andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-16 11:38:31 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

Merge branch 'main' of github.com:crewAIInc/crewAI into lorenze/agent-query-for-knowledge

Browse Source
This commit is contained in:
lorenzejay
2025-05-05 21:38:31 -07:00
parent a9decb54c8 dabf02a90d
commit 5fa8cdbb48
92 changed files with 14270 additions and 3742 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1095
tests/cassettes/test_after_kickoff_modification.yaml
View File

File diff suppressed because it is too large Load Diff

1091
tests/cassettes/test_before_kickoff_modification.yaml
View File

File diff suppressed because it is too large Load Diff

1125
tests/cassettes/test_before_kickoff_with_none_input.yaml
View File

File diff suppressed because it is too large Load Diff

1899
tests/cassettes/test_docling_source.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

713
tests/cassettes/test_guardrail_emits_events.yaml Normal file
View File

@@ -0,0 +1,713 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour
personal goal is: Test Goal\nTo give my best complete final answer to the task
respond using the exact following format:\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\nI MUST use these formats, my job
depends on it!"}, {"role": "user", "content": "\nCurrent Task: Gather information
about available books on the First World War\n\nThis is the expected criteria
for your final answer: A list of available books on the First World War\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-mini", "stop":
["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '903'
content-type:
- application/json
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:
body:
string: !!binary |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headers:
CF-RAY:
- 937ec970ab837df5-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 29 Apr 2025 12:26:28 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=lSQwOucDEe7UVr7Rj6WZvsTkBkgGT9q7hgVX9AzK42s-1745929588-1.0.1.1-6m0TeDAKI0Hgbl6.GmWHMBMkIpmnfhOu3jQKfjmcvWLHqWUWoE1O4xa9VCtZYXv6_9poUVQq_oCNtzy8eL1XDc8_J3aRMOG3LCvOyvqCawk;
path=/; expires=Tue, 29-Apr-25 12:56:28 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=TeUS2y0sO.6zigvKZd5.0zRS7sujoYCd9.wMQJboxxo-1745929588265-0.0.1.1-604800000;
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:
- '10782'
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:
- '149999808'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_cbf6ad64d8b470c6d9eff91852f85e1c
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Guardrail Agent. You
are a expert at validating the output of a task. By providing effective feedback
if the output is not valid.\nYour personal goal is: Validate the output of the
task\n\nTo give my best complete final answer to the task respond using the
exact following format:\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\nI MUST use these formats, my job depends on it!\nIMPORTANT:
Your final answer MUST contain all the information requested in the following
format: {\n \"valid\": bool,\n \"feedback\": str | None\n}\n\nIMPORTANT: Ensure
the final output does not include any code block markers like ```json or ```python."},
{"role": "user", "content": "\n Ensure the following task result complies
with the given guardrail.\n\n Task result:\n Here is a list of
notable books on the First World War, encompassing various perspectives and
themes:\n\n1. **\"All Quiet on the Western Front\" by Erich Maria Remarque**
- A novel depicting the experiences of German soldiers during World War I, highlighting
the horrors of trench warfare.\n\n2. **\"The First World War\" by John Keegan**
- A comprehensive overview of the war, analyzing its causes, major battles,
and consequences.\n\n3. **\"A World Undone: The Story of the Great War, 1914
to 1918\" by G.J. Meyer** - A narrative history that covers the entire conflict
with a focus on key events and figures.\n\n4. **\"The Guns of August\" by Barbara
W. Tuchman** - An acclaimed work detailing the events leading up to the war
and the early stages of combat, emphasizing the decisions of leaders.\n\n5.
**\"Goodbye to All That\" by Robert Graves** - An autobiography that captures
the experience of trench warfare from a soldier''s perspective, along with the
transition to post-war life.\n\n6. **\"With Our Backs to the Wall: Victory and
Defeat in 1918\" by David Stevenson** - An analysis of the final year of the
war, outlining both the military strategies and the socio-political contexts
that shaped the outcome.\n\n7. **\"The Great War: A Combat History of the First
World War\" by Peter Hart** - This book provides a battle-by-battle account,
using personal diaries and accounts to bring the war''s events to life.\n\n8.
**\"The War to End All Wars: The American Military Experience in World War I\"
by Edward M. Coffman** - An exploration of American involvement in the war,
discussing military strategies and impacts.\n\n9. **\"Over the Top: A Soldier\u2019s
Diary of the First World War\" by Arthur Empey** - A firsthand account of trench
warfare written by an American volunteer, offering a raw depiction of combat
experiences.\n\n10. **\"The First World War: A New Illustrated History\" by
Gordon Corrigan** - A richly illustrated book that presents a chronological
history of the war, accessible for readers of all backgrounds.\n\nThis list
provides a variety of insights and narratives that capture the complexity and
significance of the First World War.\n\n Guardrail:\n Ensure the
authors are from Italy\n \n Your task:\n - Confirm if the
Task result complies with the guardrail.\n - If not, provide clear feedback
explaining what is wrong (e.g., by how much it violates the rule, or what specific
part fails).\n - Focus only on identifying issues \u2014 do not propose
corrections.\n - If the Task result complies with the guardrail, saying
that is valid\n "}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3636'
content-type:
- application/json
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:
body:
string: !!binary |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=
headers:
CF-RAY:
- 937ec9b72e717e0f-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 29 Apr 2025 12:26:30 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=2Kv7JW0NnxXgvGH0KQnR1VcNF47nEYxhEB4bYlFvRfA-1745929590-1.0.1.1-gmQvNlZR_WoNPIkf.07YchEy.a13FU2sP7wZropzue.84PKf6DVY_clzo6DqmBOk8PtKtM3gV952vhWHuE0ygk7096hW9jQTST91FDi30Jc;
path=/; expires=Tue, 29-Apr-25 12:56:30 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=HHxY6s22oZkfAHAh8HGGIeDkKOuavigZ5DkKL6.WyGc-1745929590485-0.0.1.1-604800000;
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:
- '1744'
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:
- '149999140'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_74247d0bd52dcebe834bd1cdb4b38470
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour
personal goal is: Test Goal\nTo give my best complete final answer to the task
respond using the exact following format:\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\nI MUST use these formats, my job
depends on it!"}, {"role": "user", "content": "\nCurrent Task: Gather information
about available books on the First World War\n\nThis is the expected criteria
for your final answer: A list of available books on the First World War\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\n### Previous attempt failed validation:
The task result does not comply with the guardrail because none of the listed
authors are from Italy. All authors mentioned are from different countries,
including Germany, the UK, the USA, and others, which violates the requirement
that authors must be Italian.\n\n\n### Previous result:\nHere is a list of notable
books on the First World War, encompassing various perspectives and themes:\n\n1.
**\"All Quiet on the Western Front\" by Erich Maria Remarque** - A novel depicting
the experiences of German soldiers during World War I, highlighting the horrors
of trench warfare.\n\n2. **\"The First World War\" by John Keegan** - A comprehensive
overview of the war, analyzing its causes, major battles, and consequences.\n\n3.
**\"A World Undone: The Story of the Great War, 1914 to 1918\" by G.J. Meyer**
- A narrative history that covers the entire conflict with a focus on key events
and figures.\n\n4. **\"The Guns of August\" by Barbara W. Tuchman** - An acclaimed
work detailing the events leading up to the war and the early stages of combat,
emphasizing the decisions of leaders.\n\n5. **\"Goodbye to All That\" by Robert
Graves** - An autobiography that captures the experience of trench warfare from
a soldier''s perspective, along with the transition to post-war life.\n\n6.
**\"With Our Backs to the Wall: Victory and Defeat in 1918\" by David Stevenson**
- An analysis of the final year of the war, outlining both the military strategies
and the socio-political contexts that shaped the outcome.\n\n7. **\"The Great
War: A Combat History of the First World War\" by Peter Hart** - This book provides
a battle-by-battle account, using personal diaries and accounts to bring the
war''s events to life.\n\n8. **\"The War to End All Wars: The American Military
Experience in World War I\" by Edward M. Coffman** - An exploration of American
involvement in the war, discussing military strategies and impacts.\n\n9. **\"Over
the Top: A Soldier\u2019s Diary of the First World War\" by Arthur Empey** -
A firsthand account of trench warfare written by an American volunteer, offering
a raw depiction of combat experiences.\n\n10. **\"The First World War: A New
Illustrated History\" by Gordon Corrigan** - A richly illustrated book that
presents a chronological history of the war, accessible for readers of all backgrounds.\n\nThis
list provides a variety of insights and narratives that capture the complexity
and significance of the First World War.\n\n\nTry again, making sure to address
the validation error.\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-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3509'
content-type:
- application/json
cookie:
- __cf_bm=2Kv7JW0NnxXgvGH0KQnR1VcNF47nEYxhEB4bYlFvRfA-1745929590-1.0.1.1-gmQvNlZR_WoNPIkf.07YchEy.a13FU2sP7wZropzue.84PKf6DVY_clzo6DqmBOk8PtKtM3gV952vhWHuE0ygk7096hW9jQTST91FDi30Jc;
_cfuvid=HHxY6s22oZkfAHAh8HGGIeDkKOuavigZ5DkKL6.WyGc-1745929590485-0.0.1.1-604800000
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:
body:
string: !!binary |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headers:
CF-RAY:
- 937ec9c4b8307e0f-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 29 Apr 2025 12:26:41 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:
- '10386'
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:
- '149999169'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_7e9c58909cf39af106866bae0c0cf7e1
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Guardrail Agent. You
are a expert at validating the output of a task. By providing effective feedback
if the output is not valid.\nYour personal goal is: Validate the output of the
task\n\nTo give my best complete final answer to the task respond using the
exact following format:\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\nI MUST use these formats, my job depends on it!\nIMPORTANT:
Your final answer MUST contain all the information requested in the following
format: {\n \"valid\": bool,\n \"feedback\": str | None\n}\n\nIMPORTANT: Ensure
the final output does not include any code block markers like ```json or ```python."},
{"role": "user", "content": "\n Ensure the following task result complies
with the given guardrail.\n\n Task result:\n Here is a list of
notable books on the First World War written by Italian authors, incorporating
various perspectives and themes:\n\n1. **\"Il mio nome \u00e8 nessuno\" by Dario
Fo** - A unique narrative intertwining personal stories and historical facts
about the impacts of World War I on Italian society.\n\n2. **\"La guerra dei
nostri nonni\" by Mario avagliano and Marco Palmieri** - This book provides
a detailed account of the experiences of Italian soldiers during the First World
War, focusing on their motivations and struggles.\n\n3. **\"Sulle tracce della
Grande Guerra\" by Sergio Staino** - A graphic novel that blends artistic expression
with historical narrative to depict the life of soldiers in the trenches of
the Great War.\n\n4. **\"L''intera storia della Prima Guerra Mondiale\" by Giuseppe
De Lutiis** - A comprehensive overview that explores the geopolitical causes,
major battles, and long-term effects of the war on Italy and beyond.\n\n5. **\"La
Grande Guerra in Friuli\" by Paolo Cattaruzza** - This book emphasizes the regional
impact of World War I in Friuli, highlighting the significant battles and the
experiences of local civilians and soldiers.\n\n6. **\"Lettere di un soldato\"
by Alessandro F. Brigante** - A collection of letters written by a soldier during
the war, providing a personal and intimate perspective on the realities of combat.\n\n7.
**\"Azzurri in trincea\" by Mario Isnenghi** - The book examines the experience
of Italian soldiers in the front lines, focusing on their culture, morale, and
the shared camaraderie among troops.\n\n8. **\"La guerra di Matteo\" by Franco
Cardini** - A historical fiction that follows a young Italian man\u2019s journey
through the war, offering insights into the emotional and psychological impacts
of conflict.\n\n9. **\"1915-1918. La Grande Guerra\" by Andrea Nativi** - A
scholarly work that analyzes the strategies and technological advancements employed
by Italian forces during the First World War.\n\n10. **\"Il giorno della vittoria\"
by Vincenzo Pardini** - A captivating exploration of the final offensives leading
to the end of the war, examining how they shaped Italy\u2019s national identity.\n\nThis
list highlights a range of Italian authors who offer diverse narratives and
profound insights into the multifaceted experiences and legacies of the First
World War.\n\n Guardrail:\n Ensure the authors are from Italy\n \n Your
task:\n - Confirm if the Task result complies with the guardrail.\n -
If not, provide clear feedback explaining what is wrong (e.g., by how much it
violates the rule, or what specific part fails).\n - Focus only on identifying
issues \u2014 do not propose corrections.\n - If the Task result complies
with the guardrail, saying that is valid\n "}], "model": "gpt-4o-mini",
"stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3829'
content-type:
- application/json
cookie:
- __cf_bm=2Kv7JW0NnxXgvGH0KQnR1VcNF47nEYxhEB4bYlFvRfA-1745929590-1.0.1.1-gmQvNlZR_WoNPIkf.07YchEy.a13FU2sP7wZropzue.84PKf6DVY_clzo6DqmBOk8PtKtM3gV952vhWHuE0ygk7096hW9jQTST91FDi30Jc;
_cfuvid=HHxY6s22oZkfAHAh8HGGIeDkKOuavigZ5DkKL6.WyGc-1745929590485-0.0.1.1-604800000
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:
body:
string: !!binary |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headers:
CF-RAY:
- 937eca0769737e0f-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 29 Apr 2025 12:26:42 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:
- '924'
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:
- '149999094'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_242f5797b2a0bf5867b01ab6027921fa
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour
personal goal is: Test Goal\nTo give my best complete final answer to the task
respond using the exact following format:\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\nI MUST use these formats, my job
depends on it!"}, {"role": "user", "content": "\nCurrent Task: Test task\n\nThis
is the expected criteria for your final answer: Output\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-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '807'
content-type:
- application/json
cookie:
- __cf_bm=2Kv7JW0NnxXgvGH0KQnR1VcNF47nEYxhEB4bYlFvRfA-1745929590-1.0.1.1-gmQvNlZR_WoNPIkf.07YchEy.a13FU2sP7wZropzue.84PKf6DVY_clzo6DqmBOk8PtKtM3gV952vhWHuE0ygk7096hW9jQTST91FDi30Jc;
_cfuvid=HHxY6s22oZkfAHAh8HGGIeDkKOuavigZ5DkKL6.WyGc-1745929590485-0.0.1.1-604800000
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:
body:
string: !!binary |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headers:
CF-RAY:
- 937eca0f18177e0f-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 29 Apr 2025 12:26:44 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:
- '1988'
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:
- '149999832'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_99b127ab59c932c0b46dbecc738df8ba
status:
code: 200
message: OK
version: 1

288
tests/cassettes/test_guardrail_when_an_error_occurs.yaml Normal file
View File

@@ -0,0 +1,288 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour
personal goal is: Test Goal\nTo give my best complete final answer to the task
respond using the exact following format:\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\nI MUST use these formats, my job
depends on it!"}, {"role": "user", "content": "\nCurrent Task: Gather information
about available books on the First World War\n\nThis is the expected criteria
for your final answer: A list of available books on the First World War\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-mini", "stop":
["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '903'
content-type:
- application/json
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:
body:
string: !!binary |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headers:
CF-RAY:
- 937ed42dee2e621f-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 29 Apr 2025 12:33:48 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=mLRCnpdB3n_6medIZWHnUu8MNRGZsD6riaRhN47PK74-1745930028-1.0.1.1-M2lDM1_V9hNCK0MZrBnFalF3lndC3JkS8zhDOGww_LmOrgdpU9fZLpNZUmyinCQOnlCjDjDYJUECM82ffT1anqBiO1NoDeNp91EPKiK7s.8;
path=/; expires=Tue, 29-Apr-25 13:03:48 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=eTrj_ZhCx2XuylS5vYROwUlPrJBwOyrbS2Ki.msl45E-1745930028010-0.0.1.1-604800000;
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:
- '10856'
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:
- '149999807'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_bc2d62d8325b2bdd3e98544a66389132
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Guardrail Agent. You
are a expert at validating the output of a task. By providing effective feedback
if the output is not valid.\nYour personal goal is: Validate the output of the
task\n\nTo give my best complete final answer to the task respond using the
exact following format:\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\nI MUST use these formats, my job depends on it!\nIMPORTANT:
Your final answer MUST contain all the information requested in the following
format: {\n \"valid\": bool,\n \"feedback\": str | None\n}\n\nIMPORTANT: Ensure
the final output does not include any code block markers like ```json or ```python."},
{"role": "user", "content": "\n Ensure the following task result complies
with the given guardrail.\n\n Task result:\n Here is a comprehensive
list of available books on the First World War:\n\n1. **\"The Sleepwalkers:
How Europe Went to War in 1914\" by Christopher Clark** \n This book delves
into the complex factors that led to the outbreak of the war, offering insights
into the political and social dynamics of early 20th century Europe.\n\n2. **\"A
World Undone: The Story of the Great War, 1914 to 1918\" by G.J. Meyer** \n Meyer''s
expansive narrative covers the entire war with a focus on both military strategies
and the human experiences endured by soldiers and civilians alike.\n\n3. **\"All
Quiet on the Western Front\" by Erich Maria Remarque** \n A poignant novel
that captures the resilience and trauma experienced by German soldiers during
World War I, based on the author''s own experiences.\n\n4. **\"The First World
War\" by John Keegan** \n Keegan provides a detailed military history of
the war, featuring insights on battles, strategies, and the overall impact on
global affairs.\n\n5. **\"Goodbye to All That\" by Robert Graves** \n This
autobiography recounts the author''s experiences as a soldier during the war,
offering a personal and critical perspective on the conflicts and the post-war
era.\n\n6. **\"Catastrophe 1914: Europe Goes to War\" by Max Hastings** \n Hastings
chronicles the events leading up to World War I and the early battles, detailing
the war''s initial impact on European societies.\n\n7. **\"The War That Ended
Peace: The Road to 1914\" by Margaret MacMillan** \n MacMillan explores the
political and historical factors that contributed to the outbreak of war, emphasizing
the decisions made by leaders across Europe.\n\n8. **\"The First World War:
A Complete History\" by Martin Gilbert** \n This complete history takes readers
through the entirety of the war, from its causes to its aftermath, using a wide
range of sources.\n\n9. **\"1914: The Year the World Ended\" by Paul Ham** \n Ham
focuses on the pivotal year of 1914 and the early war''s devastation, analyzing
its long-lasting effects on the world.\n\n10. **\"War Horse\" by Michael Morpurgo** \n This
children''s novel tells the story of a horse and his experiences during the
war, highlighting the bond between animals and humans amidst the chaos.\n\nEach
of these books offers unique perspectives and rich details about the First World
War, making them valuable resources for anyone interested in this pivotal period
in history.\n\n Guardrail:\n Ensure the authors are from Italy\n \n Your
task:\n - Confirm if the Task result complies with the guardrail.\n -
If not, provide clear feedback explaining what is wrong (e.g., by how much it
violates the rule, or what specific part fails).\n - Focus only on identifying
issues \u2014 do not propose corrections.\n - If the Task result complies
with the guardrail, saying that is valid\n "}], "model": "gpt-4o-mini",
"stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3917'
content-type:
- application/json
cookie:
- __cf_bm=mLRCnpdB3n_6medIZWHnUu8MNRGZsD6riaRhN47PK74-1745930028-1.0.1.1-M2lDM1_V9hNCK0MZrBnFalF3lndC3JkS8zhDOGww_LmOrgdpU9fZLpNZUmyinCQOnlCjDjDYJUECM82ffT1anqBiO1NoDeNp91EPKiK7s.8;
_cfuvid=eTrj_ZhCx2XuylS5vYROwUlPrJBwOyrbS2Ki.msl45E-1745930028010-0.0.1.1-604800000
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:
body:
string: !!binary |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==
headers:
CF-RAY:
- 937ed6bd68faa435-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 29 Apr 2025 12:35:23 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:
- '1138'
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:
- '149999072'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_2ba1be014a5974ba354aff564e26516a
status:
code: 200
message: OK
version: 1

1092
tests/cassettes/test_multiple_before_after_kickoff.yaml
View File

File diff suppressed because it is too large Load Diff

3321
tests/cassettes/test_multiple_docling_sources.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

250
tests/cassettes/test_task_guardrail_process_output.yaml Normal file
View File

@@ -0,0 +1,250 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Guardrail Agent. You
are a expert at validating the output of a task. By providing effective feedback
if the output is not valid.\nYour personal goal is: Validate the output of the
task\n\nTo give my best complete final answer to the task respond using the
exact following format:\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\nI MUST use these formats, my job depends on it!\nIMPORTANT:
Your final answer MUST contain all the information requested in the following
format: {\n \"valid\": bool,\n \"feedback\": str | None\n}\n\nIMPORTANT: Ensure
the final output does not include any code block markers like ```json or ```python."},
{"role": "user", "content": "\n Ensure the following task result complies
with the given guardrail.\n\n Task result:\n \n Lorem Ipsum
is simply dummy text of the printing and typesetting industry. Lorem Ipsum has
been the industry''s standard dummy text ever\n \n\n Guardrail:\n Ensure
the result has less than 10 words\n \n Your task:\n - Confirm
if the Task result complies with the guardrail.\n - If not, provide clear
feedback explaining what is wrong (e.g., by how much it violates the rule, or
what specific part fails).\n - Focus only on identifying issues \u2014
do not propose corrections.\n - If the Task result complies with the
guardrail, saying that is valid\n "}], "model": "gpt-4o-mini", "stop":
["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1629'
content-type:
- application/json
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:
body:
string: !!binary |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headers:
CF-RAY:
- 937b20ddf9607def-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 29 Apr 2025 01:46:56 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=nHa2kVJI_yO1RIsmZcEednJ1e9UVy1liv_sjBNtSj7Q-1745891216-1.0.1.1-jUH9kFawVBjnbq8sIL2.MQx.p7JvBZWUhqlkNKRlStWSgQxT0eZMPcgq9TCQoJAjuyNwhqfpK4HuX6x5n8UbQgAb6JrWJEG823e6GpGROEA;
path=/; expires=Tue, 29-Apr-25 02:16:56 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=gg2UeahMCOOR8YhitRtzDwENMOnTOuQdyTMVJVHG0Mg-1745891216085-0.0.1.1-604800000;
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:
- '896'
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:
- '149999631'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_859221ed1aedb26cc9d335004ccf183e
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Guardrail Agent. You
are a expert at validating the output of a task. By providing effective feedback
if the output is not valid.\nYour personal goal is: Validate the output of the
task\n\nTo give my best complete final answer to the task respond using the
exact following format:\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\nI MUST use these formats, my job depends on it!\nIMPORTANT:
Your final answer MUST contain all the information requested in the following
format: {\n \"valid\": bool,\n \"feedback\": str | None\n}\n\nIMPORTANT: Ensure
the final output does not include any code block markers like ```json or ```python."},
{"role": "user", "content": "\n Ensure the following task result complies
with the given guardrail.\n\n Task result:\n \n Lorem Ipsum
is simply dummy text of the printing and typesetting industry. Lorem Ipsum has
been the industry''s standard dummy text ever\n \n\n Guardrail:\n Ensure
the result has less than 500 words\n \n Your task:\n -
Confirm if the Task result complies with the guardrail.\n - If not, provide
clear feedback explaining what is wrong (e.g., by how much it violates the rule,
or what specific part fails).\n - Focus only on identifying issues \u2014
do not propose corrections.\n - If the Task result complies with the
guardrail, saying that is valid\n "}], "model": "gpt-4o-mini", "stop":
["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1630'
content-type:
- application/json
cookie:
- __cf_bm=nHa2kVJI_yO1RIsmZcEednJ1e9UVy1liv_sjBNtSj7Q-1745891216-1.0.1.1-jUH9kFawVBjnbq8sIL2.MQx.p7JvBZWUhqlkNKRlStWSgQxT0eZMPcgq9TCQoJAjuyNwhqfpK4HuX6x5n8UbQgAb6JrWJEG823e6GpGROEA;
_cfuvid=gg2UeahMCOOR8YhitRtzDwENMOnTOuQdyTMVJVHG0Mg-1745891216085-0.0.1.1-604800000
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:
body:
string: !!binary |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headers:
CF-RAY:
- 937b2311ee091b1b-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 29 Apr 2025 01:48:26 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:
- '610'
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:
- '149999631'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_c136835c16be6bc1e4d820f239c4b620
status:
code: 200
message: OK
version: 1

221
tests/cassettes/test_telemetry_fails_due_connect_timeout.yaml Normal file
View File

File diff suppressed because one or more lines are too long

151
tests/cli/cli_test.py
View File

@@ -18,6 +18,7 @@ from crewai.cli.cli import (
train,
version,
)
from crewai.crew import Crew
@pytest.fixture
@@ -55,81 +56,133 @@ def test_train_invalid_string_iterations(train_crew, runner):
)
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_all_memories(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
@pytest.fixture
def mock_crew():
_mock = mock.Mock(spec=Crew, name="test_crew")
_mock.name = "test_crew"
return _mock
@pytest.fixture
def mock_get_crews(mock_crew):
with mock.patch(
"crewai.cli.reset_memories_command.get_crews", return_value=[mock_crew]
) as mock_get_crew:
yield mock_get_crew
def test_reset_all_memories(mock_get_crews, runner):
result = runner.invoke(reset_memories, ["-a"])
mock_crew.reset_memories.assert_called_once_with(command_type="all")
assert result.output == "All memories have been reset.\n"
call_count = 0
for crew in mock_get_crews.return_value:
crew.reset_memories.assert_called_once_with(command_type="all")
assert (
f"[Crew ({crew.name})] Reset memories command has been completed."
in result.output
)
call_count += 1
assert call_count == 1, "reset_memories should have been called once"
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_short_term_memories(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
def test_reset_short_term_memories(mock_get_crews, runner):
result = runner.invoke(reset_memories, ["-s"])
call_count = 0
for crew in mock_get_crews.return_value:
crew.reset_memories.assert_called_once_with(command_type="short")
assert (
f"[Crew ({crew.name})] Short term memory has been reset." in result.output
)
call_count += 1
mock_crew.reset_memories.assert_called_once_with(command_type="short")
assert result.output == "Short term memory has been reset.\n"
assert call_count == 1, "reset_memories should have been called once"
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_entity_memories(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
def test_reset_entity_memories(mock_get_crews, runner):
result = runner.invoke(reset_memories, ["-e"])
call_count = 0
for crew in mock_get_crews.return_value:
crew.reset_memories.assert_called_once_with(command_type="entity")
assert f"[Crew ({crew.name})] Entity memory has been reset." in result.output
call_count += 1
mock_crew.reset_memories.assert_called_once_with(command_type="entity")
assert result.output == "Entity memory has been reset.\n"
assert call_count == 1, "reset_memories should have been called once"
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_long_term_memories(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
def test_reset_long_term_memories(mock_get_crews, runner):
result = runner.invoke(reset_memories, ["-l"])
call_count = 0
for crew in mock_get_crews.return_value:
crew.reset_memories.assert_called_once_with(command_type="long")
assert f"[Crew ({crew.name})] Long term memory has been reset." in result.output
call_count += 1
mock_crew.reset_memories.assert_called_once_with(command_type="long")
assert result.output == "Long term memory has been reset.\n"
assert call_count == 1, "reset_memories should have been called once"
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_kickoff_outputs(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
def test_reset_kickoff_outputs(mock_get_crews, runner):
result = runner.invoke(reset_memories, ["-k"])
call_count = 0
for crew in mock_get_crews.return_value:
crew.reset_memories.assert_called_once_with(command_type="kickoff_outputs")
assert (
f"[Crew ({crew.name})] Latest Kickoff outputs stored has been reset."
in result.output
)
call_count += 1
mock_crew.reset_memories.assert_called_once_with(command_type="kickoff_outputs")
assert result.output == "Latest Kickoff outputs stored has been reset.\n"
assert call_count == 1, "reset_memories should have been called once"
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_multiple_memory_flags(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
def test_reset_multiple_memory_flags(mock_get_crews, runner):
result = runner.invoke(reset_memories, ["-s", "-l"])
call_count = 0
for crew in mock_get_crews.return_value:
crew.reset_memories.assert_has_calls(
[mock.call(command_type="long"), mock.call(command_type="short")]
)
assert (
f"[Crew ({crew.name})] Long term memory has been reset.\n"
f"[Crew ({crew.name})] Short term memory has been reset.\n" in result.output
)
call_count += 1
# Check that reset_memories was called twice with the correct arguments
assert mock_crew.reset_memories.call_count == 2
mock_crew.reset_memories.assert_has_calls(
[mock.call(command_type="long"), mock.call(command_type="short")]
)
assert (
result.output
== "Long term memory has been reset.\nShort term memory has been reset.\n"
)
assert call_count == 1, "reset_memories should have been called once"
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_knowledge(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
def test_reset_knowledge(mock_get_crews, runner):
result = runner.invoke(reset_memories, ["--knowledge"])
call_count = 0
for crew in mock_get_crews.return_value:
crew.reset_memories.assert_called_once_with(command_type="knowledge")
assert f"[Crew ({crew.name})] Knowledge has been reset." in result.output
call_count += 1
assert call_count == 1, "reset_memories should have been called once"
def test_reset_memory_from_many_crews(mock_get_crews, runner):
crews = []
for crew_id in ["id-1234", "id-5678"]:
mock_crew = mock.Mock(spec=Crew)
mock_crew.name = None
mock_crew.id = crew_id
crews.append(mock_crew)
mock_get_crews.return_value = crews
# Run the command
result = runner.invoke(reset_memories, ["--knowledge"])
mock_crew.reset_memories.assert_called_once_with(command_type="knowledge")
assert result.output == "Knowledge has been reset.\n"
call_count = 0
for crew in crews:
call_count += 1
crew.reset_memories.assert_called_once_with(command_type="knowledge")
assert f"[Crew ({crew.id})] Knowledge has been reset." in result.output
assert call_count == 2, "reset_memories should have been called twice"
def test_reset_no_memory_flags(runner):

115
tests/cli/tools/test_main.py
View File

@@ -3,12 +3,13 @@ import tempfile
import unittest
import unittest.mock
from contextlib import contextmanager
from io import StringIO
from unittest import mock
from unittest.mock import MagicMock, patch
import pytest
from pytest import raises
from crewai.cli.authentication.utils import TokenManager
from crewai.cli.tools.main import ToolCommand
@@ -23,17 +24,20 @@ def in_temp_dir():
os.chdir(original_dir)
@patch("crewai.cli.tools.main.subprocess.run")
def test_create_success(mock_subprocess):
with in_temp_dir():
tool_command = ToolCommand()
@pytest.fixture
def tool_command():
TokenManager().save_tokens("test-token", 36000)
tool_command = ToolCommand()
with patch.object(tool_command, "login"):
yield tool_command
with (
patch.object(tool_command, "login") as mock_login,
patch("sys.stdout", new=StringIO()) as fake_out,
):
tool_command.create("test-tool")
output = fake_out.getvalue()
@patch("crewai.cli.tools.main.subprocess.run")
def test_create_success(mock_subprocess, capsys, tool_command):
with in_temp_dir():
tool_command.create("test-tool")
output = capsys.readouterr().out
assert "Creating custom tool test_tool..." in output
assert os.path.isdir("test_tool")
assert os.path.isfile(os.path.join("test_tool", "README.md"))
@@ -47,15 +51,12 @@ def test_create_success(mock_subprocess):
content = f.read()
assert "class TestTool" in content
mock_login.assert_called_once()
mock_subprocess.assert_called_once_with(["git", "init"], check=True)
assert "Creating custom tool test_tool..." in output
@patch("crewai.cli.tools.main.subprocess.run")
@patch("crewai.cli.plus_api.PlusAPI.get_tool")
def test_install_success(mock_get, mock_subprocess_run):
def test_install_success(mock_get, mock_subprocess_run, capsys, tool_command):
mock_get_response = MagicMock()
mock_get_response.status_code = 200
mock_get_response.json.return_value = {
@@ -65,11 +66,9 @@ def test_install_success(mock_get, mock_subprocess_run):
mock_get.return_value = mock_get_response
mock_subprocess_run.return_value = MagicMock(stderr=None)
tool_command = ToolCommand()
with patch("sys.stdout", new=StringIO()) as fake_out:
tool_command.install("sample-tool")
output = fake_out.getvalue()
tool_command.install("sample-tool")
output = capsys.readouterr().out
assert "Successfully installed sample-tool" in output
mock_get.assert_has_calls([mock.call("sample-tool"), mock.call().json()])
mock_subprocess_run.assert_any_call(
@@ -86,54 +85,42 @@ def test_install_success(mock_get, mock_subprocess_run):
env=unittest.mock.ANY,
)
assert "Successfully installed sample-tool" in output
@patch("crewai.cli.plus_api.PlusAPI.get_tool")
def test_install_tool_not_found(mock_get):
def test_install_tool_not_found(mock_get, capsys, tool_command):
mock_get_response = MagicMock()
mock_get_response.status_code = 404
mock_get.return_value = mock_get_response
tool_command = ToolCommand()
with patch("sys.stdout", new=StringIO()) as fake_out:
try:
tool_command.install("non-existent-tool")
except SystemExit:
pass
output = fake_out.getvalue()
with raises(SystemExit):
tool_command.install("non-existent-tool")
output = capsys.readouterr().out
assert "No tool found with this name" in output
mock_get.assert_called_once_with("non-existent-tool")
assert "No tool found with this name" in output
@patch("crewai.cli.plus_api.PlusAPI.get_tool")
def test_install_api_error(mock_get):
def test_install_api_error(mock_get, capsys, tool_command):
mock_get_response = MagicMock()
mock_get_response.status_code = 500
mock_get.return_value = mock_get_response
tool_command = ToolCommand()
with patch("sys.stdout", new=StringIO()) as fake_out:
try:
tool_command.install("error-tool")
except SystemExit:
pass
output = fake_out.getvalue()
with raises(SystemExit):
tool_command.install("error-tool")
output = capsys.readouterr().out
assert "Failed to get tool details" in output
mock_get.assert_called_once_with("error-tool")
assert "Failed to get tool details" in output
@patch("crewai.cli.tools.main.git.Repository.is_synced", return_value=False)
def test_publish_when_not_in_sync(mock_is_synced):
with patch("sys.stdout", new=StringIO()) as fake_out, raises(SystemExit):
tool_command = ToolCommand()
def test_publish_when_not_in_sync(mock_is_synced, capsys, tool_command):
with raises(SystemExit):
tool_command.publish(is_public=True)
assert "Local changes need to be resolved before publishing" in fake_out.getvalue()
output = capsys.readouterr().out
assert "Local changes need to be resolved before publishing" in output
@patch("crewai.cli.tools.main.get_project_name", return_value="sample-tool")
@@ -157,13 +144,13 @@ def test_publish_when_not_in_sync_and_force(
mock_get_project_description,
mock_get_project_version,
mock_get_project_name,
tool_command,
):
mock_publish_response = MagicMock()
mock_publish_response.status_code = 200
mock_publish_response.json.return_value = {"handle": "sample-tool"}
mock_publish.return_value = mock_publish_response
tool_command = ToolCommand()
tool_command.publish(is_public=True, force=True)
mock_get_project_name.assert_called_with(require=True)
@@ -205,13 +192,13 @@ def test_publish_success(
mock_get_project_description,
mock_get_project_version,
mock_get_project_name,
tool_command,
):
mock_publish_response = MagicMock()
mock_publish_response.status_code = 200
mock_publish_response.json.return_value = {"handle": "sample-tool"}
mock_publish.return_value = mock_publish_response
tool_command = ToolCommand()
tool_command.publish(is_public=True)
mock_get_project_name.assert_called_with(require=True)
@@ -251,25 +238,22 @@ def test_publish_failure(
mock_get_project_description,
mock_get_project_version,
mock_get_project_name,
capsys,
tool_command,
):
mock_publish_response = MagicMock()
mock_publish_response.status_code = 422
mock_publish_response.json.return_value = {"name": ["is already taken"]}
mock_publish.return_value = mock_publish_response
tool_command = ToolCommand()
with patch("sys.stdout", new=StringIO()) as fake_out:
try:
tool_command.publish(is_public=True)
except SystemExit:
pass
output = fake_out.getvalue()
mock_publish.assert_called_once()
with raises(SystemExit):
tool_command.publish(is_public=True)
output = capsys.readouterr().out
assert "Failed to complete operation" in output
assert "Name is already taken" in output
mock_publish.assert_called_once()
@patch("crewai.cli.tools.main.get_project_name", return_value="sample-tool")
@patch("crewai.cli.tools.main.get_project_version", return_value="1.0.0")
@@ -290,6 +274,8 @@ def test_publish_api_error(
mock_get_project_description,
mock_get_project_version,
mock_get_project_name,
capsys,
tool_command,
):
mock_response = MagicMock()
mock_response.status_code = 500
@@ -297,14 +283,9 @@ def test_publish_api_error(
mock_response.ok = False
mock_publish.return_value = mock_response
tool_command = ToolCommand()
with patch("sys.stdout", new=StringIO()) as fake_out:
try:
tool_command.publish(is_public=True)
except SystemExit:
pass
output = fake_out.getvalue()
with raises(SystemExit):
tool_command.publish(is_public=True)
output = capsys.readouterr().out
assert "Request to Enterprise API failed" in output
mock_publish.assert_called_once()
assert "Request to Enterprise API failed" in output

1
tests/config/tasks.yaml
View File

@@ -6,6 +6,7 @@ research_task:
expected_output: >
A list with 10 bullet points of the most relevant information about {topic}
agent: researcher
guardrail: ensure each bullet contains its source
reporting_task:
description: >

176
tests/crew_test.py
View File

@@ -17,6 +17,7 @@ from crewai.agents.cache import CacheHandler
from crewai.agents.crew_agent_executor import CrewAgentExecutor
from crewai.crew import Crew
from crewai.crews.crew_output import CrewOutput
from crewai.flow import Flow, listen, start
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
from crewai.llm import LLM
from crewai.memory.contextual.contextual_memory import ContextualMemory
@@ -42,29 +43,38 @@ from crewai.utilities.events.event_listener import EventListener
from crewai.utilities.rpm_controller import RPMController
from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
ceo = Agent(
role="CEO",
goal="Make sure the writers in your company produce amazing content.",
backstory="You're an long time CEO of a content creation agency with a Senior Writer on the team. You're now working on a new project and want to make sure the content produced is amazing.",
allow_delegation=True,
)
researcher = Agent(
role="Researcher",
goal="Make the best research and analysis on content about AI and AI agents",
backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
allow_delegation=False,
)
writer = Agent(
role="Senior Writer",
goal="Write the best content about AI and AI agents.",
backstory="You're a senior writer, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer.",
allow_delegation=False,
)
@pytest.fixture
def ceo():
return Agent(
role="CEO",
goal="Make sure the writers in your company produce amazing content.",
backstory="You're an long time CEO of a content creation agency with a Senior Writer on the team. You're now working on a new project and want to make sure the content produced is amazing.",
allow_delegation=True,
)
def test_crew_with_only_conditional_tasks_raises_error():
@pytest.fixture
def researcher():
return Agent(
role="Researcher",
goal="Make the best research and analysis on content about AI and AI agents",
backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
allow_delegation=False,
)
@pytest.fixture
def writer():
return Agent(
role="Senior Writer",
goal="Write the best content about AI and AI agents.",
backstory="You're a senior writer, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer.",
allow_delegation=False,
)
def test_crew_with_only_conditional_tasks_raises_error(researcher):
"""Test that creating a crew with only conditional tasks raises an error."""
def condition_func(task_output: TaskOutput) -> bool:
@@ -146,7 +156,9 @@ def test_crew_config_conditional_requirement():
]
def test_async_task_cannot_include_sequential_async_tasks_in_context():
def test_async_task_cannot_include_sequential_async_tasks_in_context(
researcher, writer
):
task1 = Task(
description="Task 1",
async_execution=True,
@@ -194,7 +206,7 @@ def test_async_task_cannot_include_sequential_async_tasks_in_context():
pytest.fail("Unexpected ValidationError raised")
def test_context_no_future_tasks():
def test_context_no_future_tasks(researcher, writer):
task2 = Task(
description="Task 2",
expected_output="output",
@@ -258,7 +270,7 @@ def test_crew_config_with_wrong_keys():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_creation():
def test_crew_creation(researcher, writer):
tasks = [
Task(
description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
@@ -290,7 +302,7 @@ def test_crew_creation():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_sync_task_execution():
def test_sync_task_execution(researcher, writer):
from unittest.mock import patch
tasks = [
@@ -331,7 +343,7 @@ def test_sync_task_execution():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_hierarchical_process():
def test_hierarchical_process(researcher, writer):
task = Task(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
@@ -352,7 +364,7 @@ def test_hierarchical_process():
)
def test_manager_llm_requirement_for_hierarchical_process():
def test_manager_llm_requirement_for_hierarchical_process(researcher, writer):
task = Task(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
@@ -367,7 +379,7 @@ def test_manager_llm_requirement_for_hierarchical_process():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_manager_agent_delegating_to_assigned_task_agent():
def test_manager_agent_delegating_to_assigned_task_agent(researcher, writer):
"""
Test that the manager agent delegates to the assigned task agent.
"""
@@ -419,7 +431,7 @@ def test_manager_agent_delegating_to_assigned_task_agent():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_manager_agent_delegating_to_all_agents():
def test_manager_agent_delegating_to_all_agents(researcher, writer):
"""
Test that the manager agent delegates to all agents when none are specified.
"""
@@ -529,7 +541,7 @@ def test_manager_agent_delegates_with_varied_role_cases():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_with_delegating_agents():
def test_crew_with_delegating_agents(ceo, writer):
tasks = [
Task(
description="Produce and amazing 1 paragraph draft of an article about AI Agents.",
@@ -553,7 +565,7 @@ def test_crew_with_delegating_agents():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_with_delegating_agents_should_not_override_task_tools():
def test_crew_with_delegating_agents_should_not_override_task_tools(ceo, writer):
from typing import Type
from pydantic import BaseModel, Field
@@ -615,7 +627,7 @@ def test_crew_with_delegating_agents_should_not_override_task_tools():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_with_delegating_agents_should_not_override_agent_tools():
def test_crew_with_delegating_agents_should_not_override_agent_tools(ceo, writer):
from typing import Type
from pydantic import BaseModel, Field
@@ -679,7 +691,7 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_task_tools_override_agent_tools():
def test_task_tools_override_agent_tools(researcher):
from typing import Type
from pydantic import BaseModel, Field
@@ -734,7 +746,7 @@ def test_task_tools_override_agent_tools():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_task_tools_override_agent_tools_with_allow_delegation():
def test_task_tools_override_agent_tools_with_allow_delegation(researcher, writer):
"""
Test that task tools override agent tools while preserving delegation tools when allow_delegation=True
"""
@@ -817,7 +829,7 @@ def test_task_tools_override_agent_tools_with_allow_delegation():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_verbose_output(capsys):
def test_crew_verbose_output(researcher, writer, capsys):
tasks = [
Task(
description="Research AI advancements.",
@@ -877,7 +889,7 @@ def test_crew_verbose_output(capsys):
@pytest.mark.vcr(filter_headers=["authorization"])
def test_cache_hitting_between_agents():
def test_cache_hitting_between_agents(researcher, writer, ceo):
from unittest.mock import call, patch
from crewai.tools import tool
@@ -1050,7 +1062,7 @@ def test_agents_rpm_is_never_set_if_crew_max_RPM_is_not_set():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_sequential_async_task_execution_completion():
def test_sequential_async_task_execution_completion(researcher, writer):
list_ideas = Task(
description="Give me a list of 5 interesting ideas to explore for an article, what makes them unique and interesting.",
expected_output="Bullet point list of 5 important events.",
@@ -1204,7 +1216,7 @@ async def test_crew_async_kickoff():
@pytest.mark.asyncio
@pytest.mark.vcr(filter_headers=["authorization"])
async def test_async_task_execution_call_count():
async def test_async_task_execution_call_count(researcher, writer):
from unittest.mock import MagicMock, patch
list_ideas = Task(
@@ -1707,7 +1719,7 @@ def test_agents_do_not_get_delegation_tools_with_there_is_only_one_agent():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_sequential_crew_creation_tasks_without_agents():
def test_sequential_crew_creation_tasks_without_agents(researcher):
task = Task(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
@@ -1757,7 +1769,7 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_hierarchical_crew_creation_tasks_with_agents():
def test_hierarchical_crew_creation_tasks_with_agents(researcher, writer):
"""
Agents are not required for tasks in a hierarchical process but sometimes they are still added
This test makes sure that the manager still delegates the task to the agent even if the agent is passed in the task
@@ -1810,7 +1822,7 @@ def test_hierarchical_crew_creation_tasks_with_agents():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_hierarchical_crew_creation_tasks_with_async_execution():
def test_hierarchical_crew_creation_tasks_with_async_execution(researcher, writer, ceo):
"""
Tests that async tasks in hierarchical crews are handled correctly with proper delegation tools
"""
@@ -1867,7 +1879,7 @@ def test_hierarchical_crew_creation_tasks_with_async_execution():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_hierarchical_crew_creation_tasks_with_sync_last():
def test_hierarchical_crew_creation_tasks_with_sync_last(researcher, writer, ceo):
"""
Agents are not required for tasks in a hierarchical process but sometimes they are still added
This test makes sure that the manager still delegates the task to the agent even if the agent is passed in the task
@@ -2153,7 +2165,6 @@ def test_tools_with_custom_caching():
with patch.object(
CacheHandler, "add", wraps=crew._cache_handler.add
) as add_to_cache:
result = crew.kickoff()
# Check that add_to_cache was called exactly twice
@@ -2170,7 +2181,7 @@ def test_tools_with_custom_caching():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_conditional_task_uses_last_output():
def test_conditional_task_uses_last_output(researcher, writer):
"""Test that conditional tasks use the last task output for condition evaluation."""
task1 = Task(
description="First task",
@@ -2244,7 +2255,7 @@ def test_conditional_task_uses_last_output():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_conditional_tasks_result_collection():
def test_conditional_tasks_result_collection(researcher, writer):
"""Test that task outputs are properly collected based on execution status."""
task1 = Task(
description="Normal task that always executes",
@@ -2325,7 +2336,7 @@ def test_conditional_tasks_result_collection():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_multiple_conditional_tasks():
def test_multiple_conditional_tasks(researcher, writer):
"""Test that having multiple conditional tasks in sequence works correctly."""
task1 = Task(
description="Initial research task",
@@ -2560,7 +2571,7 @@ def test_disabled_memory_using_contextual_memory():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_log_file_output(tmp_path):
def test_crew_log_file_output(tmp_path, researcher):
test_file = tmp_path / "logs.txt"
tasks = [
Task(
@@ -2658,7 +2669,7 @@ def test_crew_output_file_validation_failures():
Crew(agents=[agent], tasks=[task]).kickoff()
def test_manager_agent():
def test_manager_agent(researcher, writer):
from unittest.mock import patch
task = Task(
@@ -2696,7 +2707,7 @@ def test_manager_agent():
mock_execute_sync.assert_called()
def test_manager_agent_in_agents_raises_exception():
def test_manager_agent_in_agents_raises_exception(researcher, writer):
task = Task(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
@@ -2718,7 +2729,7 @@ def test_manager_agent_in_agents_raises_exception():
)
def test_manager_agent_with_tools_raises_exception():
def test_manager_agent_with_tools_raises_exception(researcher, writer):
from crewai.tools import tool
@tool
@@ -2755,7 +2766,7 @@ def test_manager_agent_with_tools_raises_exception():
@patch("crewai.crew.TaskEvaluator")
@patch("crewai.crew.Crew.copy")
def test_crew_train_success(
copy_mock, task_evaluator, crew_training_handler, kickoff_mock
copy_mock, task_evaluator, crew_training_handler, kickoff_mock, researcher, writer
):
task = Task(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
@@ -2831,7 +2842,7 @@ def test_crew_train_success(
assert isinstance(received_events[1], CrewTrainCompletedEvent)
def test_crew_train_error():
def test_crew_train_error(researcher, writer):
task = Task(
description="Come up with a list of 5 interesting ideas to explore for an article",
expected_output="5 bullet points with a paragraph for each idea.",
@@ -2850,7 +2861,7 @@ def test_crew_train_error():
)
def test__setup_for_training():
def test__setup_for_training(researcher, writer):
researcher.allow_delegation = True
writer.allow_delegation = True
agents = [researcher, writer]
@@ -2881,7 +2892,7 @@ def test__setup_for_training():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_replay_feature():
def test_replay_feature(researcher, writer):
list_ideas = Task(
description="Generate a list of 5 interesting ideas to explore for an article, where each bulletpoint is under 15 words.",
expected_output="Bullet point list of 5 important events. No additional commentary.",
@@ -2918,7 +2929,7 @@ def test_replay_feature():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_replay_error():
def test_crew_replay_error(researcher, writer):
task = Task(
description="Come up with a list of 5 interesting ideas to explore for an article",
expected_output="5 bullet points with a paragraph for each idea.",
@@ -3314,7 +3325,7 @@ def test_replay_setup_context():
assert crew.tasks[1].prompt_context == "context raw output"
def test_key():
def test_key(researcher, writer):
tasks = [
Task(
description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
@@ -3383,7 +3394,9 @@ def test_key_with_interpolated_inputs():
assert crew.key == curr_key
def test_conditional_task_requirement_breaks_when_singular_conditional_task():
def test_conditional_task_requirement_breaks_when_singular_conditional_task(
researcher, writer
):
def condition_fn(output) -> bool:
return output.raw.startswith("Andrew Ng has!!")
@@ -3401,7 +3414,7 @@ def test_conditional_task_requirement_breaks_when_singular_conditional_task():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_conditional_task_last_task_when_conditional_is_true():
def test_conditional_task_last_task_when_conditional_is_true(researcher, writer):
def condition_fn(output) -> bool:
return True
@@ -3428,7 +3441,7 @@ def test_conditional_task_last_task_when_conditional_is_true():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_conditional_task_last_task_when_conditional_is_false():
def test_conditional_task_last_task_when_conditional_is_false(researcher, writer):
def condition_fn(output) -> bool:
return False
@@ -3452,7 +3465,7 @@ def test_conditional_task_last_task_when_conditional_is_false():
assert result.raw == "Hi"
def test_conditional_task_requirement_breaks_when_task_async():
def test_conditional_task_requirement_breaks_when_task_async(researcher, writer):
def my_condition(context):
return context.get("some_value") > 10
@@ -3477,7 +3490,7 @@ def test_conditional_task_requirement_breaks_when_task_async():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_conditional_should_skip():
def test_conditional_should_skip(researcher, writer):
task1 = Task(description="Return hello", expected_output="say hi", agent=researcher)
condition_mock = MagicMock(return_value=False)
@@ -3509,7 +3522,7 @@ def test_conditional_should_skip():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_conditional_should_execute():
def test_conditional_should_execute(researcher, writer):
task1 = Task(description="Return hello", expected_output="say hi", agent=researcher)
condition_mock = MagicMock(
@@ -3542,7 +3555,7 @@ def test_conditional_should_execute():
@mock.patch("crewai.crew.CrewEvaluator")
@mock.patch("crewai.crew.Crew.copy")
@mock.patch("crewai.crew.Crew.kickoff")
def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator, researcher):
task = Task(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
@@ -3592,7 +3605,7 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
@pytest.mark.vcr(filter_headers=["authorization"])
def test_hierarchical_verbose_manager_agent():
def test_hierarchical_verbose_manager_agent(researcher, writer):
task = Task(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
@@ -3613,7 +3626,7 @@ def test_hierarchical_verbose_manager_agent():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_hierarchical_verbose_false_manager_agent():
def test_hierarchical_verbose_false_manager_agent(researcher, writer):
task = Task(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
@@ -4186,7 +4199,7 @@ def test_before_kickoff_without_inputs():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_with_knowledge_sources_works_with_copy():
def test_crew_with_knowledge_sources_works_with_copy(researcher, writer):
content = "Brandon's favorite color is red and he likes Mexican food."
string_source = StringKnowledgeSource(content=content)
@@ -4195,7 +4208,6 @@ def test_crew_with_knowledge_sources_works_with_copy():
tasks=[Task(description="test", expected_output="test", agent=researcher)],
knowledge_sources=[string_source],
)
crew_copy = crew.copy()
assert crew_copy.knowledge_sources == crew.knowledge_sources
@@ -4339,3 +4351,35 @@ def test_crew_copy_with_memory():
raise e # Re-raise other validation errors
except Exception as e:
pytest.fail(f"Copying crew raised an unexpected exception: {e}")
def test_sets_parent_flow_when_outside_flow(researcher, writer):
crew = Crew(
agents=[researcher, writer],
process=Process.sequential,
tasks=[
Task(description="Task 1", expected_output="output", agent=researcher),
Task(description="Task 2", expected_output="output", agent=writer),
],
)
assert crew.parent_flow is None
def test_sets_parent_flow_when_inside_flow(researcher, writer):
class MyFlow(Flow):
@start()
def start(self):
return Crew(
agents=[researcher, writer],
process=Process.sequential,
tasks=[
Task(
description="Task 1", expected_output="output", agent=researcher
),
Task(description="Task 2", expected_output="output", agent=writer),
],
)
flow = MyFlow()
result = flow.kickoff()
assert result.parent_flow is flow

2
tests/knowledge/knowledge_test.py
View File

@@ -547,6 +547,7 @@ def test_excel_knowledge_source(mock_vector_db, tmpdir):
mock_vector_db.query.assert_called_once()
@pytest.mark.vcr
def test_docling_source(mock_vector_db):
docling_source = CrewDoclingSource(
file_paths=[
@@ -567,6 +568,7 @@ def test_docling_source(mock_vector_db):
mock_vector_db.query.assert_called_once()
@pytest.mark.vcr
def test_multiple_docling_sources():
urls: List[Union[Path, str]] = [
"https://lilianweng.github.io/posts/2024-11-28-reward-hacking/",

10
tests/project_test.py
View File

@@ -1,4 +1,5 @@
from typing import List
from unittest.mock import patch
import pytest
@@ -142,6 +143,15 @@ def test_agent_function_calling_llm():
), "agent's function_calling_llm is incorrect"
def test_task_guardrail():
crew = InternalCrew()
research_task = crew.research_task()
assert research_task.guardrail == "ensure each bullet contains its source"
reporting_task = crew.reporting_task()
assert reporting_task.guardrail is None
@pytest.mark.vcr(filter_headers=["authorization"])
def test_before_kickoff_modification():
crew = InternalCrew()

69
tests/telemetry/test_telemetry.py Normal file
View File

@@ -0,0 +1,69 @@
import os
from unittest.mock import patch
import pytest
from crewai import Agent, Crew, Task
from crewai.telemetry import Telemetry
@pytest.mark.parametrize(
"env_var,value,expected_ready",
[
("OTEL_SDK_DISABLED", "true", False),
("OTEL_SDK_DISABLED", "TRUE", False),
("CREWAI_DISABLE_TELEMETRY", "true", False),
("CREWAI_DISABLE_TELEMETRY", "TRUE", False),
("OTEL_SDK_DISABLED", "false", True),
("CREWAI_DISABLE_TELEMETRY", "false", True),
],
)
def test_telemetry_environment_variables(env_var, value, expected_ready):
"""Test telemetry state with different environment variable configurations."""
with patch.dict(os.environ, {env_var: value}):
with patch("crewai.telemetry.telemetry.TracerProvider"):
telemetry = Telemetry()
assert telemetry.ready is expected_ready
def test_telemetry_enabled_by_default():
"""Test that telemetry is enabled by default."""
with patch.dict(os.environ, {}, clear=True):
with patch("crewai.telemetry.telemetry.TracerProvider"):
telemetry = Telemetry()
assert telemetry.ready is True
from opentelemetry import trace
@patch("crewai.telemetry.telemetry.logger.error")
@patch(
"opentelemetry.exporter.otlp.proto.http.trace_exporter.OTLPSpanExporter.export",
side_effect=Exception("Test exception"),
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_telemetry_fails_due_connect_timeout(export_mock, logger_mock):
error = Exception("Test exception")
export_mock.side_effect = error
tracer = trace.get_tracer(__name__)
with tracer.start_as_current_span("test-span"):
agent = Agent(
role="agent",
llm="gpt-4o-mini",
goal="Just say hi",
backstory="You are a helpful assistant that just says hi",
)
task = Task(
description="Just say hi",
expected_output="hi",
agent=agent,
)
crew = Crew(agents=[agent], tasks=[task], name="TestCrew")
crew.kickoff()
trace.get_tracer_provider().force_flush()
export_mock.assert_called_once()
logger_mock.assert_called_once_with(error)

60
tests/test_lite_agent.py
View File

@@ -1,13 +1,16 @@
import asyncio
from typing import cast
from unittest.mock import Mock
import pytest
from pydantic import BaseModel, Field
from crewai import LLM, Agent
from crewai.flow import Flow, start
from crewai.lite_agent import LiteAgent, LiteAgentOutput
from crewai.tools import BaseTool
from crewai.utilities.events import crewai_event_bus
from crewai.utilities.events.agent_events import LiteAgentExecutionStartedEvent
from crewai.utilities.events.tool_usage_events import ToolUsageStartedEvent
@@ -255,3 +258,60 @@ async def test_lite_agent_returns_usage_metrics_async():
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
class TestFlow(Flow):
"""A test flow that creates and runs an agent."""
def __init__(self, llm, tools):
self.llm = llm
self.tools = tools
super().__init__()
@start()
def start(self):
agent = Agent(
role="Test Agent",
goal="Test Goal",
backstory="Test Backstory",
llm=self.llm,
tools=self.tools,
)
return agent.kickoff("Test query")
def verify_agent_parent_flow(result, agent, flow):
"""Verify that both the result and agent have the correct parent flow."""
assert result.parent_flow is flow
assert agent is not None
assert agent.parent_flow is flow
def test_sets_parent_flow_when_inside_flow():
captured_agent = None
mock_llm = Mock(spec=LLM)
mock_llm.call.return_value = "Test response"
class MyFlow(Flow):
@start()
def start(self):
agent = Agent(
role="Test Agent",
goal="Test Goal",
backstory="Test Backstory",
llm=mock_llm,
tools=[WebSearchTool()],
)
return agent.kickoff("Test query")
flow = MyFlow()
with crewai_event_bus.scoped_handlers():
@crewai_event_bus.on(LiteAgentExecutionStartedEvent)
def capture_agent(source, event):
nonlocal captured_agent
captured_agent = source
result = flow.kickoff()
assert captured_agent.parent_flow is flow

150
tests/test_task_guardrails.py
View File

@@ -1,11 +1,16 @@
"""Tests for task guardrails functionality."""
from unittest.mock import Mock
from unittest.mock import ANY, Mock, patch
import pytest
from crewai.task import Task
from crewai import Agent, Task
from crewai.llm import LLM
from crewai.tasks.llm_guardrail import LLMGuardrail
from crewai.tasks.task_output import TaskOutput
from crewai.utilities.events import (
LLMGuardrailCompletedEvent,
LLMGuardrailStartedEvent,
)
from crewai.utilities.events.crewai_event_bus import crewai_event_bus
def test_task_without_guardrail():
@@ -22,7 +27,7 @@ def test_task_without_guardrail():
assert result.raw == "test result"
def test_task_with_successful_guardrail():
def test_task_with_successful_guardrail_func():
"""Test that successful guardrail validation passes transformed result."""
def guardrail(result: TaskOutput):
@@ -127,3 +132,138 @@ def test_guardrail_error_in_context():
assert "Task failed guardrail validation" in str(exc_info.value)
assert "Expected JSON, got string" in str(exc_info.value)
@pytest.fixture
def sample_agent():
return Agent(role="Test Agent", goal="Test Goal", backstory="Test Backstory")
@pytest.fixture
def task_output():
return TaskOutput(
raw="""
Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever
""",
description="Test task",
expected_output="Output",
agent="Test Agent",
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_task_guardrail_process_output(task_output):
guardrail = LLMGuardrail(
description="Ensure the result has less than 10 words", llm=LLM(model="gpt-4o")
)
result = guardrail(task_output)
assert result[0] is False
assert "exceeding the guardrail limit of fewer than" in result[1].lower()
guardrail = LLMGuardrail(
description="Ensure the result has less than 500 words", llm=LLM(model="gpt-4o")
)
result = guardrail(task_output)
assert result[0] is True
assert result[1] == task_output.raw
@pytest.mark.vcr(filter_headers=["authorization"])
def test_guardrail_emits_events(sample_agent):
started_guardrail = []
completed_guardrail = []
with crewai_event_bus.scoped_handlers():
@crewai_event_bus.on(LLMGuardrailStartedEvent)
def handle_guardrail_started(source, event):
started_guardrail.append(
{"guardrail": event.guardrail, "retry_count": event.retry_count}
)
@crewai_event_bus.on(LLMGuardrailCompletedEvent)
def handle_guardrail_completed(source, event):
completed_guardrail.append(
{
"success": event.success,
"result": event.result,
"error": event.error,
"retry_count": event.retry_count,
}
)
task = Task(
description="Gather information about available books on the First World War",
agent=sample_agent,
expected_output="A list of available books on the First World War",
guardrail="Ensure the authors are from Italy",
)
result = task.execute_sync(agent=sample_agent)
def custom_guardrail(result: TaskOutput):
return (True, "good result from callable function")
task = Task(
description="Test task",
expected_output="Output",
guardrail=custom_guardrail,
)
task.execute_sync(agent=sample_agent)
expected_started_events = [
{"guardrail": "Ensure the authors are from Italy", "retry_count": 0},
{"guardrail": "Ensure the authors are from Italy", "retry_count": 1},
{
"guardrail": """def custom_guardrail(result: TaskOutput):
return (True, "good result from callable function")""",
"retry_count": 0,
},
]
expected_completed_events = [
{
"success": False,
"result": None,
"error": "The task result does not comply with the guardrail because none of "
"the listed authors are from Italy. All authors mentioned are from "
"different countries, including Germany, the UK, the USA, and others, "
"which violates the requirement that authors must be Italian.",
"retry_count": 0,
},
{"success": True, "result": result.raw, "error": None, "retry_count": 1},
{
"success": True,
"result": "good result from callable function",
"error": None,
"retry_count": 0,
},
]
assert started_guardrail == expected_started_events
assert completed_guardrail == expected_completed_events
@pytest.mark.vcr(filter_headers=["authorization"])
def test_guardrail_when_an_error_occurs(sample_agent, task_output):
with (
patch(
"crewai.Agent.kickoff",
side_effect=Exception("Unexpected error"),
),
pytest.raises(
Exception,
match="Error while validating the task output: Unexpected error",
),
):
task = Task(
description="Gather information about available books on the First World War",
agent=sample_agent,
expected_output="A list of available books on the First World War",
guardrail="Ensure the authors are from Italy",
max_retries=0,
)
task.execute_sync(agent=sample_agent)

13
tests/utilities/events/test_crewai_event_bus.py
View File

@@ -32,3 +32,16 @@ def test_wildcard_event_handler():
crewai_event_bus.emit("source_object", event)
mock_handler.assert_called_once_with("source_object", event)
def test_event_bus_error_handling(capfd):
@crewai_event_bus.on(BaseEvent)
def broken_handler(source, event):
raise ValueError("Simulated handler failure")
event = TestEvent(type="test_event")
crewai_event_bus.emit("source_object", event)
out, err = capfd.readouterr()
assert "Simulated handler failure" in out
assert "Handler 'broken_handler' failed" in out