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

Merge branch 'main' into feature/procedure_v2

Browse Source
This commit is contained in:
Brandon Hancock
2024-07-22 09:55:03 -04:00
parent afd6bff159 349753a013
commit e95ef6fca9
30 changed files with 1275 additions and 405 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

78
tests/cli/cli_test.py
View File

@@ -3,7 +3,7 @@ from unittest import mock
import pytest
from click.testing import CliRunner
from crewai.cli.cli import train, version
from crewai.cli.cli import train, version, reset_memories
@pytest.fixture
@@ -41,6 +41,82 @@ def test_train_invalid_string_iterations(train_crew, runner):
)
@mock.patch("crewai.cli.reset_memories_command.ShortTermMemory")
@mock.patch("crewai.cli.reset_memories_command.EntityMemory")
@mock.patch("crewai.cli.reset_memories_command.LongTermMemory")
@mock.patch("crewai.cli.reset_memories_command.TaskOutputStorageHandler")
def test_reset_all_memories(
MockTaskOutputStorageHandler,
MockLongTermMemory,
MockEntityMemory,
MockShortTermMemory,
runner,
):
result = runner.invoke(reset_memories, ["--all"])
MockShortTermMemory().reset.assert_called_once()
MockEntityMemory().reset.assert_called_once()
MockLongTermMemory().reset.assert_called_once()
MockTaskOutputStorageHandler().reset.assert_called_once()
assert result.output == "All memories have been reset.\n"
@mock.patch("crewai.cli.reset_memories_command.ShortTermMemory")
def test_reset_short_term_memories(MockShortTermMemory, runner):
result = runner.invoke(reset_memories, ["-s"])
MockShortTermMemory().reset.assert_called_once()
assert result.output == "Short term memory has been reset.\n"
@mock.patch("crewai.cli.reset_memories_command.EntityMemory")
def test_reset_entity_memories(MockEntityMemory, runner):
result = runner.invoke(reset_memories, ["-e"])
MockEntityMemory().reset.assert_called_once()
assert result.output == "Entity memory has been reset.\n"
@mock.patch("crewai.cli.reset_memories_command.LongTermMemory")
def test_reset_long_term_memories(MockLongTermMemory, runner):
result = runner.invoke(reset_memories, ["-l"])
MockLongTermMemory().reset.assert_called_once()
assert result.output == "Long term memory has been reset.\n"
@mock.patch("crewai.cli.reset_memories_command.TaskOutputStorageHandler")
def test_reset_kickoff_outputs(MockTaskOutputStorageHandler, runner):
result = runner.invoke(reset_memories, ["-k"])
MockTaskOutputStorageHandler().reset.assert_called_once()
assert result.output == "Latest Kickoff outputs stored has been reset.\n"
@mock.patch("crewai.cli.reset_memories_command.ShortTermMemory")
@mock.patch("crewai.cli.reset_memories_command.LongTermMemory")
def test_reset_multiple_memory_flags(MockShortTermMemory, MockLongTermMemory, runner):
result = runner.invoke(
reset_memories,
[
"-s",
"-l",
],
)
MockShortTermMemory().reset.assert_called_once()
MockLongTermMemory().reset.assert_called_once()
assert (
result.output
== "Long term memory has been reset.\nShort term memory has been reset.\n"
)
def test_reset_no_memory_flags(runner):
result = runner.invoke(
reset_memories,
)
assert (
result.output
== "Please specify at least one memory type to reset using the appropriate flags.\n"
)
def test_version_command(runner):
result = runner.invoke(version)

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

5
tests/task_test.py
View File

@@ -5,12 +5,13 @@ import json
from unittest.mock import MagicMock, patch
import pytest
from pydantic import BaseModel
from pydantic_core import ValidationError
from crewai import Agent, Crew, Process, Task
from crewai.tasks.conditional_task import ConditionalTask
from crewai.tasks.task_output import TaskOutput
from crewai.utilities.converter import Converter
from pydantic import BaseModel
from pydantic_core import ValidationError
def test_task_tool_reflect_agent_tools():

74
tests/utilities/test_planning_handler.py Normal file
View File

@@ -0,0 +1,74 @@
from unittest.mock import patch
from crewai.tasks.task_output import TaskOutput
import pytest
from crewai.agent import Agent
from crewai.task import Task
from crewai.utilities.planning_handler import CrewPlanner, PlannerTaskPydanticOutput
class TestCrewPlanner:
@pytest.fixture
def crew_planner(self):
tasks = [
Task(
description="Task 1",
expected_output="Output 1",
agent=Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1"),
),
Task(
description="Task 2",
expected_output="Output 2",
agent=Agent(role="Agent 2", goal="Goal 2", backstory="Backstory 2"),
),
Task(
description="Task 3",
expected_output="Output 3",
agent=Agent(role="Agent 3", goal="Goal 3", backstory="Backstory 3"),
),
]
return CrewPlanner(tasks)
def test_handle_crew_planning(self, crew_planner):
with patch.object(Task, "execute_sync") as execute:
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()
def test_create_planning_agent(self, crew_planner):
agent = crew_planner._create_planning_agent()
assert isinstance(agent, Agent)
assert agent.role == "Task Execution Planner"
def test_create_planner_task(self, crew_planner):
planning_agent = Agent(
role="Planning Agent",
goal="Plan Step by Step Plan",
backstory="Master in Planning",
)
tasks_summary = "Summary of tasks"
task = crew_planner._create_planner_task(planning_agent, tasks_summary)
assert isinstance(task, Task)
assert task.description.startswith("Based on these tasks summary")
assert task.agent == planning_agent
assert (
task.expected_output
== "Step by step plan on how the agents can execute their tasks using the available tools with mastery"
)
def test_create_tasks_summary(self, crew_planner):
tasks_summary = crew_planner._create_tasks_summary()
assert isinstance(tasks_summary, str)
assert tasks_summary.startswith("\n Task Number 1 - Task 1")
assert tasks_summary.endswith('"agent_tools": []\n ')