mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-05-03 00:02:36 +00:00
Lorenze/better tracing events (#3382)
Some checks failed
Notify Downstream / notify-downstream (push) Has been cancelled
Some checks failed
Notify Downstream / notify-downstream (push) Has been cancelled
* feat: implement tool usage limit exception handling - Introduced `ToolUsageLimitExceeded` exception to manage maximum usage limits for tools. - Enhanced `CrewStructuredTool` to check and raise this exception when the usage limit is reached. - Updated `_run` and `_execute` methods to include usage limit checks and handle exceptions appropriately, improving reliability and user feedback. * feat: enhance PlusAPI and ToolUsage with task metadata - Removed the `send_trace_batch` method from PlusAPI to streamline the API. - Added timeout parameters to trace event methods in PlusAPI for improved reliability. - Updated ToolUsage to include task metadata (task name and ID) in event emissions, enhancing traceability and context during tool usage. - Refactored event handling in LLM and ToolUsage events to ensure task information is consistently captured. * feat: enhance memory and event handling with task and agent metadata - Added task and agent metadata to various memory and event classes, improving traceability and context during memory operations. - Updated the `ContextualMemory` and `Memory` classes to associate tasks and agents, allowing for better context management. - Enhanced event emissions in `LLM`, `ToolUsage`, and memory events to include task and agent information, facilitating improved debugging and monitoring. - Refactored event handling to ensure consistent capture of task and agent details across the system. * drop * refactor: clean up unused imports in memory and event modules - Removed unused TYPE_CHECKING imports from long_term_memory.py to streamline the code. - Eliminated unnecessary import from memory_events.py, enhancing clarity and maintainability. * fix memory tests * fix task_completed payload * fix: remove unused test agent variable in external memory tests * refactor: remove unused agent parameter from Memory class save method - Eliminated the agent parameter from the save method in the Memory class to streamline the code and improve clarity. - Updated the TraceBatchManager class by moving initialization of attributes into the constructor for better organization and readability. * refactor: enhance ExecutionState and ReasoningEvent classes with optional task and agent identifiers - Added optional `current_agent_id` and `current_task_id` attributes to the `ExecutionState` class for better tracking of agent and task states. - Updated the `from_task` attribute in the `ReasoningEvent` class to use `Optional[Any]` instead of a specific type, improving flexibility in event handling. * refactor: update ExecutionState class by removing unused agent and task identifiers - Removed the `current_agent_id` and `current_task_id` attributes from the `ExecutionState` class to simplify the code and enhance clarity. - Adjusted the import statements to include `Optional` for better type handling. * refactor: streamline LLM event handling in LiteAgent - Removed unused LLM event emissions (LLMCallStartedEvent, LLMCallCompletedEvent, LLMCallFailedEvent) from the LiteAgent class to simplify the code and improve performance. - Adjusted the flow of LLM response handling by eliminating unnecessary event bus interactions, enhancing clarity and maintainability. * flow ownership and not emitting events when a crew is done * refactor: remove unused agent parameter from ShortTermMemory save method - Eliminated the agent parameter from the save method in the ShortTermMemory class to streamline the code and improve clarity. - This change enhances the maintainability of the memory management system by reducing unnecessary complexity. * runtype check fix * fixing tests * fix lints * fix: update event assertions in test_llm_emits_event_with_lite_agent - Adjusted the expected counts for completed and started events in the test to reflect the correct behavior of the LiteAgent. - Updated assertions for agent roles and IDs to match the expected values after recent changes in event handling. * fix: update task name assertions in event tests - Modified assertions in `test_stream_llm_emits_event_with_task_and_agent_info` and `test_llm_emits_event_with_task_and_agent_info` to use `task.description` as a fallback for `task.name`. This ensures that the tests correctly validate the task name even when it is not explicitly set. * fix: update test assertions for output values and improve readability - Updated assertions in `test_output_json_dict_hierarchical` to reflect the correct expected score value. - Enhanced readability of assertions in `test_output_pydantic_to_another_task` and `test_key` by formatting the error messages for clarity. - These changes ensure that the tests accurately validate the expected outputs and improve overall code quality. * test fixes * fix crew_test * added another fixture * fix: ensure agent and task assignments in contextual memory are conditional - Updated the ContextualMemory class to check for the existence of short-term, long-term, external, and extended memory before assigning agent and task attributes. This prevents potential attribute errors when memory types are not initialized.
This commit is contained in:
Lorenze Jay
@@ -561,4 +561,634 @@ interactions:
|
||||
- req_c8bb2af8f4a63658c3c9316045a413e1
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
- 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: Scorer\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 absolutely 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: Scorer\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 absolutely 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: Give me
|
||||
an integer score between 1-5 for the following title: ''The impact of AI in
|
||||
the future of work''\n\nThis is the expected criteria for your final answer:
|
||||
The score of the title.\nyou MUST return the actual complete content as the
|
||||
final answer, not a summary.\nEnsure your final answer contains only the content
|
||||
in the following format: {\n \"score\": int\n}\n\nEnsure the final output does
|
||||
not include any code block markers like ```json or ```python.\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, zstd
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '3194'
|
||||
content-type:
|
||||
- application/json
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.93.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.93.0
|
||||
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 |
|
||||
H4sIAAAAAAAAA4xUTW/bMAy951cQuvSSFEnbpI1vxYYBxbC1w3rZ5iJQJNrWKouCRLstivz3QY4T
|
||||
u/sAdjEMPvLxPYrS6wRAGC0yEKqSrGpvZ++utud36tZ8jtWHL/rO8O26/fbykb/P3ScnpqmCtj9R
|
||||
8aHqVFHtLbKhHlYBJWNiXVwuV4vVcr5edkBNGm0qKz3PLmh2Nj+7mM2vZvNVX1iRURhFBj8mAACv
|
||||
3TdJdBqfRQbz6SFSY4yyRJEdkwBEIJsiQsZoIkvHYjqAihyj61TfV9SUFWdwAw5RAxNotFhKRuAK
|
||||
gWV8BCogKgrGlfuYYYspk5oAXxUFDFPwgVqj+5QangxX0PV5ZpBbanhUKp0eyCVDJZ0+zV3urlUa
|
||||
XQbvDxKeKDymTorSH4ZDCtw433AGr7lIJLnIIBedlFGbk/sKwdReKk4Wrm/AuA4uGm4CplhiPQFy
|
||||
ICEqaRGKQDUsUsvlaS6mkIvexL7F/UG1cS3ZFiNgK20j+TCb0rToRjaHsUgHxjGWGLphImyRnxAd
|
||||
LLrEJWxlRJ20HB2cRPCUTspI2xuZQkCLrXQKp11d4gwYGSy2aI+a+3ENcwm52I13IGDRRJlW0DXW
|
||||
jgDpHLFMQ+6276FHdsd9s1T6QNv4W6kojDOx2gSUkVzarcjkRYfuJgAP3V43b1ZV+EC15w3TI3bt
|
||||
VperPZ8YbtKALhYXPcrE0g7A5bq/Dm8JNxpZGhtHV0MoqSrUQ+lwj2SjDY2Aycj2n3L+xr23blz5
|
||||
P/QDoBR6Rr3xAbVRby0PaQHTS/OvtOOYO8EiYmiNwg0bDOkoNBaysftHQMSXyFhvCuNKDD6Y/UtQ
|
||||
+M3VfL1cLc/P1VZMdpNfAAAA//8DAFYiBXASBQAA
|
||||
headers:
|
||||
CF-RAY:
|
||||
- 974eec034af08486-SJC
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Mon, 25 Aug 2025 23:38:17 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- __cf_bm=N_ULh2gJbt2dWumbG8h6_rw_QD0TBQ3f1NYS.FsG3w0-1756165097-1.0.1.1-fGULs7H8u7wOLv7QAwRQdlWcZr2zj6dkLXQk5xPa.7SBOn9qj1nh6.VDONMzgxqO2telES4KZZPzeC2G4YFJXV5Q4hemTm4jcMsXA10XFYM;
|
||||
path=/; expires=Tue, 26-Aug-25 00:08:17 GMT; domain=.api.openai.com; HttpOnly;
|
||||
Secure; SameSite=None
|
||||
- _cfuvid=_3IyqhyxR3x9q67TqmIC1eWhmeXZIMbk_6ChUHMngHM-1756165097262-0.0.1.1-604800000;
|
||||
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
||||
Strict-Transport-Security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
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:
|
||||
- '2201'
|
||||
openai-project:
|
||||
- proj_xitITlrFeen7zjNSzML82h9x
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '2275'
|
||||
x-ratelimit-limit-project-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-project-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999242'
|
||||
x-ratelimit-reset-project-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 1ms
|
||||
x-request-id:
|
||||
- req_8253241bc24547018d1600b0ec310060
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"messages": [{"role": "system", "content": "You are Scorer. You''re an
|
||||
expert scorer, specialized in scoring titles.\nYour personal goal is: Score
|
||||
the title\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: Score the title ''The impact of
|
||||
AI in the future of work'' on a scale from 1 to 5.\n\nThis is the expected criteria
|
||||
for your final answer: Your best answer to your coworker asking you this, accounting
|
||||
for the context shared.\nyou MUST return the actual complete content as the
|
||||
final answer, not a summary.\n\nThis is the context you''re working with:\nThe
|
||||
task involves evaluating the given title and providing an integer score between
|
||||
1 and 5 based on the title''s potential impact, relevance, and interest level.\n\nBegin!
|
||||
This is VERY important to you, use the tools available and give your best Final
|
||||
Answer, your job depends on it!\n\nThought:"}, {"role": "assistant", "content":
|
||||
"Thought: I need to delegate the task of scoring the title to our Scorer, providing
|
||||
them with context about the title and the task at hand.\n\nAction: Delegate
|
||||
work to coworker\nAction Input: {\"task\": \"Score the title ''The impact of
|
||||
AI in the future of work'' on a scale from 1 to 5.\", \"context\": \"The task
|
||||
involves evaluating the given title and providing an integer score between 1
|
||||
and 5 based on the title''s potential impact, relevance, and interest level.\",
|
||||
\"coworker\": \"Scorer\"}\nObservation: I encountered an error: Action ''Delegate
|
||||
work to coworker'' don''t exist, these are the only available Actions:\n\nMoving
|
||||
on then. I MUST either use a tool (use one at time) OR give my best final answer
|
||||
not both at the same time. When responding, I must use the following format:\n\n```\nThought:
|
||||
you should always think about what to do\nAction: the action to take, should
|
||||
be one of []\nAction Input: the input to the action, dictionary enclosed in
|
||||
curly braces\nObservation: the result of the action\n```\nThis Thought/Action/Action
|
||||
Input/Result can repeat N times. Once I know the final answer, I must return
|
||||
the following format:\n\n```\nThought: I now can give a great answer\nFinal
|
||||
Answer: Your final answer must be the great and the most complete as possible,
|
||||
it must be outcome described\n\n```"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate, zstd
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '2548'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=N_ULh2gJbt2dWumbG8h6_rw_QD0TBQ3f1NYS.FsG3w0-1756165097-1.0.1.1-fGULs7H8u7wOLv7QAwRQdlWcZr2zj6dkLXQk5xPa.7SBOn9qj1nh6.VDONMzgxqO2telES4KZZPzeC2G4YFJXV5Q4hemTm4jcMsXA10XFYM;
|
||||
_cfuvid=_3IyqhyxR3x9q67TqmIC1eWhmeXZIMbk_6ChUHMngHM-1756165097262-0.0.1.1-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.93.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.93.0
|
||||
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 |
|
||||
H4sIAAAAAAAAA5xVTY/bRgy9+1cQuvRiL7zfW98WKVoYCNoiSHpoHRjjESUxOxoKQ8peI9j/XnC0
|
||||
lrxpChS9CNJw+PhIPlJfZwAFlcUKCt849W0XFu8edtcfPskfhO/p+Vjq49Ofx19/2/10uPz0Cxdz
|
||||
8+DdF/R68rrw3HYBlTgOZp/QKRrq5f3t3eXd7fLH+2xoucRgbnWnixteXC2vbhbLh8Xy7tWxYfIo
|
||||
xQr+mgEAfM1PoxhLfC5WsJyfTloUcTUWq/ESQJE42EnhREjURS3mk9FzVIyZ9ceG+7rRFazhQCEA
|
||||
7l3onSJog6CkAWHnBEvgCKQCHZsnuQDUds7rHBIG3LvocQ4ulkBRMaEoBNxjACfQYcpoNe0xQo79
|
||||
rBebuIkL+H2EW2e4FXwc424Kex/CAFfwuAaKGanqtU9oZwdOT5sCpK9rFBVwUJL4XoQ4GuWGD+an
|
||||
6JvIgWtCGfLU5KJUnNoM0QXnUeZwaMg3QIYjVEeqyLuoOS+lFsMRlDvycCBt4EAlLhI631CsjWcg
|
||||
76z1cmGpfTjVZchJ+qwUA2+obsLxVDi1Gj2uoXECO8QIFE01QrEOx1zOOpmG7JVh7xJxL+CkQ69y
|
||||
qsEcKFahx+iNyxfegQlAhpYkLLGimFnGshdNhAPH9alZ761ZRpTktfokEOhpSBmcarIunBdlbHTZ
|
||||
o93JLU58sDC+T8RCeszxPUePKULC2qXS7I/rHyQzPHXUcqg4mYha95SZKjiwccIQ7HsofMXpvMND
|
||||
doIu+SYr6h1HoRJT9mhQ8FSo+UngXeI9lWgd9pwwI45azxhnIxH5AN7FLF1wUNs0g4tywLSJP1N0
|
||||
AR7z1wpuYfH/tDsJYrhe9WEcKn07U5bVWbVHDTs1ftNoDgHfiJ7iKB1Th6BXTjKgq0xDbNgca86h
|
||||
xkILuB33+k0C2HaBjy1GvTjfLgmrXpwtt9iHcGZwMbIOE2J77fOr5WXcZIHrLvFOvnEtTLzSbG0q
|
||||
ONrWEuWuyNaXGcDnvDH7N0uw6BK3nW6VnzCHu72+GvCKaUdP1qvl7atVWV2YDPfX9/PvAG5LVEdB
|
||||
zpZu4Z1vsJxcpw3t+pL4zDA7S/ufdL6HPaROsf4v8JPBe+wUy22XsCT/NuXpWkLbTP92bSxzJlwI
|
||||
pj153CphslaUWLk+DL+XQo6i2G4rijWmLtHwj6m67c3drqqWuPQPxexl9jcAAAD//wMAzZYQhWwH
|
||||
AAA=
|
||||
headers:
|
||||
CF-RAY:
|
||||
- 974eec121c168486-SJC
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Mon, 25 Aug 2025 23:38:21 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Strict-Transport-Security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
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:
|
||||
- '3958'
|
||||
openai-project:
|
||||
- proj_xitITlrFeen7zjNSzML82h9x
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '4032'
|
||||
x-ratelimit-limit-project-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-project-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999412'
|
||||
x-ratelimit-reset-project-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 1ms
|
||||
x-request-id:
|
||||
- req_bd8ada32c9474dad85877e84f73b632b
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- 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: Scorer\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 absolutely 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: Scorer\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 absolutely 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: Give me
|
||||
an integer score between 1-5 for the following title: ''The impact of AI in
|
||||
the future of work''\n\nThis is the expected criteria for your final answer:
|
||||
The score of the title.\nyou MUST return the actual complete content as the
|
||||
final answer, not a summary.\nEnsure your final answer contains only the content
|
||||
in the following format: {\n \"score\": int\n}\n\nEnsure the final output does
|
||||
not include any code block markers like ```json or ```python.\n\nBegin! This
|
||||
is VERY important to you, use the tools available and give your best Final Answer,
|
||||
your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "Thought:
|
||||
I need to delegate the task of scoring the title to our Scorer, providing them
|
||||
with context about the title and the task at hand.\n\nAction: Delegate work
|
||||
to coworker\nAction Input: {\"task\": \"Score the title ''The impact of AI in
|
||||
the future of work'' on a scale from 1 to 5.\", \"context\": \"The task involves
|
||||
evaluating the given title and providing an integer score between 1 and 5 based
|
||||
on the title''s potential impact, relevance, and interest level.\", \"coworker\":
|
||||
\"Scorer\"}\nObservation: 5 - The title \"The impact of AI in the future of
|
||||
work\" is highly impactful, relevant, and interesting due to the transformative
|
||||
potential of AI technologies in various job sectors and its relevance to ongoing
|
||||
discussions about the future of employment."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate, zstd
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '3994'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=N_ULh2gJbt2dWumbG8h6_rw_QD0TBQ3f1NYS.FsG3w0-1756165097-1.0.1.1-fGULs7H8u7wOLv7QAwRQdlWcZr2zj6dkLXQk5xPa.7SBOn9qj1nh6.VDONMzgxqO2telES4KZZPzeC2G4YFJXV5Q4hemTm4jcMsXA10XFYM;
|
||||
_cfuvid=_3IyqhyxR3x9q67TqmIC1eWhmeXZIMbk_6ChUHMngHM-1756165097262-0.0.1.1-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.93.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.93.0
|
||||
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 |
|
||||
H4sIAAAAAAAAAwAAAP//jFLBbtQwEL3nK0Y+b6pkd5OmuRUQEgiJIgE9kCry2pPErGNbtsOCVvvv
|
||||
yMl2k9JW4uLDvHnj997MMQIggpMSCOuoZ72R8dtit/levOkG/u72k9x/zL7d8DuXfjl8vr++I6vA
|
||||
0LufyPwj64rp3kj0QqsJZhapxzA1vc7yNM/SJB2BXnOUgdYaH291vE7W2zgp4iQ/EzstGDpSwo8I
|
||||
AOA4vkGi4viblJCsHis9OkdbJOWlCYBYLUOFUOeE81R5sppBppVHNar+2umh7XwJH0DpA+zD4zuE
|
||||
RigqgSp3QHtVqUq9Hwu3Y6GEY6UAKuKYtliRErJKnZY/WGwGR4NBNUi5AKhS2tMQ0Ojt4YycLm6k
|
||||
bo3VO/cPlTRCCdfVFqnTKih3XhsyoqcI4GFMbXgSBDFW98bXXu9x/K7Ybqd5ZN7TjK7TM+i1p3LB
|
||||
yrPVC/Nqjp4K6Ra5E0ZZh3ymzkuiAxd6AUQL18/VvDR7ci5U+z/jZ4AxNB55bSxywZ46ntsshjN+
|
||||
re2S8iiYOLS/BMPaC7RhExwbOsjpwoj74zz2dSNUi9ZYMZ1ZY+oiucnybLNhOxKdor8AAAD//wMA
|
||||
Q4ZWRG8DAAA=
|
||||
headers:
|
||||
CF-RAY:
|
||||
- 974eec2bee738486-SJC
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Mon, 25 Aug 2025 23:38:22 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Strict-Transport-Security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
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:
|
||||
- '879'
|
||||
openai-project:
|
||||
- proj_xitITlrFeen7zjNSzML82h9x
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '923'
|
||||
x-ratelimit-limit-project-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-project-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999055'
|
||||
x-ratelimit-reset-project-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 1ms
|
||||
x-request-id:
|
||||
- req_5699dd0d905247f6b4b41d76411079e0
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- 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: Scorer\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 absolutely 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: Scorer\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 absolutely 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: Give me
|
||||
an integer score between 1-5 for the following title: ''The impact of AI in
|
||||
the future of work''\n\nThis is the expected criteria for your final answer:
|
||||
The score of the title.\nyou MUST return the actual complete content as the
|
||||
final answer, not a summary.\nEnsure your final answer contains only the content
|
||||
in the following format: {\n \"score\": int\n}\n\nEnsure the final output does
|
||||
not include any code block markers like ```json or ```python.\n\nBegin! This
|
||||
is VERY important to you, use the tools available and give your best Final Answer,
|
||||
your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "Thought:
|
||||
I need to delegate the task of scoring the title to our Scorer, providing them
|
||||
with context about the title and the task at hand.\n\nAction: Delegate work
|
||||
to coworker\nAction Input: {\"task\": \"Score the title ''The impact of AI in
|
||||
the future of work'' on a scale from 1 to 5.\", \"context\": \"The task involves
|
||||
evaluating the given title and providing an integer score between 1 and 5 based
|
||||
on the title''s potential impact, relevance, and interest level.\", \"coworker\":
|
||||
\"Scorer\"}\nObservation: {\n \"score\": 5\n}"}], "model": "gpt-4o", "stop":
|
||||
["\nObservation:"]}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate, zstd
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '3760'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=N_ULh2gJbt2dWumbG8h6_rw_QD0TBQ3f1NYS.FsG3w0-1756165097-1.0.1.1-fGULs7H8u7wOLv7QAwRQdlWcZr2zj6dkLXQk5xPa.7SBOn9qj1nh6.VDONMzgxqO2telES4KZZPzeC2G4YFJXV5Q4hemTm4jcMsXA10XFYM;
|
||||
_cfuvid=_3IyqhyxR3x9q67TqmIC1eWhmeXZIMbk_6ChUHMngHM-1756165097262-0.0.1.1-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.93.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.93.0
|
||||
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 |
|
||||
H4sIAAAAAAAAAwAAAP//jFJBbtswELzrFQuerUB2LVXVLQnQoufmEKAKBJpaSawpLkFSdgvDfy9I
|
||||
u5bSpkAuBMjZGc7s7ikBYLJlFTAxcC9Go9LHcrf9dnh+mO7p+VN+3PdPGvcH9+XD7rHs2CowaPcD
|
||||
hf/DuhM0GoVekr7AwiL3GFTXH/NiXeTrIovASC2qQOuNT7eUbrLNNs3KNCuuxIGkQMcq+J4AAJzi
|
||||
GSzqFn+yCqJMfBnROd4jq25FAMySCi+MOyed59qz1QwK0h51dP000NQPvoKvoOkI+3D4AaGTmivg
|
||||
2h3R3tX6c7zex2sFp1oD1MwJslizCvJan5f6FrvJ8RBPT0otAK41eR7aE5O9XJHzLYui3ljaub+o
|
||||
rJNauqGxyB3p4Nt5Miyi5wTgJfZsetUGZiyNxjee9hi/K7P8osfmKc3oZn0FPXmuFqxNsXpDr2nR
|
||||
c6ncoutMcDFgO1PnEfGplbQAkkXqf928pX1JLnX/HvkZEAKNx7YxFlspXieeyyyGJf5f2a3L0TBz
|
||||
aA9SYOMl2jCJFjs+qct+MffLeRybTuoerbHysmSdabbFrusyzETJknPyGwAA//8DAAH6vKZtAwAA
|
||||
headers:
|
||||
CF-RAY:
|
||||
- 974eed9bdf8aeb2a-SJC
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Mon, 25 Aug 2025 23:39:21 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Strict-Transport-Security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
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:
|
||||
- '1085'
|
||||
openai-project:
|
||||
- proj_xitITlrFeen7zjNSzML82h9x
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '1107'
|
||||
x-ratelimit-limit-project-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-project-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999114'
|
||||
x-ratelimit-reset-project-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 1ms
|
||||
x-request-id:
|
||||
- req_1b900c7238124d04835cb54adf6d7aeb
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
|
||||
Reference in New Issue
Block a user