mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-05-08 02:29:00 +00:00
Merge branch 'main' into devin/1737479945-fix-conditional-index
This commit is contained in:
Brandon Hancock (bhancock_ai)
@@ -10,13 +10,14 @@ 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.base_knowledge_source import BaseKnowledgeSource
|
||||
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 Printer, RPMController
|
||||
from crewai.utilities import RPMController
|
||||
from crewai.utilities.events import Emitter
|
||||
|
||||
|
||||
@@ -1602,6 +1603,45 @@ def test_agent_with_knowledge_sources():
|
||||
assert "red" in result.raw.lower()
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_agent_with_knowledge_sources_works_with_copy():
|
||||
content = "Brandon's favorite color is red and he likes Mexican food."
|
||||
string_source = StringKnowledgeSource(content=content)
|
||||
|
||||
with patch(
|
||||
"crewai.knowledge.source.base_knowledge_source.BaseKnowledgeSource",
|
||||
autospec=True,
|
||||
) as MockKnowledgeSource:
|
||||
mock_knowledge_source_instance = MockKnowledgeSource.return_value
|
||||
mock_knowledge_source_instance.__class__ = BaseKnowledgeSource
|
||||
mock_knowledge_source_instance.sources = [string_source]
|
||||
|
||||
agent = Agent(
|
||||
role="Information Agent",
|
||||
goal="Provide information based on knowledge sources",
|
||||
backstory="You have access to specific knowledge sources.",
|
||||
llm=LLM(model="gpt-4o-mini"),
|
||||
knowledge_sources=[string_source],
|
||||
)
|
||||
|
||||
with patch(
|
||||
"crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"
|
||||
) as MockKnowledgeStorage:
|
||||
mock_knowledge_storage = MockKnowledgeStorage.return_value
|
||||
agent.knowledge_storage = mock_knowledge_storage
|
||||
|
||||
agent_copy = agent.copy()
|
||||
|
||||
assert agent_copy.role == agent.role
|
||||
assert agent_copy.goal == agent.goal
|
||||
assert agent_copy.backstory == agent.backstory
|
||||
assert agent_copy.knowledge_sources is not None
|
||||
assert len(agent_copy.knowledge_sources) == 1
|
||||
assert isinstance(agent_copy.knowledge_sources[0], StringKnowledgeSource)
|
||||
assert agent_copy.knowledge_sources[0].content == content
|
||||
assert isinstance(agent_copy.llm, LLM)
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_litellm_auth_error_handling():
|
||||
"""Test that LiteLLM authentication errors are handled correctly and not retried."""
|
||||
@@ -1623,7 +1663,7 @@ def test_litellm_auth_error_handling():
|
||||
agent=agent,
|
||||
)
|
||||
|
||||
# Mock the LLM call to raise LiteLLMAuthenticationError
|
||||
# Mock the LLM call to raise AuthenticationError
|
||||
with (
|
||||
patch.object(LLM, "call") as mock_llm_call,
|
||||
pytest.raises(LiteLLMAuthenticationError, match="Invalid API key"),
|
||||
@@ -1638,13 +1678,13 @@ def test_litellm_auth_error_handling():
|
||||
|
||||
|
||||
def test_crew_agent_executor_litellm_auth_error():
|
||||
"""Test that CrewAgentExecutor properly identifies and handles LiteLLM authentication errors."""
|
||||
from litellm import AuthenticationError as LiteLLMAuthenticationError
|
||||
"""Test that CrewAgentExecutor handles LiteLLM authentication errors by raising them."""
|
||||
from litellm.exceptions import AuthenticationError
|
||||
|
||||
from crewai.agents.tools_handler import ToolsHandler
|
||||
from crewai.utilities import Printer
|
||||
|
||||
# Create an agent and executor with max_retry_limit=0
|
||||
# Create an agent and executor
|
||||
agent = Agent(
|
||||
role="test role",
|
||||
goal="test goal",
|
||||
@@ -1672,13 +1712,13 @@ def test_crew_agent_executor_litellm_auth_error():
|
||||
tools_handler=ToolsHandler(),
|
||||
)
|
||||
|
||||
# Mock the LLM call to raise LiteLLMAuthenticationError
|
||||
# Mock the LLM call to raise AuthenticationError
|
||||
with (
|
||||
patch.object(LLM, "call") as mock_llm_call,
|
||||
patch.object(Printer, "print") as mock_printer,
|
||||
pytest.raises(LiteLLMAuthenticationError, match="Invalid API key"),
|
||||
pytest.raises(AuthenticationError) as exc_info,
|
||||
):
|
||||
mock_llm_call.side_effect = LiteLLMAuthenticationError(
|
||||
mock_llm_call.side_effect = AuthenticationError(
|
||||
message="Invalid API key", llm_provider="openai", model="gpt-4"
|
||||
)
|
||||
executor.invoke(
|
||||
@@ -1689,14 +1729,53 @@ def test_crew_agent_executor_litellm_auth_error():
|
||||
}
|
||||
)
|
||||
|
||||
# Verify error handling
|
||||
# Verify error handling messages
|
||||
error_message = f"Error during LLM call: {str(mock_llm_call.side_effect)}"
|
||||
mock_printer.assert_any_call(
|
||||
content="Authentication error with litellm occurred. Please check your API key and configuration.",
|
||||
color="red",
|
||||
)
|
||||
mock_printer.assert_any_call(
|
||||
content="Error details: litellm.AuthenticationError: Invalid API key",
|
||||
content=error_message,
|
||||
color="red",
|
||||
)
|
||||
|
||||
# Verify the call was only made once (no retries)
|
||||
mock_llm_call.assert_called_once()
|
||||
|
||||
# Assert that the exception was raised and has the expected attributes
|
||||
assert exc_info.type is AuthenticationError
|
||||
assert "Invalid API key".lower() in exc_info.value.message.lower()
|
||||
assert exc_info.value.llm_provider == "openai"
|
||||
assert exc_info.value.model == "gpt-4"
|
||||
|
||||
|
||||
def test_litellm_anthropic_error_handling():
|
||||
"""Test that AnthropicError from LiteLLM is handled correctly and not retried."""
|
||||
from litellm.llms.anthropic.common_utils import AnthropicError
|
||||
|
||||
# Create an agent with a mocked LLM that uses an Anthropic model
|
||||
agent = Agent(
|
||||
role="test role",
|
||||
goal="test goal",
|
||||
backstory="test backstory",
|
||||
llm=LLM(model="claude-3.5-sonnet-20240620"),
|
||||
max_retry_limit=0,
|
||||
)
|
||||
|
||||
# Create a task
|
||||
task = Task(
|
||||
description="Test task",
|
||||
expected_output="Test output",
|
||||
agent=agent,
|
||||
)
|
||||
|
||||
# Mock the LLM call to raise AnthropicError
|
||||
with (
|
||||
patch.object(LLM, "call") as mock_llm_call,
|
||||
pytest.raises(AnthropicError, match="Test Anthropic error"),
|
||||
):
|
||||
mock_llm_call.side_effect = AnthropicError(
|
||||
status_code=500,
|
||||
message="Test Anthropic error",
|
||||
)
|
||||
agent.execute_task(task)
|
||||
|
||||
# Verify the LLM call was only made once (no retries)
|
||||
mock_llm_call.assert_called_once()
|
||||
|
||||
@@ -1,117 +0,0 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
|
||||
Futel Football Club info\nYour personal goal is: Answer questions about Futel\nTo
|
||||
give my best complete final answer to the task respond using the exact following
|
||||
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
|
||||
answer must be the great and the most complete as possible, it must be outcome
|
||||
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
|
||||
"content": "\nCurrent Task: Test task\n\nThis is the expect criteria for your
|
||||
final answer: Your best answer to your coworker asking you this, accounting
|
||||
for the context shared.\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", "stop": ["\nObservation:"], "stream": false}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '939'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
|
||||
_cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
|
||||
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-AnuRlxiTxduAVoXHHY58Fvfbll5IS\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1736458417,\n \"model\": \"gpt-4o-2024-08-06\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
|
||||
Answer: This is a test task, and the context or question from the coworker is
|
||||
not specified. Therefore, my best effort would be to affirm my readiness to
|
||||
answer accurately and in detail any question about Futel Football Club based
|
||||
on the context described. If provided with specific information or questions,
|
||||
I will ensure to respond comprehensively as required by my job directives.\",\n
|
||||
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
|
||||
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 177,\n \"completion_tokens\":
|
||||
82,\n \"total_tokens\": 259,\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_703d4ff298\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8ff78bf7bd6cc002-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Thu, 09 Jan 2025 21:33:40 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:
|
||||
- '2263'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999786'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_7c1a31da73cd103e9f410f908e59187f
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
@@ -1,119 +0,0 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
|
||||
Futel Football Club info\nYour personal goal is: Answer questions about Futel\nTo
|
||||
give my best complete final answer to the task respond using the exact following
|
||||
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
|
||||
answer must be the great and the most complete as possible, it must be outcome
|
||||
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
|
||||
"content": "\nCurrent Task: Test task\n\nThis is the expect criteria for your
|
||||
final answer: Your best answer to your coworker asking you this, accounting
|
||||
for the context shared.\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", "stop": ["\nObservation:"], "stream": false}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '939'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
|
||||
_cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
|
||||
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-AnuRrFJZGKw8cIEshvuW1PKwFZFKs\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1736458423,\n \"model\": \"gpt-4o-2024-08-06\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
|
||||
Answer: Although you mentioned this being a \\\"Test task\\\" and haven't provided
|
||||
a specific question regarding Futel Football Club, your request appears to involve
|
||||
ensuring accuracy and detail in responses. For a proper answer about Futel,
|
||||
I'd be ready to provide details about the club's history, management, players,
|
||||
match schedules, and recent performance statistics. Remember to ask specific
|
||||
questions to receive a targeted response. If this were a real context where
|
||||
information was shared, I would respond precisely to what's been asked regarding
|
||||
Futel Football Club.\",\n \"refusal\": null\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
177,\n \"completion_tokens\": 113,\n \"total_tokens\": 290,\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_703d4ff298\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8ff78c1d0ecdc002-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Thu, 09 Jan 2025 21:33:47 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:
|
||||
- '3097'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999786'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_179e1d56e2b17303e40480baffbc7b08
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
@@ -1,114 +0,0 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
|
||||
Futel Football Club info\nYour personal goal is: Answer questions about Futel\nTo
|
||||
give my best complete final answer to the task respond using the exact following
|
||||
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
|
||||
answer must be the great and the most complete as possible, it must be outcome
|
||||
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
|
||||
"content": "\nCurrent Task: Test task\n\nThis is the expect criteria for your
|
||||
final answer: Your best answer to your coworker asking you this, accounting
|
||||
for the context shared.\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", "stop": ["\nObservation:"], "stream": false}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '939'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
|
||||
_cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
|
||||
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-AnuRqgg7eiHnDi2DOqdk99fiqOboz\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1736458422,\n \"model\": \"gpt-4o-2024-08-06\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
|
||||
Answer: Your best answer to your coworker asking you this, accounting for the
|
||||
context shared. You MUST return the actual complete content as the final answer,
|
||||
not a summary.\",\n \"refusal\": null\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
177,\n \"completion_tokens\": 44,\n \"total_tokens\": 221,\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_703d4ff298\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8ff78c164ad2c002-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Thu, 09 Jan 2025 21:33:43 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:
|
||||
- '899'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999786'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_9f5226208edb90a27987aaf7e0ca03d3
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
@@ -1,119 +0,0 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
|
||||
Futel Football Club info\nYour personal goal is: Answer questions about Futel\nTo
|
||||
give my best complete final answer to the task respond using the exact following
|
||||
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
|
||||
answer must be the great and the most complete as possible, it must be outcome
|
||||
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
|
||||
"content": "\nCurrent Task: Test task\n\nThis is the expect criteria for your
|
||||
final answer: Your best answer to your coworker asking you this, accounting
|
||||
for the context shared.\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", "stop": ["\nObservation:"], "stream": false}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '939'
|
||||
content-type:
|
||||
- application/json
|
||||
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-AnuRjmwH5mrykLxQhFwTqqTiDtuTf\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1736458415,\n \"model\": \"gpt-4o-2024-08-06\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
|
||||
Answer: As this is a test task, please note that Futel Football Club is fictional
|
||||
and any specific details about it would not be available. However, if you have
|
||||
specific questions or need information about a particular aspect of Futel or
|
||||
any general football club inquiry, feel free to ask, and I'll do my best to
|
||||
assist you with your query!\",\n \"refusal\": null\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
177,\n \"completion_tokens\": 79,\n \"total_tokens\": 256,\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_703d4ff298\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8ff78be5eebfc002-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Thu, 09 Jan 2025 21:33:37 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
|
||||
path=/; expires=Thu, 09-Jan-25 22:03:37 GMT; domain=.api.openai.com; HttpOnly;
|
||||
Secure; SameSite=None
|
||||
- _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000;
|
||||
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:
|
||||
- '2730'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999786'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_014478ba748f860d10ac250ca0ba824a
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
@@ -1,119 +0,0 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
|
||||
Futel Football Club info\nYour personal goal is: Answer questions about Futel\nTo
|
||||
give my best complete final answer to the task respond using the exact following
|
||||
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
|
||||
answer must be the great and the most complete as possible, it must be outcome
|
||||
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
|
||||
"content": "\nCurrent Task: Test task\n\nThis is the expect criteria for your
|
||||
final answer: Your best answer to your coworker asking you this, accounting
|
||||
for the context shared.\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", "stop": ["\nObservation:"], "stream": false}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '939'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
|
||||
_cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
|
||||
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-AnuRofLgmzWcDya5LILqYwIJYgFoq\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1736458420,\n \"model\": \"gpt-4o-2024-08-06\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
|
||||
Answer: As an official Futel Football Club infopoint, my responsibility is to
|
||||
provide detailed and accurate information about the club. This includes answering
|
||||
questions regarding team statistics, player performances, upcoming fixtures,
|
||||
ticketing and fan zone details, club history, and community initiatives. Our
|
||||
focus is to ensure that fans and stakeholders have access to the latest and
|
||||
most precise information about the club's on and off-pitch activities. If there's
|
||||
anything specific you need to know, just let me know, and I'll be more than
|
||||
happy to assist!\",\n \"refusal\": null\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
177,\n \"completion_tokens\": 115,\n \"total_tokens\": 292,\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_703d4ff298\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8ff78c066f37c002-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Thu, 09 Jan 2025 21:33:42 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:
|
||||
- '2459'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999786'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_a146dd27f040f39a576750970cca0f52
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -14,6 +14,7 @@ from crewai.agent import Agent
|
||||
from crewai.agents.cache import CacheHandler
|
||||
from crewai.crew import Crew
|
||||
from crewai.crews.crew_output import CrewOutput
|
||||
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
|
||||
from crewai.memory.contextual.contextual_memory import ContextualMemory
|
||||
from crewai.process import Process
|
||||
from crewai.project import crew
|
||||
@@ -588,12 +589,12 @@ def test_crew_with_delegating_agents_should_not_override_task_tools():
|
||||
_, kwargs = mock_execute_sync.call_args
|
||||
tools = kwargs["tools"]
|
||||
|
||||
assert any(
|
||||
isinstance(tool, TestTool) for tool in tools
|
||||
), "TestTool should be present"
|
||||
assert any(
|
||||
"delegate" in tool.name.lower() for tool in tools
|
||||
), "Delegation tool should be present"
|
||||
assert any(isinstance(tool, TestTool) for tool in tools), (
|
||||
"TestTool should be present"
|
||||
)
|
||||
assert any("delegate" in tool.name.lower() for tool in tools), (
|
||||
"Delegation tool should be present"
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
@@ -652,12 +653,12 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
|
||||
_, kwargs = mock_execute_sync.call_args
|
||||
tools = kwargs["tools"]
|
||||
|
||||
assert any(
|
||||
isinstance(tool, TestTool) for tool in new_ceo.tools
|
||||
), "TestTool should be present"
|
||||
assert any(
|
||||
"delegate" in tool.name.lower() for tool in tools
|
||||
), "Delegation tool should be present"
|
||||
assert any(isinstance(tool, TestTool) for tool in new_ceo.tools), (
|
||||
"TestTool should be present"
|
||||
)
|
||||
assert any("delegate" in tool.name.lower() for tool in tools), (
|
||||
"Delegation tool should be present"
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
@@ -781,17 +782,17 @@ def test_task_tools_override_agent_tools_with_allow_delegation():
|
||||
used_tools = kwargs["tools"]
|
||||
|
||||
# Confirm AnotherTestTool is present but TestTool is not
|
||||
assert any(
|
||||
isinstance(tool, AnotherTestTool) for tool in used_tools
|
||||
), "AnotherTestTool should be present"
|
||||
assert not any(
|
||||
isinstance(tool, TestTool) for tool in used_tools
|
||||
), "TestTool should not be present among used tools"
|
||||
assert any(isinstance(tool, AnotherTestTool) for tool in used_tools), (
|
||||
"AnotherTestTool should be present"
|
||||
)
|
||||
assert not any(isinstance(tool, TestTool) for tool in used_tools), (
|
||||
"TestTool should not be present among used tools"
|
||||
)
|
||||
|
||||
# Confirm delegation tool(s) are present
|
||||
assert any(
|
||||
"delegate" in tool.name.lower() for tool in used_tools
|
||||
), "Delegation tool should be present"
|
||||
assert any("delegate" in tool.name.lower() for tool in used_tools), (
|
||||
"Delegation tool should be present"
|
||||
)
|
||||
|
||||
# Finally, make sure the agent's original tools remain unchanged
|
||||
assert len(researcher_with_delegation.tools) == 1
|
||||
@@ -1499,7 +1500,6 @@ def test_dont_set_agents_step_callback_if_already_set():
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_crew_function_calling_llm():
|
||||
|
||||
from crewai import LLM
|
||||
from crewai.tools import tool
|
||||
|
||||
@@ -1593,9 +1593,9 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
|
||||
|
||||
# Verify that exactly one tool was used and it was a CodeInterpreterTool
|
||||
assert len(used_tools) == 1, "Should have exactly one tool"
|
||||
assert isinstance(
|
||||
used_tools[0], CodeInterpreterTool
|
||||
), "Tool should be CodeInterpreterTool"
|
||||
assert isinstance(used_tools[0], CodeInterpreterTool), (
|
||||
"Tool should be CodeInterpreterTool"
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
@@ -3329,9 +3329,9 @@ def test_fetch_inputs():
|
||||
expected_placeholders = {"role_detail", "topic", "field"}
|
||||
actual_placeholders = crew.fetch_inputs()
|
||||
|
||||
assert (
|
||||
actual_placeholders == expected_placeholders
|
||||
), f"Expected {expected_placeholders}, but got {actual_placeholders}"
|
||||
assert actual_placeholders == expected_placeholders, (
|
||||
f"Expected {expected_placeholders}, but got {actual_placeholders}"
|
||||
)
|
||||
|
||||
|
||||
def test_task_tools_preserve_code_execution_tools():
|
||||
@@ -3404,20 +3404,20 @@ def test_task_tools_preserve_code_execution_tools():
|
||||
used_tools = kwargs["tools"]
|
||||
|
||||
# Verify all expected tools are present
|
||||
assert any(
|
||||
isinstance(tool, TestTool) for tool in used_tools
|
||||
), "Task's TestTool should be present"
|
||||
assert any(
|
||||
isinstance(tool, CodeInterpreterTool) for tool in used_tools
|
||||
), "CodeInterpreterTool should be present"
|
||||
assert any(
|
||||
"delegate" in tool.name.lower() for tool in used_tools
|
||||
), "Delegation tool should be present"
|
||||
assert any(isinstance(tool, TestTool) for tool in used_tools), (
|
||||
"Task's TestTool should be present"
|
||||
)
|
||||
assert any(isinstance(tool, CodeInterpreterTool) for tool in used_tools), (
|
||||
"CodeInterpreterTool should be present"
|
||||
)
|
||||
assert any("delegate" in tool.name.lower() for tool in used_tools), (
|
||||
"Delegation tool should be present"
|
||||
)
|
||||
|
||||
# Verify the total number of tools (TestTool + CodeInterpreter + 2 delegation tools)
|
||||
assert (
|
||||
len(used_tools) == 4
|
||||
), "Should have TestTool, CodeInterpreter, and 2 delegation tools"
|
||||
assert len(used_tools) == 4, (
|
||||
"Should have TestTool, CodeInterpreter, and 2 delegation tools"
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
@@ -3461,9 +3461,9 @@ def test_multimodal_flag_adds_multimodal_tools():
|
||||
used_tools = kwargs["tools"]
|
||||
|
||||
# Check that the multimodal tool was added
|
||||
assert any(
|
||||
isinstance(tool, AddImageTool) for tool in used_tools
|
||||
), "AddImageTool should be present when agent is multimodal"
|
||||
assert any(isinstance(tool, AddImageTool) for tool in used_tools), (
|
||||
"AddImageTool should be present when agent is multimodal"
|
||||
)
|
||||
|
||||
# Verify we have exactly one tool (just the AddImageTool)
|
||||
assert len(used_tools) == 1, "Should only have the AddImageTool"
|
||||
@@ -3689,9 +3689,9 @@ def test_crew_guardrail_feedback_in_context():
|
||||
assert len(execution_contexts) > 1, "Task should have been executed multiple times"
|
||||
|
||||
# Verify that the second execution included the guardrail feedback
|
||||
assert (
|
||||
"Output must contain the keyword 'IMPORTANT'" in execution_contexts[1]
|
||||
), "Guardrail feedback should be included in retry context"
|
||||
assert "Output must contain the keyword 'IMPORTANT'" in execution_contexts[1], (
|
||||
"Guardrail feedback should be included in retry context"
|
||||
)
|
||||
|
||||
# Verify final output meets guardrail requirements
|
||||
assert "IMPORTANT" in result.raw, "Final output should contain required keyword"
|
||||
@@ -3716,7 +3716,6 @@ def test_before_kickoff_callback():
|
||||
|
||||
@before_kickoff
|
||||
def modify_inputs(self, inputs):
|
||||
|
||||
self.inputs_modified = True
|
||||
inputs["modified"] = True
|
||||
return inputs
|
||||
@@ -3818,3 +3817,21 @@ def test_before_kickoff_without_inputs():
|
||||
# Verify that the inputs were initialized and modified inside the before_kickoff method
|
||||
assert test_crew_instance.received_inputs is not None
|
||||
assert test_crew_instance.received_inputs.get("modified") is True
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_crew_with_knowledge_sources_works_with_copy():
|
||||
content = "Brandon's favorite color is red and he likes Mexican food."
|
||||
string_source = StringKnowledgeSource(content=content)
|
||||
|
||||
crew = Crew(
|
||||
agents=[researcher, writer],
|
||||
tasks=[Task(description="test", expected_output="test", agent=researcher)],
|
||||
knowledge_sources=[string_source],
|
||||
)
|
||||
|
||||
crew_copy = crew.copy()
|
||||
|
||||
assert crew_copy.knowledge_sources == crew.knowledge_sources
|
||||
assert len(crew_copy.agents) == len(crew.agents)
|
||||
assert len(crew_copy.tasks) == len(crew.tasks)
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
from time import sleep
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
import pytest
|
||||
|
||||
@@ -154,3 +155,50 @@ def test_llm_call_with_tool_and_message_list():
|
||||
|
||||
assert isinstance(result, int)
|
||||
assert result == 25
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_llm_passes_additional_params():
|
||||
llm = LLM(
|
||||
model="gpt-4o-mini",
|
||||
vertex_credentials="test_credentials",
|
||||
vertex_project="test_project",
|
||||
)
|
||||
|
||||
messages = [{"role": "user", "content": "Hello, world!"}]
|
||||
|
||||
with patch("litellm.completion") as mocked_completion:
|
||||
# Create mocks for response structure
|
||||
mock_message = MagicMock()
|
||||
mock_message.content = "Test response"
|
||||
mock_choice = MagicMock()
|
||||
mock_choice.message = mock_message
|
||||
mock_response = MagicMock()
|
||||
mock_response.choices = [mock_choice]
|
||||
mock_response.usage = {
|
||||
"prompt_tokens": 5,
|
||||
"completion_tokens": 5,
|
||||
"total_tokens": 10,
|
||||
}
|
||||
|
||||
# Set up the mocked completion to return the mock response
|
||||
mocked_completion.return_value = mock_response
|
||||
|
||||
result = llm.call(messages)
|
||||
|
||||
# Assert that litellm.completion was called once
|
||||
mocked_completion.assert_called_once()
|
||||
|
||||
# Retrieve the actual arguments with which litellm.completion was called
|
||||
_, kwargs = mocked_completion.call_args
|
||||
|
||||
# Check that the additional_params were passed to litellm.completion
|
||||
assert kwargs["vertex_credentials"] == "test_credentials"
|
||||
assert kwargs["vertex_project"] == "test_project"
|
||||
|
||||
# Also verify that other expected parameters are present
|
||||
assert kwargs["model"] == "gpt-4o-mini"
|
||||
assert kwargs["messages"] == messages
|
||||
|
||||
# Check the result from llm.call
|
||||
assert result == "Test response"
|
||||
|
||||
@@ -779,6 +779,43 @@ def test_interpolate_only():
|
||||
assert result == no_placeholders
|
||||
|
||||
|
||||
def test_interpolate_only_with_dict_inside_expected_output():
|
||||
"""Test the interpolate_only method for various scenarios including JSON structure preservation."""
|
||||
task = Task(
|
||||
description="Unused in this test",
|
||||
expected_output="Unused in this test: {questions}",
|
||||
)
|
||||
|
||||
json_string = '{"questions": {"main_question": "What is the user\'s name?", "secondary_question": "What is the user\'s age?"}}'
|
||||
result = task.interpolate_only(
|
||||
input_string=json_string,
|
||||
inputs={
|
||||
"questions": {
|
||||
"main_question": "What is the user's name?",
|
||||
"secondary_question": "What is the user's age?",
|
||||
}
|
||||
},
|
||||
)
|
||||
assert '"main_question": "What is the user\'s name?"' in result
|
||||
assert '"secondary_question": "What is the user\'s age?"' in result
|
||||
assert result == json_string
|
||||
|
||||
normal_string = "Hello {name}, welcome to {place}!"
|
||||
result = task.interpolate_only(
|
||||
input_string=normal_string, inputs={"name": "John", "place": "CrewAI"}
|
||||
)
|
||||
assert result == "Hello John, welcome to CrewAI!"
|
||||
|
||||
result = task.interpolate_only(input_string="", inputs={"unused": "value"})
|
||||
assert result == ""
|
||||
|
||||
no_placeholders = "Hello, this is a test"
|
||||
result = task.interpolate_only(
|
||||
input_string=no_placeholders, inputs={"unused": "value"}
|
||||
)
|
||||
assert result == no_placeholders
|
||||
|
||||
|
||||
def test_task_output_str_with_pydantic():
|
||||
from crewai.tasks.output_format import OutputFormat
|
||||
|
||||
@@ -966,3 +1003,283 @@ def test_task_execution_times():
|
||||
assert task.start_time is not None
|
||||
assert task.end_time is not None
|
||||
assert task.execution_duration == (task.end_time - task.start_time).total_seconds()
|
||||
|
||||
|
||||
def test_interpolate_with_list_of_strings():
|
||||
task = Task(
|
||||
description="Test list interpolation",
|
||||
expected_output="List: {items}",
|
||||
)
|
||||
|
||||
# Test simple list of strings
|
||||
input_str = "Available items: {items}"
|
||||
inputs = {"items": ["apple", "banana", "cherry"]}
|
||||
result = task.interpolate_only(input_str, inputs)
|
||||
assert result == f"Available items: {inputs['items']}"
|
||||
|
||||
# Test empty list
|
||||
empty_list_input = {"items": []}
|
||||
result = task.interpolate_only(input_str, empty_list_input)
|
||||
assert result == "Available items: []"
|
||||
|
||||
|
||||
def test_interpolate_with_list_of_dicts():
|
||||
task = Task(
|
||||
description="Test list of dicts interpolation",
|
||||
expected_output="People: {people}",
|
||||
)
|
||||
|
||||
input_data = {
|
||||
"people": [
|
||||
{"name": "Alice", "age": 30, "skills": ["Python", "AI"]},
|
||||
{"name": "Bob", "age": 25, "skills": ["Java", "Cloud"]},
|
||||
]
|
||||
}
|
||||
result = task.interpolate_only("{people}", input_data)
|
||||
|
||||
parsed_result = eval(result)
|
||||
assert isinstance(parsed_result, list)
|
||||
assert len(parsed_result) == 2
|
||||
assert parsed_result[0]["name"] == "Alice"
|
||||
assert parsed_result[0]["age"] == 30
|
||||
assert parsed_result[0]["skills"] == ["Python", "AI"]
|
||||
assert parsed_result[1]["name"] == "Bob"
|
||||
assert parsed_result[1]["age"] == 25
|
||||
assert parsed_result[1]["skills"] == ["Java", "Cloud"]
|
||||
|
||||
|
||||
def test_interpolate_with_nested_structures():
|
||||
task = Task(
|
||||
description="Test nested structures",
|
||||
expected_output="Company: {company}",
|
||||
)
|
||||
|
||||
input_data = {
|
||||
"company": {
|
||||
"name": "TechCorp",
|
||||
"departments": [
|
||||
{
|
||||
"name": "Engineering",
|
||||
"employees": 50,
|
||||
"tools": ["Git", "Docker", "Kubernetes"],
|
||||
},
|
||||
{"name": "Sales", "employees": 20, "regions": {"north": 5, "south": 3}},
|
||||
],
|
||||
}
|
||||
}
|
||||
result = task.interpolate_only("{company}", input_data)
|
||||
parsed = eval(result)
|
||||
|
||||
assert parsed["name"] == "TechCorp"
|
||||
assert len(parsed["departments"]) == 2
|
||||
assert parsed["departments"][0]["tools"] == ["Git", "Docker", "Kubernetes"]
|
||||
assert parsed["departments"][1]["regions"]["north"] == 5
|
||||
|
||||
|
||||
def test_interpolate_with_special_characters():
|
||||
task = Task(
|
||||
description="Test special characters in dicts",
|
||||
expected_output="Data: {special_data}",
|
||||
)
|
||||
|
||||
input_data = {
|
||||
"special_data": {
|
||||
"quotes": """This has "double" and 'single' quotes""",
|
||||
"unicode": "文字化けテスト",
|
||||
"symbols": "!@#$%^&*()",
|
||||
"empty": "",
|
||||
}
|
||||
}
|
||||
result = task.interpolate_only("{special_data}", input_data)
|
||||
parsed = eval(result)
|
||||
|
||||
assert parsed["quotes"] == """This has "double" and 'single' quotes"""
|
||||
assert parsed["unicode"] == "文字化けテスト"
|
||||
assert parsed["symbols"] == "!@#$%^&*()"
|
||||
assert parsed["empty"] == ""
|
||||
|
||||
|
||||
def test_interpolate_mixed_types():
|
||||
task = Task(
|
||||
description="Test mixed type interpolation",
|
||||
expected_output="Mixed: {data}",
|
||||
)
|
||||
|
||||
input_data = {
|
||||
"data": {
|
||||
"name": "Test Dataset",
|
||||
"samples": 1000,
|
||||
"features": ["age", "income", "location"],
|
||||
"metadata": {
|
||||
"source": "public",
|
||||
"validated": True,
|
||||
"tags": ["demo", "test", "temp"],
|
||||
},
|
||||
}
|
||||
}
|
||||
result = task.interpolate_only("{data}", input_data)
|
||||
parsed = eval(result)
|
||||
|
||||
assert parsed["name"] == "Test Dataset"
|
||||
assert parsed["samples"] == 1000
|
||||
assert parsed["metadata"]["tags"] == ["demo", "test", "temp"]
|
||||
|
||||
|
||||
def test_interpolate_complex_combination():
|
||||
task = Task(
|
||||
description="Test complex combination",
|
||||
expected_output="Report: {report}",
|
||||
)
|
||||
|
||||
input_data = {
|
||||
"report": [
|
||||
{
|
||||
"month": "January",
|
||||
"metrics": {"sales": 15000, "expenses": 8000, "profit": 7000},
|
||||
"top_products": ["Product A", "Product B"],
|
||||
},
|
||||
{
|
||||
"month": "February",
|
||||
"metrics": {"sales": 18000, "expenses": 8500, "profit": 9500},
|
||||
"top_products": ["Product C", "Product D"],
|
||||
},
|
||||
]
|
||||
}
|
||||
result = task.interpolate_only("{report}", input_data)
|
||||
parsed = eval(result)
|
||||
|
||||
assert len(parsed) == 2
|
||||
assert parsed[0]["month"] == "January"
|
||||
assert parsed[1]["metrics"]["profit"] == 9500
|
||||
assert "Product D" in parsed[1]["top_products"]
|
||||
|
||||
|
||||
def test_interpolate_invalid_type_validation():
|
||||
task = Task(
|
||||
description="Test invalid type validation",
|
||||
expected_output="Should never reach here",
|
||||
)
|
||||
|
||||
# Test with invalid top-level type
|
||||
with pytest.raises(ValueError) as excinfo:
|
||||
task.interpolate_only("{data}", {"data": set()}) # type: ignore we are purposely testing this failure
|
||||
|
||||
assert "Unsupported type set" in str(excinfo.value)
|
||||
|
||||
# Test with invalid nested type
|
||||
invalid_nested = {
|
||||
"profile": {
|
||||
"name": "John",
|
||||
"age": 30,
|
||||
"tags": {"a", "b", "c"}, # Set is invalid
|
||||
}
|
||||
}
|
||||
with pytest.raises(ValueError) as excinfo:
|
||||
task.interpolate_only("{data}", {"data": invalid_nested})
|
||||
assert "Unsupported type set" in str(excinfo.value)
|
||||
|
||||
|
||||
def test_interpolate_custom_object_validation():
|
||||
task = Task(
|
||||
description="Test custom object rejection",
|
||||
expected_output="Should never reach here",
|
||||
)
|
||||
|
||||
class CustomObject:
|
||||
def __init__(self, value):
|
||||
self.value = value
|
||||
|
||||
def __str__(self):
|
||||
return str(self.value)
|
||||
|
||||
# Test with custom object at top level
|
||||
with pytest.raises(ValueError) as excinfo:
|
||||
task.interpolate_only("{obj}", {"obj": CustomObject(5)}) # type: ignore we are purposely testing this failure
|
||||
assert "Unsupported type CustomObject" in str(excinfo.value)
|
||||
|
||||
# Test with nested custom object in dictionary
|
||||
with pytest.raises(ValueError) as excinfo:
|
||||
task.interpolate_only(
|
||||
"{data}", {"data": {"valid": 1, "invalid": CustomObject(5)}}
|
||||
)
|
||||
assert "Unsupported type CustomObject" in str(excinfo.value)
|
||||
|
||||
# Test with nested custom object in list
|
||||
with pytest.raises(ValueError) as excinfo:
|
||||
task.interpolate_only("{data}", {"data": [1, "valid", CustomObject(5)]})
|
||||
assert "Unsupported type CustomObject" in str(excinfo.value)
|
||||
|
||||
# Test with deeply nested custom object
|
||||
with pytest.raises(ValueError) as excinfo:
|
||||
task.interpolate_only(
|
||||
"{data}", {"data": {"level1": {"level2": [{"level3": CustomObject(5)}]}}}
|
||||
)
|
||||
assert "Unsupported type CustomObject" in str(excinfo.value)
|
||||
|
||||
|
||||
def test_interpolate_valid_complex_types():
|
||||
task = Task(
|
||||
description="Test valid complex types",
|
||||
expected_output="Validation should pass",
|
||||
)
|
||||
|
||||
# Valid complex structure
|
||||
valid_data = {
|
||||
"name": "Valid Dataset",
|
||||
"stats": {
|
||||
"count": 1000,
|
||||
"distribution": [0.2, 0.3, 0.5],
|
||||
"features": ["age", "income"],
|
||||
"nested": {"deep": [1, 2, 3], "deeper": {"a": 1, "b": 2.5}},
|
||||
},
|
||||
}
|
||||
|
||||
# Should not raise any errors
|
||||
result = task.interpolate_only("{data}", {"data": valid_data})
|
||||
parsed = eval(result)
|
||||
assert parsed["name"] == "Valid Dataset"
|
||||
assert parsed["stats"]["nested"]["deeper"]["b"] == 2.5
|
||||
|
||||
|
||||
def test_interpolate_edge_cases():
|
||||
task = Task(
|
||||
description="Test edge cases",
|
||||
expected_output="Edge case handling",
|
||||
)
|
||||
|
||||
# Test empty dict and list
|
||||
assert task.interpolate_only("{}", {"data": {}}) == "{}"
|
||||
assert task.interpolate_only("[]", {"data": []}) == "[]"
|
||||
|
||||
# Test numeric types
|
||||
assert task.interpolate_only("{num}", {"num": 42}) == "42"
|
||||
assert task.interpolate_only("{num}", {"num": 3.14}) == "3.14"
|
||||
|
||||
# Test boolean values (valid JSON types)
|
||||
assert task.interpolate_only("{flag}", {"flag": True}) == "True"
|
||||
assert task.interpolate_only("{flag}", {"flag": False}) == "False"
|
||||
|
||||
|
||||
def test_interpolate_valid_types():
|
||||
task = Task(
|
||||
description="Test valid types including null and boolean",
|
||||
expected_output="Should pass validation",
|
||||
)
|
||||
|
||||
# Test with boolean and null values (valid JSON types)
|
||||
valid_data = {
|
||||
"name": "Test",
|
||||
"active": True,
|
||||
"deleted": False,
|
||||
"optional": None,
|
||||
"nested": {"flag": True, "empty": None},
|
||||
}
|
||||
|
||||
result = task.interpolate_only("{data}", {"data": valid_data})
|
||||
parsed = eval(result)
|
||||
|
||||
assert parsed["active"] is True
|
||||
assert parsed["deleted"] is False
|
||||
assert parsed["optional"] is None
|
||||
assert parsed["nested"]["flag"] is True
|
||||
assert parsed["nested"]["empty"] is None
|
||||
|
||||
@@ -1,51 +0,0 @@
|
||||
import pytest
|
||||
|
||||
from crewai import Agent
|
||||
from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
|
||||
|
||||
|
||||
class InternalAgentTool(BaseAgentTool):
|
||||
"""Concrete implementation of BaseAgentTool for testing."""
|
||||
|
||||
def _run(self, *args, **kwargs):
|
||||
"""Implement required _run method."""
|
||||
return "Test response"
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"role_name,should_match",
|
||||
[
|
||||
("Futel Official Infopoint", True), # exact match
|
||||
(' "Futel Official Infopoint" ', True), # extra quotes and spaces
|
||||
("Futel Official Infopoint\n", True), # trailing newline
|
||||
('"Futel Official Infopoint"', True), # embedded quotes
|
||||
(" FUTEL\nOFFICIAL INFOPOINT ", True), # multiple whitespace and newline
|
||||
],
|
||||
)
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_agent_tool_role_matching(role_name, should_match):
|
||||
"""Test that agent tools can match roles regardless of case, whitespace, and special characters."""
|
||||
# Create test agent
|
||||
test_agent = Agent(
|
||||
role="Futel Official Infopoint",
|
||||
goal="Answer questions about Futel",
|
||||
backstory="Futel Football Club info",
|
||||
allow_delegation=False,
|
||||
)
|
||||
|
||||
# Create test agent tool
|
||||
agent_tool = InternalAgentTool(
|
||||
name="test_tool", description="Test tool", agents=[test_agent]
|
||||
)
|
||||
|
||||
# Test role matching
|
||||
result = agent_tool._execute(agent_name=role_name, task="Test task", context=None)
|
||||
|
||||
if should_match:
|
||||
assert (
|
||||
"coworker mentioned not found" not in result.lower()
|
||||
), f"Should find agent with role name: {role_name}"
|
||||
else:
|
||||
assert (
|
||||
"coworker mentioned not found" in result.lower()
|
||||
), f"Should not find agent with role name: {role_name}"
|
||||
@@ -231,3 +231,255 @@ def test_validate_tool_input_with_special_characters():
|
||||
|
||||
arguments = tool_usage._validate_tool_input(tool_input)
|
||||
assert arguments == expected_arguments
|
||||
|
||||
|
||||
def test_validate_tool_input_none_input():
|
||||
tool_usage = ToolUsage(
|
||||
tools_handler=MagicMock(),
|
||||
tools=[],
|
||||
original_tools=[],
|
||||
tools_description="",
|
||||
tools_names="",
|
||||
task=MagicMock(),
|
||||
function_calling_llm=None,
|
||||
agent=MagicMock(),
|
||||
action=MagicMock(),
|
||||
)
|
||||
|
||||
arguments = tool_usage._validate_tool_input(None)
|
||||
assert arguments == {}
|
||||
|
||||
|
||||
def test_validate_tool_input_valid_json():
|
||||
tool_usage = ToolUsage(
|
||||
tools_handler=MagicMock(),
|
||||
tools=[],
|
||||
original_tools=[],
|
||||
tools_description="",
|
||||
tools_names="",
|
||||
task=MagicMock(),
|
||||
function_calling_llm=None,
|
||||
agent=MagicMock(),
|
||||
action=MagicMock(),
|
||||
)
|
||||
|
||||
tool_input = '{"key": "value", "number": 42, "flag": true}'
|
||||
expected_arguments = {"key": "value", "number": 42, "flag": True}
|
||||
|
||||
arguments = tool_usage._validate_tool_input(tool_input)
|
||||
assert arguments == expected_arguments
|
||||
|
||||
|
||||
def test_validate_tool_input_python_dict():
|
||||
tool_usage = ToolUsage(
|
||||
tools_handler=MagicMock(),
|
||||
tools=[],
|
||||
original_tools=[],
|
||||
tools_description="",
|
||||
tools_names="",
|
||||
task=MagicMock(),
|
||||
function_calling_llm=None,
|
||||
agent=MagicMock(),
|
||||
action=MagicMock(),
|
||||
)
|
||||
|
||||
tool_input = "{'key': 'value', 'number': 42, 'flag': True}"
|
||||
expected_arguments = {"key": "value", "number": 42, "flag": True}
|
||||
|
||||
arguments = tool_usage._validate_tool_input(tool_input)
|
||||
assert arguments == expected_arguments
|
||||
|
||||
|
||||
def test_validate_tool_input_json5_unquoted_keys():
|
||||
tool_usage = ToolUsage(
|
||||
tools_handler=MagicMock(),
|
||||
tools=[],
|
||||
original_tools=[],
|
||||
tools_description="",
|
||||
tools_names="",
|
||||
task=MagicMock(),
|
||||
function_calling_llm=None,
|
||||
agent=MagicMock(),
|
||||
action=MagicMock(),
|
||||
)
|
||||
|
||||
tool_input = "{key: 'value', number: 42, flag: true}"
|
||||
expected_arguments = {"key": "value", "number": 42, "flag": True}
|
||||
|
||||
arguments = tool_usage._validate_tool_input(tool_input)
|
||||
assert arguments == expected_arguments
|
||||
|
||||
|
||||
def test_validate_tool_input_with_trailing_commas():
|
||||
tool_usage = ToolUsage(
|
||||
tools_handler=MagicMock(),
|
||||
tools=[],
|
||||
original_tools=[],
|
||||
tools_description="",
|
||||
tools_names="",
|
||||
task=MagicMock(),
|
||||
function_calling_llm=None,
|
||||
agent=MagicMock(),
|
||||
action=MagicMock(),
|
||||
)
|
||||
|
||||
tool_input = '{"key": "value", "number": 42, "flag": true,}'
|
||||
expected_arguments = {"key": "value", "number": 42, "flag": True}
|
||||
|
||||
arguments = tool_usage._validate_tool_input(tool_input)
|
||||
assert arguments == expected_arguments
|
||||
|
||||
|
||||
def test_validate_tool_input_invalid_input():
|
||||
tool_usage = ToolUsage(
|
||||
tools_handler=MagicMock(),
|
||||
tools=[],
|
||||
original_tools=[],
|
||||
tools_description="",
|
||||
tools_names="",
|
||||
task=MagicMock(),
|
||||
function_calling_llm=None,
|
||||
agent=MagicMock(),
|
||||
action=MagicMock(),
|
||||
)
|
||||
|
||||
invalid_inputs = [
|
||||
"Just a string",
|
||||
"['list', 'of', 'values']",
|
||||
"12345",
|
||||
"",
|
||||
]
|
||||
|
||||
for invalid_input in invalid_inputs:
|
||||
with pytest.raises(Exception) as e_info:
|
||||
tool_usage._validate_tool_input(invalid_input)
|
||||
assert (
|
||||
"Tool input must be a valid dictionary in JSON or Python literal format"
|
||||
in str(e_info.value)
|
||||
)
|
||||
|
||||
# Test for None input separately
|
||||
arguments = tool_usage._validate_tool_input(None)
|
||||
assert arguments == {} # Expecting an empty dictionary
|
||||
|
||||
|
||||
def test_validate_tool_input_complex_structure():
|
||||
tool_usage = ToolUsage(
|
||||
tools_handler=MagicMock(),
|
||||
tools=[],
|
||||
original_tools=[],
|
||||
tools_description="",
|
||||
tools_names="",
|
||||
task=MagicMock(),
|
||||
function_calling_llm=None,
|
||||
agent=MagicMock(),
|
||||
action=MagicMock(),
|
||||
)
|
||||
|
||||
tool_input = """
|
||||
{
|
||||
"user": {
|
||||
"name": "Alice",
|
||||
"age": 30
|
||||
},
|
||||
"items": [
|
||||
{"id": 1, "value": "Item1"},
|
||||
{"id": 2, "value": "Item2",}
|
||||
],
|
||||
"active": true,
|
||||
}
|
||||
"""
|
||||
expected_arguments = {
|
||||
"user": {"name": "Alice", "age": 30},
|
||||
"items": [
|
||||
{"id": 1, "value": "Item1"},
|
||||
{"id": 2, "value": "Item2"},
|
||||
],
|
||||
"active": True,
|
||||
}
|
||||
|
||||
arguments = tool_usage._validate_tool_input(tool_input)
|
||||
assert arguments == expected_arguments
|
||||
|
||||
|
||||
def test_validate_tool_input_code_content():
|
||||
tool_usage = ToolUsage(
|
||||
tools_handler=MagicMock(),
|
||||
tools=[],
|
||||
original_tools=[],
|
||||
tools_description="",
|
||||
tools_names="",
|
||||
task=MagicMock(),
|
||||
function_calling_llm=None,
|
||||
agent=MagicMock(),
|
||||
action=MagicMock(),
|
||||
)
|
||||
|
||||
tool_input = '{"filename": "script.py", "content": "def hello():\\n print(\'Hello, world!\')"}'
|
||||
expected_arguments = {
|
||||
"filename": "script.py",
|
||||
"content": "def hello():\n print('Hello, world!')",
|
||||
}
|
||||
|
||||
arguments = tool_usage._validate_tool_input(tool_input)
|
||||
assert arguments == expected_arguments
|
||||
|
||||
|
||||
def test_validate_tool_input_with_escaped_quotes():
|
||||
tool_usage = ToolUsage(
|
||||
tools_handler=MagicMock(),
|
||||
tools=[],
|
||||
original_tools=[],
|
||||
tools_description="",
|
||||
tools_names="",
|
||||
task=MagicMock(),
|
||||
function_calling_llm=None,
|
||||
agent=MagicMock(),
|
||||
action=MagicMock(),
|
||||
)
|
||||
|
||||
tool_input = '{"text": "He said, \\"Hello, world!\\""}'
|
||||
expected_arguments = {"text": 'He said, "Hello, world!"'}
|
||||
|
||||
arguments = tool_usage._validate_tool_input(tool_input)
|
||||
assert arguments == expected_arguments
|
||||
|
||||
|
||||
def test_validate_tool_input_large_json_content():
|
||||
tool_usage = ToolUsage(
|
||||
tools_handler=MagicMock(),
|
||||
tools=[],
|
||||
original_tools=[],
|
||||
tools_description="",
|
||||
tools_names="",
|
||||
task=MagicMock(),
|
||||
function_calling_llm=None,
|
||||
agent=MagicMock(),
|
||||
action=MagicMock(),
|
||||
)
|
||||
|
||||
# Simulate a large JSON content
|
||||
tool_input = (
|
||||
'{"data": ' + json.dumps([{"id": i, "value": i * 2} for i in range(1000)]) + "}"
|
||||
)
|
||||
expected_arguments = {"data": [{"id": i, "value": i * 2} for i in range(1000)]}
|
||||
|
||||
arguments = tool_usage._validate_tool_input(tool_input)
|
||||
assert arguments == expected_arguments
|
||||
|
||||
|
||||
def test_validate_tool_input_none_input():
|
||||
tool_usage = ToolUsage(
|
||||
tools_handler=MagicMock(),
|
||||
tools=[],
|
||||
original_tools=[],
|
||||
tools_description="",
|
||||
tools_names="",
|
||||
task=MagicMock(),
|
||||
function_calling_llm=None,
|
||||
agent=MagicMock(),
|
||||
action=MagicMock(),
|
||||
)
|
||||
|
||||
arguments = tool_usage._validate_tool_input(None)
|
||||
assert arguments == {} # Expecting an empty dictionary
|
||||
|
||||
@@ -48,9 +48,9 @@ def test_evaluate_training_data(converter_mock):
|
||||
mock.call(
|
||||
llm=original_agent.llm,
|
||||
text="Assess the quality of the training data based on the llm output, human feedback , and llm "
|
||||
"output improved result.\n\nInitial Output:\nInitial output 1\n\nHuman Feedback:\nHuman feedback "
|
||||
"1\n\nImproved Output:\nImproved output 1\n\nInitial Output:\nInitial output 2\n\nHuman "
|
||||
"Feedback:\nHuman feedback 2\n\nImproved Output:\nImproved output 2\n\nPlease provide:\n- Provide "
|
||||
"output improved result.\n\nIteration: data1\nInitial Output:\nInitial output 1\n\nHuman Feedback:\nHuman feedback "
|
||||
"1\n\nImproved Output:\nImproved output 1\n\n------------------------------------------------\n\nIteration: data2\nInitial Output:\nInitial output 2\n\nHuman "
|
||||
"Feedback:\nHuman feedback 2\n\nImproved Output:\nImproved output 2\n\n------------------------------------------------\n\nPlease provide:\n- Provide "
|
||||
"a list of clear, actionable instructions derived from the Human Feedbacks to enhance the Agent's "
|
||||
"performance. Analyze the differences between Initial Outputs and Improved Outputs to generate specific "
|
||||
"action items for future tasks. Ensure all key and specificpoints from the human feedback are "
|
||||
|
||||
Reference in New Issue
Block a user