andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2025-12-16 04:18:35 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

KISS: Refactor LiteAgent integration in flows to use Agents instead. … (#2556)

Browse Source 
* KISS: Refactor LiteAgent integration in flows to use Agents instead. Update documentation and examples to reflect changes in class usage, including async support and structured output handling. Enhance tests for Agent functionality and ensure compatibility with new features.

* lint fix

* dropped for clarity
This commit is contained in:
Lorenze Jay
2025-04-09 11:54:45 -07:00
committed by GitHub
parent 10328f3db4
commit b73960cebe
9 changed files with 3160 additions and 293 deletions
Download Patch File Download Diff File Expand all files Collapse all files

94
docs/concepts/flows.mdx
View File

@@ -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

242
docs/concepts/lite-agent.mdx
View File

@@ -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
```

3
docs/docs.json
View File

@@ -66,7 +66,6 @@
"concepts/tasks",
"concepts/crews",
"concepts/flows",
"concepts/lite-agent",
"concepts/knowledge",
"concepts/llms",
"concepts/processes",
@@ -231,4 +230,4 @@
"reddit": "https://www.reddit.com/r/crewAIInc/"
}
}
}
}

75
src/crewai/agent.py
View File

@@ -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 +449,74 @@ 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,
)
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)

2
src/crewai/lite_agent.py
View File

@@ -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

486
tests/cassettes/test_lite_agent_created_with_correct_parameters[False].yaml Normal file
View File

@@ -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

2199
tests/cassettes/test_lite_agent_created_with_correct_parameters[True].yaml Normal file
View File

File diff suppressed because it is too large Load Diff

249
tests/cassettes/test_lite_agent_returns_usage_metrics_async.yaml Normal file
View File

@@ -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

103
tests/test_lite_agent.py
View File

@@ -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