mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-05-02 15:52:34 +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
@@ -607,4 +607,163 @@ interactions:
|
||||
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.\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 get an integer score between
|
||||
1-5 for the given title. To do this, I''ll ask the Scorer to evaluate the title
|
||||
based on specific criteria.\n\nAction: Ask question to coworker\nAction Input:
|
||||
{\"question\": \"Can you provide an integer score between 1-5 for the following
|
||||
title: ''The impact of AI in the future of work''?\", \"context\": \"We need
|
||||
a score for the title to assess its impact and relevance. Please evaluate based
|
||||
on factors such as clarity, relevance, and potential interest to readers.\",
|
||||
\"coworker\": \"Scorer\"}\nObservation: The score for the title ''The impact
|
||||
of AI in the future of work'' is 4 out of 5."}], "model": "gpt-4o", "stop":
|
||||
["\nObservation:"]}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate, zstd
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '3675'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- _cfuvid=lnKPmS3pW0Tw6qE4ZI8cf4lyVDuLg7ZNxmzxi7CqlME-1756165116673-0.0.1.1-604800000;
|
||||
__cf_bm=r95s2Hh1kHgI6PI08wwTySLyufxeDnmixIX5GVDEyoA-1756165116-1.0.1.1-X5dML3NG4uvFgDnjqJ4pQWbB9MyxJisxAZJlRivMc7T1f83cCNBH_cy5fJjn4XjKks_UKUUj5PvBGifu2gLkaiqYYWvbSjrhjKseuPN8.Q4
|
||||
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//jFLva9swEP3uv0LoczzsJnYTfyuFsUHHftDA2FJsRT7bamRJSOd1o+R/
|
||||
H5LT2F1b2BfB3bv3dO/uHiNCqKhpQSjvGPLeyPh6vV8e7vHbdvv5dtvfaPhw/WX59dOP71l+dUMX
|
||||
nqH398DxifWO695IQKHVCHMLDMGrppdZnuZZmuYB6HUN0tNag/FKxxfJxSpO1nGSn4idFhwcLcjP
|
||||
iBBCHsPrW1Q1/KYFSRZPmR6cYy3Q4lxECLVa+gxlzgmHTCFdTCDXCkGFrquq2qnbTg9thwX5SJR+
|
||||
IAf/YAekEYpJwpR7ALtT70N0FaKCrHaqqqq5qoVmcMybUoOUM4AppZH5oQQ/dyfkeHYgdWus3rt/
|
||||
qLQRSriutMCcVr5bh9rQgB4jQu7CpIZn5qmxujdYoj5A+O5yk456dNrNhKbrE4gamZzy62SzeEWv
|
||||
rAGZkG42a8oZ76CeqNNi2FALPQOimeuX3bymPToXqv0f+QngHAxCXRoLteDPHU9lFvzpvlV2nnJo
|
||||
mDqwvwSHEgVYv4kaGjbI8aqo++MQ+rIRqgVrrBhPqzHlOtlkebZc8j2NjtFfAAAA//8DAJCAq9Rj
|
||||
AwAA
|
||||
headers:
|
||||
CF-RAY:
|
||||
- 974eec8be8b98486-SJC
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Mon, 25 Aug 2025 23:38:37 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:
|
||||
- '383'
|
||||
openai-project:
|
||||
- proj_xitITlrFeen7zjNSzML82h9x
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '488'
|
||||
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:
|
||||
- '29999132'
|
||||
x-ratelimit-reset-project-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 1ms
|
||||
x-request-id:
|
||||
- req_58742f78663b48c2be01fcc6497a46da
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
|
||||
Reference in New Issue
Block a user