andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-05-07 18:19:00 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

Merge branch 'main' into main

Browse Source
This commit is contained in:
PJ
2024-12-18 09:30:25 -05:00
committed by GitHub
parent 4d06dc262c 627b9f1abb
commit d1df81a001
115 changed files with 2262 additions and 12444 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
tests/agent_test.py
View File

@@ -3,19 +3,20 @@
import os
from unittest import mock
from unittest.mock import patch
import pytest
from crewai import Agent, Crew, Task
from crewai.agents.cache import CacheHandler
from crewai.agents.crew_agent_executor import CrewAgentExecutor
from crewai.agents.parser import AgentAction, CrewAgentParser, OutputParserException
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
from crewai.llm import LLM
from crewai.tools import tool
from crewai.tools.tool_calling import InstructorToolCalling
from crewai.tools.tool_usage import ToolUsage
from crewai.tools.tool_usage_events import ToolUsageFinished
from crewai.utilities import RPMController
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
from crewai.utilities.events import Emitter
@@ -985,8 +986,7 @@ def test_agent_definition_based_on_dict():
# test for human input
@pytest.mark.vcr(filter_headers=["authorization"])
def test_agent_human_input():
from unittest.mock import patch
# Agent configuration
config = {
"role": "test role",
"goal": "test goal",
@@ -995,6 +995,7 @@ def test_agent_human_input():
agent = Agent(**config)
# Task configuration with human input enabled
task = Task(
agent=agent,
description="Say the word: Hi",
@@ -1002,11 +1003,26 @@ def test_agent_human_input():
human_input=True,
)
with patch.object(CrewAgentExecutor, "_ask_human_input") as mock_human_input:
mock_human_input.return_value = "Don't say hi, say Hello instead!"
# Side effect function for _ask_human_input to simulate multiple feedback iterations
feedback_responses = iter(
[
"Don't say hi, say Hello instead!", # First feedback
"looks good", # Second feedback to exit loop
]
)
def ask_human_input_side_effect(*args, **kwargs):
return next(feedback_responses)
with patch.object(
CrewAgentExecutor, "_ask_human_input", side_effect=ask_human_input_side_effect
) as mock_human_input:
# Execute the task
output = agent.execute_task(task)
mock_human_input.assert_called_once()
assert output == "Hello"
# Assertions to ensure the agent behaves correctly
assert mock_human_input.call_count == 2 # Should have asked for feedback twice
assert output.strip().lower() == "hello" # Final output should be 'Hello'
def test_interpolate_inputs():
@@ -1579,19 +1595,15 @@ def test_agent_execute_task_with_ollama():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_agent_with_knowledge_sources():
# Create a knowledge source with some content
content = "Brandon's favorite color is blue and he likes Mexican food."
string_source = StringKnowledgeSource(
content=content, metadata={"preference": "personal"}
)
content = "Brandon's favorite color is red and he likes Mexican food."
string_source = StringKnowledgeSource(content=content)
with patch(
"crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"
) as MockKnowledge:
mock_knowledge_instance = MockKnowledge.return_value
mock_knowledge_instance.sources = [string_source]
mock_knowledge_instance.query.return_value = [
{"content": content, "metadata": {"preference": "personal"}}
]
mock_knowledge_instance.query.return_value = [{"content": content}]
agent = Agent(
role="Information Agent",
@@ -1612,4 +1624,4 @@ def test_agent_with_knowledge_sources():
result = crew.kickoff()
# Assert that the agent provides the correct information
assert "blue" in result.raw.lower()
assert "red" in result.raw.lower()

3
tests/agents/agent_builder/base_agent_test.py
View File

@@ -1,9 +1,10 @@
import hashlib
from typing import Any, List, Optional
from pydantic import BaseModel
from crewai.agents.agent_builder.base_agent import BaseAgent
from crewai.tools.base_tool import BaseTool
from pydantic import BaseModel
class TestAgent(BaseAgent):

3
tests/agents/test_crew_agent_parser.py
View File

@@ -1,10 +1,11 @@
import pytest
from crewai.agents.parser import CrewAgentParser
from crewai.agents.crew_agent_executor import (
AgentAction,
AgentFinish,
OutputParserException,
)
from crewai.agents.parser import CrewAgentParser
@pytest.fixture

321
tests/cassettes/test_agent_human_input.yaml
View File

@@ -9,7 +9,8 @@ interactions:
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.\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:"}], "model": "gpt-4o"}'
your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
@@ -18,16 +19,13 @@ interactions:
connection:
- keep-alive
content-length:
- '774'
- '824'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
@@ -37,29 +35,34 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7WMYMmqACvaemh26N6a62wxlxvx\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213882,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-AaqIIsTxhvf75xvuu7gQScIlRSKbW\",\n \"object\":
\"chat.completion\",\n \"created\": 1733344190,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: Hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
158,\n \"completion_tokens\": 14,\n \"total_tokens\": 172,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
158,\n \"completion_tokens\": 12,\n \"total_tokens\": 170,\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 \"system_fingerprint\":
\"fp_0705bf87c0\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85eb4f58751cf3-GRU
- 8ece8cfc3b1f4532-ATL
Connection:
- keep-alive
Content-Encoding:
@@ -67,7 +70,118 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:03 GMT
- Wed, 04 Dec 2024 20:29:50 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=QJZZjZ6eqnVamqUkw.Bx0mj7oBi3a_vGEH1VODcUxlg-1733344190-1.0.1.1-xyN0ekA9xIrSwEhRBmTiWJ3Pt72UYLU5owKfkz5yihVmMTfsr_Qz.ssGPJ5cuft066v1xVjb4zOSTdFmesMSKg;
path=/; expires=Wed, 04-Dec-24 20:59:50 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=eCIkP8GVPvpkg19eOhCquWFHm.RTQBQy4yHLGGEAH5c-1733344190334-0.0.1.1-604800000;
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
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '313'
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:
- '149999816'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_9fd9a8ee688045dcf7ac5f6fdf689372
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "Determine if the following
feedback indicates that the user is satisfied or if further changes are needed.
Respond with ''True'' if further changes are needed, or ''False'' if the user
is satisfied. **Important** Do not include any additional commentary outside
of your ''True'' or ''False'' response.\n\nFeedback: \"Don''t say hi, say Hello
instead!\""}], "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream":
false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '461'
content-type:
- application/json
cookie:
- __cf_bm=QJZZjZ6eqnVamqUkw.Bx0mj7oBi3a_vGEH1VODcUxlg-1733344190-1.0.1.1-xyN0ekA9xIrSwEhRBmTiWJ3Pt72UYLU5owKfkz5yihVmMTfsr_Qz.ssGPJ5cuft066v1xVjb4zOSTdFmesMSKg;
_cfuvid=eCIkP8GVPvpkg19eOhCquWFHm.RTQBQy4yHLGGEAH5c-1733344190334-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
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-AaqIIaQlLyoyPmk909PvAIfA2TmJL\",\n \"object\":
\"chat.completion\",\n \"created\": 1733344190,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"True\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 78,\n \"completion_tokens\":
1,\n \"total_tokens\": 79,\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 \"system_fingerprint\":
\"fp_0705bf87c0\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8ece8d060b5e4532-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 04 Dec 2024 20:29:50 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -76,28 +190,30 @@ interactions:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '262'
- '375'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
- '30000'
x-ratelimit-limit-tokens:
- '30000000'
- '150000000'
x-ratelimit-remaining-requests:
- '9999'
- '29999'
x-ratelimit-remaining-tokens:
- '29999817'
- '149999898'
x-ratelimit-reset-requests:
- 6ms
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_69b1deae1cc3cbf488cee975cd3b04df
- req_be7cb475e0859a82c37ee3f2871ea5ea
http_version: HTTP/1.1
status_code: 200
- request:
@@ -110,8 +226,10 @@ interactions:
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.\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:"}, {"role": "user", "content": "Feedback:
Don''t say hi, say Hello instead!"}], "model": "gpt-4o"}'
your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I now
can give a great answer \nFinal Answer: Hi"}, {"role": "user", "content": "Feedback:
Don''t say hi, say Hello instead!"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
@@ -120,16 +238,16 @@ interactions:
connection:
- keep-alive
content-length:
- '849'
- '986'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
- __cf_bm=QJZZjZ6eqnVamqUkw.Bx0mj7oBi3a_vGEH1VODcUxlg-1733344190-1.0.1.1-xyN0ekA9xIrSwEhRBmTiWJ3Pt72UYLU5owKfkz5yihVmMTfsr_Qz.ssGPJ5cuft066v1xVjb4zOSTdFmesMSKg;
_cfuvid=eCIkP8GVPvpkg19eOhCquWFHm.RTQBQy4yHLGGEAH5c-1733344190334-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
@@ -139,29 +257,34 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7WNec1Ohw0pEU91kuCTuts2hXWM\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213883,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-AaqIJAAxpVfUOdrsgYKHwfRlHv4RS\",\n \"object\":
\"chat.completion\",\n \"created\": 1733344191,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: Hello\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
172,\n \"completion_tokens\": 14,\n \"total_tokens\": 186,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
\"assistant\",\n \"content\": \"Thought: I now can give a great answer
\ \\nFinal Answer: Hello\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
188,\n \"completion_tokens\": 14,\n \"total_tokens\": 202,\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 \"system_fingerprint\":
\"fp_0705bf87c0\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85eb52cd7c1cf3-GRU
- 8ece8d090fc34532-ATL
Connection:
- keep-alive
Content-Encoding:
@@ -169,7 +292,7 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:03 GMT
- Wed, 04 Dec 2024 20:29:51 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -178,28 +301,134 @@ interactions:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '261'
- '484'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
- '30000'
x-ratelimit-limit-tokens:
- '30000000'
- '150000000'
x-ratelimit-remaining-requests:
- '9999'
- '29999'
x-ratelimit-remaining-tokens:
- '29999806'
- '149999793'
x-ratelimit-reset-requests:
- 6ms
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_11a316792b5f54af94cce0c702aec290
- req_5bf4a565ad6c2567a1ed204ecac89134
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "Determine if the following
feedback indicates that the user is satisfied or if further changes are needed.
Respond with ''True'' if further changes are needed, or ''False'' if the user
is satisfied. **Important** Do not include any additional commentary outside
of your ''True'' or ''False'' response.\n\nFeedback: \"looks good\""}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '439'
content-type:
- application/json
cookie:
- __cf_bm=QJZZjZ6eqnVamqUkw.Bx0mj7oBi3a_vGEH1VODcUxlg-1733344190-1.0.1.1-xyN0ekA9xIrSwEhRBmTiWJ3Pt72UYLU5owKfkz5yihVmMTfsr_Qz.ssGPJ5cuft066v1xVjb4zOSTdFmesMSKg;
_cfuvid=eCIkP8GVPvpkg19eOhCquWFHm.RTQBQy4yHLGGEAH5c-1733344190334-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
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-AaqIJqyG8vl9mxj2qDPZgaxyNLLIq\",\n \"object\":
\"chat.completion\",\n \"created\": 1733344191,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"False\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 73,\n \"completion_tokens\":
1,\n \"total_tokens\": 74,\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 \"system_fingerprint\":
\"fp_0705bf87c0\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8ece8d0cfdeb4532-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 04 Dec 2024 20:29:51 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '341'
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:
- '149999902'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_5554bade8ceda00cf364b76a51b708ff
http_version: HTTP/1.1
status_code: 200
version: 1

431
tests/cassettes/test_agent_with_knowledge_sources.yaml
View File

File diff suppressed because one or more lines are too long

182
tests/cassettes/test_crew_kickoff_usage_metrics.yaml
View File

@@ -28,13 +28,13 @@ interactions:
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- x64
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
@@ -44,26 +44,27 @@ interactions:
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.9
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA4xSy27bMBC86ysWPEuB7ciV7VuAIkUObQ+59QFhTa0kttQuS9Jx08D/XkhyLAVJ
gV4EaGdnMLPDpwRAmUrtQOkWo+6czW7u41q2t3+cvCvuPvxafSG+58XHTzXlxWeV9gzZ/yAdn1lX
WjpnKRrhEdaeMFKvuiyul3m+uV7lA9BJRbanNS5muWSdYZOtFqs8WxTZcnNmt2I0BbWDrwkAwNPw
7X1yRb/VDhbp86SjELAhtbssASgvtp8oDMGEiBxVOoFaOBIP1u+A5QgaGRrzQIDQ9LYBORzJA3zj
W8No4Wb438F7aQKgJ7DyiBb6zMhGOKRA3CJrww10xBEttIQ2toBcgTyQR2vhSNZmezLcXM39eKoP
Afub8MHa8/x0CWilcV724Yxf5rVhE9rSEwbhPkyI4tSAnhKA78MhDy9uo5yXzsUyyk/iMHSzHvXU
1N+Ejo0BqCgR7Yy13aZv6JUVRTQ2zKpQGnVL1USdesNDZWQGJLPUr928pT0mN9z8j/wEaE0uUlU6
T5XRLxNPa5765/2vtcuVB8MqPIZIXVkbbsg7b8bHVbuyXm9xs8xXRa2SU/IXAAD//wMAq2ZCBWoD
AAA=
content: "{\n \"id\": \"chatcmpl-AcdAr57gPSeXoBUvpM7ihR5ocSg8K\",\n \"object\":
\"chat.completion\",\n \"created\": 1733770413,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: Dogs are loyal companions, enhancing human lives with love and joy.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 175,\n \"completion_tokens\":
24,\n \"total_tokens\": 199,\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 \"system_fingerprint\":
\"fp_bba3c8e70b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8e19bf36db158761-GRU
- 8ef732d93c754554-ATL
Connection:
- keep-alive
Content-Encoding:
@@ -71,14 +72,14 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 12 Nov 2024 21:52:04 GMT
- Mon, 09 Dec 2024 18:53:33 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=MkvcnvacGpTyn.y0OkFRoFXuAwg4oxjMhViZJTt9mw0-1731448324-1.0.1.1-oekkH_B0xOoPnIFw15LpqFCkZ2cu7VBTJVLDGylan4I67NjX.tlPvOiX9kvtP5Acewi28IE2IwlwtrZWzCH3vw;
path=/; expires=Tue, 12-Nov-24 22:22:04 GMT; domain=.api.openai.com; HttpOnly;
- __cf_bm=zftDGzMKnU559gRET72hds3.GZV1di4sti_Q8aIdqPg-1733770413-1.0.1.1-AXqWYLVe2ClCqIFObmsZXfjYEbJ8Ahbl74TpjGzyxfP1UsSB3HisukLyoXLq52raWViSlB3tLosiLnNEWwWMdw;
path=/; expires=Mon, 09-Dec-24 19:23:33 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=4.17346mfw5npZfYNbCx3Vj1VAVPy.tH0Jm2gkTteJ8-1731448324998-0.0.1.1-604800000;
- _cfuvid=eff7OIkJ0zWRunpA6z67LHqscmSe6XjNxXiPw1R3xCc-1733770413538-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
@@ -89,30 +90,29 @@ interactions:
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- user-tqfegqsiobpvvjmn0giaipdq
- crewai-iuxna1
openai-processing-ms:
- '601'
- '476'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
- '30000'
x-ratelimit-limit-tokens:
- '200000'
- '150000000'
x-ratelimit-remaining-requests:
- '9999'
- '29999'
x-ratelimit-remaining-tokens:
- '199793'
- '149999793'
x-ratelimit-reset-requests:
- 8.64s
- 2ms
x-ratelimit-reset-tokens:
- 62ms
- 0s
x-request-id:
- req_77fb166b4e272bfd45c37c08d2b93b0c
status:
code: 200
message: OK
- req_0d2fbea0013ad1ad0768fcdd457f5be3
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are cat Researcher. You
have a lot of experience with cat.\nYour personal goal is: Express hot takes
@@ -138,20 +138,20 @@ interactions:
content-type:
- application/json
cookie:
- __cf_bm=MkvcnvacGpTyn.y0OkFRoFXuAwg4oxjMhViZJTt9mw0-1731448324-1.0.1.1-oekkH_B0xOoPnIFw15LpqFCkZ2cu7VBTJVLDGylan4I67NjX.tlPvOiX9kvtP5Acewi28IE2IwlwtrZWzCH3vw;
_cfuvid=4.17346mfw5npZfYNbCx3Vj1VAVPy.tH0Jm2gkTteJ8-1731448324998-0.0.1.1-604800000
- __cf_bm=zftDGzMKnU559gRET72hds3.GZV1di4sti_Q8aIdqPg-1733770413-1.0.1.1-AXqWYLVe2ClCqIFObmsZXfjYEbJ8Ahbl74TpjGzyxfP1UsSB3HisukLyoXLq52raWViSlB3tLosiLnNEWwWMdw;
_cfuvid=eff7OIkJ0zWRunpA6z67LHqscmSe6XjNxXiPw1R3xCc-1733770413538-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- x64
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
@@ -161,26 +161,27 @@ interactions:
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.9
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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content: "{\n \"id\": \"chatcmpl-AcdArzlm4vKRhN7P4mtNE7X3UrCb3\",\n \"object\":
\"chat.completion\",\n \"created\": 1733770413,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: Cats are independent yet affectionate, making them unique companions
for humans.\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
175,\n \"completion_tokens\": 24,\n \"total_tokens\": 199,\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 \"system_fingerprint\":
\"fp_818c284075\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8e19bf3fae118761-GRU
- 8ef732dcfadf4554-ATL
Connection:
- keep-alive
Content-Encoding:
@@ -188,7 +189,7 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 12 Nov 2024 21:52:05 GMT
- Mon, 09 Dec 2024 18:53:34 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -200,30 +201,29 @@ interactions:
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- user-tqfegqsiobpvvjmn0giaipdq
- crewai-iuxna1
openai-processing-ms:
- '464'
- '418'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
- '30000'
x-ratelimit-limit-tokens:
- '200000'
- '150000000'
x-ratelimit-remaining-requests:
- '9998'
- '29999'
x-ratelimit-remaining-tokens:
- '199792'
- '149999793'
x-ratelimit-reset-requests:
- 16.369s
- 2ms
x-ratelimit-reset-tokens:
- 62ms
- 0s
x-request-id:
- req_91706b23d0ef23458ba63ec18304cd28
status:
code: 200
message: OK
- req_483f4fc624bef1034c884b5d0e847aee
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are apple Researcher.
You have a lot of experience with apple.\nYour personal goal is: Express hot
@@ -249,20 +249,20 @@ interactions:
content-type:
- application/json
cookie:
- __cf_bm=MkvcnvacGpTyn.y0OkFRoFXuAwg4oxjMhViZJTt9mw0-1731448324-1.0.1.1-oekkH_B0xOoPnIFw15LpqFCkZ2cu7VBTJVLDGylan4I67NjX.tlPvOiX9kvtP5Acewi28IE2IwlwtrZWzCH3vw;
_cfuvid=4.17346mfw5npZfYNbCx3Vj1VAVPy.tH0Jm2gkTteJ8-1731448324998-0.0.1.1-604800000
- __cf_bm=zftDGzMKnU559gRET72hds3.GZV1di4sti_Q8aIdqPg-1733770413-1.0.1.1-AXqWYLVe2ClCqIFObmsZXfjYEbJ8Ahbl74TpjGzyxfP1UsSB3HisukLyoXLq52raWViSlB3tLosiLnNEWwWMdw;
_cfuvid=eff7OIkJ0zWRunpA6z67LHqscmSe6XjNxXiPw1R3xCc-1733770413538-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- x64
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
@@ -272,26 +272,27 @@ interactions:
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.9
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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content: "{\n \"id\": \"chatcmpl-AcdAsHWkJ3K1sBl3O6XYMZZ3BhHx4\",\n \"object\":
\"chat.completion\",\n \"created\": 1733770414,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: Apple consistently innovates, leading the tech industry with flagship
products.\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
175,\n \"completion_tokens\": 24,\n \"total_tokens\": 199,\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 \"system_fingerprint\":
\"fp_818c284075\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8e19bf447ba48761-GRU
- 8ef732e028194554-ATL
Connection:
- keep-alive
Content-Encoding:
@@ -299,7 +300,7 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 12 Nov 2024 21:52:06 GMT
- Mon, 09 Dec 2024 18:53:34 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -311,28 +312,27 @@ interactions:
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- user-tqfegqsiobpvvjmn0giaipdq
- crewai-iuxna1
openai-processing-ms:
- '655'
- '393'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
- '30000'
x-ratelimit-limit-tokens:
- '200000'
- '150000000'
x-ratelimit-remaining-requests:
- '9997'
- '29999'
x-ratelimit-remaining-tokens:
- '199791'
- '149999791'
x-ratelimit-reset-requests:
- 24.239s
- 2ms
x-ratelimit-reset-tokens:
- 62ms
- 0s
x-request-id:
- req_a228208b0e965ecee334a6947d6c9e7c
status:
code: 200
message: OK
- req_01df88b62376d0b63fb3fa2761bc9c2b
http_version: HTTP/1.1
status_code: 200
version: 1

11356
tests/cassettes/test_increment_tool_errors.yaml
View File

File diff suppressed because it is too large Load Diff

118
tests/cassettes/test_llm_callback_replacement.yaml
View File

@@ -18,13 +18,13 @@ interactions:
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- x64
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
@@ -34,25 +34,26 @@ interactions:
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.9
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA4xSwWrcMBS8+ytedY6LvWvYZi8lpZSkBJLSQiChGK307FUi66nSc9Ml7L8H2e56
l7bQiw8zb8Yzg14yAGG0WINQW8mq8za/+Oqv5MUmXv+8+/Hl3uO3j59u1efreHO+/PAszpKCNo+o
+LfqraLOW2RDbqRVQMmYXMvVsqyWy1VVDERHGm2StZ7zivLOOJMvikWVF6u8fDept2QURrGGhwwA
4GX4ppxO4y+xhsFrQDqMUbYo1ocjABHIJkTIGE1k6ViczaQix+iG6JdoLb2BS3oGJR1cwSiAHfXA
pOXu/bEwYNNHmcK73toJ3x+SWGp9oE2c+APeGGfitg4oI7n018jkxcDuM4DvQ+P+pITwgTrPNdMT
umRYlqOdmHeeyfOJY2JpZ3gxjXRqVmtkaWw8GkwoqbaoZ+W8ruy1oSMiO6r8Z5a/eY+1jWv/x34m
lELPqGsfUBt12nc+C5ge4b/ODhMPgUXcRcauboxrMfhgxifQ+LrYyEKXi6opRbbPXgEAAP//AwAM
DMWoEAMAAA==
content: "{\n \"id\": \"chatcmpl-AcdBV2knOF2soWLszceiA08K8W8nE\",\n \"object\":
\"chat.completion\",\n \"created\": 1733770453,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Hello! How can I assist you today?\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 11,\n \"completion_tokens\":
9,\n \"total_tokens\": 20,\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 \"system_fingerprint\":
\"fp_bba3c8e70b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8e185b2c1b790303-GRU
- 8ef733d51801bada-ATL
Connection:
- keep-alive
Content-Encoding:
@@ -60,14 +61,14 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 12 Nov 2024 17:49:00 GMT
- Mon, 09 Dec 2024 18:54:13 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=l.QrRLcNZkML_KSfxjir6YCV35B8GNTitBTNh7cPGc4-1731433740-1.0.1.1-j1ejlmykyoI8yk6i6pQjtPoovGzfxI2f5vG6u0EqodQMjCvhbHfNyN_wmYkeT._BMvFi.zDQ8m_PqEHr8tSdEQ;
path=/; expires=Tue, 12-Nov-24 18:19:00 GMT; domain=.api.openai.com; HttpOnly;
- __cf_bm=_fEt57lre0.E_IZaebjaDAcrpBbzGhLWW6KtQ4FjLxo-1733770453-1.0.1.1-ndzEQCfExSp1asSdBXxS0fGYQnKVTivInc1MHN.ZjnmGmkAmEp0EPwiJlcAMvQaMCMZ7a_vKqAEMbz8ZbzTYYg;
path=/; expires=Mon, 09-Dec-24 19:24:13 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=jcCDyMK__Fd0V5DMeqt9yXdlKc7Hsw87a1K01pZu9l0-1731433740848-0.0.1.1-604800000;
- _cfuvid=2gTS3no9rova7t6URcfR30yzeZdKkL.9.lvsZXgmbVw-1733770453657-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
@@ -78,30 +79,29 @@ interactions:
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- user-tqfegqsiobpvvjmn0giaipdq
- crewai-iuxna1
openai-processing-ms:
- '322'
- '275'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
- '30000'
x-ratelimit-limit-tokens:
- '200000'
- '150000000'
x-ratelimit-remaining-requests:
- '9999'
- '29999'
x-ratelimit-remaining-tokens:
- '199978'
- '149999979'
x-ratelimit-reset-requests:
- 8.64s
- 2ms
x-ratelimit-reset-tokens:
- 6ms
- 0s
x-request-id:
- req_037288753767e763a51a04eae757ca84
status:
code: 200
message: OK
- req_82ef8940a3291813e6a347535ab6bf26
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Hello, world from another agent!"}],
"model": "gpt-4o-mini", "stream": false}'
@@ -117,20 +117,20 @@ interactions:
content-type:
- application/json
cookie:
- __cf_bm=l.QrRLcNZkML_KSfxjir6YCV35B8GNTitBTNh7cPGc4-1731433740-1.0.1.1-j1ejlmykyoI8yk6i6pQjtPoovGzfxI2f5vG6u0EqodQMjCvhbHfNyN_wmYkeT._BMvFi.zDQ8m_PqEHr8tSdEQ;
_cfuvid=jcCDyMK__Fd0V5DMeqt9yXdlKc7Hsw87a1K01pZu9l0-1731433740848-0.0.1.1-604800000
- __cf_bm=_fEt57lre0.E_IZaebjaDAcrpBbzGhLWW6KtQ4FjLxo-1733770453-1.0.1.1-ndzEQCfExSp1asSdBXxS0fGYQnKVTivInc1MHN.ZjnmGmkAmEp0EPwiJlcAMvQaMCMZ7a_vKqAEMbz8ZbzTYYg;
_cfuvid=2gTS3no9rova7t6URcfR30yzeZdKkL.9.lvsZXgmbVw-1733770453657-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- x64
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
@@ -140,25 +140,26 @@ interactions:
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.9
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA4xSy27bMBC86yu2PFuBZAt14UvRU5MA7aVAEKAIBJpcSUwoLkuu6jiB/z3QI5aM
tkAvPMzsDGZ2+ZoACKPFDoRqJKvW2/TLD3+z//oiD8dfL7d339zvW125x9zX90/3mVj1Cto/ouJ3
1ZWi1ltkQ26kVUDJ2Lvm201ebDbbIh+IljTaXlZ7TgtKW+NMus7WRZpt0/zTpG7IKIxiBz8TAIDX
4e1zOo3PYgfZ6h1pMUZZo9idhwBEINsjQsZoIkvHYjWTihyjG6Jfo7X0Ab4bhcAEipxDxXAw3IB0
xA0GkDU6voJrOoCSDm5gNIUjdcCk5fHz0jxg1UXZF3SdtRN+Oqe1VPtA+zjxZ7wyzsSmDCgjuT5Z
ZPJiYE8JwMOwle6iqPCBWs8l0xO63jAvRjsx32JBfpxIJpZ2xjfTJi/dSo0sjY2LrQolVYN6Vs4n
kJ02tCCSRec/w/zNe+xtXP0/9jOhFHpGXfqA2qjLwvNYwP6n/mvsvOMhsIjHyNiWlXE1Bh/M+E8q
X2Z7mel8XVS5SE7JGwAAAP//AwA/cK4yNQMAAA==
content: "{\n \"id\": \"chatcmpl-AcdBWMAembczwWDLdjIRYwtbMLONh\",\n \"object\":
\"chat.completion\",\n \"created\": 1733770454,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Hello! It\u2019s great to connect with
you. How can I assist you today?\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
14,\n \"completion_tokens\": 17,\n \"total_tokens\": 31,\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 \"system_fingerprint\":
\"fp_bba3c8e70b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8e185b31398a0303-GRU
- 8ef733d7bc41bada-ATL
Connection:
- keep-alive
Content-Encoding:
@@ -166,7 +167,7 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 12 Nov 2024 17:49:02 GMT
- Mon, 09 Dec 2024 18:54:14 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -178,28 +179,27 @@ interactions:
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- user-tqfegqsiobpvvjmn0giaipdq
- crewai-iuxna1
openai-processing-ms:
- '889'
- '659'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
- '30000'
x-ratelimit-limit-tokens:
- '200000'
- '150000000'
x-ratelimit-remaining-requests:
- '9998'
- '29999'
x-ratelimit-remaining-tokens:
- '199975'
- '149999974'
x-ratelimit-reset-requests:
- 16.489s
- 2ms
x-ratelimit-reset-tokens:
- 7ms
- 0s
x-request-id:
- req_bde3810b36a4859688e53d1df64bdd20
status:
code: 200
message: OK
- req_da24049df911504f5102825db6b4aea9
http_version: HTTP/1.1
status_code: 200
version: 1

9
tests/cli/authentication/test_auth_main.py
View File

@@ -2,6 +2,7 @@ import unittest
from unittest.mock import MagicMock, patch
import requests
from crewai.cli.authentication.main import AuthenticationCommand
@@ -47,7 +48,9 @@ class TestAuthenticationCommand(unittest.TestCase):
@patch("crewai.cli.authentication.main.requests.post")
@patch("crewai.cli.authentication.main.validate_token")
@patch("crewai.cli.authentication.main.console.print")
def test_poll_for_token_success(self, mock_print, mock_validate_token, mock_post, mock_tool):
def test_poll_for_token_success(
self, mock_print, mock_validate_token, mock_post, mock_tool
):
mock_response = MagicMock()
mock_response.status_code = 200
mock_response.json.return_value = {
@@ -62,7 +65,9 @@ class TestAuthenticationCommand(unittest.TestCase):
self.auth_command._poll_for_token({"device_code": "123456"})
mock_validate_token.assert_called_once_with("TOKEN")
mock_print.assert_called_once_with("\n[bold green]Welcome to CrewAI Enterprise![/bold green]\n")
mock_print.assert_called_once_with(
"\n[bold green]Welcome to CrewAI Enterprise![/bold green]\n"
)
@patch("crewai.cli.authentication.main.requests.post")
@patch("crewai.cli.authentication.main.console.print")

3
tests/cli/authentication/test_utils.py
View File

@@ -3,9 +3,10 @@ import unittest
from datetime import datetime, timedelta
from unittest.mock import MagicMock, patch
from crewai.cli.authentication.utils import TokenManager, validate_token
from cryptography.fernet import Fernet
from crewai.cli.authentication.utils import TokenManager, validate_token
class TestValidateToken(unittest.TestCase):
@patch("crewai.cli.authentication.utils.AsymmetricSignatureVerifier")

7
tests/cli/cli_test.py
View File

@@ -131,6 +131,13 @@ def test_reset_no_memory_flags(runner):
)
def test_version_flag(runner):
result = runner.invoke(version)
assert result.exit_code == 0
assert "crewai version:" in result.output
def test_version_command(runner):
result = runner.invoke(version)

34
tests/cli/config_test.py
View File

@@ -1,10 +1,12 @@
import unittest
import json
import tempfile
import shutil
import tempfile
import unittest
from pathlib import Path
from crewai.cli.config import Settings
class TestSettings(unittest.TestCase):
def setUp(self):
self.test_dir = Path(tempfile.mkdtemp())
@@ -20,8 +22,7 @@ class TestSettings(unittest.TestCase):
def test_initialization_with_data(self):
settings = Settings(
config_path=self.config_path,
tool_repository_username="user1"
config_path=self.config_path, tool_repository_username="user1"
)
self.assertEqual(settings.tool_repository_username, "user1")
self.assertIsNone(settings.tool_repository_password)
@@ -37,22 +38,23 @@ class TestSettings(unittest.TestCase):
def test_merge_file_and_input_data(self):
self.config_path.parent.mkdir(parents=True, exist_ok=True)
with self.config_path.open("w") as f:
json.dump({
"tool_repository_username": "file_user",
"tool_repository_password": "file_pass"
}, f)
json.dump(
{
"tool_repository_username": "file_user",
"tool_repository_password": "file_pass",
},
f,
)
settings = Settings(
config_path=self.config_path,
tool_repository_username="new_user"
config_path=self.config_path, tool_repository_username="new_user"
)
self.assertEqual(settings.tool_repository_username, "new_user")
self.assertEqual(settings.tool_repository_password, "file_pass")
def test_dump_new_settings(self):
settings = Settings(
config_path=self.config_path,
tool_repository_username="user1"
config_path=self.config_path, tool_repository_username="user1"
)
settings.dump()
@@ -67,8 +69,7 @@ class TestSettings(unittest.TestCase):
json.dump({"existing_setting": "value"}, f)
settings = Settings(
config_path=self.config_path,
tool_repository_username="user1"
config_path=self.config_path, tool_repository_username="user1"
)
settings.dump()
@@ -79,10 +80,7 @@ class TestSettings(unittest.TestCase):
self.assertEqual(saved_data["tool_repository_username"], "user1")
def test_none_values(self):
settings = Settings(
config_path=self.config_path,
tool_repository_username=None
)
settings = Settings(config_path=self.config_path, tool_repository_username=None)
settings.dump()
with self.config_path.open("r") as f:

15
tests/cli/deploy/test_deploy_main.py
View File

@@ -228,17 +228,18 @@ class TestDeployCommand(unittest.TestCase):
"builtins.open",
new_callable=unittest.mock.mock_open,
read_data="""
[project]
name = "test_project"
version = "0.1.0"
requires-python = ">=3.10,<=3.13"
dependencies = ["crewai"]
""",
[project]
name = "test_project"
version = "0.1.0"
requires-python = ">=3.10,<3.13"
dependencies = ["crewai"]
""",
)
def test_get_project_name_python_310(self, mock_open):
from crewai.cli.utils import get_project_name
project_name = get_project_name()
print("project_name", project_name)
self.assertEqual(project_name, "test_project")
@unittest.skipIf(sys.version_info < (3, 11), "Requires Python 3.11+")
@@ -249,7 +250,7 @@ class TestDeployCommand(unittest.TestCase):
[project]
name = "test_project"
version = "0.1.0"
requires-python = ">=3.10,<=3.13"
requires-python = ">=3.10,<3.13"
dependencies = ["crewai"]
""",
)

3
tests/cli/test_git.py
View File

@@ -1,6 +1,7 @@
from crewai.cli.git import Repository
import pytest
from crewai.cli.git import Repository
@pytest.fixture()
def repository(fp):

1
tests/cli/test_plus_api.py
View File

@@ -1,6 +1,7 @@
import os
import unittest
from unittest.mock import MagicMock, patch
from crewai.cli.plus_api import PlusAPI

6
tests/cli/test_utils.py
View File

@@ -1,7 +1,9 @@
import pytest
import os
import shutil
import tempfile
import os
import pytest
from crewai.cli import utils

2
tests/cli/tools/test_main.py
View File

@@ -85,7 +85,7 @@ def test_install_success(mock_get, mock_subprocess_run):
env=unittest.mock.ANY
)
assert "Succesfully installed sample-tool" in output
assert "Successfully installed sample-tool" in output
@patch("crewai.cli.plus_api.PlusAPI.get_tool")

24
tests/crew_test.py
View File

@@ -1285,7 +1285,7 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
prompt_tokens=1562,
completion_tokens=111,
successful_requests=3,
cached_prompt_tokens=0
cached_prompt_tokens=0,
)
@@ -1785,16 +1785,18 @@ def test_crew_train_success(
crew_training_handler.assert_any_call("trained_agents_data.pkl")
crew_training_handler().load.assert_called()
crew_training_handler().save_trained_data.assert_has_calls([
mock.call(
agent_id="Researcher",
trained_data=task_evaluator().evaluate_training_data().model_dump(),
),
mock.call(
agent_id="Senior Writer",
trained_data=task_evaluator().evaluate_training_data().model_dump(),
)
])
crew_training_handler().save_trained_data.assert_has_calls(
[
mock.call(
agent_id="Researcher",
trained_data=task_evaluator().evaluate_training_data().model_dump(),
),
mock.call(
agent_id="Senior Writer",
trained_data=task_evaluator().evaluate_training_data().model_dump(),
),
]
)
def test_crew_train_error():

1
tests/flow_test.py
View File

@@ -3,6 +3,7 @@
import asyncio
import pytest
from crewai.flow.flow import Flow, and_, listen, or_, router, start

4
tests/knowledge/knowledge_test.py
View File

@@ -3,6 +3,8 @@
from pathlib import Path
from unittest.mock import patch
import pytest
from crewai.knowledge.source.csv_knowledge_source import CSVKnowledgeSource
from crewai.knowledge.source.excel_knowledge_source import ExcelKnowledgeSource
from crewai.knowledge.source.json_knowledge_source import JSONKnowledgeSource
@@ -10,8 +12,6 @@ from crewai.knowledge.source.pdf_knowledge_source import PDFKnowledgeSource
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
from crewai.knowledge.source.text_file_knowledge_source import TextFileKnowledgeSource
import pytest
@pytest.fixture(autouse=True)
def mock_vector_db():

4
tests/memory/short_term_memory_test.py
View File

@@ -1,5 +1,7 @@
import pytest
from unittest.mock import patch
import pytest
from crewai.agent import Agent
from crewai.crew import Crew
from crewai.memory.short_term.short_term_memory import ShortTermMemory

7
tests/task_test.py
View File

@@ -6,12 +6,13 @@ import os
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():
@@ -685,7 +686,7 @@ def test_increment_tool_errors():
with patch.object(Task, "increment_tools_errors") as increment_tools_errors:
increment_tools_errors.return_value = None
crew.kickoff()
assert len(increment_tools_errors.mock_calls) == 12
assert len(increment_tools_errors.mock_calls) > 0
def test_task_definition_based_on_dict():

16
tests/tools/test_base_tool.py
View File

@@ -6,14 +6,14 @@ from crewai.tools import BaseTool, tool
def test_creating_a_tool_using_annotation():
@tool("Name of my tool")
def my_tool(question: str) -> str:
"""Clear description for what this tool is useful for, you agent will need this information to use it."""
"""Clear description for what this tool is useful for, your agent will need this information to use it."""
return question
# Assert all the right attributes were defined
assert my_tool.name == "Name of my tool"
assert (
my_tool.description
== "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, you agent will need this information to use it."
== "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
)
assert my_tool.args_schema.schema()["properties"] == {
"question": {"title": "Question", "type": "string"}
@@ -27,7 +27,7 @@ def test_creating_a_tool_using_annotation():
assert (
converted_tool.description
== "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, you agent will need this information to use it."
== "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
)
assert converted_tool.args_schema.schema()["properties"] == {
"question": {"title": "Question", "type": "string"}
@@ -41,7 +41,7 @@ def test_creating_a_tool_using_annotation():
def test_creating_a_tool_using_baseclass():
class MyCustomTool(BaseTool):
name: str = "Name of my tool"
description: str = "Clear description for what this tool is useful for, you agent will need this information to use it."
description: str = "Clear description for what this tool is useful for, your agent will need this information to use it."
def _run(self, question: str) -> str:
return question
@@ -52,7 +52,7 @@ def test_creating_a_tool_using_baseclass():
assert (
my_tool.description
== "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, you agent will need this information to use it."
== "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
)
assert my_tool.args_schema.schema()["properties"] == {
"question": {"title": "Question", "type": "string"}
@@ -64,7 +64,7 @@ def test_creating_a_tool_using_baseclass():
assert (
converted_tool.description
== "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, you agent will need this information to use it."
== "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
)
assert converted_tool.args_schema.schema()["properties"] == {
"question": {"title": "Question", "type": "string"}
@@ -78,7 +78,7 @@ def test_creating_a_tool_using_baseclass():
def test_setting_cache_function():
class MyCustomTool(BaseTool):
name: str = "Name of my tool"
description: str = "Clear description for what this tool is useful for, you agent will need this information to use it."
description: str = "Clear description for what this tool is useful for, your agent will need this information to use it."
cache_function: Callable = lambda: False
def _run(self, question: str) -> str:
@@ -92,7 +92,7 @@ def test_setting_cache_function():
def test_default_cache_function_is_true():
class MyCustomTool(BaseTool):
name: str = "Name of my tool"
description: str = "Clear description for what this tool is useful for, you agent will need this information to use it."
description: str = "Clear description for what this tool is useful for, your agent will need this information to use it."
def _run(self, question: str) -> str:
return question

2
tests/tools/test_tool_usage.py
View File

@@ -6,8 +6,8 @@ import pytest
from pydantic import BaseModel, Field
from crewai import Agent, Task
from crewai.tools.tool_usage import ToolUsage
from crewai.tools import BaseTool
from crewai.tools.tool_usage import ToolUsage
class RandomNumberToolInput(BaseModel):

1
tests/utilities/evaluators/test_crew_evaluator_handler.py
View File

@@ -1,6 +1,7 @@
from unittest import mock
import pytest
from crewai.agent import Agent
from crewai.crew import Crew
from crewai.task import Task

2
tests/utilities/prompts.json
View File

@@ -26,7 +26,7 @@
},
"errors": {
"force_final_answer": "Lorem ipsum dolor sit amet",
"agent_tool_unexsiting_coworker": "Lorem ipsum dolor sit amet",
"agent_tool_unexisting_coworker": "Lorem ipsum dolor sit amet",
"task_repeated_usage": "Lorem ipsum dolor sit amet",
"tool_usage_error": "Lorem ipsum dolor sit amet",
"tool_arguments_error": "Lorem ipsum dolor sit amet",