Compare commits

...

13 Commits

Author SHA1 Message Date
Devin AI
65ce1dbf31 fix: Fix type-checker error in crew_agent_executor.py
Co-Authored-By: Joe Moura <joao@crewai.com>
2025-02-12 11:19:28 +00:00
Devin AI
7ada6daa39 test: Update VCR configuration and test cases
Co-Authored-By: Joe Moura <joao@crewai.com>
2025-02-12 11:15:03 +00:00
Devin AI
16ab38f330 test: Add VCR cassettes for tool output formatting tests
Co-Authored-By: Joe Moura <joao@crewai.com>
2025-02-12 11:13:54 +00:00
Devin AI
09417f9821 style: Fix import sorting in crew_test.py
Co-Authored-By: Joe Moura <joao@crewai.com>
2025-02-12 11:10:49 +00:00
Devin AI
77fa4a548e test: Update test environment and VCR configuration
- Add mock_openai_key fixture for consistent test API key
- Update VCR configuration to record API interactions
- Update test cases to handle None and whitespace inputs

Co-Authored-By: Joe Moura <joao@crewai.com>
2025-02-12 11:06:44 +00:00
Devin AI
e9e998e8b2 test: Update VCR cassette with proper test API key
Co-Authored-By: Joe Moura <joao@crewai.com>
2025-02-12 11:02:18 +00:00
Devin AI
4c7fe88ca2 test: Add negative test cases for tool output formatting
Co-Authored-By: Joe Moura <joao@crewai.com>
2025-02-12 11:01:37 +00:00
Devin AI
9c2d49d3de fix: Fix indentation in crew_agent_executor.py
Co-Authored-By: Joe Moura <joao@crewai.com>
2025-02-12 11:00:42 +00:00
Devin AI
892e4f6154 style: Fix import sorting in crew_test.py
Co-Authored-By: Joe Moura <joao@crewai.com>
2025-02-12 10:58:12 +00:00
Devin AI
c8bb9561ce refactor: Improve backtick stripping and test coverage
- Extract backtick stripping to _clean_tool_result method
- Add docstrings explaining the backtick cleaning logic
- Add parameterized tests for various backtick scenarios

Co-Authored-By: Joe Moura <joao@crewai.com>
2025-02-12 10:56:42 +00:00
Devin AI
4073d9a103 style: Fix import sorting in crew_test.py
Co-Authored-By: Joe Moura <joao@crewai.com>
2025-02-12 10:55:31 +00:00
Devin AI
4129a93993 test: Add VCR cassette for hierarchical tool output test
Co-Authored-By: Joe Moura <joao@crewai.com>
2025-02-12 10:53:43 +00:00
Devin AI
c830ffab7a fix: Remove extra backticks from hierarchical tool outputs
Issue #2105 - Tool outputs in hierarchical mode were getting extra backticks
appended. This fix:
- Strips trailing backticks from tool results
- Adds test to verify tool output formatting in hierarchical mode

Co-Authored-By: Joe Moura <joao@crewai.com>
2025-02-12 10:53:11 +00:00
11 changed files with 1044 additions and 61 deletions

View File

@@ -366,23 +366,41 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
tool_result = tool_calling.message
return ToolResult(result=tool_result, result_as_answer=False)
else:
if tool_calling.tool_name.casefold().strip() in [
name.casefold().strip() for name in self.tool_name_to_tool_map
] or tool_calling.tool_name.casefold().replace("_", " ") in [
name.casefold().strip() for name in self.tool_name_to_tool_map
]:
valid_names = [name.casefold().strip() for name in self.tool_name_to_tool_map]
tool_name = tool_calling.tool_name.casefold().strip()
tool_name_alt = tool_calling.tool_name.casefold().replace("_", " ")
if tool_name in valid_names or tool_name_alt in valid_names:
tool_result = tool_usage.use(tool_calling, agent_action.text)
tool_result = self._clean_tool_result(tool_result)
tool = self.tool_name_to_tool_map.get(tool_calling.tool_name)
if tool:
return ToolResult(
result=tool_result, result_as_answer=tool.result_as_answer
)
else:
tool_result = self._i18n.errors("wrong_tool_name").format(
tool=tool_calling.tool_name,
tools=", ".join([tool.name.casefold() for tool in self.tools]),
return ToolResult(
result=tool_result,
result_as_answer=tool.result_as_answer if tool else False
)
return ToolResult(result=tool_result, result_as_answer=False)
tool_result = self._i18n.errors("wrong_tool_name").format(
tool=tool_calling.tool_name,
tools=", ".join([tool.name.casefold() for tool in self.tools]),
)
return ToolResult(result=tool_result, result_as_answer=False)
def _clean_tool_result(self, tool_result: Any) -> Any:
"""Clean tool result by removing trailing backticks.
This is particularly important in hierarchical mode where tool outputs
might contain markdown formatting that needs to be cleaned up.
Args:
tool_result: The result from a tool execution, can be any type
Returns:
The cleaned result with any trailing backticks removed if it's a string,
otherwise returns the original result unchanged
"""
if isinstance(tool_result, str):
return tool_result.rstrip('`').rstrip('```')
return tool_result
def _summarize_messages(self) -> None:
messages_groups = []

View File

@@ -0,0 +1,111 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate a specific task to one of the following
coworkers: Researcher\nThe input to this tool should be the coworker, the task
you want them to do, and ALL necessary context to execute the task, they know
nothing about the task, so share absolute everything you know, don''t reference
things but instead explain them.\nTool Name: Ask question to coworker\nTool
Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
of the following coworkers: Researcher\nThe input to this tool should be the
coworker, the question you have for them, and ALL necessary context to ask the
question properly, they know nothing about the question, so share absolute everything
you know, don''t reference things but instead explain them.\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 [Delegate work
to coworker, Ask question to coworker], 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: Test task
using test_tool\n\nThis is the expected criteria for your final answer: Test
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", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2915'
content-type:
- application/json
cookie:
- __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
_cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- x64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
x-stainless-package-version:
- 1.61.0
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 \"error\": {\n \"message\": \"Incorrect API key provided:
sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
\ \"type\": \"invalid_request_error\",\n \"param\": null,\n \"code\":
\"invalid_api_key\"\n }\n}\n"
headers:
CF-RAY:
- 910c25fe3c8ca373-SEA
Connection:
- keep-alive
Content-Length:
- '272'
Content-Type:
- application/json; charset=utf-8
Date:
- Wed, 12 Feb 2025 11:13:16 GMT
Server:
- cloudflare
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
vary:
- Origin
x-request-id:
- req_a5651cefb4c7ae9483499a8e538f579d
http_version: HTTP/1.1
status_code: 401
version: 1

View File

@@ -0,0 +1,111 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate a specific task to one of the following
coworkers: Researcher\nThe input to this tool should be the coworker, the task
you want them to do, and ALL necessary context to execute the task, they know
nothing about the task, so share absolute everything you know, don''t reference
things but instead explain them.\nTool Name: Ask question to coworker\nTool
Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
of the following coworkers: Researcher\nThe input to this tool should be the
coworker, the question you have for them, and ALL necessary context to ask the
question properly, they know nothing about the question, so share absolute everything
you know, don''t reference things but instead explain them.\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 [Delegate work
to coworker, Ask question to coworker], 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: Test task
using test_tool\n\nThis is the expected criteria for your final answer: Test
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", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2915'
content-type:
- application/json
cookie:
- __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
_cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- x64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
x-stainless-package-version:
- 1.61.0
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 \"error\": {\n \"message\": \"Incorrect API key provided:
sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
\ \"type\": \"invalid_request_error\",\n \"param\": null,\n \"code\":
\"invalid_api_key\"\n }\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 910c25fa2a76a373-SEA
Connection:
- keep-alive
Content-Length:
- '272'
Content-Type:
- application/json; charset=utf-8
Date:
- Wed, 12 Feb 2025 11:13:15 GMT
Server:
- cloudflare
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
vary:
- Origin
x-request-id:
- req_3ad40f35d4ad6d42f9bbb7fd8ace9a68
http_version: HTTP/1.1
status_code: 401
version: 1

View File

@@ -0,0 +1,111 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate a specific task to one of the following
coworkers: Researcher\nThe input to this tool should be the coworker, the task
you want them to do, and ALL necessary context to execute the task, they know
nothing about the task, so share absolute everything you know, don''t reference
things but instead explain them.\nTool Name: Ask question to coworker\nTool
Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
of the following coworkers: Researcher\nThe input to this tool should be the
coworker, the question you have for them, and ALL necessary context to ask the
question properly, they know nothing about the question, so share absolute everything
you know, don''t reference things but instead explain them.\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 [Delegate work
to coworker, Ask question to coworker], 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: Test task
using test_tool\n\nThis is the expected criteria for your final answer: Test
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", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2915'
content-type:
- application/json
cookie:
- __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
_cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- x64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
x-stainless-package-version:
- 1.61.0
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 \"error\": {\n \"message\": \"Incorrect API key provided:
sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
\ \"type\": \"invalid_request_error\",\n \"param\": null,\n \"code\":
\"invalid_api_key\"\n }\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 910c26028e7ba373-SEA
Connection:
- keep-alive
Content-Length:
- '272'
Content-Type:
- application/json; charset=utf-8
Date:
- Wed, 12 Feb 2025 11:13:17 GMT
Server:
- cloudflare
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
vary:
- Origin
x-request-id:
- req_6f0f7d9e36bbb3ffea4d672b30b700b9
http_version: HTTP/1.1
status_code: 401
version: 1

View File

@@ -0,0 +1,111 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate a specific task to one of the following
coworkers: Researcher\nThe input to this tool should be the coworker, the task
you want them to do, and ALL necessary context to execute the task, they know
nothing about the task, so share absolute everything you know, don''t reference
things but instead explain them.\nTool Name: Ask question to coworker\nTool
Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
of the following coworkers: Researcher\nThe input to this tool should be the
coworker, the question you have for them, and ALL necessary context to ask the
question properly, they know nothing about the question, so share absolute everything
you know, don''t reference things but instead explain them.\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 [Delegate work
to coworker, Ask question to coworker], 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: Test task
using test_tool\n\nThis is the expected criteria for your final answer: Test
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", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2915'
content-type:
- application/json
cookie:
- __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
_cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- x64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
x-stainless-package-version:
- 1.61.0
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 \"error\": {\n \"message\": \"Incorrect API key provided:
sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
\ \"type\": \"invalid_request_error\",\n \"param\": null,\n \"code\":
\"invalid_api_key\"\n }\n}\n"
headers:
CF-RAY:
- 910c25f5e85ba373-SEA
Connection:
- keep-alive
Content-Length:
- '272'
Content-Type:
- application/json; charset=utf-8
Date:
- Wed, 12 Feb 2025 11:13:15 GMT
Server:
- cloudflare
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
vary:
- Origin
x-request-id:
- req_49a0c35d5999eb9f6d71fcea9fa3c68f
http_version: HTTP/1.1
status_code: 401
version: 1

View File

@@ -0,0 +1,111 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate a specific task to one of the following
coworkers: Researcher\nThe input to this tool should be the coworker, the task
you want them to do, and ALL necessary context to execute the task, they know
nothing about the task, so share absolute everything you know, don''t reference
things but instead explain them.\nTool Name: Ask question to coworker\nTool
Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
of the following coworkers: Researcher\nThe input to this tool should be the
coworker, the question you have for them, and ALL necessary context to ask the
question properly, they know nothing about the question, so share absolute everything
you know, don''t reference things but instead explain them.\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 [Delegate work
to coworker, Ask question to coworker], 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: Test task
using test_tool\n\nThis is the expected criteria for your final answer: Test
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", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2915'
content-type:
- application/json
cookie:
- __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
_cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- x64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
x-stainless-package-version:
- 1.61.0
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 \"error\": {\n \"message\": \"Incorrect API key provided:
sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
\ \"type\": \"invalid_request_error\",\n \"param\": null,\n \"code\":
\"invalid_api_key\"\n }\n}\n"
headers:
CF-RAY:
- 910c25f1be28a373-SEA
Connection:
- keep-alive
Content-Length:
- '272'
Content-Type:
- application/json; charset=utf-8
Date:
- Wed, 12 Feb 2025 11:13:14 GMT
Server:
- cloudflare
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
vary:
- Origin
x-request-id:
- req_573ccd417b499cf38012dec20261964d
http_version: HTTP/1.1
status_code: 401
version: 1

View File

@@ -0,0 +1,111 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate a specific task to one of the following
coworkers: Researcher\nThe input to this tool should be the coworker, the task
you want them to do, and ALL necessary context to execute the task, they know
nothing about the task, so share absolute everything you know, don''t reference
things but instead explain them.\nTool Name: Ask question to coworker\nTool
Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
of the following coworkers: Researcher\nThe input to this tool should be the
coworker, the question you have for them, and ALL necessary context to ask the
question properly, they know nothing about the question, so share absolute everything
you know, don''t reference things but instead explain them.\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 [Delegate work
to coworker, Ask question to coworker], 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: Test task
using test_tool\n\nThis is the expected criteria for your final answer: Test
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", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2915'
content-type:
- application/json
cookie:
- __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
_cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- x64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
x-stainless-package-version:
- 1.61.0
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 \"error\": {\n \"message\": \"Incorrect API key provided:
sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
\ \"type\": \"invalid_request_error\",\n \"param\": null,\n \"code\":
\"invalid_api_key\"\n }\n}\n"
headers:
CF-RAY:
- 910c25e84886a373-SEA
Connection:
- keep-alive
Content-Length:
- '272'
Content-Type:
- application/json; charset=utf-8
Date:
- Wed, 12 Feb 2025 11:13:13 GMT
Server:
- cloudflare
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
vary:
- Origin
x-request-id:
- req_e48016407be31edd1f9ee2e1bb4d1b30
http_version: HTTP/1.1
status_code: 401
version: 1

View File

@@ -0,0 +1,114 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate a specific task to one of the following
coworkers: Researcher\nThe input to this tool should be the coworker, the task
you want them to do, and ALL necessary context to execute the task, they know
nothing about the task, so share absolute everything you know, don''t reference
things but instead explain them.\nTool Name: Ask question to coworker\nTool
Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
of the following coworkers: Researcher\nThe input to this tool should be the
coworker, the question you have for them, and ALL necessary context to ask the
question properly, they know nothing about the question, so share absolute everything
you know, don''t reference things but instead explain them.\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 [Delegate work
to coworker, Ask question to coworker], 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: Test task
using test_tool\n\nThis is the expected criteria for your final answer: Test
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", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2915'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- x64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
x-stainless-package-version:
- 1.61.0
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 \"error\": {\n \"message\": \"Incorrect API key provided:
sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
\ \"type\": \"invalid_request_error\",\n \"param\": null,\n \"code\":
\"invalid_api_key\"\n }\n}\n"
headers:
CF-RAY:
- 910c25e11d1da373-SEA
Connection:
- keep-alive
Content-Length:
- '272'
Content-Type:
- application/json; charset=utf-8
Date:
- Wed, 12 Feb 2025 11:13:11 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
path=/; expires=Wed, 12-Feb-25 11:43:11 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
vary:
- Origin
x-request-id:
- req_e07e0bddd718b7d5978b6bd9f138fa40
http_version: HTTP/1.1
status_code: 401
version: 1

View File

@@ -0,0 +1,111 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate a specific task to one of the following
coworkers: Researcher\nThe input to this tool should be the coworker, the task
you want them to do, and ALL necessary context to execute the task, they know
nothing about the task, so share absolute everything you know, don''t reference
things but instead explain them.\nTool Name: Ask question to coworker\nTool
Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
of the following coworkers: Researcher\nThe input to this tool should be the
coworker, the question you have for them, and ALL necessary context to ask the
question properly, they know nothing about the question, so share absolute everything
you know, don''t reference things but instead explain them.\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 [Delegate work
to coworker, Ask question to coworker], 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: Test task
using test_tool\n\nThis is the expected criteria for your final answer: Test
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", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2915'
content-type:
- application/json
cookie:
- __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
_cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- x64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
x-stainless-package-version:
- 1.61.0
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 \"error\": {\n \"message\": \"Incorrect API key provided:
sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
\ \"type\": \"invalid_request_error\",\n \"param\": null,\n \"code\":
\"invalid_api_key\"\n }\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 910c25ec6a9fa373-SEA
Connection:
- keep-alive
Content-Length:
- '272'
Content-Type:
- application/json; charset=utf-8
Date:
- Wed, 12 Feb 2025 11:13:13 GMT
Server:
- cloudflare
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
vary:
- Origin
x-request-id:
- req_f9215c0efc514e3dfea73d6c5f49eb4e
http_version: HTTP/1.1
status_code: 401
version: 1

View File

@@ -8,6 +8,11 @@ from dotenv import load_dotenv
load_result = load_dotenv(override=True)
@pytest.fixture(autouse=True)
def mock_openai_key(monkeypatch):
"""Mock OpenAI API key for VCR cassettes."""
monkeypatch.setenv("OPENAI_API_KEY", "sk-fake-test-key-12345")
@pytest.fixture(autouse=True)
def setup_test_environment():
"""Set up test environment with a temporary directory for SQLite storage."""

View File

@@ -3,6 +3,7 @@
import hashlib
import json
from concurrent.futures import Future
from typing import Any
from unittest import mock
from unittest.mock import MagicMock, patch
@@ -14,7 +15,9 @@ from crewai.agent import Agent
from crewai.agents.cache import CacheHandler
from crewai.crew import Crew
from crewai.crews.crew_output import CrewOutput
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
from crewai.knowledge.source.string_knowledge_source import (
StringKnowledgeSource,
)
from crewai.memory.contextual.contextual_memory import ContextualMemory
from crewai.process import Process
from crewai.project import crew
@@ -22,10 +25,13 @@ from crewai.task import Task
from crewai.tasks.conditional_task import ConditionalTask
from crewai.tasks.output_format import OutputFormat
from crewai.tasks.task_output import TaskOutput
from crewai.tools.base_tool import BaseTool
from crewai.types.usage_metrics import UsageMetrics
from crewai.utilities import Logger
from crewai.utilities.rpm_controller import RPMController
from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
from crewai.utilities.task_output_storage_handler import (
TaskOutputStorageHandler,
)
ceo = Agent(
role="CEO",
@@ -315,6 +321,69 @@ def test_sync_task_execution():
assert mock_execute_sync.call_count == len(tasks)
@pytest.mark.vcr(
filter_headers=["authorization"],
record_mode="once",
decode_compressed_response=True,
ignore_localhost=True,
match_on=["method", "scheme", "host", "port", "path"]
)
@pytest.mark.parametrize(
"tool_output,expected",
[
("test result```", "test result"),
("test result`", "test result"),
("test result``````", "test result"),
("test result", "test result"),
("test ```result```", "test ```result"), # Only strip trailing backticks
(None, "None"), # Test non-string input gets converted to string
(" ", " "), # Test whitespace string
(
"malformed`result```test",
"malformed`result```test",
), # Test non-trailing backticks
],
)
def test_hierarchical_tool_output_formatting(tool_output, expected):
"""Test that tool outputs in hierarchical mode don't have extra backticks.
This test verifies that the tool output cleaning functionality correctly handles
various scenarios of backtick formatting, ensuring only trailing backticks are
removed while preserving any inline markdown formatting.
"""
class TestTool(BaseTool):
name: str = "test_tool"
description: str = "A test tool"
def _run(self, *args: Any, **kwargs: Any) -> str:
return tool_output
task = Task(
description="Test task using test_tool",
expected_output="Test output",
)
crew = Crew(
agents=[researcher],
process=Process.hierarchical,
manager_llm="gpt-4o",
tasks=[task],
tools=[TestTool()],
)
with patch.object(
Task,
"execute_sync",
return_value=TaskOutput(
description="Test task", raw=expected, agent="researcher"
),
) as mock_execute_sync:
result = crew.kickoff()
assert mock_execute_sync.called
assert result.raw == expected
@pytest.mark.vcr(filter_headers=["authorization"])
def test_hierarchical_process():
task = Task(
@@ -591,12 +660,12 @@ def test_crew_with_delegating_agents_should_not_override_task_tools():
_, kwargs = mock_execute_sync.call_args
tools = kwargs["tools"]
assert any(
isinstance(tool, TestTool) for tool in tools
), "TestTool should be present"
assert any(
"delegate" in tool.name.lower() for tool in tools
), "Delegation tool should be present"
assert any(isinstance(tool, TestTool) for tool in tools), (
"TestTool should be present"
)
assert any("delegate" in tool.name.lower() for tool in tools), (
"Delegation tool should be present"
)
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -655,12 +724,12 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
_, kwargs = mock_execute_sync.call_args
tools = kwargs["tools"]
assert any(
isinstance(tool, TestTool) for tool in new_ceo.tools
), "TestTool should be present"
assert any(
"delegate" in tool.name.lower() for tool in tools
), "Delegation tool should be present"
assert any(isinstance(tool, TestTool) for tool in new_ceo.tools), (
"TestTool should be present"
)
assert any("delegate" in tool.name.lower() for tool in tools), (
"Delegation tool should be present"
)
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -784,17 +853,17 @@ def test_task_tools_override_agent_tools_with_allow_delegation():
used_tools = kwargs["tools"]
# Confirm AnotherTestTool is present but TestTool is not
assert any(
isinstance(tool, AnotherTestTool) for tool in used_tools
), "AnotherTestTool should be present"
assert not any(
isinstance(tool, TestTool) for tool in used_tools
), "TestTool should not be present among used tools"
assert any(isinstance(tool, AnotherTestTool) for tool in used_tools), (
"AnotherTestTool should be present"
)
assert not any(isinstance(tool, TestTool) for tool in used_tools), (
"TestTool should not be present among used tools"
)
# Confirm delegation tool(s) are present
assert any(
"delegate" in tool.name.lower() for tool in used_tools
), "Delegation tool should be present"
assert any("delegate" in tool.name.lower() for tool in used_tools), (
"Delegation tool should be present"
)
# Finally, make sure the agent's original tools remain unchanged
assert len(researcher_with_delegation.tools) == 1
@@ -1595,9 +1664,9 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
# Verify that exactly one tool was used and it was a CodeInterpreterTool
assert len(used_tools) == 1, "Should have exactly one tool"
assert isinstance(
used_tools[0], CodeInterpreterTool
), "Tool should be CodeInterpreterTool"
assert isinstance(used_tools[0], CodeInterpreterTool), (
"Tool should be CodeInterpreterTool"
)
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -3418,9 +3487,9 @@ def test_fetch_inputs():
expected_placeholders = {"role_detail", "topic", "field"}
actual_placeholders = crew.fetch_inputs()
assert (
actual_placeholders == expected_placeholders
), f"Expected {expected_placeholders}, but got {actual_placeholders}"
assert actual_placeholders == expected_placeholders, (
f"Expected {expected_placeholders}, but got {actual_placeholders}"
)
def test_task_tools_preserve_code_execution_tools():
@@ -3493,20 +3562,20 @@ def test_task_tools_preserve_code_execution_tools():
used_tools = kwargs["tools"]
# Verify all expected tools are present
assert any(
isinstance(tool, TestTool) for tool in used_tools
), "Task's TestTool should be present"
assert any(
isinstance(tool, CodeInterpreterTool) for tool in used_tools
), "CodeInterpreterTool should be present"
assert any(
"delegate" in tool.name.lower() for tool in used_tools
), "Delegation tool should be present"
assert any(isinstance(tool, TestTool) for tool in used_tools), (
"Task's TestTool should be present"
)
assert any(isinstance(tool, CodeInterpreterTool) for tool in used_tools), (
"CodeInterpreterTool should be present"
)
assert any("delegate" in tool.name.lower() for tool in used_tools), (
"Delegation tool should be present"
)
# Verify the total number of tools (TestTool + CodeInterpreter + 2 delegation tools)
assert (
len(used_tools) == 4
), "Should have TestTool, CodeInterpreter, and 2 delegation tools"
assert len(used_tools) == 4, (
"Should have TestTool, CodeInterpreter, and 2 delegation tools"
)
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -3550,9 +3619,9 @@ def test_multimodal_flag_adds_multimodal_tools():
used_tools = kwargs["tools"]
# Check that the multimodal tool was added
assert any(
isinstance(tool, AddImageTool) for tool in used_tools
), "AddImageTool should be present when agent is multimodal"
assert any(isinstance(tool, AddImageTool) for tool in used_tools), (
"AddImageTool should be present when agent is multimodal"
)
# Verify we have exactly one tool (just the AddImageTool)
assert len(used_tools) == 1, "Should only have the AddImageTool"
@@ -3778,9 +3847,9 @@ def test_crew_guardrail_feedback_in_context():
assert len(execution_contexts) > 1, "Task should have been executed multiple times"
# Verify that the second execution included the guardrail feedback
assert (
"Output must contain the keyword 'IMPORTANT'" in execution_contexts[1]
), "Guardrail feedback should be included in retry context"
assert "Output must contain the keyword 'IMPORTANT'" in execution_contexts[1], (
"Guardrail feedback should be included in retry context"
)
# Verify final output meets guardrail requirements
assert "IMPORTANT" in result.raw, "Final output should contain required keyword"