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

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

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

102
tests/agent_test.py
View File

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

183
tests/cassettes/test_agent_error_on_parsing_tool.yaml
View File

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

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

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

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

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

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

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

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

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

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

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

117
tests/llm_test.py
View File

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

112
tests/test_flow_default_override.py Normal file
View File

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

131
tests/test_flow_persistence.py
View File

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