mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-10 00:28:31 +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
@@ -449,4 +449,162 @@ interactions:
|
||||
- req_32907c02e96c6932e9424220bb24bb7a
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
- request:
|
||||
body: '{"messages": [{"role": "system", "content": "You are Manager. You''re great
|
||||
at delegating work about scoring.\nYour personal goal is: Coordinate scoring
|
||||
processes\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.\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: To provide
|
||||
an accurate score for the title \"The impact of AI in the future of work,\"
|
||||
I need to delegate the task of scoring it to the Scorer, who is specialized
|
||||
in this activity.\n\nAction: Delegate work to coworker\nAction Input: {\"coworker\":
|
||||
\"Scorer\", \"task\": \"Give me an integer score between 1-5 for the following
|
||||
title: ''The impact of AI in the future of work''\", \"context\": \"Your task
|
||||
is to evaluate the provided title on a scale from 1 to 5 based on criteria such
|
||||
as relevance, clarity, and intrigue.\"}\n\nObservation: The scorer has received
|
||||
the task to score the title ''The impact of AI in the future of work''.\nObservation:
|
||||
4"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate, zstd
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '3322'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- _cfuvid=CW_cKQGYWY3cL.S6Xo5z0cmkmWHy5Q50OA_KjPEijNk-1735926034530-0.0.1.1-604800000
|
||||
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 |
|
||||
H4sIAAAAAAAAA4xSTWvcMBC9+1cMOq+Dvd/1LTQt5NJLP6C0wWjlsa1G1ghpnLSE/e9F2uzaaVPo
|
||||
RSC9eU/vzcxTBiB0IyoQqpesBmfyt/vDSpvbDx+97L+gftjhzVdX3rzT1/3nrVhEBh1+oOIz60rR
|
||||
4AyyJnuClUfJGFXL3WZbbjdluU7AQA2aSOsc52vKl8VynRf7vHjWVT1phUFU8C0DAHhKZ7RoG/wp
|
||||
KigW55cBQ5AdiupSBCA8mfgiZAg6sLQsFhOoyDLa5PpTT2PXcwW3YOkR7uPBPUKrrTQgbXhEf/Xd
|
||||
vk/X63StYD0X89iOQcYsdjRmBkhriWXsRYpx94wcL8YNdc7TIfxBFa22OvS1RxnIRpOByYmEHjOA
|
||||
u9Sg8UVm4TwNjmume0zf7U59TmHPI5nQC8jE0sxYy/3iFb26QZbahFmLhZKqx2aiTvOQY6NpBmSz
|
||||
1H+7eU37lFzb7n/kJ0ApdIxN7Tw2Wr1MPJV5jBv7r7JLl5NhEdA/aIU1a/RxEg22cjSnZRLhV2Ac
|
||||
6lbbDr3z+rRRrav3xZvNdrNaqYPIjtlvAAAA//8DAAsTiaNaAwAA
|
||||
headers:
|
||||
CF-RAY:
|
||||
- 974eec7c4d438486-SJC
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Mon, 25 Aug 2025 23:38:35 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- __cf_bm=ULOCzvd5MabFyMl9eSNQ3Sk_hNbVH25aTAfkSaYM6Cw-1756165115-1.0.1.1-jeyMlIwg.jml3h9XQDOYQXVxEFP44CSbUCENlr4W6RpdsZg08M.fWUD5kBWDNcupp2skTxNh5gCYFNop3HIrWq5pzgrydiA3FuSe7U15X1Y;
|
||||
path=/; expires=Tue, 26-Aug-25 00:08:35 GMT; domain=.api.openai.com; HttpOnly;
|
||||
Secure; SameSite=None
|
||||
- _cfuvid=e_81pnlfj.JohLmFm8gTRISqkPCT6GwCVpOdPsECI.s-1756165115098-0.0.1.1-604800000;
|
||||
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:
|
||||
- '680'
|
||||
openai-project:
|
||||
- proj_xitITlrFeen7zjNSzML82h9x
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '715'
|
||||
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:
|
||||
- '29999221'
|
||||
x-ratelimit-reset-project-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 1ms
|
||||
x-request-id:
|
||||
- req_4006f3362c434ea2a39b9901f3f2e5cb
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
|
||||
Reference in New Issue
Block a user