andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2025-12-16 04:18:35 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

prepping new version

Browse Source
This commit is contained in:
João Moura
2024-07-20 12:26:32 -04:00
parent f53a3a00e1
commit 349753a013
9 changed files with 676 additions and 374 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/core-concepts/Crews.md
View File

@@ -220,7 +220,7 @@ These methods provide flexibility in how you manage and execute tasks within you
### Replaying from specific task:
You can now replay from a specific task using our cli command replay.
The replay_from_tasks feature in CrewAI allows you to replay from a specific task using the command-line interface (CLI). By running the command `crewai replay -t <task_id>`, you can specify the `task_id` for the replay process.
The replay feature in CrewAI allows you to replay from a specific task using the command-line interface (CLI). By running the command `crewai replay -t <task_id>`, you can specify the `task_id` for the replay process.
Kickoffs will now save the latest kickoffs returned task outputs locally for you to be able to replay from.

4
docs/how-to/Replay-tasks-from-latest-Crew-Kickoff.md
View File

@@ -36,14 +36,14 @@ To replay from a task programmatically, use the following steps:
2. Execute the replay command within a try-except block to handle potential errors.
```python
def replay_from_task():
def replay():
"""
Replay the crew execution from a specific task.
"""
task_id = '<task_id>'
inputs = {"topic": "CrewAI Training"} # this is optional, you can pass in the inputs you want to replay otherwise uses the previous kickoffs inputs
try:
YourCrewName_Crew().crew().replay_from_task(task_id=task_id, inputs=inputs)
YourCrewName_Crew().crew().replay(task_id=task_id, inputs=inputs)
except Exception as e:
raise Exception(f"An error occurred while replaying the crew: {e}")

688
poetry.lock generated
View File

File diff suppressed because it is too large Load Diff

2
pyproject.toml
View File

@@ -1,6 +1,6 @@
[tool.poetry]
name = "crewai"
version = "0.41.0"
version = "0.41.1"
description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
authors = ["Joao Moura <joao@crewai.com>"]
readme = "README.md"

2
src/crewai/cli/templates/pyproject.toml
View File

@@ -6,7 +6,7 @@ authors = ["Your Name <you@example.com>"]
[tool.poetry.dependencies]
python = ">=3.10,<=3.13"
crewai = { extras = ["tools"], version = "^0.41.0" }
crewai = { extras = ["tools"], version = "^0.41.1" }
[tool.poetry.scripts]
{{folder_name}} = "{{folder_name}}.main:run"

163
tests/cassettes/test_replay_setup_context.yaml Normal file
View File

@@ -0,0 +1,163 @@
interactions:
- request:
body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
goal is: Test GoalTo give my best complete final answer to the task use the
exact following format:\n\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\nI MUST use
these formats, my job depends on it!\nCurrent Task: Test Task\n\nThis is the
expect criteria for your final answer: Say Hi to John \n you MUST return the
actual complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\ncontext raw output\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:\n", "role": "user"}], "model": "gpt-4o", "logprobs": false,
"n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '937'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.36.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.36.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
Hi"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
John"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a643794fe0341e9-EWR
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Sat, 20 Jul 2024 16:09:42 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=7kfE3khl2E.6zM44yel5nToHzdtz0QeQ4wkLuGYyqSs-1721491782-1.0.1.1-XUb95eXTriHvSUSCH.TCyAmCGCbPK6L7p_tRTDBon8Fo6ns8TDbDoDGA.wVCFI4MTXSxkqrjD0GpYDj4GBTeSQ;
path=/; expires=Sat, 20-Jul-24 16:39:42 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=iN41lAEk.DjpRMAtG.K0NEvIN0xB9eS0CUCU2iWmjv4-1721491782137-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '104'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999791'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_4d90924dd28a0fb48c857f03515f0ca8
status:
code: 200
message: OK
version: 1

159
tests/cassettes/test_replay_with_context.yaml Normal file
View File

@@ -0,0 +1,159 @@
interactions:
- request:
body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
goal is: Test GoalTo give my best complete final answer to the task use the
exact following format:\n\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\nI MUST use
these formats, my job depends on it!\nCurrent Task: Test Task\n\nThis is the
expect criteria for your final answer: Say Hi \n you MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\ncontext raw output\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:\n", "role": "user"}], "model": "gpt-4o", "logprobs": false,
"n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '929'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.36.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.36.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
Hi"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a643791a80e8c96-EWR
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Sat, 20 Jul 2024 16:09:41 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=cam5sECdaTzbttLIOaiuvh9flDIAXp_FLPODnDEOn6k-1721491781-1.0.1.1-hyFl43P7HIWZsGueyWuDeO579sZ41as2mvrM.cQS1E8KSLG2ZZ0DxDGbVvHYRO0eflTUJohgZu6CGltvjQfMtQ;
path=/; expires=Sat, 20-Jul-24 16:39:41 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=nmlgS.bqXAu0rZ.OlHPfXrIrdnVgrBSW3e0UuU3N5ng-1721491781661-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '126'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999794'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_31484eeb0af939af4e0d9c47441ba2db
status:
code: 200
message: OK
version: 1

20
tests/crew_test.py
View File

@@ -1917,13 +1917,13 @@ def test_replay_feature():
)
crew.kickoff()
crew.replay_from_task(str(write.id))
crew.replay(str(write.id))
# Ensure context was passed correctly
assert mock_execute_task.call_count == 3
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_replay_from_task_error():
def test_crew_replay_error():
task = Task(
description="Come up with a list of 5 interesting ideas to explore for an article",
expected_output="5 bullet points with a paragraph for each idea.",
@@ -1936,7 +1936,7 @@ def test_crew_replay_from_task_error():
)
with pytest.raises(TypeError) as e:
crew.replay_from_task() # type: ignore purposefully throwing err
crew.replay() # type: ignore purposefully throwing err
assert "task_id is required" in str(e)
@@ -2071,14 +2071,14 @@ def test_replay_task_with_context():
with patch.object(Task, "execute_sync") as mock_replay_task:
mock_replay_task.return_value = mock_task_output4
replayed_output = crew.replay_from_task(str(task4.id))
replayed_output = crew.replay(str(task4.id))
assert replayed_output.raw == "Presentation on AI advancements..."
db_handler.reset()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_replay_from_task_with_context():
def test_replay_with_context():
agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
task1 = Task(
description="Context Task", expected_output="Say Task Output", agent=agent
@@ -2130,7 +2130,7 @@ def test_replay_from_task_with_context():
},
],
):
crew.replay_from_task(str(task2.id))
crew.replay(str(task2.id))
assert crew.tasks[1].context[0].output.raw == "context raw output"
@@ -2192,7 +2192,7 @@ def test_replay_with_invalid_task_id():
ValueError,
match="Task with id bf5b09c9-69bd-4eb8-be12-f9e5bae31c2d not found in the crew's tasks.",
):
crew.replay_from_task("bf5b09c9-69bd-4eb8-be12-f9e5bae31c2d")
crew.replay("bf5b09c9-69bd-4eb8-be12-f9e5bae31c2d")
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -2251,13 +2251,13 @@ def test_replay_interpolates_inputs_properly(mock_interpolate_inputs):
},
],
):
crew.replay_from_task(str(task2.id))
crew.replay(str(task2.id))
assert crew._inputs == {"name": "John"}
assert mock_interpolate_inputs.call_count == 2
@pytest.mark.vcr(filter_headers=["authorization"])
def test_replay_from_task_setup_context():
def test_replay_setup_context():
agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
task1 = Task(description="Context Task", expected_output="Say {name}", agent=agent)
task2 = Task(
@@ -2306,7 +2306,7 @@ def test_replay_from_task_setup_context():
},
],
):
crew.replay_from_task(str(task2.id))
crew.replay(str(task2.id))
# Check if the first task's output was set correctly
assert crew.tasks[0].output is not None

10
tests/utilities/test_planning_handler.py
View File

@@ -1,4 +1,5 @@
from unittest.mock import patch
from crewai.tasks.task_output import TaskOutput
import pytest
@@ -31,10 +32,15 @@ class TestCrewPlanner:
def test_handle_crew_planning(self, crew_planner):
with patch.object(Task, "execute_sync") as execute:
execute.return_value = PlannerTaskPydanticOutput(
list_of_plans_per_task=["Plan 1", "Plan 2", "Plan 3"]
execute.return_value = TaskOutput(
description="Description",
agent="agent",
pydantic=PlannerTaskPydanticOutput(
list_of_plans_per_task=["Plan 1", "Plan 2", "Plan 3"]
),
)
result = crew_planner._handle_crew_planning()
assert isinstance(result, PlannerTaskPydanticOutput)
assert len(result.list_of_plans_per_task) == len(crew_planner.tasks)
execute.assert_called_once()