andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-08 15:48:29 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

improving test

Browse Source
This commit is contained in:
João Moura
2025-05-27 01:27:25 -07:00
parent 556ce2300c
commit 2c2b60410b
13 changed files with 3221 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
score.json Normal file
View File

@@ -0,0 +1,3 @@
{
"score": 4
}

430
tests/cassettes/test_agent_error_on_parsing_tool.yaml
View File

File diff suppressed because one or more lines are too long

110
tests/cassettes/test_agent_with_knowledge_sources.yaml
View File

File diff suppressed because one or more lines are too long

110
tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold.yaml
View File

File diff suppressed because one or more lines are too long

110
tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default.yaml
View File

File diff suppressed because one or more lines are too long

860
tests/cassettes/test_agent_with_ollama_llama3.yaml
View File

File diff suppressed because one or more lines are too long

430
tests/cassettes/test_agent_without_max_rpm_respects_crew_rpm.yaml
View File

File diff suppressed because one or more lines are too long

59
tests/cassettes/test_cache_hitting.yaml
View File

@@ -1020,4 +1020,63 @@ interactions:
- req_83a900d075a98ab391c27c5d1cd4fbcb
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1626'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.31.1
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Tue, 27 May 2025 08:13:05 GMT
status:
code: 200
message: OK
version: 1

110
tests/cassettes/test_increment_tool_errors.yaml
View File

File diff suppressed because one or more lines are too long

110
tests/cassettes/test_tool_result_as_answer_is_the_final_answer_for_the_agent.yaml
View File

File diff suppressed because one or more lines are too long

825
tests/cassettes/test_using_contextual_memory.yaml
View File

@@ -199,4 +199,829 @@ interactions:
- req_2ac1e3cef69e9b09b7ade0e1d010fc08
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"input": ["I now can give a great answer. Final Answer: **Topic**: Basic
Addition **Explanation**: Addition is a fundamental concept in math that means
combining two or more numbers to get a new total. It''s like putting together
pieces of a puzzle to see the whole picture. When we add, we take two or more
groups of things and count them all together. **Angle**: Use relatable and
engaging real-life scenarios to illustrate addition, making it fun and easier
for a 6-year-old to understand and apply. **Examples**: 1. **Counting Apples**: Let''s
say you have 2 apples and your friend gives you 3 more apples. How many apples
do you have in total? - You start with 2 apples. - Your friend gives you
3 more apples. - Now, you count all the apples together: 2 + 3 = 5. -
So, you have 5 apples in total. 2. **Toy Cars**: Imagine you have 4 toy
cars and you find 2 more toy cars in your room. How many toy cars do you have
now? - You start with 4 toy cars. - You find 2 more toy cars. - You
count them all together: 4 + 2 = 6. - So, you have 6 toy cars in total. 3.
**Drawing Pictures**: If you draw 3 pictures today and 2 pictures tomorrow,
how many pictures will you have drawn in total? - You draw 3 pictures today. -
You draw 2 pictures tomorrow. - You add them together: 3 + 2 = 5. - So,
you will have drawn 5 pictures in total. 4. **Using Fingers**: Let''s use
your fingers to practice addition. Show 3 fingers on one hand and 1 finger on
the other hand. How many fingers are you holding up? - 3 fingers on one hand. -
1 finger on the other hand. - Put them together and count: 3 + 1 = 4. -
So, you are holding up 4 fingers. By using objects that kids are familiar with,
such as apples, toy cars, drawings, and even their own fingers, we can make
the concept of addition relatable and enjoyable. Practicing with real items
helps children visualize the math and understand that addition is simply combining
groups to find out how many there are altogether."], "model": "text-embedding-3-small",
"encoding_format": "base64"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2092'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-read-timeout:
- '600'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/embeddings
response:
body:
string: !!binary |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headers:
CF-RAY:
- 94640d271c367db6-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 27 May 2025 08:13:10 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=zxXbTMyK.67_c.SQXNivPXTcfsIBL5Vl1Q7WXFcTgxU-1748333590-1.0.1.1-ArIOxtxz6HMOCmEGGFc.Hxs19gY1LkxaxTZYc9hAE7zSdmh2fCrczDquGUovgGjYHvCJ94TxWQTCVlo1v7kDhnnrF0jwHy_U_LaR6AbA.94;
path=/; expires=Tue, 27-May-25 08:43:10 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=4YFW5U1WwjrbdrZ7OWIvzgymvtGAnmnPEu1zeEdQsGg-1748333590310-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-allow-origin:
- '*'
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-model:
- text-embedding-3-small
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '180'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
via:
- envoy-router-5f689c5f9d-mdwg9
x-envoy-upstream-service-time:
- '185'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '10000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '9999496'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 3ms
x-request-id:
- req_421cd0437639cc5312b23b1d7727f0a4
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nResearch a topic to teach a kid aged 6 about math.\n\nExpected
Output:\nA topic, explanation, angle, and examples.\n\nActual Output:\nI now
can give a great answer.\nFinal Answer: \n**Topic**: Basic Addition\n\n**Explanation**:\nAddition
is a fundamental concept in math that means combining two or more numbers to
get a new total. It''s like putting together pieces of a puzzle to see the whole
picture. When we add, we take two or more groups of things and count them all
together.\n\n**Angle**:\nUse relatable and engaging real-life scenarios to illustrate
addition, making it fun and easier for a 6-year-old to understand and apply.\n\n**Examples**:\n\n1.
**Counting Apples**:\n Let''s say you have 2 apples and your friend gives
you 3 more apples. How many apples do you have in total?\n - You start with
2 apples.\n - Your friend gives you 3 more apples.\n - Now, you count all
the apples together: 2 + 3 = 5.\n - So, you have 5 apples in total.\n\n2.
**Toy Cars**:\n Imagine you have 4 toy cars and you find 2 more toy cars in
your room. How many toy cars do you have now?\n - You start with 4 toy cars.\n -
You find 2 more toy cars.\n - You count them all together: 4 + 2 = 6.\n -
So, you have 6 toy cars in total.\n\n3. **Drawing Pictures**:\n If you draw
3 pictures today and 2 pictures tomorrow, how many pictures will you have drawn
in total?\n - You draw 3 pictures today.\n - You draw 2 pictures tomorrow.\n -
You add them together: 3 + 2 = 5.\n - So, you will have drawn 5 pictures in
total.\n\n4. **Using Fingers**:\n Let''s use your fingers to practice addition.
Show 3 fingers on one hand and 1 finger on the other hand. How many fingers
are you holding up?\n - 3 fingers on one hand.\n - 1 finger on the other
hand.\n - Put them together and count: 3 + 1 = 4.\n - So, you are holding
up 4 fingers.\n\nBy using objects that kids are familiar with, such as apples,
toy cars, drawings, and even their own fingers, we can make the concept of addition
relatable and enjoyable. Practicing with real items helps children visualize
the math and understand that addition is simply combining groups to find out
how many there are altogether.\n\nPlease provide:\n- Bullet points suggestions
to improve future similar tasks\n- A score from 0 to 10 evaluating on completion,
quality, and overall performance- Entities extracted from the task output, if
any, their type, description, and relationships"}], "model": "gpt-4o-mini",
"tool_choice": {"type": "function", "function": {"name": "TaskEvaluation"}},
"tools": [{"type": "function", "function": {"name": "TaskEvaluation", "description":
"Correctly extracted `TaskEvaluation` with all the required parameters with
correct types", "parameters": {"$defs": {"Entity": {"properties": {"name": {"description":
"The name of the entity.", "title": "Name", "type": "string"}, "type": {"description":
"The type of the entity.", "title": "Type", "type": "string"}, "description":
{"description": "Description of the entity.", "title": "Description", "type":
"string"}, "relationships": {"description": "Relationships of the entity.",
"items": {"type": "string"}, "title": "Relationships", "type": "array"}}, "required":
["name", "type", "description", "relationships"], "title": "Entity", "type":
"object"}}, "properties": {"suggestions": {"description": "Suggestions to improve
future similar tasks.", "items": {"type": "string"}, "title": "Suggestions",
"type": "array"}, "quality": {"description": "A score from 0 to 10 evaluating
on completion, quality, and overall performance, all taking into account the
task description, expected output, and the result of the task.", "title": "Quality",
"type": "number"}, "entities": {"description": "Entities extracted from the
task output.", "items": {"$ref": "#/$defs/Entity"}, "title": "Entities", "type":
"array"}}, "required": ["entities", "quality", "suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4092'
content-type:
- application/json
cookie:
- _cfuvid=SlnUP7AT9jJlQiN.Fm1c7MDyo78_hBRAz8PoabvHVSU-1736018539826-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 94640d2c4fbb14f8-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 27 May 2025 08:13:14 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=2gcR.TdsIISbWE0mGGmusReUBNsIatAwc18zV72zD20-1748333594-1.0.1.1-qeHSEYFoSHrtU4ZrkbG05aW.fPl53pBh5THKK8DsmUMObmaOM2VjUu.LX4CG.kTiSHKPDctGkrALLResb.5.jJ8KafoAb00ULAntajitgj0;
path=/; expires=Tue, 27-May-25 08:43:14 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=JuFQuJzf0SDdTXeiRyPt8YpIoGL3iM9ZMap_LG1xa5k-1748333594521-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '3966'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-envoy-upstream-service-time:
- '3976'
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999368'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_da07dbd4e017b1837841676fb84c2e7f
status:
code: 200
message: OK
- request:
body: '{"input": ["Apples(Object): Fruits used in an example to illustrate basic
addition."], "model": "text-embedding-3-small", "encoding_format": "base64"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '150'
content-type:
- application/json
cookie:
- __cf_bm=zxXbTMyK.67_c.SQXNivPXTcfsIBL5Vl1Q7WXFcTgxU-1748333590-1.0.1.1-ArIOxtxz6HMOCmEGGFc.Hxs19gY1LkxaxTZYc9hAE7zSdmh2fCrczDquGUovgGjYHvCJ94TxWQTCVlo1v7kDhnnrF0jwHy_U_LaR6AbA.94;
_cfuvid=4YFW5U1WwjrbdrZ7OWIvzgymvtGAnmnPEu1zeEdQsGg-1748333590310-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-read-timeout:
- '600'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/embeddings
response:
body:
string: !!binary |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headers:
CF-RAY:
- 94640d46896fb6c9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 27 May 2025 08:13:14 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-allow-origin:
- '*'
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-model:
- text-embedding-3-small
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '196'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
via:
- envoy-router-5f689c5f9d-svjx7
x-envoy-upstream-service-time:
- '200'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '10000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '9999982'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_51978202e4a91acdb0b2cf314d536032
status:
code: 200
message: OK
- request:
body: '{"input": ["Pictures(Object): Visual art pieces used in an example to illustrate
basic addition."], "model": "text-embedding-3-small", "encoding_format": "base64"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '163'
content-type:
- application/json
cookie:
- __cf_bm=zxXbTMyK.67_c.SQXNivPXTcfsIBL5Vl1Q7WXFcTgxU-1748333590-1.0.1.1-ArIOxtxz6HMOCmEGGFc.Hxs19gY1LkxaxTZYc9hAE7zSdmh2fCrczDquGUovgGjYHvCJ94TxWQTCVlo1v7kDhnnrF0jwHy_U_LaR6AbA.94;
_cfuvid=4YFW5U1WwjrbdrZ7OWIvzgymvtGAnmnPEu1zeEdQsGg-1748333590310-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-read-timeout:
- '600'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/embeddings
response:
body:
string: !!binary |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headers:
CF-RAY:
- 94640d492fdbb6c9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 27 May 2025 08:13:15 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-allow-origin:
- '*'
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-model:
- text-embedding-3-small
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '393'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
via:
- envoy-router-78456c78d9-689qp
x-envoy-upstream-service-time:
- '395'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '10000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '9999979'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_c9c729639c1a9714296bd221d8edd696
status:
code: 200
message: OK
version: 1

6
tests/crew_test.py
View File

@@ -4418,7 +4418,7 @@ def test_reset_knowledge_with_no_crew_knowledge(researcher,writer):
with pytest.raises(RuntimeError) as excinfo:
crew.reset_memories(command_type='knowledge')
# Optionally, you can also check the error message
assert "Crew Knowledge and Agent Knowledge memory system is not initialized" in str(excinfo.value) # Replace with the expected message
@@ -4497,7 +4497,7 @@ def test_reset_agent_knowledge_with_no_agent_knowledge(researcher,writer):
with pytest.raises(RuntimeError) as excinfo:
crew.reset_memories(command_type='agent_knowledge')
# Optionally, you can also check the error message
assert "Agent Knowledge memory system is not initialized" in str(excinfo.value) # Replace with the expected message
@@ -4517,7 +4517,7 @@ def test_reset_agent_knowledge_with_only_crew_knowledge(researcher,writer):
with pytest.raises(RuntimeError) as excinfo:
crew.reset_memories(command_type='agent_knowledge')
# Optionally, you can also check the error message
assert "Agent Knowledge memory system is not initialized" in str(excinfo.value) # Replace with the expected message

126
tests/reasoning_interval_test.py
View File

@@ -8,62 +8,58 @@ from crewai.agents.crew_agent_executor import CrewAgentExecutor
from crewai.utilities.reasoning_handler import AgentReasoning
@pytest.fixture
def mock_llm_responses():
"""Fixture for mock LLM responses."""
return {
"initial_reasoning": "I'll solve this task step by step.\n\nREADY: I am ready to execute the task.\n\n",
"mid_execution_reasoning": "Based on progress so far, I'll adjust my approach.\n\nREADY: I am ready to continue executing the task.",
"execution_step": "I'm working on the task...",
"final_result": "Task completed successfully."
}
def test_agent_with_reasoning_interval():
"""Ensure that the agent triggers mid-execution reasoning based on the fixed interval."""
# Use a mock LLM to avoid real network calls
llm = MagicMock()
agent = Agent(
role="Test Agent",
goal="To test the reasoning interval feature",
backstory="I am a test agent created to verify the reasoning interval feature works correctly.",
llm=llm,
reasoning=True,
reasoning_interval=2, # Reason every 2 steps
verbose=True,
)
def test_agent_with_reasoning_interval(mock_llm_responses):
"""Test agent with reasoning interval."""
with patch('crewai.llm.LLM.call') as mock_llm_call:
mock_llm_call.return_value = mock_llm_responses["initial_reasoning"]
llm = MagicMock()
llm.call.return_value = mock_llm_responses["initial_reasoning"]
agent = Agent(
role="Test Agent",
goal="To test the reasoning interval feature",
backstory="I am a test agent created to verify the reasoning interval feature works correctly.",
llm=llm,
reasoning=True,
reasoning_interval=2, # Reason every 2 steps
verbose=True
)
task = Task(
description="Multi-step task that requires periodic reasoning.",
expected_output="The task should be completed with periodic reasoning.",
agent=agent
agent=agent,
)
with patch('crewai.agent.Agent.create_agent_executor') as mock_create_executor:
mock_executor = MagicMock()
mock_executor._handle_mid_execution_reasoning = MagicMock()
mock_executor.invoke.return_value = mock_llm_responses["final_result"]
mock_create_executor.return_value = mock_executor
# Create a mock executor that will be injected into the agent
mock_executor = MagicMock()
# Simulate the executor deciding to reason on the second step
mock_executor._should_trigger_reasoning = MagicMock(side_effect=[False, True])
mock_executor._handle_mid_execution_reasoning = MagicMock()
mock_executor.invoke.return_value = "Task completed successfully."
# Monkey-patch create_agent_executor so that it sets our mock_executor
def _fake_create_agent_executor(self, tools=None, task=None): # noqa: D401,E501
"""Replace the real executor with the mock while preserving behaviour."""
self.agent_executor = mock_executor
return mock_executor
with patch.object(Agent, "create_agent_executor", _fake_create_agent_executor):
result = agent.execute_task(task)
assert result == mock_llm_responses["final_result"]
mock_executor._handle_mid_execution_reasoning.assert_called()
# Validate results and that reasoning happened when expected
assert result == "Task completed successfully."
# _handle_mid_execution_reasoning should be called once (on the second step)
mock_executor._handle_mid_execution_reasoning.assert_called()
def test_agent_with_adaptive_reasoning(mock_llm_responses):
"""Test agent with adaptive reasoning."""
with patch('crewai.llm.LLM.call') as mock_llm_call:
mock_llm_call.return_value = mock_llm_responses["initial_reasoning"]
llm = MagicMock()
llm.call.return_value = mock_llm_responses["initial_reasoning"]
agent = Agent(
role="Test Agent",
goal="To test the adaptive reasoning feature",
@@ -73,26 +69,26 @@ def test_agent_with_adaptive_reasoning(mock_llm_responses):
adaptive_reasoning=True,
verbose=True
)
task = Task(
description="Complex task that requires adaptive reasoning.",
expected_output="The task should be completed with adaptive reasoning.",
agent=agent
)
with patch('crewai.agent.Agent.create_agent_executor') as mock_create_executor:
mock_executor = MagicMock()
mock_executor._should_adaptive_reason = MagicMock(return_value=True)
mock_executor._handle_mid_execution_reasoning = MagicMock()
mock_executor.invoke.return_value = mock_llm_responses["final_result"]
mock_create_executor.return_value = mock_executor
result = agent.execute_task(task)
assert result == mock_llm_responses["final_result"]
mock_executor._should_adaptive_reason.assert_called()
mock_executor._handle_mid_execution_reasoning.assert_called()
@@ -100,7 +96,7 @@ def test_mid_execution_reasoning_handler():
"""Test the mid-execution reasoning handler."""
llm = MagicMock()
llm.call.return_value = "Based on progress, I'll adjust my approach.\n\nREADY: I am ready to continue executing the task."
agent = Agent(
role="Test Agent",
goal="To test the mid-execution reasoning handler",
@@ -109,17 +105,17 @@ def test_mid_execution_reasoning_handler():
reasoning=True,
verbose=True
)
task = Task(
description="Task to test mid-execution reasoning handler.",
expected_output="The mid-execution reasoning handler should work correctly.",
agent=agent
)
agent.llm.call = MagicMock(return_value="Based on progress, I'll adjust my approach.\n\nREADY: I am ready to continue executing the task.")
reasoning_handler = AgentReasoning(task=task, agent=agent)
result = reasoning_handler.handle_mid_execution_reasoning(
current_steps=3,
tools_used=["search_tool", "calculator_tool"],
@@ -131,7 +127,7 @@ def test_mid_execution_reasoning_handler():
{"role": "system", "content": "Calculation result: 42"}
]
)
assert result is not None
assert hasattr(result, 'plan')
assert hasattr(result.plan, 'plan')
@@ -145,7 +141,7 @@ def test_should_trigger_reasoning_interval():
agent.reasoning = True
agent.reasoning_interval = 3
agent.adaptive_reasoning = False
executor = CrewAgentExecutor(
llm=MagicMock(),
task=MagicMock(),
@@ -159,16 +155,16 @@ def test_should_trigger_reasoning_interval():
tools_description="",
tools_handler=MagicMock()
)
executor.steps_since_reasoning = 0
assert executor._should_trigger_reasoning() is False
executor.steps_since_reasoning = 2
assert executor._should_trigger_reasoning() is False
executor.steps_since_reasoning = 3
assert executor._should_trigger_reasoning() is True
executor.steps_since_reasoning = 4
assert executor._should_trigger_reasoning() is True
@@ -179,7 +175,7 @@ def test_should_trigger_adaptive_reasoning():
agent.reasoning = True
agent.reasoning_interval = None
agent.adaptive_reasoning = True
executor = CrewAgentExecutor(
llm=MagicMock(),
task=MagicMock(),
@@ -193,14 +189,14 @@ def test_should_trigger_adaptive_reasoning():
tools_description="",
tools_handler=MagicMock()
)
executor.tools_used = ["tool1", "tool2", "tool3"]
assert executor._should_adaptive_reason() is True
executor.tools_used = ["tool1", "tool1", "tool1"]
executor.iterations = 6 # > max_iter // 2
assert executor._should_adaptive_reason() is True
executor.tools_used = ["tool1", "tool1", "tool1"]
executor.iterations = 2
executor.messages = [
@@ -209,7 +205,7 @@ def test_should_trigger_adaptive_reasoning():
{"role": "assistant", "content": "Let me try something else."}
]
assert executor._should_adaptive_reason() is True
executor.tools_used = ["tool1", "tool1", "tool1"]
executor.iterations = 2
executor.messages = [
@@ -233,7 +229,7 @@ def test_reasoning_interval_scenarios(interval, steps, should_reason):
agent.reasoning = True
agent.reasoning_interval = interval
agent.adaptive_reasoning = False
executor = CrewAgentExecutor(
llm=MagicMock(),
task=MagicMock(),
@@ -247,6 +243,6 @@ def test_reasoning_interval_scenarios(interval, steps, should_reason):
tools_description="",
tools_handler=MagicMock()
)
executor.steps_since_reasoning = steps
assert executor._should_trigger_reasoning() is should_reason