andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-08 23:58:34 +00:00
Code Issues Actions 4 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

2
src/crewai/agents/executor.py
View File

@@ -58,7 +58,7 @@ class CrewAgentExecutor(AgentExecutor):
if (
self.crew
and self.crew.memory
and "Action: Delegate work to co-worker" not in output.log
and "Action: Delegate work to coworker" not in output.log
):
memory = ShortTermMemoryItem(
data=output.log,

46
src/crewai/tools/agent_tools.py
View File

@@ -18,14 +18,14 @@ class AgentTools(BaseModel):
tools = [
StructuredTool.from_function(
func=self.delegate_work,
name="Delegate work to co-worker",
name="Delegate work to coworker",
description=self.i18n.tools("delegate_work").format(
coworkers=f"[{', '.join([f'{agent.role}' for agent in self.agents])}]"
),
),
StructuredTool.from_function(
func=self.ask_question,
name="Ask question to co-worker",
name="Ask question to coworker",
description=self.i18n.tools("ask_question").format(
coworkers=f"[{', '.join([f'{agent.role}' for agent in self.agents])}]"
),
@@ -34,34 +34,54 @@ class AgentTools(BaseModel):
return tools
def delegate_work(
self, task: str, context: str, coworker: Union[str, None] = None, **kwargs
self,
task: str,
context: Union[str, None] = None,
coworker: Union[str, None] = None,
**kwargs,
):
"""Useful to delegate a specific task to a co-worker passing all necessary context and names."""
coworker = coworker or kwargs.get("co_worker") or kwargs.get("co-worker")
if coworker is not None:
"""Useful to delegate a specific task to a coworker passing all necessary context and names."""
coworker = coworker or kwargs.get("co_worker") or kwargs.get("coworker")
if coworker:
is_list = coworker.startswith("[") and coworker.endswith("]")
if is_list:
coworker = coworker[1:-1].split(",")[0]
return self._execute(coworker, task, context)
def ask_question(
self, question: str, context: str, coworker: Union[str, None] = None, **kwargs
self,
question: str,
context: Union[str, None] = None,
coworker: Union[str, None] = None,
**kwargs,
):
"""Useful to ask a question, opinion or take from a co-worker passing all necessary context and names."""
coworker = coworker or kwargs.get("co_worker") or kwargs.get("co-worker")
if coworker is not None:
"""Useful to ask a question, opinion or take from a coworker passing all necessary context and names."""
coworker = coworker or kwargs.get("co_worker") or kwargs.get("coworker")
if coworker:
is_list = coworker.startswith("[") and coworker.endswith("]")
if is_list:
coworker = coworker[1:-1].split(",")[0]
return self._execute(coworker, question, context)
def _execute(self, agent, task, context):
def _execute(self, agent: Union[str, None], task: str, context: Union[str, None]):
"""Execute the command."""
try:
if agent is None:
agent = ""
# It is important to remove the quotes from the agent name.
# The reason we have to do this is because less-powerful LLM's
# have difficulty producing valid JSON.
# As a result, we end up with invalid JSON that is truncated like this:
# {"task": "....", "coworker": "....
# when it should look like this:
# {"task": "....", "coworker": "...."}
agent_name = agent.casefold().replace('"', "")
agent = [
available_agent
for available_agent in self.agents
if available_agent.role.casefold().strip() == agent.casefold().strip()
if available_agent.role.casefold() == agent_name
]
except Exception as _:
return self.i18n.errors("agent_tool_unexsiting_coworker").format(
@@ -81,6 +101,6 @@ class AgentTools(BaseModel):
task = Task(
description=task,
agent=agent,
expected_output="Your best answer to your co-worker asking you this, accounting for the context shared.",
expected_output="Your best answer to your coworker asking you this, accounting for the context shared.",
)
return agent.execute_task(task, context)

4
src/crewai/tools/tool_usage.py
View File

@@ -126,8 +126,8 @@ class ToolUsage:
if not result:
try:
if calling.tool_name in [
"Delegate work to co-worker",
"Ask question to co-worker",
"Delegate work to coworker",
"Ask question to coworker",
]:
self.task.increment_delegations()

6
src/crewai/translations/en.json
View File

@@ -21,7 +21,7 @@
},
"errors": {
"force_final_answer": "Tool won't be use because it's time to give your final answer. Don't use tools and just your absolute BEST Final answer.",
"agent_tool_unexsiting_coworker": "\nError executing tool. Co-worker mentioned not found, it must to be one of the following options:\n{coworkers}\n",
"agent_tool_unexsiting_coworker": "\nError executing tool. coworker mentioned not found, it must be one of the following options:\n{coworkers}\n",
"task_repeated_usage": "I tried reusing the same input, I must stop using this action input. I'll try something else instead.\n\n",
"tool_usage_error": "I encountered an error: {error}",
"tool_arguments_error": "Error: the Action Input is not a valid key, value dictionary.",
@@ -29,7 +29,7 @@
"tool_usage_exception": "I encountered an error while trying to use the tool. This was the error: {error}.\n Tool {tool} accepts these inputs: {tool_inputs}"
},
"tools": {
"delegate_work": "Delegate a specific task to one of the following co-workers: {coworkers}\nThe input to this tool should be the co-worker, 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.",
"ask_question": "Ask a specific question to one of the following co-workers: {coworkers}\nThe input to this tool should be the co-worker, 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."
"delegate_work": "Delegate a specific task to one of the following coworkers: {coworkers}\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.",
"ask_question": "Ask a specific question to one of the following coworkers: {coworkers}\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."
}
}

1
src/crewai/utilities/logger.py
View File

@@ -1,4 +1,5 @@
from datetime import datetime
from crewai.utilities.printer import Printer

6
tests/agent_tools/agent_tools_test.py
View File

@@ -55,6 +55,7 @@ def test_ask_question():
== "As an AI researcher, I don't have personal feelings or emotions like love or hate. However, I recognize the importance of AI Agents in today's technological landscape. They have the potential to greatly enhance our lives and make tasks more efficient. At the same time, it is crucial to consider the ethical implications and societal impacts that come with their use. My role is to provide objective research and analysis on these topics."
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_ask_question_with_wrong_co_worker_variable():
result = tools.ask_question(
@@ -68,6 +69,7 @@ def test_ask_question_with_wrong_co_worker_variable():
== "No, I don't hate AI agents. In fact, I find them quite fascinating. They are powerful tools that can greatly assist in various tasks, including my research. As a technology researcher, AI and AI agents are subjects of interest to me due to their potential in advancing our understanding and capabilities in various fields. My supposed love for them stems from this professional interest and the potential they hold."
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_delegate_work_withwith_coworker_as_array():
result = tools.delegate_work(
@@ -105,7 +107,7 @@ def test_delegate_work_to_wrong_agent():
assert (
result
== "\nError executing tool. Co-worker mentioned not found, it must to be one of the following options:\n- researcher\n"
== "\nError executing tool. coworker mentioned not found, it must be one of the following options:\n- researcher\n"
)
@@ -118,5 +120,5 @@ def test_ask_question_to_wrong_agent():
assert (
result
== "\nError executing tool. Co-worker mentioned not found, it must to be one of the following options:\n- researcher\n"
== "\nError executing tool. coworker mentioned not found, it must be one of the following options:\n- researcher\n"
)

2
tests/agent_tools/cassettes/test_ask_question_with_coworker_as_array.yaml
View File

@@ -8,7 +8,7 @@ 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: do you hate AI Agents?\n\nThis is the expect criteria for
your final answer: Your best answer to your co-worker asking you this, accounting
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:\nI
heard you LOVE them\n\nBegin! This is VERY important to you, use the tools available

2
tests/agent_tools/cassettes/test_ask_question_with_wrong_co_worker_variable.yaml
View File

@@ -200797,7 +200797,7 @@ 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: do you hate AI Agents?\n\nThis is the expect criteria for
your final answer: Your best answer to your co-worker asking you this, accounting
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:\nI
heard you LOVE them\n\nBegin! This is VERY important to you, use the tools available

2
tests/agent_tools/cassettes/test_delegate_work_with_wrong_co_worker_variable.yaml
View File

@@ -95,7 +95,7 @@ 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: share your take on AI Agents\n\nThis is the expect criteria
for your final answer: Your best answer to your co-worker asking you this, accounting
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:\nI
heard you hate them\n\nBegin! This is VERY important to you, use the tools available

2
tests/agent_tools/cassettes/test_delegate_work_withwith_coworker_as_array.yaml
View File

@@ -95,7 +95,7 @@ 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: share your take on AI Agents\n\nThis is the expect criteria
for your final answer: Your best answer to your co-worker asking you this, accounting
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:\nI
heard you hate them\n\nBegin! This is VERY important to you, use the tools available

30
tests/cassettes/test_agent_usage_metrics_are_captured_for_hierarchical_process.yaml
View File

@@ -8,20 +8,20 @@ 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(coworker:
are not listed here:\n\nDelegate work to coworker: Delegate work to coworker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: [Researcher]\nThe input to this tool should be the coworker, the
coworkers: [Researcher]\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(coworker: str, question: str, context: str) - Ask a specific question
to one of the following co-workers: [Researcher]\nThe input to this tool should
things but instead explain them.\nAsk question to coworker: Ask question to
coworker(coworker: str, question: str, context: str) - Ask a specific question
to one of the following coworkers: [Researcher]\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, exactly as it''s written.\nAction Input: the input
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 a python dictionary using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
@@ -1027,20 +1027,20 @@ 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(coworker:
are not listed here:\n\nDelegate work to coworker: Delegate work to coworker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: [Researcher]\nThe input to this tool should be the coworker, the
coworkers: [Researcher]\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(coworker: str, question: str, context: str) - Ask a specific question
to one of the following co-workers: [Researcher]\nThe input to this tool should
things but instead explain them.\nAsk question to coworker: Ask question to
coworker(coworker: str, question: str, context: str) - Ask a specific question
to one of the following coworkers: [Researcher]\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, exactly as it''s written.\nAction Input: the input
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 a python dictionary using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
@@ -1051,7 +1051,7 @@ interactions:
job depends on it!\n\nThought: \nI need to delegate the task of saying \"hi\"
to the researcher. I will provide them with the context that this is a simple
greeting task and they should respond with \"Howdy!\".\n\nAction: \nDelegate
work to co-worker\n\nAction Input: \n{\n \"coworker\": \"Researcher\",\n \"task\":
work to coworker\n\nAction Input: \n{\n \"coworker\": \"Researcher\",\n \"task\":
\"Say hi\",\n \"context\": \"This is a simple task where you need to greet
by saying ''Howdy!''. This is a common greeting in certain parts of the world,
particularly in the southern United States. It''s a friendly, informal way to

96
tests/cassettes/test_agent_use_specific_tasks_output_as_context.yaml
View File

@@ -3,19 +3,19 @@ interactions:
body: '{"messages": [{"role": "user", "content": "You are test role. test backstory\nYour
personal goal is: test goal\n\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(coworker: str, task: str, context: str)
- Delegate a specific task to one of the following co-workers: [''test role2'']\nThe
coworker: Delegate work to coworker(coworker: str, task: str, context: str)
- Delegate a specific task to one of the following coworkers: [''test role2'']\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(coworker: str, question:
str, context: str) - Ask a specific question to one of the following co-workers:
them.\nAsk question to coworker: Ask question to coworker(coworker: str, question:
str, context: str) - Ask a specific question to one of the following coworkers:
[''test role2'']\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 using \" to wrap keys and values.\nObservation: the result
of the action\n\nOnce all necessary information is gathered:\n\nThought: I now
@@ -323,19 +323,19 @@ interactions:
body: '{"messages": [{"role": "user", "content": "You are test role. test backstory\nYour
personal goal is: test goal\n\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(coworker: str, task: str, context: str)
- Delegate a specific task to one of the following co-workers: [''test role2'']\nThe
coworker: Delegate work to coworker(coworker: str, task: str, context: str)
- Delegate a specific task to one of the following coworkers: [''test role2'']\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(coworker: str, question:
str, context: str) - Ask a specific question to one of the following co-workers:
them.\nAsk question to coworker: Ask question to coworker(coworker: str, question:
str, context: str) - Ask a specific question to one of the following coworkers:
[''test role2'']\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 using \" to wrap keys and values.\nObservation: the result
of the action\n\nOnce all necessary information is gathered:\n\nThought: I now
@@ -345,23 +345,23 @@ interactions:
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: \nAs this task is very straightforward and doesn''t require
any input or help from my co-worker, I should go ahead and complete it myself.\n\nAction:
any input or help from my coworker, I should go ahead and complete it myself.\n\nAction:
None\n\nAction Input: None\n\nObservation: I encountered an error: Action ''None''
don''t exist, these are the only available Actions: Delegate work to co-worker:
Delegate work to co-worker(coworker: str, task: str, context: str) - Delegate
a specific task to one of the following co-workers: [''test role2'']\nThe input
don''t exist, these are the only available Actions: Delegate work to coworker:
Delegate work to coworker(coworker: str, task: str, context: str) - Delegate
a specific task to one of the following coworkers: [''test role2'']\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(coworker: str, question: str,
context: str) - Ask a specific question to one of the following co-workers:
question to coworker: Ask question to coworker(coworker: str, question: str,
context: str) - Ask a specific question to one of the following coworkers:
[''test role2'']\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.\nMoving on then. I MUST either use
a tool (use one at time) OR give my best final answer. To Use the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, should be one of [Delegate work to co-worker, Ask question to co-worker]\nAction
to take, should be one of [Delegate work to coworker, Ask question to coworker]\nAction
Input: the input to the action, dictionary\nObservation: the result of the action\n...
(this Thought/Action/Action Input/Observation can repeat N times)\nThought:
I now can give a great answer\nFinal Answer: my best complete final answer to
@@ -1024,19 +1024,19 @@ interactions:
body: '{"messages": [{"role": "user", "content": "You are test role. test backstory\nYour
personal goal is: test goal\n\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(coworker: str, task: str, context: str)
- Delegate a specific task to one of the following co-workers: [''test role2'']\nThe
coworker: Delegate work to coworker(coworker: str, task: str, context: str)
- Delegate a specific task to one of the following coworkers: [''test role2'']\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(coworker: str, question:
str, context: str) - Ask a specific question to one of the following co-workers:
them.\nAsk question to coworker: Ask question to coworker(coworker: str, question:
str, context: str) - Ask a specific question to one of the following coworkers:
[''test role2'']\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 using \" to wrap keys and values.\nObservation: the result
of the action\n\nOnce all necessary information is gathered:\n\nThought: I now
@@ -1046,31 +1046,31 @@ interactions:
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: \nAs this task is very straightforward and doesn''t require
any input or help from my co-worker, I should go ahead and complete it myself.\n\nAction:
any input or help from my coworker, I should go ahead and complete it myself.\n\nAction:
None\n\nAction Input: None\n\nObservation: I encountered an error: Action ''None''
don''t exist, these are the only available Actions: Delegate work to co-worker:
Delegate work to co-worker(coworker: str, task: str, context: str) - Delegate
a specific task to one of the following co-workers: [''test role2'']\nThe input
don''t exist, these are the only available Actions: Delegate work to coworker:
Delegate work to coworker(coworker: str, task: str, context: str) - Delegate
a specific task to one of the following coworkers: [''test role2'']\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(coworker: str, question: str,
context: str) - Ask a specific question to one of the following co-workers:
question to coworker: Ask question to coworker(coworker: str, question: str,
context: str) - Ask a specific question to one of the following coworkers:
[''test role2'']\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.\nMoving on then. I MUST either use
a tool (use one at time) OR give my best final answer. To Use the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, should be one of [Delegate work to co-worker, Ask question to co-worker]\nAction
to take, should be one of [Delegate work to coworker, Ask question to coworker]\nAction
Input: the input to the action, dictionary\nObservation: the result of the action\n...
(this Thought/Action/Action Input/Observation can repeat N times)\nThought:
I now can give a great answer\nFinal Answer: my best complete final answer to
the task.\nYour final answer must be the great and the most complete as possible,
it must be outcome described\n\n \nThought: \nAlthough I initially thought that
I could just say hi myself, this system seems to require me to use one of the
tools available. Therefore, I''ll delegate this task to my co-worker.\n\nAction:
Delegate work to co-worker\n\nAction Input: {\"coworker\": \"test role2\", \"task\":
tools available. Therefore, I''ll delegate this task to my coworker.\n\nAction:
Delegate work to coworker\n\nAction Input: {\"coworker\": \"test role2\", \"task\":
\"Just say hi\", \"context\": \"We need to greet someone. Just say ''hi'' to
them.\"}\n\nObservation: Hi there!\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
@@ -1233,19 +1233,19 @@ interactions:
body: '{"messages": [{"role": "user", "content": "You are test role. test backstory\nYour
personal goal is: test goal\n\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(coworker: str, task: str, context: str)
- Delegate a specific task to one of the following co-workers: [''test role2'']\nThe
coworker: Delegate work to coworker(coworker: str, task: str, context: str)
- Delegate a specific task to one of the following coworkers: [''test role2'']\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(coworker: str, question:
str, context: str) - Ask a specific question to one of the following co-workers:
them.\nAsk question to coworker: Ask question to coworker(coworker: str, question:
str, context: str) - Ask a specific question to one of the following coworkers:
[''test role2'']\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 using \" to wrap keys and values.\nObservation: the result
of the action\n\nOnce all necessary information is gathered:\n\nThought: I now
@@ -1482,19 +1482,19 @@ interactions:
body: '{"messages": [{"role": "user", "content": "You are test role2. test backstory2\nYour
personal goal is: test goal2\n\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(coworker: str, task: str, context: str)
- Delegate a specific task to one of the following co-workers: [''test role'']\nThe
coworker: Delegate work to coworker(coworker: str, task: str, context: str)
- Delegate a specific task to one of the following coworkers: [''test role'']\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(coworker: str, question:
str, context: str) - Ask a specific question to one of the following co-workers:
them.\nAsk question to coworker: Ask question to coworker(coworker: str, question:
str, context: str) - Ask a specific question to one of the following coworkers:
[''test role'']\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 using \" to wrap keys and values.\nObservation: the result
of the action\n\nOnce all necessary information is gathered:\n\nThought: I now
@@ -2487,19 +2487,19 @@ interactions:
body: '{"messages": [{"role": "user", "content": "You are test role2. test backstory2\nYour
personal goal is: test goal2\n\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(coworker: str, task: str, context: str)
- Delegate a specific task to one of the following co-workers: [''test role'']\nThe
coworker: Delegate work to coworker(coworker: str, task: str, context: str)
- Delegate a specific task to one of the following coworkers: [''test role'']\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(coworker: str, question:
str, context: str) - Ask a specific question to one of the following co-workers:
them.\nAsk question to coworker: Ask question to coworker(coworker: str, question:
str, context: str) - Ask a specific question to one of the following coworkers:
[''test role'']\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 using \" to wrap keys and values.\nObservation: the result
of the action\n\nOnce all necessary information is gathered:\n\nThought: I now
@@ -2511,8 +2511,8 @@ interactions:
you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought: \nI need to understand the context better before I can provide
a final answer. It seems I''m missing crucial information to proceed. I will
ask a question to my co-worker, ''test role'', to gather more details about
the situation.\n\nAction: \nAsk question to co-worker\n\nAction Input: \n{\"coworker\":
ask a question to my coworker, ''test role'', to gather more details about
the situation.\n\nAction: \nAsk question to coworker\n\nAction Input: \n{\"coworker\":
\"test role\", \"question\": \"Could you please provide more details about the
situation?\", \"context\": \"Hi there!\"}\n\nObservation: Could you please provide
more details about the situation?\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],

22
tests/cassettes/test_cache_hitting_between_agents.yaml
View File

@@ -64,19 +64,19 @@ interactions:
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nmultiplier: multiplier(first_number: int, second_number:
int) -> float - Useful for when you need to multiply two numbers together.\nDelegate
work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
str) - Delegate a specific task to one of the following co-workers: [''Researcher'']\nThe
work to coworker: Delegate work to coworker(coworker: str, task: str, context:
str) - Delegate a specific task to one of the following coworkers: [''Researcher'']\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(coworker: str, question:
str, context: str) - Ask a specific question to one of the following co-workers:
them.\nAsk question to coworker: Ask question to coworker(coworker: str, question:
str, context: str) - Ask a specific question to one of the following coworkers:
[''Researcher'']\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 [multiplier, Delegate work to co-worker, Ask question to co-worker],
name of [multiplier, 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 using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
@@ -439,19 +439,19 @@ interactions:
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nmultiplier: multiplier(first_number: int, second_number:
int) -> float - Useful for when you need to multiply two numbers together.\nDelegate
work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
str) - Delegate a specific task to one of the following co-workers: [''Researcher'']\nThe
work to coworker: Delegate work to coworker(coworker: str, task: str, context:
str) - Delegate a specific task to one of the following coworkers: [''Researcher'']\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(coworker: str, question:
str, context: str) - Ask a specific question to one of the following co-workers:
them.\nAsk question to coworker: Ask question to coworker(coworker: str, question:
str, context: str) - Ask a specific question to one of the following coworkers:
[''Researcher'']\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 [multiplier, Delegate work to co-worker, Ask question to co-worker],
name of [multiplier, 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 using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
@@ -463,7 +463,7 @@ interactions:
Answer, your job depends on it!\n\nThought: \nThe task at hand is to find the
product of 2 and 6. Since I have the tool ''multiplier'' which multiplies two
numbers, I can directly use it without needing to delegate or ask questions
to a co-worker.\n\nAction: multiplier\nAction Input: {\"first_number\": 2, \"second_number\":
to a coworker.\n\nAction: multiplier\nAction Input: {\"first_number\": 2, \"second_number\":
6}\n\nObservation: 12\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:

30
tests/cassettes/test_crew_with_delegating_agents.yaml
View File

@@ -83,20 +83,20 @@ interactions:
now working on a new project and want to make sure the content produced is amazing.\nYour
personal goal is: Make sure the writers in your company produce amazing content.\n\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(coworker:
are not listed here:\n\nDelegate work to coworker: Delegate work to coworker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: [''Senior Writer'']\nThe input to this tool should be the coworker,
coworkers: [''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 absolute everything you know, don''t
reference things but instead explain them.\nAsk question to co-worker: Ask question
to co-worker(coworker: str, question: str, context: str) - Ask a specific question
to one of the following co-workers: [''Senior Writer'']\nThe input to this tool
reference things but instead explain them.\nAsk question to coworker: Ask question
to coworker(coworker: str, question: str, context: str) - Ask a specific question
to one of the following coworkers: [''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
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, exactly as it''s written.\nAction Input: the input
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 a python dictionary using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
@@ -1713,20 +1713,20 @@ interactions:
now working on a new project and want to make sure the content produced is amazing.\nYour
personal goal is: Make sure the writers in your company produce amazing content.\n\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(coworker:
are not listed here:\n\nDelegate work to coworker: Delegate work to coworker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: [''Senior Writer'']\nThe input to this tool should be the coworker,
coworkers: [''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 absolute everything you know, don''t
reference things but instead explain them.\nAsk question to co-worker: Ask question
to co-worker(coworker: str, question: str, context: str) - Ask a specific question
to one of the following co-workers: [''Senior Writer'']\nThe input to this tool
reference things but instead explain them.\nAsk question to coworker: Ask question
to coworker(coworker: str, question: str, context: str) - Ask a specific question
to one of the following coworkers: [''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
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, exactly as it''s written.\nAction Input: the input
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 a python dictionary using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
@@ -1738,7 +1738,7 @@ interactions:
it!\n\nThought: \nI want to ensure that the Senior Writer understands the topic
and the standard of quality that we aim to achieve. I''ll provide them with
all the information they need to produce an amazing 1 paragraph draft about
AI Agents. \n\nAction: Delegate work to co-worker\nAction Input: {\"coworker\":
AI Agents. \n\nAction: Delegate work to coworker\nAction Input: {\"coworker\":
\"Senior Writer\", \"task\": \"Produce a 1 paragraph draft of an article about
AI Agents.\", \"context\": \"We are working on a new project that requires high-quality
content about AI Agents. We want to make sure that the content is engaging,

36
tests/cassettes/test_hierarchical_process.yaml
View File

@@ -63,20 +63,20 @@ 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.\n\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(coworker:
are not listed here:\n\nDelegate work to coworker: Delegate work to coworker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: [''Researcher'', ''Senior Writer'']\nThe input to this tool should
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 absolute everything
you know, don''t reference things but instead explain them.\nAsk question to
co-worker: Ask question to co-worker(coworker: str, question: str, context:
str) - Ask a specific question to one of the following co-workers: [''Researcher'',
coworker: Ask question to coworker(coworker: str, question: str, context:
str) - 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 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 using \" to wrap keys and values.\nObservation: the result
of the action\n\nOnce all necessary information is gathered:\n\nThought: I now
@@ -2444,20 +2444,20 @@ 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.\n\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(coworker:
are not listed here:\n\nDelegate work to coworker: Delegate work to coworker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: [''Researcher'', ''Senior Writer'']\nThe input to this tool should
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 absolute everything
you know, don''t reference things but instead explain them.\nAsk question to
co-worker: Ask question to co-worker(coworker: str, question: str, context:
str) - Ask a specific question to one of the following co-workers: [''Researcher'',
coworker: Ask question to coworker(coworker: str, question: str, context:
str) - 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 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 using \" to wrap keys and values.\nObservation: the result
of the action\n\nOnce all necessary information is gathered:\n\nThought: I now
@@ -2474,7 +2474,7 @@ interactions:
a paragraph for each idea that showcases how good an article about this topic
could be. I will delegate the task of coming up with the ideas to the Researcher
and the task of writing the paragraphs to the Senior Writer.\n\nAction: \nDelegate
work to co-worker\n\nAction Input: \n{\n \"coworker\": \"Researcher\",\n \"task\":
work to coworker\n\nAction Input: \n{\n \"coworker\": \"Researcher\",\n \"task\":
\"Come up with 5 interesting ideas for an article\",\n \"context\": \"We need
to create a list of 5 interesting ideas for an article. These ideas should be
unique, engaging, and have the potential to be developed into a full-length
@@ -5363,20 +5363,20 @@ 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.\n\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(coworker:
are not listed here:\n\nDelegate work to coworker: Delegate work to coworker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: [''Researcher'', ''Senior Writer'']\nThe input to this tool should
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 absolute everything
you know, don''t reference things but instead explain them.\nAsk question to
co-worker: Ask question to co-worker(coworker: str, question: str, context:
str) - Ask a specific question to one of the following co-workers: [''Researcher'',
coworker: Ask question to coworker(coworker: str, question: str, context:
str) - 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 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 using \" to wrap keys and values.\nObservation: the result
of the action\n\nOnce all necessary information is gathered:\n\nThought: I now
@@ -5393,7 +5393,7 @@ interactions:
a paragraph for each idea that showcases how good an article about this topic
could be. I will delegate the task of coming up with the ideas to the Researcher
and the task of writing the paragraphs to the Senior Writer.\n\nAction: \nDelegate
work to co-worker\n\nAction Input: \n{\n \"coworker\": \"Researcher\",\n \"task\":
work to coworker\n\nAction Input: \n{\n \"coworker\": \"Researcher\",\n \"task\":
\"Come up with 5 interesting ideas for an article\",\n \"context\": \"We need
to create a list of 5 interesting ideas for an article. These ideas should be
unique, engaging, and have the potential to be developed into a full-length
@@ -5406,7 +5406,7 @@ interactions:
for the article. Now, I need to delegate the task of writing a paragraph for
each idea to the Senior Writer. I will provide the Senior Writer with the ideas
and ask them to write a paragraph that showcases how good an article about each
topic could be.\n\nAction: \nDelegate work to co-worker\n\nAction Input: \n{\n \"coworker\":
topic could be.\n\nAction: \nDelegate work to coworker\n\nAction Input: \n{\n \"coworker\":
\"Senior Writer\",\n \"task\": \"Write one amazing paragraph highlight for
each idea\",\n \"context\": \"We have 5 interesting ideas for an article. They
are: 1. ''Demystifying AI: An in-depth exploration of Artificial Intelligence

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,

32
tests/cassettes/test_increment_tool_errors.yaml
View File

@@ -57,20 +57,20 @@ 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.\n\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(coworker:
are not listed here:\n\nDelegate work to coworker: Delegate work to coworker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: [''Scorer'']\nThe input to this tool should be the coworker, the
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(coworker: str, question: str, context: str) - Ask a specific question
to one of the following co-workers: [''Scorer'']\nThe input to this tool should
things but instead explain them.\nAsk question to coworker: Ask question to
coworker(coworker: str, question: str, context: str) - 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 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, exactly as it''s written.\nAction Input: the input
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 a python dictionary using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
@@ -3197,20 +3197,20 @@ 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.\n\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(coworker:
are not listed here:\n\nDelegate work to coworker: Delegate work to coworker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: [''Scorer'']\nThe input to this tool should be the coworker, the
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(coworker: str, question: str, context: str) - Ask a specific question
to one of the following co-workers: [''Scorer'']\nThe input to this tool should
things but instead explain them.\nAsk question to coworker: Ask question to
coworker(coworker: str, question: str, context: str) - 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 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, exactly as it''s written.\nAction Input: the input
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 a python dictionary using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
@@ -3225,8 +3225,8 @@ interactions:
it. Since scoring can be subjective, it''s essential to establish clear criteria
based on relevance, insightfulness, current interest in the topic, and perhaps
its specificity or ability to provoke thought. As I don''t have direct guidelines,
I will need to consult with my co-worker, Scorer, who might have a set of criteria
or insights on how to approach this task.\n\nAction: Ask question to co-worker\nAction
I will need to consult with my coworker, Scorer, who might have a set of criteria
or insights on how to approach this task.\n\nAction: Ask question to coworker\nAction
Input: {\"coworker\": \"Scorer\", \"question\": \"What criteria should we use
to evaluate and score the title ''The impact of AI in the future of work''?\",
\"context\": \"We need to assign a score between 1-5 for the title ''The impact