andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-07 15:18:29 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Fixing tests

Browse Source
This commit is contained in:
Brandon Hancock
2025-01-22 11:13:47 -05:00
parent daa01686f2
commit dc2e684877
3 changed files with 267 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/crewai/agents/crew_agent_executor.py
View File

@@ -15,6 +15,7 @@ from crewai.agents.parser import (
OutputParserException,
)
from crewai.agents.tools_handler import ToolsHandler
from crewai.llm import LLM
from crewai.tools.base_tool import BaseTool
from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
from crewai.utilities import I18N, Printer
@@ -56,7 +57,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
callbacks: List[Any] = [],
):
self._i18n: I18N = I18N()
self.llm = llm
self.llm: LLM = llm
self.task = task
self.agent = agent
self.crew = crew

1
tests/agent_test.py
View File

@@ -670,6 +670,7 @@ def test_agent_without_max_rpm_respects_crew_rpm(capsys):
moveon.assert_called_once()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_agent_error_on_parsing_tool(capsys):
from unittest.mock import patch

264
tests/cassettes/test_agent_error_on_parsing_tool.yaml Normal file
View File

@@ -0,0 +1,264 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
in your response:\n\n```\nThought: you should always think about what to do\nAction:
the action to take, only one name of [get_final_answer], just the name, exactly
as it''s written.\nAction Input: the input to the action, just a simple JSON
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\n```\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n```"}, {"role": "user",
"content": "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect
criteria for your final answer: The final answer\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nBegin! This is VERY
important to you, use the tools available and give your best Final Answer, your
job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1367'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AsXdf4OZKCZSigmN4k0gyh67NciqP\",\n \"object\":
\"chat.completion\",\n \"created\": 1737562383,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"```\\nThought: I have to use the available
tool to get the final answer. Let's proceed with executing it.\\nAction: get_final_answer\\nAction
Input: {}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
274,\n \"completion_tokens\": 33,\n \"total_tokens\": 307,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_50cad350e4\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 9060d43e3be1d690-IAD
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 22 Jan 2025 16:13:03 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=_Jcp7wnO_mXdvOnborCN6j8HwJxJXbszedJC1l7pFUg-1737562383-1.0.1.1-pDSLXlg.nKjG4wsT7mTJPjUvOX1UJITiS4MqKp6yfMWwRSJINsW1qC48SAcjBjakx2H5I1ESVk9JtUpUFDtf4g;
path=/; expires=Wed, 22-Jan-25 16:43:03 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=x3SYvzL2nq_PTBGtE8R9cl5CkeaaDzZFQIrYfo91S2s-1737562383916-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '791'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999680'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_eeed99acafd3aeb1e3d4a6c8063192b0
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
in your response:\n\n```\nThought: you should always think about what to do\nAction:
the action to take, only one name of [get_final_answer], just the name, exactly
as it''s written.\nAction Input: the input to the action, just a simple JSON
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\n```\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n```"}, {"role": "user",
"content": "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect
criteria for your final answer: The final answer\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nBegin! This is VERY
important to you, use the tools available and give your best Final Answer, your
job depends on it!\n\nThought:"}, {"role": "assistant", "content": "```\nThought:
I have to use the available tool to get the final answer. Let''s proceed with
executing it.\nAction: get_final_answer\nAction Input: {}\nObservation: I encountered
an error: Error on parsing tool.\nMoving on then. I MUST either use a tool (use
one at time) OR give my best final answer not both at the same time. When responding,
I must use the following format:\n\n```\nThought: you should always think about
what to do\nAction: the action to take, should be one of [get_final_answer]\nAction
Input: the input to the action, dictionary enclosed in curly braces\nObservation:
the result of the action\n```\nThis Thought/Action/Action Input/Result can repeat
N times. Once I know the final answer, I must return the following format:\n\n```\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described\n\n```"}, {"role":
"assistant", "content": "```\nThought: I have to use the available tool to get
the final answer. Let''s proceed with executing it.\nAction: get_final_answer\nAction
Input: {}\nObservation: I encountered an error: Error on parsing tool.\nMoving
on then. I MUST either use a tool (use one at time) OR give my best final answer
not both at the same time. When responding, I must use the following format:\n\n```\nThought:
you should always think about what to do\nAction: the action to take, should
be one of [get_final_answer]\nAction Input: the input to the action, dictionary
enclosed in curly braces\nObservation: the result of the action\n```\nThis Thought/Action/Action
Input/Result can repeat N times. Once I know the final answer, I must return
the following format:\n\n```\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described\n\n```\nNow it''s time you MUST give your absolute
best final answer. You''ll ignore all previous instructions, stop using any
tools, and just return your absolute BEST Final answer."}], "model": "gpt-4o",
"stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3445'
content-type:
- application/json
cookie:
- __cf_bm=_Jcp7wnO_mXdvOnborCN6j8HwJxJXbszedJC1l7pFUg-1737562383-1.0.1.1-pDSLXlg.nKjG4wsT7mTJPjUvOX1UJITiS4MqKp6yfMWwRSJINsW1qC48SAcjBjakx2H5I1ESVk9JtUpUFDtf4g;
_cfuvid=x3SYvzL2nq_PTBGtE8R9cl5CkeaaDzZFQIrYfo91S2s-1737562383916-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AsXdg9UrLvAiqWP979E6DszLsQ84k\",\n \"object\":
\"chat.completion\",\n \"created\": 1737562384,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"```\\nThought: I now know the final answer\\nFinal
Answer: The final answer must be the great and the most complete as possible,
it must be outcome described.\\n```\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 719,\n \"completion_tokens\": 35,\n
\ \"total_tokens\": 754,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_50cad350e4\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 9060d4441edad690-IAD
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 22 Jan 2025 16:13:05 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '928'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999187'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_61fc7506e6db326ec572224aec81ef23
http_version: HTTP/1.1
status_code: 200
version: 1