andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 00:28:31 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Resolved Merge Conflicts for PR #712: Remove Hyphen in co-workers (#786)

Browse Source 
* removed hyphen in co-workers

* Fix issue with AgentTool agent selection. The LLM included double quotes in the agent name which messed up the string comparison. Added additional types. Cleaned up error messaging.

* Remove duplicate import

* Improve explanation

* Revert poetry.lock changes

* Fix missing line in poetry.lock

---------

Co-authored-by: madmag77 <goncharov.artemv@gmail.com>
This commit is contained in:
Brandon Hancock (bhancock_ai)
2024-06-18 15:57:56 -04:00
committed by GitHub
parent e6445afac5
commit 377f919d42
17 changed files with 194 additions and 171 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
tests/cassettes/test_increment_delegations_for_hierarchical_process.yaml
View File

@@ -144,20 +144,20 @@ interactions:
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\nDelegate work to co-worker: Delegate work to co-worker(task:
are not listed here:\n\nDelegate work to coworker: Delegate work to coworker(task:
str, context: str, coworker: Optional[str] = None, **kwargs) - Delegate a specific
task to one of the following co-workers: [Scorer]\nThe input to this tool should
be the co-worker, the task you want them to do, and ALL necessary context to
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 absolute everything
you know, don''t reference things but instead explain them.\nAsk question to
co-worker: Ask question to co-worker(question: str, context: str, coworker:
coworker: Ask question to coworker(question: str, context: str, coworker:
Optional[str] = None, **kwargs) - Ask a specific question to one of the following
co-workers: [Scorer]\nThe input to this tool should be the co-worker, the question
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 absolute everything you know, don''t
reference things but instead explain them.\n\nUse the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [Delegate work to co-worker, Ask question to co-worker], just the name,
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
a python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
@@ -1391,7 +1391,7 @@ interactions:
it must be outcome described.\n\nI MUST use these formats, my job depends on
it!\nCurrent Task: What criteria do you use to score a title and how are these
criteria weighted?\n\nThis is the expect criteria for your final answer: Your
best answer to your co-worker asking you this, accounting for the context shared.
best answer to your coworker asking you this, accounting for the context shared.
\n you MUST return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\nI need to assign a score between 1-5 to
the title ''The impact of AI in the future of work.'' To ensure I understand
@@ -3120,20 +3120,20 @@ interactions:
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\nDelegate work to co-worker: Delegate work to co-worker(task:
are not listed here:\n\nDelegate work to coworker: Delegate work to coworker(task:
str, context: str, coworker: Optional[str] = None, **kwargs) - Delegate a specific
task to one of the following co-workers: [Scorer]\nThe input to this tool should
be the co-worker, the task you want them to do, and ALL necessary context to
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 absolute everything
you know, don''t reference things but instead explain them.\nAsk question to
co-worker: Ask question to co-worker(question: str, context: str, coworker:
coworker: Ask question to coworker(question: str, context: str, coworker:
Optional[str] = None, **kwargs) - Ask a specific question to one of the following
co-workers: [Scorer]\nThe input to this tool should be the co-worker, the question
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 absolute everything you know, don''t
reference things but instead explain them.\n\nUse the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [Delegate work to co-worker, Ask question to co-worker], just the name,
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
a python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
@@ -3149,7 +3149,7 @@ interactions:
contribute to a title''s score and how these factors are weighted. Given I can''t
make assumptions and have to provide all necessary context, I need to first
gather this information to ensure the task is completed accurately.\n\nAction:
Ask question to co-worker\n\nAction Input: {\"question\": \"What criteria do
Ask question to coworker\n\nAction Input: {\"question\": \"What criteria do
you use to score a title and how are these criteria weighted?\", \"context\":
\"I need to assign a score between 1-5 to the title ''The impact of AI in the
future of work.'' To ensure I understand how to evaluate this title accurately,
@@ -4438,7 +4438,7 @@ interactions:
the task.\nYour 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!\nCurrent Task: Score the title using the provided criteria\n\nThis is the
expect criteria for your final answer: Your best answer to your co-worker asking
expect criteria for your final answer: Your best answer to your coworker asking
you this, accounting for the context shared. \n you MUST return the actual complete
content as the final answer, not a summary.\n\nThis is the context you''re working
with:\nThe title to be scored is ''The impact of AI in the future of work.''
@@ -4936,20 +4936,20 @@ interactions:
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\nDelegate work to co-worker: Delegate work to co-worker(task:
are not listed here:\n\nDelegate work to coworker: Delegate work to coworker(task:
str, context: str, coworker: Optional[str] = None, **kwargs) - Delegate a specific
task to one of the following co-workers: [Scorer]\nThe input to this tool should
be the co-worker, the task you want them to do, and ALL necessary context to
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 absolute everything
you know, don''t reference things but instead explain them.\nAsk question to
co-worker: Ask question to co-worker(question: str, context: str, coworker:
coworker: Ask question to coworker(question: str, context: str, coworker:
Optional[str] = None, **kwargs) - Ask a specific question to one of the following
co-workers: [Scorer]\nThe input to this tool should be the co-worker, the question
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 absolute everything you know, don''t
reference things but instead explain them.\n\nUse the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [Delegate work to co-worker, Ask question to co-worker], just the name,
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
a python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
@@ -4965,7 +4965,7 @@ interactions:
contribute to a title''s score and how these factors are weighted. Given I can''t
make assumptions and have to provide all necessary context, I need to first
gather this information to ensure the task is completed accurately.\n\nAction:
Ask question to co-worker\n\nAction Input: {\"question\": \"What criteria do
Ask question to coworker\n\nAction Input: {\"question\": \"What criteria do
you use to score a title and how are these criteria weighted?\", \"context\":
\"I need to assign a score between 1-5 to the title ''The impact of AI in the
future of work.'' To ensure I understand how to evaluate this title accurately,
@@ -4997,7 +4997,7 @@ interactions:
impact of AI in the future of work\" based on Relevance, Clarity, Originality,
Engagement, and Length. Given my understanding of the title''s subject and the
criteria provided, I can now delegate the task of scoring the title using these
specific guidelines.\n\nAction: Delegate work to co-worker\n\nAction Input:
specific guidelines.\n\nAction: Delegate work to coworker\n\nAction Input:
{\"task\": \"Score the title using the provided criteria\", \"context\": \"The
title to be scored is ''The impact of AI in the future of work.'' Based on our
scoring system, please evaluate the title against the following five criteria,