d88cf
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour
+      personal goal is: Test Goal\n\nYou ONLY have access to the following tools,
+      and should NEVER make up tools that are not listed here:\n\nTool Name: search_web\nTool
+      Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Search the web for information about a topic.\nTool Name: calculate\nTool Arguments:
+      {''expression'': {''description'': None, ''type'': ''str''}}\nTool Description:
+      Calculate the result of a mathematical expression.\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 [search_web, calculate],
+      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```\nIMPORTANT:
+      Your final answer MUST contain all the information requested in the following
+      format: {\n  \"test_field\": str\n}\n\nIMPORTANT: Ensure the final output does
+      not include any code block markers like ```json or ```python."}, {"role": "user",
+      "content": "Test query"}, {"role": "assistant", "content": "```\nThought: I
+      need to clarify what specific information or topic the test query is targeting.\nAction:
+      search_web\nAction Input: {\"query\":\"What is the purpose of a test query in
+      data retrieval?\"}\nObservation: Found information about What is the purpose
+      of a test query in data retrieval?: This is a simulated search result for demonstration
+      purposes."}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1846'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=skEg5DBE_nQ5gLAsfGzhjTetiNUJ_Y2bXWLMsvjIi7s-1744222695-1.0.1.1-qyjwnTgJKwF54pRhf0YHxW_BUw6p7SC60kwFsF9XTq4i2u2mnFKVq4WbsgvQDeuDEIxyaNb.ngWUVOU1GIX1O2Hcxcdn6TSaJ8NXTQw28F8;
+        _cfuvid=Hwvd7n4RVfOZLGiOKPaHmYJC7h8rCQmlmnBgBsKqy4Y-1744222695443-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BKUIOqyLDCIZv6YIz1hlaW479SIzg\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744222716,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"```\\nThought: I now know the final answer\\nFinal
+      Answer: {\\n  \\\"test_field\\\": \\\"A test query is utilized to evaluate the
+      functionality, performance, and accuracy of data retrieval systems, ensuring
+      they return expected results.\\\"\\n}\\n```\",\n        \"refusal\": null,\n
+      \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 362,\n    \"completion_tokens\":
+      49,\n    \"total_tokens\": 411,\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_b376dfbbd5\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92dc020a3defcf41-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 09 Apr 2025 18:18:37 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '805'
+      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:
+      - '149999588'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_3b6c80fd3066b9e0054d0d2280bc4c98
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_lite_agent_returns_usage_metrics_async.yaml

@@ -0,0 +1,249 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Research Assistant.
+      You are a helpful research assistant who can search for information about the
+      population of Tokyo.\nYour personal goal is: Find information about the population
+      of Tokyo\n\nYou ONLY have access to the following tools, and should NEVER make
+      up tools that are not listed here:\n\nTool Name: search_web\nTool Arguments:
+      {''query'': {''description'': None, ''type'': ''str''}}\nTool Description: Search
+      the web for information about a topic.\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 [search_web], 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":
+      "What is the population of Tokyo? Return your strucutred output in JSON format
+      with the following fields: summary, confidence"}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1290'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=u769MG.poap6iEjFpbByMFUC0FygMEqYSurr5DfLbas-1743447969501-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BKUM5MZbz4TG6qmUtTrgKo8gI48FO\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744222945,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"```\\nThought: I need to find the current
+      population of Tokyo.\\nAction: search_web\\nAction Input: {\\\"query\\\":\\\"current
+      population of Tokyo 2023\\\"}\",\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 248,\n    \"completion_tokens\":
+      33,\n    \"total_tokens\": 281,\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_b376dfbbd5\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92dc079f8e5a7ab0-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 09 Apr 2025 18:22:26 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=1F.UUVSjZyp8QMRT0dTQXUJc5WlGpC3xAx4FY7KCQbs-1744222946-1.0.1.1-vcXIZcokSjfxyFeoTTUAWmBGmJpv0ss9iFqt5EJVZGE1PvSV2ov0erCS.KIo0xItBMuX_MtCgDSaYMPI3L9QDsLatWqfUFieHiFh0CrX4h8;
+        path=/; expires=Wed, 09-Apr-25 18:52:26 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=RbJuVW8hReYElyyghEbAFletdnJZ2mk5rn9D8EGuyNk-1744222946580-0.0.1.1-604800000;
+        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
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1282'
+      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:
+      - '149999713'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_845ed875afd48dee3d88f33cbab88cc2
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Research Assistant.
+      You are a helpful research assistant who can search for information about the
+      population of Tokyo.\nYour personal goal is: Find information about the population
+      of Tokyo\n\nYou ONLY have access to the following tools, and should NEVER make
+      up tools that are not listed here:\n\nTool Name: search_web\nTool Arguments:
+      {''query'': {''description'': None, ''type'': ''str''}}\nTool Description: Search
+      the web for information about a topic.\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 [search_web], 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":
+      "What is the population of Tokyo? Return your strucutred output in JSON format
+      with the following fields: summary, confidence"}, {"role": "assistant", "content":
+      "```\nThought: I need to find the current population of Tokyo.\nAction: search_web\nAction
+      Input: {\"query\":\"current population of Tokyo 2023\"}\nObservation: Tokyo''s
+      population in 2023 was approximately 21 million people in the city proper, and
+      37 million in the greater metropolitan area."}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1619'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=RbJuVW8hReYElyyghEbAFletdnJZ2mk5rn9D8EGuyNk-1744222946580-0.0.1.1-604800000;
+        __cf_bm=1F.UUVSjZyp8QMRT0dTQXUJc5WlGpC3xAx4FY7KCQbs-1744222946-1.0.1.1-vcXIZcokSjfxyFeoTTUAWmBGmJpv0ss9iFqt5EJVZGE1PvSV2ov0erCS.KIo0xItBMuX_MtCgDSaYMPI3L9QDsLatWqfUFieHiFh0CrX4h8
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BKUM69pnk6VLn5rpDjGdg21mOxFke\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1744222946,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"```\\nThought: I now know the final answer\\nFinal
+      Answer: {\\\"summary\\\":\\\"The population of Tokyo is approximately 21 million
+      in the city proper and 37 million in the greater metropolitan area as of 2023.\\\",\\\"confidence\\\":\\\"high\\\"}\\n```\",\n
+      \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      315,\n    \"completion_tokens\": 51,\n    \"total_tokens\": 366,\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_b376dfbbd5\"\n}\n"
+    headers:
+      CF-RAY:
+      - 92dc07a8ac9f7ab0-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 09 Apr 2025 18:22:27 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1024'
+      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:
+      - '149999642'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_d72860d8629025988b1170e939bc1f20
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_tool_execution_error_event.yaml

@@ -1,112 +0,0 @@
-interactions:
-- request:
-    body: '{"messages": [{"role": "user", "content": "Use the failing tool"}], "model":
-      "gpt-4o-mini", "stop": [], "tools": [{"type": "function", "function": {"name":
-      "failing_tool", "description": "This tool always fails.", "parameters": {"type":
-      "object", "properties": {"param": {"type": "string", "description": "A test
-      parameter"}}, "required": ["param"]}}}]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '353'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.8
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-B2P4zoJZuES7Aom8ugEq1modz5Vsl\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1739912761,\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_F6fJxISpMKUBIGV6dd2vjRNG\",\n            \"type\":
-      \"function\",\n            \"function\": {\n              \"name\": \"failing_tool\",\n
-      \             \"arguments\": \"{\\\"param\\\":\\\"test\\\"}\"\n            }\n
-      \         }\n        ],\n        \"refusal\": null\n      },\n      \"logprobs\":
-      null,\n      \"finish_reason\": \"tool_calls\"\n    }\n  ],\n  \"usage\": {\n
-      \   \"prompt_tokens\": 51,\n    \"completion_tokens\": 15,\n    \"total_tokens\":
-      66,\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_00428b782a\"\n}\n"
-    headers:
-      CF-RAY:
-      - 9140fa827f38eb1e-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 18 Feb 2025 21:06:02 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=xbuu3IQpCMh.43ZrqL1TRMECOc6QldgHV0hzOX1GrWI-1739912762-1.0.1.1-t7iyq5xMioPrwfeaHLvPT9rwRPp7Q9A9uIm69icH9dPxRD4xMA3cWqb1aXj1_e2IyAEQQWFe1UWjlmJ22aHh3Q;
-        path=/; expires=Tue, 18-Feb-25 21:36:02 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=x9l.Rhja8_wXDN.j8qcEU1PvvEqAwZp4Fd3s_aj4qwM-1739912762161-0.0.1.1-604800000;
-        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
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '861'
-      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:
-      - '149999978'
-      x-ratelimit-reset-requests:
-      - 2ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_8666ec3aa6677cb346ba00993556051d
-    http_version: HTTP/1.1
-    status_code: 200
-version: 1

tests/llm_test.py

@@ -395,51 +395,3 @@ def test_deepseek_r1_with_open_router():
     result = llm.call("What is the capital of France?")
     assert isinstance(result, str)
     assert "Paris" in result
-
-
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_tool_execution_error_event():
-    llm = LLM(model="gpt-4o-mini")
-
-    def failing_tool(param: str) -> str:
-        """This tool always fails."""
-        raise Exception("Tool execution failed!")
-
-    tool_schema = {
-        "type": "function",
-        "function": {
-            "name": "failing_tool",
-            "description": "This tool always fails.",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "param": {"type": "string", "description": "A test parameter"}
-                },
-                "required": ["param"],
-            },
-        },
-    }
-
-    received_events = []
-
-    @crewai_event_bus.on(ToolExecutionErrorEvent)
-    def event_handler(source, event):
-        received_events.append(event)
-
-    available_functions = {"failing_tool": failing_tool}
-
-    messages = [{"role": "user", "content": "Use the failing tool"}]
-
-    llm.call(
-        messages,
-        tools=[tool_schema],
-        available_functions=available_functions,
-    )
-
-    assert len(received_events) == 1
-    event = received_events[0]
-    assert isinstance(event, ToolExecutionErrorEvent)
-    assert event.tool_name == "failing_tool"
-    assert event.tool_args == {"param": "test"}
-    assert event.tool_class == failing_tool
-    assert "Tool execution failed!" in event.error

tests/test_lite_agent.py

@@ -4,8 +4,8 @@ from typing import cast
 import pytest
 from pydantic import BaseModel, Field
 
-from crewai import LLM
-from crewai.lite_agent import LiteAgent
+from crewai import LLM, Agent
+from crewai.lite_agent import LiteAgent, LiteAgentOutput
 from crewai.tools import BaseTool
 from crewai.utilities.events import crewai_event_bus
 from crewai.utilities.events.tool_usage_events import ToolUsageStartedEvent
@@ -63,12 +63,74 @@ class ResearchResult(BaseModel):
     sources: list[str] = Field(description="List of sources used")
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.parametrize("verbose", [True, False])
+def test_lite_agent_created_with_correct_parameters(monkeypatch, verbose):
+    """Test that LiteAgent is created with the correct parameters when Agent.kickoff() is called."""
+    # Create a test agent with specific parameters
+    llm = LLM(model="gpt-4o-mini")
+    custom_tools = [WebSearchTool(), CalculatorTool()]
+    max_iter = 10
+    max_execution_time = 300
+
+    agent = Agent(
+        role="Test Agent",
+        goal="Test Goal",
+        backstory="Test Backstory",
+        llm=llm,
+        tools=custom_tools,
+        max_iter=max_iter,
+        max_execution_time=max_execution_time,
+        verbose=verbose,
+    )
+
+    # Create a mock to capture the created LiteAgent
+    created_lite_agent = None
+    original_lite_agent = LiteAgent
+
+    # Define a mock LiteAgent class that captures its arguments
+    class MockLiteAgent(original_lite_agent):
+        def __init__(self, **kwargs):
+            nonlocal created_lite_agent
+            created_lite_agent = kwargs
+            super().__init__(**kwargs)
+
+    # Patch the LiteAgent class
+    monkeypatch.setattr("crewai.agent.LiteAgent", MockLiteAgent)
+
+    # Call kickoff to create the LiteAgent
+    agent.kickoff("Test query")
+
+    # Verify all parameters were passed correctly
+    assert created_lite_agent is not None
+    assert created_lite_agent["role"] == "Test Agent"
+    assert created_lite_agent["goal"] == "Test Goal"
+    assert created_lite_agent["backstory"] == "Test Backstory"
+    assert created_lite_agent["llm"] == llm
+    assert len(created_lite_agent["tools"]) == 2
+    assert isinstance(created_lite_agent["tools"][0], WebSearchTool)
+    assert isinstance(created_lite_agent["tools"][1], CalculatorTool)
+    assert created_lite_agent["max_iterations"] == max_iter
+    assert created_lite_agent["max_execution_time"] == max_execution_time
+    assert created_lite_agent["verbose"] == verbose
+    assert created_lite_agent["response_format"] is None
+
+    # Test with a response_format
+    monkeypatch.setattr("crewai.agent.LiteAgent", MockLiteAgent)
+
+    class TestResponse(BaseModel):
+        test_field: str
+
+    agent.kickoff("Test query", response_format=TestResponse)
+    assert created_lite_agent["response_format"] == TestResponse
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_lite_agent_with_tools():
-    """Test that LiteAgent can use tools."""
+    """Test that Agent can use tools."""
     # Create a LiteAgent with tools
     llm = LLM(model="gpt-4o-mini")
-    agent = LiteAgent(
+    agent = Agent(
         role="Research Assistant",
         goal="Find information about the population of Tokyo",
         backstory="You are a helpful research assistant who can search for information about the population of Tokyo.",
@@ -106,7 +168,7 @@ def test_lite_agent_with_tools():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_lite_agent_structured_output():
-    """Test that LiteAgent can return a simple structured output."""
+    """Test that Agent can return a simple structured output."""
 
     class SimpleOutput(BaseModel):
         """Simple structure for agent outputs."""
@@ -117,18 +179,18 @@ def test_lite_agent_structured_output():
     web_search_tool = WebSearchTool()
 
     llm = LLM(model="gpt-4o-mini")
-    agent = LiteAgent(
+    agent = Agent(
         role="Info Gatherer",
         goal="Provide brief information",
         backstory="You gather and summarize information quickly.",
         llm=llm,
         tools=[web_search_tool],
         verbose=True,
-        response_format=SimpleOutput,
     )
 
     result = agent.kickoff(
-        "What is the population of Tokyo? Return your strucutred output in JSON format with the following fields: summary, confidence"
+        "What is the population of Tokyo? Return your strucutred output in JSON format with the following fields: summary, confidence",
+        response_format=SimpleOutput,
     )
 
     print(f"\n=== Agent Result Type: {type(result)}")
@@ -155,7 +217,7 @@ def test_lite_agent_structured_output():
 def test_lite_agent_returns_usage_metrics():
     """Test that LiteAgent returns usage metrics."""
     llm = LLM(model="gpt-4o-mini")
-    agent = LiteAgent(
+    agent = Agent(
         role="Research Assistant",
         goal="Find information about the population of Tokyo",
         backstory="You are a helpful research assistant who can search for information about the population of Tokyo.",
@@ -170,3 +232,26 @@ def test_lite_agent_returns_usage_metrics():
 
     assert result.usage_metrics is not None
     assert result.usage_metrics["total_tokens"] > 0
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.asyncio
+async def test_lite_agent_returns_usage_metrics_async():
+    """Test that LiteAgent returns usage metrics when run asynchronously."""
+    llm = LLM(model="gpt-4o-mini")
+    agent = Agent(
+        role="Research Assistant",
+        goal="Find information about the population of Tokyo",
+        backstory="You are a helpful research assistant who can search for information about the population of Tokyo.",
+        llm=llm,
+        tools=[WebSearchTool()],
+        verbose=True,
+    )
+
+    result = await agent.kickoff_async(
+        "What is the population of Tokyo? Return your strucutred output in JSON format with the following fields: summary, confidence"
+    )
+    assert isinstance(result, LiteAgentOutput)
+    assert "21 million" in result.raw or "37 million" in result.raw
+    assert result.usage_metrics is not None
+    assert result.usage_metrics["total_tokens"] > 0

tests/tools/test_base_tool.py

@@ -1,4 +1,8 @@
-from typing import Callable
+import asyncio
+import inspect
+import unittest
+from typing import Any, Callable, Dict, List
+from unittest.mock import patch
 
 from crewai.tools import BaseTool, tool
 
@@ -100,3 +104,91 @@ def test_default_cache_function_is_true():
     my_tool = MyCustomTool()
     # Assert all the right attributes were defined
     assert my_tool.cache_function()
+
+
+def test_result_as_answer_in_tool_decorator():
+    @tool("Tool with result as answer", result_as_answer=True)
+    def my_tool_with_result_as_answer(question: str) -> str:
+        """This tool will return its result as the final answer."""
+        return question
+    
+    assert my_tool_with_result_as_answer.result_as_answer is True
+    
+    converted_tool = my_tool_with_result_as_answer.to_structured_tool()
+    assert converted_tool.result_as_answer is True
+    
+    @tool("Tool with default result_as_answer")
+    def my_tool_with_default(question: str) -> str:
+        """This tool uses the default result_as_answer value."""
+        return question
+    
+    assert my_tool_with_default.result_as_answer is False
+    
+    converted_tool = my_tool_with_default.to_structured_tool()
+    assert converted_tool.result_as_answer is False
+
+
+class SyncTool(BaseTool):
+    """Test implementation with a synchronous _run method"""
+    name: str = "sync_tool"
+    description: str = "A synchronous tool for testing"
+
+    def _run(self, input_text: str) -> str:
+        """Process input text synchronously."""
+        return f"Processed {input_text} synchronously"
+
+
+class AsyncTool(BaseTool):
+    """Test implementation with an asynchronous _run method"""
+    name: str = "async_tool"
+    description: str = "An asynchronous tool for testing"
+
+    async def _run(self, input_text: str) -> str:
+        """Process input text asynchronously."""
+        await asyncio.sleep(0.1)  # Simulate async operation
+        return f"Processed {input_text} asynchronously"
+
+
+def test_sync_run_returns_direct_result():
+    """Test that _run in a synchronous tool returns a direct result, not a coroutine."""
+    tool = SyncTool()
+    result = tool._run(input_text="hello")
+
+    assert not asyncio.iscoroutine(result)
+    assert result == "Processed hello synchronously"
+
+    run_result = tool.run(input_text="hello")
+    assert run_result == "Processed hello synchronously"
+
+
+def test_async_run_returns_coroutine():
+    """Test that _run in an asynchronous tool returns a coroutine object."""
+    tool = AsyncTool()
+    result = tool._run(input_text="hello")
+
+    assert asyncio.iscoroutine(result)
+    result.close()  # Clean up the coroutine
+
+
+def test_run_calls_asyncio_run_for_async_tools():
+    """Test that asyncio.run is called when using async tools."""
+    async_tool = AsyncTool()
+
+    with patch('asyncio.run') as mock_run:
+        mock_run.return_value = "Processed test asynchronously"
+        async_result = async_tool.run(input_text="test")
+
+        mock_run.assert_called_once()
+        assert async_result == "Processed test asynchronously"
+
+
+def test_run_does_not_call_asyncio_run_for_sync_tools():
+    """Test that asyncio.run is NOT called when using sync tools."""
+    sync_tool = SyncTool()
+
+    with patch('asyncio.run') as mock_run:
+        sync_result = sync_tool.run(input_text="test")
+
+        mock_run.assert_not_called()
+        assert sync_result == "Processed test synchronously"
+

uv.lock

@@ -1,19 +1,42 @@
 version = 1
-revision = 1
 requires-python = ">=3.10, <3.13"
 resolution-markers = [
-    "python_full_version < '3.11' and sys_platform == 'darwin'",
-    "python_full_version < '3.11' and platform_machine == 'aarch64' and sys_platform == 'linux'",
-    "(python_full_version < '3.11' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.11' and sys_platform != 'darwin' and sys_platform != 'linux')",
-    "python_full_version == '3.11.*' and sys_platform == 'darwin'",
-    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and sys_platform == 'linux'",
-    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform != 'darwin' and sys_platform != 'linux')",
-    "python_full_version >= '3.12' and python_full_version < '3.12.4' and sys_platform == 'darwin'",
-    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and sys_platform == 'linux'",
-    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and sys_platform != 'darwin' and sys_platform != 'linux')",
-    "python_full_version >= '3.12.4' and sys_platform == 'darwin'",
-    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and sys_platform == 'linux'",
-    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12.4' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version < '3.11' and platform_system == 'Darwin' and sys_platform == 'darwin'",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'darwin'",
+    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform == 'darwin') or (python_full_version < '3.11' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'darwin')",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Darwin' and sys_platform == 'linux'",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'linux'",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'linux'",
+    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_system == 'Darwin' and sys_platform != 'darwin') or (python_full_version < '3.11' and platform_system == 'Darwin' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux'",
+    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform != 'darwin') or (python_full_version < '3.11' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version == '3.11.*' and platform_system == 'Darwin' and sys_platform == 'darwin'",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'darwin'",
+    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform == 'darwin') or (python_full_version == '3.11.*' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'darwin')",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Darwin' and sys_platform == 'linux'",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'linux'",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'linux'",
+    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_system == 'Darwin' and sys_platform != 'darwin') or (python_full_version == '3.11.*' and platform_system == 'Darwin' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux'",
+    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform != 'darwin') or (python_full_version == '3.11.*' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system == 'Darwin' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'darwin'",
+    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform == 'darwin') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'darwin')",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Darwin' and sys_platform == 'linux'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'linux'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'linux'",
+    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_system == 'Darwin' and sys_platform != 'darwin') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system == 'Darwin' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux'",
+    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform != 'darwin') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12.4' and platform_system == 'Darwin' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'darwin'",
+    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform == 'darwin') or (python_full_version >= '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'darwin')",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Darwin' and sys_platform == 'linux'",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'linux'",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'linux'",
+    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_system == 'Darwin' and sys_platform != 'darwin') or (python_full_version >= '3.12.4' and platform_system == 'Darwin' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux'",
+    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform != 'darwin') or (python_full_version >= '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux')",
 ]
 
 [[package]]
@@ -321,7 +344,7 @@ name = "build"
 version = "1.2.2.post1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "(os_name == 'nt' and platform_machine != 'aarch64' and sys_platform == 'linux') or (os_name == 'nt' and sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "colorama", marker = "os_name == 'nt'" },
     { name = "importlib-metadata", marker = "python_full_version < '3.10.2'" },
     { name = "packaging" },
     { name = "pyproject-hooks" },
@@ -556,7 +579,7 @@ name = "click"
 version = "8.1.8"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "colorama", marker = "platform_system == 'Windows'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/b9/2e/0090cbf739cee7d23781ad4b89a9894a41538e4fcf4c31dcdd705b78eb8b/click-8.1.8.tar.gz", hash = "sha256:ed53c9d8990d83c2a27deae68e4ee337473f6330c040a31d4225c9574d16096a", size = 226593 }
 wheels = [
@@ -607,7 +630,7 @@ wheels = [
 
 [[package]]
 name = "crewai"
-version = "0.108.0"
+version = "0.114.0"
 source = { editable = "." }
 dependencies = [
     { name = "appdirs" },
@@ -722,7 +745,6 @@ requires-dist = [
     { name = "tomli-w", specifier = ">=1.1.0" },
     { name = "uv", specifier = ">=0.4.25" },
 ]
-provides-extras = ["tools", "embeddings", "agentops", "fastembed", "pdfplumber", "pandas", "openpyxl", "mem0", "docling", "aisuite"]
 
 [package.metadata.requires-dev]
 dev = [
@@ -2496,7 +2518,7 @@ version = "1.6.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "click" },
-    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "colorama", marker = "platform_system == 'Windows'" },
     { name = "ghp-import" },
     { name = "jinja2" },
     { name = "markdown" },
@@ -2677,7 +2699,7 @@ version = "2.10.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "pygments" },
-    { name = "pywin32", marker = "sys_platform == 'win32'" },
+    { name = "pywin32", marker = "platform_system == 'Windows'" },
     { name = "tqdm" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/3a/93/80ac75c20ce54c785648b4ed363c88f148bf22637e10c9863db4fbe73e74/mpire-2.10.2.tar.gz", hash = "sha256:f66a321e93fadff34585a4bfa05e95bd946cf714b442f51c529038eb45773d97", size = 271270 }
@@ -2924,7 +2946,7 @@ name = "nvidia-cudnn-cu12"
 version = "9.1.0.70"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/9f/fd/713452cd72343f682b1c7b9321e23829f00b842ceaedcda96e742ea0b0b3/nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl", hash = "sha256:165764f44ef8c61fcdfdfdbe769d687e06374059fbb388b6c89ecb0e28793a6f", size = 664752741 },
@@ -2951,9 +2973,9 @@ name = "nvidia-cusolver-cu12"
 version = "11.4.5.107"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
-    { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
-    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/bc/1d/8de1e5c67099015c834315e333911273a8c6aaba78923dd1d1e25fc5f217/nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd", size = 124161928 },
@@ -2964,7 +2986,7 @@ name = "nvidia-cusparse-cu12"
 version = "12.1.0.106"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/65/5b/cfaeebf25cd9fdec14338ccb16f6b2c4c7fa9163aefcf057d86b9cc248bb/nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c", size = 195958278 },
@@ -2975,6 +2997,7 @@ name = "nvidia-nccl-cu12"
 version = "2.20.5"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/c1/bb/d09dda47c881f9ff504afd6f9ca4f502ded6d8fc2f572cacc5e39da91c28/nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1fc150d5c3250b170b29410ba682384b14581db722b2531b0d8d33c595f33d01", size = 176238458 },
     { url = "https://files.pythonhosted.org/packages/4b/2a/0a131f572aa09f741c30ccd45a8e56316e8be8dfc7bc19bf0ab7cfef7b19/nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:057f6bf9685f75215d0c53bf3ac4a10b3e6578351de307abad9e18a99182af56", size = 176249402 },
 ]
 
@@ -2984,6 +3007,7 @@ version = "12.6.85"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/9d/d7/c5383e47c7e9bf1c99d5bd2a8c935af2b6d705ad831a7ec5c97db4d82f4f/nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:eedc36df9e88b682efe4309aa16b5b4e78c2407eac59e8c10a6a47535164369a", size = 19744971 },
+    { url = "https://files.pythonhosted.org/packages/31/db/dc71113d441f208cdfe7ae10d4983884e13f464a6252450693365e166dcf/nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cf4eaa7d4b6b543ffd69d6abfb11efdeb2db48270d94dfd3a452c24150829e41", size = 19270338 },
 ]
 
 [[package]]
@@ -3501,7 +3525,7 @@ name = "portalocker"
 version = "2.10.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "pywin32", marker = "sys_platform == 'win32'" },
+    { name = "pywin32", marker = "platform_system == 'Windows'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/ed/d3/c6c64067759e87af98cc668c1cc75171347d0f1577fab7ca3749134e3cd4/portalocker-2.10.1.tar.gz", hash = "sha256:ef1bf844e878ab08aee7e40184156e1151f228f103aa5c6bd0724cc330960f8f", size = 40891 }
 wheels = [
@@ -5008,19 +5032,19 @@ dependencies = [
     { name = "fsspec" },
     { name = "jinja2" },
     { name = "networkx" },
-    { name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cuda-cupti-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cuda-nvrtc-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cusolver-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-nccl-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "nvidia-nvtx-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cuda-cupti-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cuda-nvrtc-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cusolver-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-nccl-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-nvtx-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
     { name = "sympy" },
-    { name = "triton", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "triton", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
     { name = "typing-extensions" },
 ]
 wheels = [
@@ -5067,7 +5091,7 @@ name = "tqdm"
 version = "4.66.5"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "colorama", marker = "platform_system == 'Windows'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/58/83/6ba9844a41128c62e810fddddd72473201f3eacde02046066142a2d96cc5/tqdm-4.66.5.tar.gz", hash = "sha256:e1020aef2e5096702d8a025ac7d16b1577279c9d63f8375b63083e9a5f0fcbad", size = 169504 }
 wheels = [
@@ -5109,7 +5133,7 @@ name = "triton"
 version = "3.0.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "filelock", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "filelock", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/45/27/14cc3101409b9b4b9241d2ba7deaa93535a217a211c86c4cc7151fb12181/triton-3.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e1efef76935b2febc365bfadf74bcb65a6f959a9872e5bddf44cc9e0adce1e1a", size = 209376304 },