andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-15 02:58:30 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

feat: merge main

Browse Source
This commit is contained in:
Eduardo Chiarotti
2025-02-10 10:18:31 -03:00
parent c06e6e0021 fbd0e015d5
commit 6a8ca951a7
50 changed files with 1955 additions and 295 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/agent_test.py
View File

@@ -1183,7 +1183,7 @@ def test_agent_max_retry_limit():
[
mock.call(
{
"input": "Say the word: Hi\n\nThis is the expect criteria for your final answer: The word: Hi\nyou MUST return the actual complete content as the final answer, not a summary.",
"input": "Say the word: Hi\n\nThis is the expected criteria for your final answer: The word: Hi\nyou MUST return the actual complete content as the final answer, not a summary.",
"tool_names": "",
"tools": "",
"ask_for_human_input": True,
@@ -1191,7 +1191,7 @@ def test_agent_max_retry_limit():
),
mock.call(
{
"input": "Say the word: Hi\n\nThis is the expect criteria for your final answer: The word: Hi\nyou MUST return the actual complete content as the final answer, not a summary.",
"input": "Say the word: Hi\n\nThis is the expected criteria for your final answer: The word: Hi\nyou MUST return the actual complete content as the final answer, not a summary.",
"tool_names": "",
"tools": "",
"ask_for_human_input": True,

100
tests/cassettes/test_deepseek_r1_with_open_router.yaml Normal file
View File

@@ -0,0 +1,100 @@
interactions:
- request:
body: '{"model": "deepseek/deepseek-r1", "messages": [{"role": "user", "content":
"What is the capital of France?"}], "stop": [], "stream": false}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '139'
host:
- openrouter.ai
http-referer:
- https://litellm.ai
user-agent:
- litellm/1.60.2
x-title:
- liteLLM
method: POST
uri: https://openrouter.ai/api/v1/chat/completions
response:
content: "\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n\n
\ \n\n \n\n \n\n \n\n \n\n \n{\"id\":\"gen-1738684300-YnD5WOSczQWsW0vQG78a\",\"provider\":\"Nebius\",\"model\":\"deepseek/deepseek-r1\",\"object\":\"chat.completion\",\"created\":1738684300,\"choices\":[{\"logprobs\":null,\"index\":0,\"message\":{\"role\":\"assistant\",\"content\":\"The
capital of France is **Paris**. Known for its iconic landmarks such as the Eiffel
Tower, Notre-Dame Cathedral, and the Louvre Museum, Paris has served as the
political and cultural center of France for centuries. \U0001F1EB\U0001F1F7\",\"refusal\":null}}],\"usage\":{\"prompt_tokens\":10,\"completion_tokens\":261,\"total_tokens\":271}}"
headers:
Access-Control-Allow-Origin:
- '*'
CF-RAY:
- 90cbd2ceaf3ead5e-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 15:51:40 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
Vary:
- Accept-Encoding
x-clerk-auth-message:
- Invalid JWT form. A JWT consists of three parts separated by dots. (reason=token-invalid,
token-carrier=header)
x-clerk-auth-reason:
- token-invalid
x-clerk-auth-status:
- signed-out
http_version: HTTP/1.1
status_code: 200
version: 1

107
tests/cassettes/test_o3_mini_reasoning_effort_high.yaml Normal file
View File

@@ -0,0 +1,107 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the capital of France?"}],
"model": "o3-mini", "reasoning_effort": "high", "stop": []}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '137'
content-type:
- application/json
cookie:
- _cfuvid=etTqqA9SBOnENmrFAUBIexdW0v2ZeO1x9_Ek_WChlfU-1737568920137-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxFNUz7l4pwtY9xhFSPIGlwNfE4Sj\",\n \"object\":
\"chat.completion\",\n \"created\": 1738683828,\n \"model\": \"o3-mini-2025-01-31\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The capital of France is Paris.\",\n
\ \"refusal\": null\n },\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 13,\n \"completion_tokens\":
81,\n \"total_tokens\": 94,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 64,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_8bcaa0ca21\"\n}\n"
headers:
CF-RAY:
- 90cbc745d91fb0ca-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 15:43:50 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=.AP74BirsYr.lu61bSaimK2HRF6126qr5vCrr3HC6ak-1738683830-1.0.1.1-feh.bcMOv9wYnitoPpr.7UR7JrzCsbRLlzct09xCDm2SwmnRQQk5ZSSV41Ywer2S0rptbvufFwklV9wo9ATvWw;
path=/; expires=Tue, 04-Feb-25 16:13:50 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=JBfx8Sl7w82A0S_K1tQd5ZcwzWaZP5Gg5W1dqAdgwNU-1738683830528-0.0.1.1-604800000;
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:
- '2169'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999974'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_163e7bd79cb5a5e62d4688245b97d1d9
http_version: HTTP/1.1
status_code: 200
version: 1

102
tests/cassettes/test_o3_mini_reasoning_effort_low.yaml Normal file
View File

@@ -0,0 +1,102 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the capital of France?"}],
"model": "o3-mini", "reasoning_effort": "low", "stop": []}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '136'
content-type:
- application/json
cookie:
- _cfuvid=JBfx8Sl7w82A0S_K1tQd5ZcwzWaZP5Gg5W1dqAdgwNU-1738683830528-0.0.1.1-604800000;
__cf_bm=.AP74BirsYr.lu61bSaimK2HRF6126qr5vCrr3HC6ak-1738683830-1.0.1.1-feh.bcMOv9wYnitoPpr.7UR7JrzCsbRLlzct09xCDm2SwmnRQQk5ZSSV41Ywer2S0rptbvufFwklV9wo9ATvWw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxFNWljEYFrf5qRwYj73OPQtAnPbF\",\n \"object\":
\"chat.completion\",\n \"created\": 1738683830,\n \"model\": \"o3-mini-2025-01-31\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The capital of France is Paris.\",\n
\ \"refusal\": null\n },\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 13,\n \"completion_tokens\":
17,\n \"total_tokens\": 30,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_8bcaa0ca21\"\n}\n"
headers:
CF-RAY:
- 90cbc7551fe0b0ca-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 15:43:51 GMT
Server:
- cloudflare
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:
- '1103'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999974'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_fd7178a0e5060216d04f3bd023e8bca1
http_version: HTTP/1.1
status_code: 200
version: 1

102
tests/cassettes/test_o3_mini_reasoning_effort_medium.yaml Normal file
View File

@@ -0,0 +1,102 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the capital of France?"}],
"model": "o3-mini", "reasoning_effort": "medium", "stop": []}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '139'
content-type:
- application/json
cookie:
- _cfuvid=JBfx8Sl7w82A0S_K1tQd5ZcwzWaZP5Gg5W1dqAdgwNU-1738683830528-0.0.1.1-604800000;
__cf_bm=.AP74BirsYr.lu61bSaimK2HRF6126qr5vCrr3HC6ak-1738683830-1.0.1.1-feh.bcMOv9wYnitoPpr.7UR7JrzCsbRLlzct09xCDm2SwmnRQQk5ZSSV41Ywer2S0rptbvufFwklV9wo9ATvWw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxFS8IuMeYs6Rky2UbG8wH8P5PR4k\",\n \"object\":
\"chat.completion\",\n \"created\": 1738684116,\n \"model\": \"o3-mini-2025-01-31\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The capital of France is Paris.\",\n
\ \"refusal\": null\n },\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 13,\n \"completion_tokens\":
145,\n \"total_tokens\": 158,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 128,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_8bcaa0ca21\"\n}\n"
headers:
CF-RAY:
- 90cbce51b946afb4-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 15:48:39 GMT
Server:
- cloudflare
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:
- '2365'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999974'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_bfd83679e674c3894991477f1fb043b2
http_version: HTTP/1.1
status_code: 200
version: 1

89
tests/cli/cli_test.py
View File

@@ -55,72 +55,83 @@ 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()
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_all_memories(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
result = runner.invoke(reset_memories, ["-a"])
mock_crew.reset_memories.assert_called_once_with(command_type="all")
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):
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_short_term_memories(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
result = runner.invoke(reset_memories, ["-s"])
MockShortTermMemory().reset.assert_called_once()
mock_crew.reset_memories.assert_called_once_with(command_type="short")
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):
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_entity_memories(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
result = runner.invoke(reset_memories, ["-e"])
MockEntityMemory().reset.assert_called_once()
mock_crew.reset_memories.assert_called_once_with(command_type="entity")
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):
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_long_term_memories(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
result = runner.invoke(reset_memories, ["-l"])
MockLongTermMemory().reset.assert_called_once()
mock_crew.reset_memories.assert_called_once_with(command_type="long")
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):
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_kickoff_outputs(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
result = runner.invoke(reset_memories, ["-k"])
MockTaskOutputStorageHandler().reset.assert_called_once()
mock_crew.reset_memories.assert_called_once_with(command_type="kickoff_outputs")
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",
],
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_multiple_memory_flags(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
result = runner.invoke(reset_memories, ["-s", "-l"])
# Check that reset_memories was called twice with the correct arguments
assert mock_crew.reset_memories.call_count == 2
mock_crew.reset_memories.assert_has_calls(
[mock.call(command_type="long"), mock.call(command_type="short")]
)
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"
)
@mock.patch("crewai.cli.reset_memories_command.get_crew")
def test_reset_knowledge(mock_get_crew, runner):
mock_crew = mock.Mock()
mock_get_crew.return_value = mock_crew
result = runner.invoke(reset_memories, ["--knowledge"])
mock_crew.reset_memories.assert_called_once_with(command_type="knowledge")
assert result.output == "Knowledge has been reset.\n"
def test_reset_no_memory_flags(runner):
result = runner.invoke(
reset_memories,

2
tests/config/tasks.yaml
View File

@@ -2,7 +2,7 @@ research_task:
description: >
Conduct a thorough research about {topic}
Make sure you find any interesting and relevant information given
the current year is 2024.
the current year is 2025.
expected_output: >
A list with 10 bullet points of the most relevant information about {topic}
agent: researcher

293
tests/crew_test.py
View File

@@ -49,6 +49,39 @@ writer = Agent(
)
def test_crew_with_only_conditional_tasks_raises_error():
"""Test that creating a crew with only conditional tasks raises an error."""
def condition_func(task_output: TaskOutput) -> bool:
return True
conditional1 = ConditionalTask(
description="Conditional task 1",
expected_output="Output 1",
agent=researcher,
condition=condition_func,
)
conditional2 = ConditionalTask(
description="Conditional task 2",
expected_output="Output 2",
agent=researcher,
condition=condition_func,
)
conditional3 = ConditionalTask(
description="Conditional task 3",
expected_output="Output 3",
agent=researcher,
condition=condition_func,
)
with pytest.raises(
pydantic_core._pydantic_core.ValidationError,
match="Crew must include at least one non-conditional task",
):
Crew(
agents=[researcher],
tasks=[conditional1, conditional2, conditional3],
)
def test_crew_config_conditional_requirement():
with pytest.raises(ValueError):
Crew(process=Process.sequential)
@@ -1917,6 +1950,77 @@ def test_task_callback_on_crew():
assert isinstance(args[0], TaskOutput)
def test_task_callback_both_on_task_and_crew():
from unittest.mock import MagicMock, patch
mock_callback_on_task = MagicMock()
mock_callback_on_crew = MagicMock()
researcher_agent = Agent(
role="Researcher",
goal="Make the best research and analysis on content about AI and AI agents",
backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
allow_delegation=False,
)
list_ideas = Task(
description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
expected_output="Bullet point list of 5 important events.",
agent=researcher_agent,
async_execution=True,
callback=mock_callback_on_task,
)
crew = Crew(
agents=[researcher_agent],
process=Process.sequential,
tasks=[list_ideas],
task_callback=mock_callback_on_crew,
)
with patch.object(Agent, "execute_task") as execute:
execute.return_value = "ok"
crew.kickoff()
assert list_ideas.callback is not None
mock_callback_on_task.assert_called_once_with(list_ideas.output)
mock_callback_on_crew.assert_called_once_with(list_ideas.output)
def test_task_same_callback_both_on_task_and_crew():
from unittest.mock import MagicMock, patch
mock_callback = MagicMock()
researcher_agent = Agent(
role="Researcher",
goal="Make the best research and analysis on content about AI and AI agents",
backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
allow_delegation=False,
)
list_ideas = Task(
description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
expected_output="Bullet point list of 5 important events.",
agent=researcher_agent,
async_execution=True,
callback=mock_callback,
)
crew = Crew(
agents=[researcher_agent],
process=Process.sequential,
tasks=[list_ideas],
task_callback=mock_callback,
)
with patch.object(Agent, "execute_task") as execute:
execute.return_value = "ok"
crew.kickoff()
assert list_ideas.callback is not None
mock_callback.assert_called_once_with(list_ideas.output)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_tools_with_custom_caching():
from unittest.mock import patch
@@ -1989,6 +2093,195 @@ def test_tools_with_custom_caching():
assert result.raw == "3"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_conditional_task_uses_last_output():
"""Test that conditional tasks use the last task output for condition evaluation."""
task1 = Task(
description="First task",
expected_output="First output",
agent=researcher,
)
def condition_fails(task_output: TaskOutput) -> bool:
# This condition will never be met
return "never matches" in task_output.raw.lower()
def condition_succeeds(task_output: TaskOutput) -> bool:
# This condition will match first task's output
return "first success" in task_output.raw.lower()
conditional_task1 = ConditionalTask(
description="Second task - conditional that fails condition",
expected_output="Second output",
agent=researcher,
condition=condition_fails,
)
conditional_task2 = ConditionalTask(
description="Third task - conditional that succeeds using first task output",
expected_output="Third output",
agent=writer,
condition=condition_succeeds,
)
crew = Crew(
agents=[researcher, writer],
tasks=[task1, conditional_task1, conditional_task2],
)
# Mock outputs for tasks
mock_first = TaskOutput(
description="First task output",
raw="First success output", # Will be used by third task's condition
agent=researcher.role,
)
mock_skipped = TaskOutput(
description="Second task output",
raw="", # Empty output since condition fails
agent=researcher.role,
)
mock_third = TaskOutput(
description="Third task output",
raw="Third task executed", # Output when condition succeeds using first task output
agent=writer.role,
)
# Set up mocks for task execution and conditional logic
with patch.object(ConditionalTask, "should_execute") as mock_should_execute:
# First conditional fails, second succeeds
mock_should_execute.side_effect = [False, True]
with patch.object(Task, "execute_sync") as mock_execute:
mock_execute.side_effect = [mock_first, mock_third]
result = crew.kickoff()
# Verify execution behavior
assert mock_execute.call_count == 2 # Only first and third tasks execute
assert mock_should_execute.call_count == 2 # Both conditionals checked
# Verify outputs collection
assert len(result.tasks_output) == 3
assert result.tasks_output[0].raw == "First success output" # First task succeeded
assert result.tasks_output[1].raw == "" # Second task skipped (condition failed)
assert result.tasks_output[2].raw == "Third task executed" # Third task used first task's output
@pytest.mark.vcr(filter_headers=["authorization"])
def test_conditional_tasks_result_collection():
"""Test that task outputs are properly collected based on execution status."""
task1 = Task(
description="Normal task that always executes",
expected_output="First output",
agent=researcher,
)
def condition_never_met(task_output: TaskOutput) -> bool:
return "never matches" in task_output.raw.lower()
def condition_always_met(task_output: TaskOutput) -> bool:
return "success" in task_output.raw.lower()
task2 = ConditionalTask(
description="Conditional task that never executes",
expected_output="Second output",
agent=researcher,
condition=condition_never_met,
)
task3 = ConditionalTask(
description="Conditional task that always executes",
expected_output="Third output",
agent=writer,
condition=condition_always_met,
)
crew = Crew(
agents=[researcher, writer],
tasks=[task1, task2, task3],
)
# Mock outputs for different execution paths
mock_success = TaskOutput(
description="Success output",
raw="Success output", # Triggers third task's condition
agent=researcher.role,
)
mock_skipped = TaskOutput(
description="Skipped output",
raw="", # Empty output for skipped task
agent=researcher.role,
)
mock_conditional = TaskOutput(
description="Conditional output",
raw="Conditional task executed",
agent=writer.role,
)
# Set up mocks for task execution and conditional logic
with patch.object(ConditionalTask, "should_execute") as mock_should_execute:
# First conditional fails, second succeeds
mock_should_execute.side_effect = [False, True]
with patch.object(Task, "execute_sync") as mock_execute:
mock_execute.side_effect = [mock_success, mock_conditional]
result = crew.kickoff()
# Verify execution behavior
assert mock_execute.call_count == 2 # Only first and third tasks execute
assert mock_should_execute.call_count == 2 # Both conditionals checked
# Verify task output collection
assert len(result.tasks_output) == 3
assert result.tasks_output[0].raw == "Success output" # Normal task executed
assert result.tasks_output[1].raw == "" # Second task skipped
assert result.tasks_output[2].raw == "Conditional task executed" # Third task executed
@pytest.mark.vcr(filter_headers=["authorization"])
def test_multiple_conditional_tasks():
"""Test that having multiple conditional tasks in sequence works correctly."""
task1 = Task(
description="Initial research task",
expected_output="Research output",
agent=researcher,
)
def condition1(task_output: TaskOutput) -> bool:
return "success" in task_output.raw.lower()
def condition2(task_output: TaskOutput) -> bool:
return "proceed" in task_output.raw.lower()
task2 = ConditionalTask(
description="First conditional task",
expected_output="Conditional output 1",
agent=writer,
condition=condition1,
)
task3 = ConditionalTask(
description="Second conditional task",
expected_output="Conditional output 2",
agent=writer,
condition=condition2,
)
crew = Crew(
agents=[researcher, writer],
tasks=[task1, task2, task3],
)
# Mock different task outputs to test conditional logic
mock_success = TaskOutput(
description="Mock success",
raw="Success and proceed output",
agent=researcher.role,
)
# Set up mocks for task execution
with patch.object(Task, "execute_sync", return_value=mock_success) as mock_execute:
result = crew.kickoff()
# Verify all tasks were executed (no IndexError)
assert mock_execute.call_count == 3
assert len(result.tasks_output) == 3
@pytest.mark.vcr(filter_headers=["authorization"])
def test_using_contextual_memory():
from unittest.mock import patch

169
tests/llm_test.py
View File

@@ -1,7 +1,9 @@
import os
from time import sleep
from unittest.mock import MagicMock, patch
import pytest
from pydantic import BaseModel
from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
from crewai.llm import LLM
@@ -202,3 +204,170 @@ def test_llm_passes_additional_params():
# Check the result from llm.call
assert result == "Test response"
def test_get_custom_llm_provider_openrouter():
llm = LLM(model="openrouter/deepseek/deepseek-chat")
assert llm._get_custom_llm_provider() == "openrouter"
def test_get_custom_llm_provider_gemini():
llm = LLM(model="gemini/gemini-1.5-pro")
assert llm._get_custom_llm_provider() == "gemini"
def test_get_custom_llm_provider_openai():
llm = LLM(model="gpt-4")
assert llm._get_custom_llm_provider() == "openai"
def test_validate_call_params_supported():
class DummyResponse(BaseModel):
a: int
# Patch supports_response_schema to simulate a supported model.
with patch("crewai.llm.supports_response_schema", return_value=True):
llm = LLM(
model="openrouter/deepseek/deepseek-chat", response_format=DummyResponse
)
# Should not raise any error.
llm._validate_call_params()
def test_validate_call_params_not_supported():
class DummyResponse(BaseModel):
a: int
# Patch supports_response_schema to simulate an unsupported model.
with patch("crewai.llm.supports_response_schema", return_value=False):
llm = LLM(model="gemini/gemini-1.5-pro", response_format=DummyResponse)
with pytest.raises(ValueError) as excinfo:
llm._validate_call_params()
assert "does not support response_format" in str(excinfo.value)
def test_validate_call_params_no_response_format():
# When no response_format is provided, no validation error should occur.
llm = LLM(model="gemini/gemini-1.5-pro", response_format=None)
llm._validate_call_params()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_o3_mini_reasoning_effort_high():
llm = LLM(
model="o3-mini",
reasoning_effort="high",
)
result = llm.call("What is the capital of France?")
assert isinstance(result, str)
assert "Paris" in result
@pytest.mark.vcr(filter_headers=["authorization"])
def test_o3_mini_reasoning_effort_low():
llm = LLM(
model="o3-mini",
reasoning_effort="low",
)
result = llm.call("What is the capital of France?")
assert isinstance(result, str)
assert "Paris" in result
@pytest.mark.vcr(filter_headers=["authorization"])
def test_o3_mini_reasoning_effort_medium():
llm = LLM(
model="o3-mini",
reasoning_effort="medium",
)
result = llm.call("What is the capital of France?")
assert isinstance(result, str)
assert "Paris" in result
@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.fixture
def anthropic_llm():
"""Fixture providing an Anthropic LLM instance."""
return LLM(model="anthropic/claude-3-sonnet")
@pytest.fixture
def system_message():
"""Fixture providing a system message."""
return {"role": "system", "content": "test"}
@pytest.fixture
def user_message():
"""Fixture providing a user message."""
return {"role": "user", "content": "test"}
def test_anthropic_message_formatting_edge_cases(anthropic_llm):
"""Test edge cases for Anthropic message formatting."""
# Test None messages
with pytest.raises(TypeError, match="Messages cannot be None"):
anthropic_llm._format_messages_for_provider(None)
# Test empty message list
formatted = anthropic_llm._format_messages_for_provider([])
assert len(formatted) == 1
assert formatted[0]["role"] == "user"
assert formatted[0]["content"] == "."
# Test invalid message format
with pytest.raises(TypeError, match="Invalid message format"):
anthropic_llm._format_messages_for_provider([{"invalid": "message"}])
def test_anthropic_model_detection():
"""Test Anthropic model detection with various formats."""
models = [
("anthropic/claude-3", True),
("claude-instant", True),
("claude/v1", True),
("gpt-4", False),
("", False),
("anthropomorphic", False), # Should not match partial words
]
for model, expected in models:
llm = LLM(model=model)
assert llm.is_anthropic == expected, f"Failed for model: {model}"
def test_anthropic_message_formatting(anthropic_llm, system_message, user_message):
"""Test Anthropic message formatting with fixtures."""
# Test when first message is system
formatted = anthropic_llm._format_messages_for_provider([system_message])
assert len(formatted) == 2
assert formatted[0]["role"] == "user"
assert formatted[0]["content"] == "."
assert formatted[1] == system_message
# Test when first message is already user
formatted = anthropic_llm._format_messages_for_provider([user_message])
assert len(formatted) == 1
assert formatted[0] == user_message
# Test with empty message list
formatted = anthropic_llm._format_messages_for_provider([])
assert len(formatted) == 1
assert formatted[0]["role"] == "user"
assert formatted[0]["content"] == "."
# Test with non-Anthropic model (should not modify messages)
non_anthropic_llm = LLM(model="gpt-4")
formatted = non_anthropic_llm._format_messages_for_provider([system_message])
assert len(formatted) == 1
assert formatted[0] == system_message
def test_deepseek_r1_with_open_router():
if not os.getenv("OPEN_ROUTER_API_KEY"):
pytest.skip("OPEN_ROUTER_API_KEY not set; skipping test.")
llm = LLM(
model="openrouter/deepseek/deepseek-r1",
base_url="https://openrouter.ai/api/v1",
api_key=os.getenv("OPEN_ROUTER_API_KEY"),
)
result = llm.call("What is the capital of France?")
assert isinstance(result, str)
assert "Paris" in result

4
tests/task_test.py
View File

@@ -723,14 +723,14 @@ def test_interpolate_inputs():
)
task.interpolate_inputs_and_add_conversation_history(
inputs={"topic": "AI", "date": "2024"}
inputs={"topic": "AI", "date": "2025"}
)
assert (
task.description
== "Give me a list of 5 interesting ideas about AI to explore for an article, what makes them unique and interesting."
)
assert task.expected_output == "Bullet point list of 5 interesting ideas about AI."
assert task.output_file == "/tmp/AI/output_2024.txt"
assert task.output_file == "/tmp/AI/output_2025.txt"
task.interpolate_inputs_and_add_conversation_history(
inputs={"topic": "ML", "date": "2025"}