mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-11 00:58:30 +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
@@ -716,4 +716,249 @@ interactions:
|
||||
- req_04659f093830c14dbc5342c119533861
|
||||
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: Researcher, Senior Writer\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: Researcher, Senior Writer\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: 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.\n\nThis is the expected criteria
|
||||
for your final answer: 5 bullet points with a paragraph for each idea.\nyou
|
||||
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
|
||||
This is VERY important to you, use the tools available and give your best Final
|
||||
Answer, your job depends on it!\n\nThought:"}, {"role": "assistant", "content":
|
||||
"```\nThought: To come up with interesting article ideas and write compelling
|
||||
highlights, I should first generate a list of potential topics. The Researcher
|
||||
can help with gathering current trends or interesting topics that might be engaging.
|
||||
Then, I can delegate writing the paragraph highlights to the Senior Writer.\n\nAction:
|
||||
Ask question to coworker\nAction Input: {\"question\": \"What are some current
|
||||
trending topics or subjects that are interesting to explore for an article?\",
|
||||
\"context\": \"I need to generate a list of 5 interesting ideas to explore for
|
||||
an article, each paired with an amazing paragraph highlight. Current trends
|
||||
or unusual insights could be a good source of inspiration for these ideas.\",
|
||||
\"coworker\": \"Researcher\"}\nObservation: **1. The Rise of Autonomous AI Agents
|
||||
in Daily Life** \nAs artificial intelligence technology progresses, the integration
|
||||
of autonomous AI agents into everyday life becomes increasingly prominent. These
|
||||
agents, capable of making decisions without human intervention, are reshaping
|
||||
industries from healthcare to finance. Exploring case studies where autonomous
|
||||
AI has successfully decreased operational costs or improved efficiency can reveal
|
||||
not only the benefits but also the ethical implications of delegating decision-making
|
||||
to machines. This topic offers an exciting opportunity to dive into the AI landscape,
|
||||
showcasing current developments such as AI assistants and autonomous vehicles.\n\n**2.
|
||||
Ethical Implications of Generative AI in Creative Industries** \nThe surge
|
||||
of generative AI tools in creative fields, such as art, music, and writing,
|
||||
has sparked a heated debate about authorship and originality. This article could
|
||||
investigate how these tools are being used by artists and creators, examining
|
||||
both the potential for innovation and the risk of devaluing traditional art
|
||||
forms. Highlighting perspectives from creators, legal experts, and ethicists
|
||||
could provide a comprehensive overview of the challenges faced, including copyright
|
||||
concerns and the emotional impact on human artists. This discussion is vital
|
||||
as the creative landscape evolves alongside technological advancements, making
|
||||
it ripe for exploration.\n\n**3. AI in Climate Change Mitigation: Current Solutions
|
||||
and Future Potential** \nAs the world grapples with climate change, AI technology
|
||||
is increasingly being harnessed to develop innovative solutions for sustainability.
|
||||
From predictive analytics that optimize energy consumption to machine learning
|
||||
algorithms that improve carbon capture methods, AI''s potential in environmental
|
||||
science is vast. This topic invites an exploration of existing AI applications
|
||||
in climate initiatives, with a focus on groundbreaking research and initiatives
|
||||
aimed at reducing humanity''s carbon footprint. Highlighting successful projects
|
||||
and technology partnerships can illustrate the positive impact AI can have on
|
||||
global climate efforts, inspiring further exploration and investment in this
|
||||
area.\n\n**4. The Future of Work: How AI is Reshaping Employment Landscapes** \nThe
|
||||
discussions around AI''s impact on the workforce are both urgent and complex,
|
||||
as advances in automation and machine learning continue to transform the job
|
||||
market. This article could delve into the current trends of AI-driven job displacement
|
||||
alongside opportunities for upskilling and the creation of new job roles. By
|
||||
examining case studies of companies that integrate AI effectively and the resulting
|
||||
workforce adaptations, readers can gain valuable insights into preparing for
|
||||
a future where humans and AI collaborate. This exploration highlights the importance
|
||||
of policies that promote workforce resilience in the face of change.\n\n**5.
|
||||
Decentralized AI: Exploring the Role of Blockchain in AI Development** \nAs
|
||||
blockchain technology sweeps through various sectors, its application in AI
|
||||
development presents a fascinating topic worth examining. Decentralized AI could
|
||||
address issues of data privacy, security, and democratization in AI models by
|
||||
allowing users to retain ownership of data while benefiting from AI''s capabilities.
|
||||
This article could analyze how decentralized networks are disrupting traditional
|
||||
AI development models, featuring innovative projects that harness the synergy
|
||||
between blockchain and AI. Highlighting potential pitfalls and the future landscape
|
||||
of decentralized AI could stimulate discussion among technologists, entrepreneurs,
|
||||
and policymakers alike.\n\nThese topics not only reflect current trends but
|
||||
also probe deeper into ethical and practical considerations, making them timely
|
||||
and relevant for contemporary audiences."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate, zstd
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '7865'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- _cfuvid=icM8L9.yRk22iqPJZhDQeVHgfWZOnl1YiBFMJmVO8_8-1743465529821-0.0.1.1-604800000
|
||||
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//bFfbbhy5EX3fryjoZQFjJNiO7az1pvUlK8ABAsdBAqweXENWd5fFZhEs
|
||||
do9G+/NBkZyLtPsiaGZYzbqcc+r0Hz8BXLC/uIYLN2FxcwqXH37Zfnz/6N/e/qBZCf3+/X/e3H+5
|
||||
j/8rMYwXG4uQ7Q9y5RB15WROgQpLbD+7TFjInvrq72/fvXr39t379/WHWTwFCxtTuXwjl69fvn5z
|
||||
+fKXy5fveuAk7EgvruH3nwAA/qh/LcXo6eHiGl5uDt/MpIojXVwfDwFcZAn2zQWqshaM5WJz+tFJ
|
||||
LBRr1t+/f7+L3yZZxqlcwy1E2cGEKwFCYC0gA3AslEkLxxGKJHYKGD2UiThDwoxjxjTBxOMUeJyK
|
||||
QpmwwExU7BC4zIUyIwySYaRIGeuzKI442j+YC7tAwJ5Qr+7iXfzMEQPcRN1Rvoa7+OoKXrz4NhF8
|
||||
ZSXL6WYpEmWWReHmFm5GikWBI3xEDnv4wgO9eAFwFwHgRusFAzvGUIsJgUeKjqCQm6IEGfeQsoyZ
|
||||
VEk3NWk7N1qiEu0+fHIfHu4rArRS3nvcQ+CBYEtOZrKfbPLKcQz12TNHiuUKvk2k1OM34DDhNtSC
|
||||
Zry3VnhyrCxRYcdlkqXAtMwY2wxWipbPBjATZNIJk8Vw9IuWzKQwZJlhIgxlcnaoCAwcMTq6gk8P
|
||||
KUi2AIdKoGXxFrKbKNOz+iZU0MU5Uh2WEPaWlpVDHiRR6woGcKJFQTLwnLKs5IEGazNFtweHETKt
|
||||
hAGiFJAY9rWxW4o0cFHYLgUwqNRvqUzsbDxzCuzqBWpt8RRobHA5tOayt6oIzOgmjqTWV9YGTpBh
|
||||
oGwQBXpwXEMlJclliVz2FuZ5pTY8u/rmFgJGrw4TbUAn2bk6OHBLzhQLeFopSJrrzHVxE2BDwYFa
|
||||
jQ9nLVxpMkA3LL827H7q9d0+q+8fnQ5rzYMjfDDBsI+3x6kekWwE0CWPFTDjk8giEioB3CF+YApe
|
||||
N8eEMZcNzIuy29R0d7n2ZtOGnTDfkwc08BTy4GmLhQC3BkFcyiRZJ041UjKPxk8u+974A4GdLMED
|
||||
x9XUYrQHTLKzJiv1DA2UW7LuLoam7b7Gam9hTV6yboAecOZo57ZSpjqnJKZZxmHTEY5R1kbPLkaQ
|
||||
We8bZlYMS4VIRs8drJiLBc56Bb8dlMrOJMqayFnPOn9OWRj2AtBDomx0tYsqUGvCrVgDPnuTS5P+
|
||||
TBNFtfbLSnll2llCVQQnDIHiaJegI78xiQiLr0CTtM+WDziJjnI8CizQLD1/nhM641FXhN63PgHP
|
||||
6hY1egArrFysYu3y2xFxRDnQKsHKxSBxVEv/qIQVpehX04y5qVTnGxfInKh2n6qW1PZXjP/NMN4B
|
||||
HHi2yX+YMI4E/+SKBJZ4DR86of4tYWkMsDI/L2XJBP86jPdcuC3/neTgwXZMCtR0EVy/xNVLNpUB
|
||||
Jy3nZ/rbADdhjibwvkpA4/QRRiuBHrOyCnXRghxxyw3nnw0ZKZPnChXAiGFfbBfWZSep8MyPBMbK
|
||||
cW+D1GVOFZ8noYJAmCuqMYySuUxzj+8KCg7zVqIthtqUmcokxuKb25/1jAEcgeLKWaLNCANoVV2q
|
||||
w0ctTwSR48qFuiIe52bApAdua93ULJ0pkwlJbzFHLlw7pJvWfFvkblGD4phliX6bqUEkkxJm05vo
|
||||
zwMBeTZ1KZDJL65Ow0DMZf+zHmoeRErKbFvyCUFPi8jIZm6r0+NseWMukapCaV08HIKJp+XfpEO5
|
||||
Tq2T6Oa2nqo+x6oIsrV11iumYZDKd46auG7MYclloie47zWa1NkMrGWlaSFh5cSbg2fpAJcB/iv5
|
||||
/hp+k10Ve4Wvxx3+aU5B9vVBXw40fSr8J4bbHdb2BoqTLnSy3A+SHTWlNe20hRFL09fqTh82dR80
|
||||
jtdZ2+qaT1X9Ca3mFzku1U+UjFFNSOt9P2QLs+2O8perwFM4X7WHjVoyRV/3383tpc+8UqxP8qwp
|
||||
YBOeM3E6re/qcSTDkvSeQ6hM6krZZK7hOtKuPs9MsF7Br/uzffLE/MhQe4LRPjQidt9XtyoNQ9sM
|
||||
YX/aMqRLqMA867XHVBp1NpAJvRkQQ9iIHMG2UbV5HLX549qQlClhQ5dkI1WDSfNjlR4N5wZWCQG3
|
||||
BjzqbT4H4hPjXTEuudhsrbwkwRxZr86cqJRzmGRSDl07GoRsPdXGVG2tUH5rUP5IjmLJGPiRLKvr
|
||||
M0dpcV+lOdlfg7h7N1nlHC37jyf/dK7t29O5MyrrjihZttleSWDFzOaolFxbyeYcz6SqX3Fm0ayv
|
||||
Wq0awoDqOOLpzcUKL9MJDVfwvKoOXPTe3gaAVZeGE48FIWVe0e03ls+SueybKfA0i7NpPJ4nVV/x
|
||||
tHqcEGTXTU82WYZMtl1Adl22jjfsJg5Hk1zBYYunMr2+Ldg64qPjfcq2upMem+nyT+qKVGzkzX95
|
||||
1ryk8twgPWtjy34DA2FZcnvPOO7KoxBXVPXNWlGg+7YAt1R2RPF8yg3Mz+3XcaclLgOGcPI+nRAn
|
||||
21K93V+OSwvPSzDWnhkhnMVKPDobNU23aEqZIi25W7r/AwAA//+MWMsOwiAQvPcrDGcPvlr1YwxB
|
||||
WCopAuFx8NB/N0ur4CvxPMuwC7vJzuQRuV3ZkGWDVgM2fdbFtWb2IFNgKNlN0roCmDF2Hn5U66cZ
|
||||
GZ/6XNveeXsOb0eJVEaFC8U9xRrU4iFaRzI6NovFKfsA6UXaExxgF2m0A+Tr1rt2PxGSYj0UuNsd
|
||||
ZzTayHQBNutVt/xCSQU2pg6VmUA44xcQ5WxxHlgSylZAUxX+mc837ql4Zfp/6AvAObgIgj4Wsrrm
|
||||
EuYBm/RX2POhc8Ik4L7OgUYFHj9DgGRJT7YJCbcQ4UqlMj34vKRgiHT0sDq2Xbvd8jNpxuYOAAD/
|
||||
/wMAWvKreUQSAAA=
|
||||
headers:
|
||||
CF-RAY:
|
||||
- 974efac6faf5cf15-SJC
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Mon, 25 Aug 2025 23:48:25 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- __cf_bm=yJXo3QqFAYYxljNSZBr47v.aphUMHM_ulx8v95ohSS4-1756165705-1.0.1.1-hhSjgTF5yD4vPuetC1LZGfC4KDF6RXEOSk8B4k4kOCq0XyfGNZkzt8kMn.F..aqu9T7UeYwKJprb.ZhscrKkokkqPou4V3aYXTAqIb2GZvE;
|
||||
path=/; expires=Tue, 26-Aug-25 00:18:25 GMT; domain=.api.openai.com; HttpOnly;
|
||||
Secure; SameSite=None
|
||||
- _cfuvid=yh2RjFXBfB0RrOxRjxqkpRIka8SH8Bv0F2PRUGTNLkY-1756165705944-0.0.1.1-604800000;
|
||||
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:
|
||||
- '6170'
|
||||
openai-project:
|
||||
- proj_xitITlrFeen7zjNSzML82h9x
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '6192'
|
||||
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:
|
||||
- '29998089'
|
||||
x-ratelimit-reset-project-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 3ms
|
||||
x-request-id:
|
||||
- req_f470345c656b4bb7abb0ab09372eabef
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
|
||||
Reference in New Issue
Block a user