andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 16:18:30 +00:00
Code Issues Actions 1 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

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