andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-25 16:18:13 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Merge branch 'main' of github.com:crewAIInc/crewAI into devin/1744622358-fix-agentops-key-check

Browse Source
This commit is contained in:
lorenzejay
2025-04-17 17:15:13 -07:00
parent 7f728c8ebf 371f19f3cd
commit 06938f0d31
73 changed files with 8692 additions and 2046 deletions
Download Patch File Download Diff File Expand all files Collapse all files

113
tests/agents/agent_adapters/test_base_agent_adapter.py Normal file
View File

@@ -0,0 +1,113 @@
from typing import Any, Dict, List, Optional
import pytest
from pydantic import BaseModel
from crewai.agent import BaseAgent
from crewai.agents.agent_adapters.base_agent_adapter import BaseAgentAdapter
from crewai.tools import BaseTool
from crewai.utilities.token_counter_callback import TokenProcess
# Concrete implementation for testing
class ConcreteAgentAdapter(BaseAgentAdapter):
def configure_tools(
self, tools: Optional[List[BaseTool]] = None, **kwargs: Any
) -> None:
# Simple implementation for testing
self.tools = tools or []
def execute_task(
self,
task: Any,
context: Optional[str] = None,
tools: Optional[List[Any]] = None,
) -> str:
# Dummy implementation needed due to BaseAgent inheritance
return "Task executed"
def create_agent_executor(self, tools: Optional[List[BaseTool]] = None) -> Any:
# Dummy implementation
return None
def get_delegation_tools(
self, tools: List[BaseTool], tool_map: Optional[Dict[str, BaseTool]]
) -> List[BaseTool]:
# Dummy implementation
return []
def _parse_output(self, agent_output: Any, token_process: TokenProcess):
# Dummy implementation
pass
def get_output_converter(self, tools: Optional[List[BaseTool]] = None) -> Any:
# Dummy implementation
return None
def test_base_agent_adapter_initialization():
"""Test initialization of the concrete agent adapter."""
adapter = ConcreteAgentAdapter(
role="test role", goal="test goal", backstory="test backstory"
)
assert isinstance(adapter, BaseAgent)
assert isinstance(adapter, BaseAgentAdapter)
assert adapter.role == "test role"
assert adapter._agent_config is None
assert adapter.adapted_structured_output is False
def test_base_agent_adapter_initialization_with_config():
"""Test initialization with agent_config."""
config = {"model": "gpt-4"}
adapter = ConcreteAgentAdapter(
agent_config=config,
role="test role",
goal="test goal",
backstory="test backstory",
)
assert adapter._agent_config == config
def test_configure_tools_method_exists():
"""Test that configure_tools method exists and can be called."""
adapter = ConcreteAgentAdapter(
role="test role", goal="test goal", backstory="test backstory"
)
# Create dummy tools if needed, or pass None
tools = []
adapter.configure_tools(tools)
assert hasattr(adapter, "tools")
assert adapter.tools == tools
def test_configure_structured_output_method_exists():
"""Test that configure_structured_output method exists and can be called."""
adapter = ConcreteAgentAdapter(
role="test role", goal="test goal", backstory="test backstory"
)
# Define a dummy structure or pass None/Any
class DummyOutput(BaseModel):
data: str
structured_output = DummyOutput
adapter.configure_structured_output(structured_output)
# Add assertions here if configure_structured_output modifies state
# For now, just ensuring it runs without error is sufficient
pass
def test_base_agent_adapter_inherits_base_agent():
"""Test that BaseAgentAdapter inherits from BaseAgent."""
assert issubclass(BaseAgentAdapter, BaseAgent)
class ConcreteAgentAdapterWithoutRequiredMethods(BaseAgentAdapter):
pass
def test_base_agent_adapter_fails_without_required_methods():
"""Test that BaseAgentAdapter fails without required methods."""
with pytest.raises(TypeError):
ConcreteAgentAdapterWithoutRequiredMethods() # type: ignore

94
tests/agents/agent_adapters/test_base_tool_adapter.py Normal file
View File

@@ -0,0 +1,94 @@
from typing import Any, List
from unittest.mock import Mock
import pytest
from crewai.agents.agent_adapters.base_tool_adapter import BaseToolAdapter
from crewai.tools.base_tool import BaseTool
class ConcreteToolAdapter(BaseToolAdapter):
def configure_tools(self, tools: List[BaseTool]) -> None:
self.converted_tools = [f"converted_{tool.name}" for tool in tools]
@pytest.fixture
def mock_tool_1():
tool = Mock(spec=BaseTool)
tool.name = "Mock Tool 1"
return tool
@pytest.fixture
def mock_tool_2():
tool = Mock(spec=BaseTool)
tool.name = "MockTool2"
return tool
@pytest.fixture
def tools_list(mock_tool_1, mock_tool_2):
return [mock_tool_1, mock_tool_2]
def test_initialization_with_tools(tools_list):
adapter = ConcreteToolAdapter(tools=tools_list)
assert adapter.original_tools == tools_list
assert adapter.converted_tools == [] # Conversion happens in configure_tools
def test_initialization_without_tools():
adapter = ConcreteToolAdapter()
assert adapter.original_tools == []
assert adapter.converted_tools == []
def test_configure_tools(tools_list):
adapter = ConcreteToolAdapter()
adapter.configure_tools(tools_list)
assert adapter.converted_tools == ["converted_Mock Tool 1", "converted_MockTool2"]
assert adapter.original_tools == [] # original_tools is only set in init
adapter_with_init_tools = ConcreteToolAdapter(tools=tools_list)
adapter_with_init_tools.configure_tools(tools_list)
assert adapter_with_init_tools.converted_tools == [
"converted_Mock Tool 1",
"converted_MockTool2",
]
assert adapter_with_init_tools.original_tools == tools_list
def test_tools_method(tools_list):
adapter = ConcreteToolAdapter()
adapter.configure_tools(tools_list)
assert adapter.tools() == ["converted_Mock Tool 1", "converted_MockTool2"]
def test_tools_method_empty():
adapter = ConcreteToolAdapter()
assert adapter.tools() == []
def test_sanitize_tool_name_with_spaces():
adapter = ConcreteToolAdapter()
assert adapter.sanitize_tool_name("Tool With Spaces") == "Tool_With_Spaces"
def test_sanitize_tool_name_without_spaces():
adapter = ConcreteToolAdapter()
assert adapter.sanitize_tool_name("ToolWithoutSpaces") == "ToolWithoutSpaces"
def test_sanitize_tool_name_empty():
adapter = ConcreteToolAdapter()
assert adapter.sanitize_tool_name("") == ""
class ConcreteToolAdapterWithoutRequiredMethods(BaseToolAdapter):
pass
def test_tool_adapted_fails_without_required_methods():
"""Test that BaseToolAdapter fails without required methods."""
with pytest.raises(TypeError):
ConcreteToolAdapterWithoutRequiredMethods() # type: ignore

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

@@ -18,9 +18,6 @@ class MockAgent(BaseAgent):
def create_agent_executor(self, tools=None) -> None: ...
def _parse_tools(self, tools: List[BaseTool]) -> List[BaseTool]:
return []
def get_delegation_tools(self, agents: List["BaseAgent"]): ...
def get_output_converter(

0
tests/memory/external/cassettes/test_crew_external_memory_save.yaml → tests/cassettes/test_crew_external_memory_save.yaml
View File

182
tests/cassettes/test_crew_external_memory_save_using_crew_without_memory_flag[save].yaml Normal file
View File

@@ -0,0 +1,182 @@
interactions:
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1634'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.31.1
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Sat, 12 Apr 2025 20:27:26 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You are
a researcher at a leading tech think tank.\nYour personal goal is: Search relevant
data and provide results\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: Perform a search
on specific topics.\n\nThis is the expected criteria for your final answer:
A list of relevant URLs based on the search query.\nyou MUST return the actual
complete content as the final answer, not a summary.\n\n# Useful context: \nExternal
memories:\n\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-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '989'
content-type:
- application/json
cookie:
- __cf_bm=nSje5Zn_Lk69BDG85XIauC2hrZjGl0pR2sel9__KWGw-1744489610-1.0.1.1-CPlAgcgTAE30uWrbi_2wiCWrbRDRWiaa.YuQMgST42DLDVg_wdNlJMDQT3Lsqk.g.BO68A66TTirWA0blQaQw.9xdBbPwKO609_ftjdwi5U;
_cfuvid=XLC52GLAWCOeWn2vI379CnSGKjPa7f.qr2vSAQ_R66M-1744489610542-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-BLbjg0OfADWdrLsZxrjKHEeVVbWle\",\n \"object\":
\"chat.completion\",\n \"created\": 1744489644,\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: Here is a list of relevant URLs based on the specified search query:
\ \\n\\n1. https://www.forbes.com/technology/ \\n2. https://www.sciencedirect.com/
\ \\n3. https://www.techcrunch.com/ \\n4. https://www.wired.com/ \\n5. https://www.researchgate.net/
\ \\n6. https://www.springer.com/ \\n7. https://www.jstor.org/ \\n8. https://www.statista.com/
\ \\n9. https://www.pwc.com/gx/en/services/consulting/technology.html \\n10.
https://www.gartner.com/en/information-technology \\n\\nThese URLs provide
access to a wealth of information on various technology-related topics, including
articles, research papers, and analytics.\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 185,\n \"completion_tokens\":
169,\n \"total_tokens\": 354,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_80cf447eee\"\n}\n"
headers:
CF-RAY:
- 92f576d83a447e05-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 12 Apr 2025 20:27:27 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '2273'
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:
- '149999788'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_38f6879956c29e6c61c844d1906fa2e8
http_version: HTTP/1.1
status_code: 200
version: 1

190
tests/cassettes/test_crew_external_memory_save_using_crew_without_memory_flag[search].yaml Normal file
View File

@@ -0,0 +1,190 @@
interactions:
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1634'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.31.1
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Sat, 12 Apr 2025 20:27:16 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You are
a researcher at a leading tech think tank.\nYour personal goal is: Search relevant
data and provide results\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: Perform a search
on specific topics.\n\nThis is the expected criteria for your final answer:
A list of relevant URLs based on the search query.\nyou MUST return the actual
complete content as the final answer, not a summary.\n\n# Useful context: \nExternal
memories:\n\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-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '989'
content-type:
- application/json
cookie:
- __cf_bm=nSje5Zn_Lk69BDG85XIauC2hrZjGl0pR2sel9__KWGw-1744489610-1.0.1.1-CPlAgcgTAE30uWrbi_2wiCWrbRDRWiaa.YuQMgST42DLDVg_wdNlJMDQT3Lsqk.g.BO68A66TTirWA0blQaQw.9xdBbPwKO609_ftjdwi5U;
_cfuvid=XLC52GLAWCOeWn2vI379CnSGKjPa7f.qr2vSAQ_R66M-1744489610542-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-BLbjXyMvmR8ctf0sqhp7F1ePskveM\",\n \"object\":
\"chat.completion\",\n \"created\": 1744489635,\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: Here is a list of relevant URLs based on the search query:\\n\\n1. **Artificial
Intelligence in Healthcare**\\n - https://www.healthit.gov/topic/scientific-initiatives/ai-healthcare\\n
\ - https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7317789/\\n - https://www.forbes.com/sites/bernardmarr/2021/10/18/the-top-5-ways-ai-is-being-used-in-healthcare/?sh=3edf5df51c9c\\n\\n2.
**Blockchain Technology in Supply Chain Management**\\n - https://www.ibm.com/blockchain/supply-chain\\n
\ - https://www.gartner.com/en/newsroom/press-releases/2021-06-23-gartner-says-three-use-cases-for-blockchain-in-supply-chain-are-scaling\\n
\ - https://www2.deloitte.com/us/en/insights/industry/retail-distribution/blockchain-in-supply-chain.html\\n\\n3.
**Renewable Energy Innovations**\\n - https://www.irena.org/publications/2020/Sep/Renewable-Power-Generation-Costs-in-2020\\n
\ - https://www.nrel.gov/docs/fy20osti/77021.pdf\\n - https://www.cnbc.com/2021/11/03/renewable-energy-could-get-its-first-taste-of-markets-in-2021.html\\n\\n4.
**7G Technology Developments**\\n - https://www.sciencedirect.com/science/article/pii/S1389128619308189\\n
\ - https://www.forbes.com/sites/bernardmarr/2021/11/01/what-is-7g-technology-a-beginners-guide-to-the-future-of-mobile-communications/?sh=51b8a7e1464a\\n
\ - https://www.ericsson.com/en/reports-and-research/reports/7g-networks-a-powerful-future-for-connected-society\\n\\n5.
**Impact of Quantum Computing on Cybersecurity**\\n - https://www.ibm.com/blogs/research/2021/09/quantum-computing-cybersecurity/\\n
\ - https://www.sciencedirect.com/science/article/pii/S0167739X21000072\\n
\ - https://www.techrepublic.com/article/how-quantum-computing-will-change-cybersecurity/\\n\\nThese
URLs should provide comprehensive information on the topics searched, providing
valuable insights and data for your research needs.\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 185,\n \"completion_tokens\":
534,\n \"total_tokens\": 719,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_80cf447eee\"\n}\n"
headers:
CF-RAY:
- 92f576a01d3b7e05-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 12 Apr 2025 20:27:24 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '8805'
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:
- '149999788'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_7c2d313d0b5997e903553a782b2afa25
http_version: HTTP/1.1
status_code: 200
version: 1

1177
tests/cassettes/test_crew_external_memory_save_with_memory_flag[save].yaml Normal file
View File

File diff suppressed because one or more lines are too long

1425
tests/cassettes/test_crew_external_memory_save_with_memory_flag[search].yaml Normal file
View File

File diff suppressed because one or more lines are too long

0
tests/memory/external/cassettes/test_crew_external_memory_search.yaml → tests/cassettes/test_crew_external_memory_search.yaml
View File

133
tests/cassettes/test_handle_streaming_tool_calls.yaml Normal file
View File

@@ -0,0 +1,133 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the weather in New York?"}],
"model": "gpt-4o", "stop": [], "stream": true, "stream_options": {"include_usage":
true}, "tools": [{"type": "function", "function": {"name": "get_weather", "description":
"Get the current weather in a given location", "parameters": {"type": "object",
"properties": {"location": {"type": "string", "description": "The city and state,
e.g. San Francisco, CA"}}, "required": ["location"]}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '470'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.74.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.74.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.12
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_bCEixqN8Y40SUyius8ZfVErH","type":"function","function":{"name":"get_weather","arguments":""}}],"refusal":null},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"location"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"New"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"
York"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"
NY"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"tool_calls"}],"usage":null}
data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[],"usage":{"prompt_tokens":68,"completion_tokens":18,"total_tokens":86,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}}}
data: [DONE]
'
headers:
CF-RAY:
- 93147723ecc1f237-GRU
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Wed, 16 Apr 2025 14:45:16 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '620'
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:
- '29999989'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_0a08d5f042ef769aeb2c941e398f65f4
status:
code: 200
message: OK
version: 1

133
tests/cassettes/test_handle_streaming_tool_calls_no_available_functions.yaml Normal file
View File

@@ -0,0 +1,133 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the weather in New York?"}],
"model": "gpt-4o", "stop": [], "stream": true, "stream_options": {"include_usage":
true}, "tools": [{"type": "function", "function": {"name": "get_weather", "description":
"Get the current weather in a given location", "parameters": {"type": "object",
"properties": {"location": {"type": "string", "description": "The city and state,
e.g. San Francisco, CA"}}, "required": ["location"]}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '470'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.74.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.74.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.12
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_ccog5nyDCLYpoWzksuCkGEqY","type":"function","function":{"name":"get_weather","arguments":""}}],"refusal":null},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"location"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"New"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"
York"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"
NY"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"tool_calls"}],"usage":null}
data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[],"usage":{"prompt_tokens":68,"completion_tokens":18,"total_tokens":86,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}}}
data: [DONE]
'
headers:
CF-RAY:
- 931461bbddc27df9-GRU
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Wed, 16 Apr 2025 14:30:39 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '445'
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:
- '29999989'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_1bb5862de2891623d44c012aba597c5e
status:
code: 200
message: OK
version: 1

279
tests/cassettes/test_handle_streaming_tool_calls_no_tools.yaml Normal file
View File

@@ -0,0 +1,279 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the weather in New York?"}],
"model": "gpt-4o", "stop": [], "stream": true, "stream_options": {"include_usage":
true}}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '169'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.74.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.74.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.12
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"I''m"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
unable"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
to"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
provide"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
real"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"-time"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
information"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
or"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
current"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
weather"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
updates"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
For"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
the"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
latest"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
weather"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
information"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
in"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
New"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
York"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
recommend"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
checking"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
reliable"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
weather"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
website"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
or"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
app"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
such"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
as"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
the"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
National"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
Weather"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
Service"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
Weather"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":".com"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
or"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
similar"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
service"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null}
data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[],"usage":{"prompt_tokens":15,"completion_tokens":47,"total_tokens":62,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}}}
data: [DONE]
'
headers:
CF-RAY:
- 931461c25bb47df9-GRU
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Wed, 16 Apr 2025 14:30:40 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '298'
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:
- '29999989'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_89971fd68e5a59c9fa50e04106228b0a
status:
code: 200
message: OK
version: 1

1035
tests/cassettes/test_long_term_memory_with_memory_flag.yaml Normal file
View File

File diff suppressed because one or more lines are too long

643
tests/cassettes/test_task_with_max_execution_time.yaml Normal file
View File

@@ -0,0 +1,643 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
an expert researcher, specialized in technology, software engineering, AI and
startups. You work as a freelancer and are now working on doing research and
analysis for a new customer.\nYour personal goal is: Make the best research
and analysis on content about AI and AI agents. Use the tool provided to you.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: what amazing tool\nTool Arguments: {}\nTool
Description: My tool\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [what amazing tool], just the name, exactly as it''s written.\nAction
Input: the input to the action, just a simple JSON object, enclosed in curly
braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
all necessary information is gathered, return the following format:\n\n```\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n```"}, {"role": "user", "content": "\nCurrent Task: Give me
a list of 5 interesting ideas to explore for an article, what makes them unique
and interesting.\n\nThis is the expected criteria for your final answer: Bullet
point list of 5 interesting ideas.\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-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1666'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.12
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-BNNPLDDeGQYegE6neZK6ogJmDOMYs\",\n \"object\":
\"chat.completion\",\n \"created\": 1744911223,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to generate interesting ideas
for an article related to AI and AI agents. \\n\\nAction: what amazing tool
\ \\nAction Input: {} \",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 326,\n \"completion_tokens\":
28,\n \"total_tokens\": 354,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_0392822090\"\n}\n"
headers:
CF-RAY:
- 931dab4c79581b2e-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 17 Apr 2025 17:33:44 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '736'
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:
- '149999620'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_0767caa75d1851f392ea34a68763b1bc
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CqzaAQokCiIKDHNlcnZpY2UubmFtZRISChBjcmV3QUktdGVsZW1ldHJ5EoLaAQoSChBjcmV3YWku
dGVsZW1ldHJ5EpYIChAm+VDVVrKTGFLYrGmqyFN/EgiVIKrLvczC6SoMQ3JldyBDcmVhdGVkMAE5
uBnOOYMrNxhBWHDXOYMrNxhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMTQuMEobCg5weXRob25f
dmVyc2lvbhIJCgczLjExLjEySi4KCGNyZXdfa2V5EiIKIDVlNmVmZmU2ODBhNWQ5N2RjMzg3M2Ix
NDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokMzI4MzZhOTctMGIyYi00MTAwLTgxZDYtYmIwZWJjY2I2
ZDYyShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRj
cmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBj
cmV3X2ZpbmdlcnByaW50EiYKJGQ5YmEwZDE3LTE5YjMtNGQ5Yi04ZTNmLThiMjNhOGM0YzgyM0o7
ChtjcmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0My4yMzg4
MzhKzQIKC2NyZXdfYWdlbnRzEr0CCroCW3sia2V5IjogIjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdk
NDI0MGEyOTRkIiwgImlkIjogImMzMWMwNzRmLTg5Y2YtNGRkNi04ZTY2LWM3NDM1OTc0NmNkMSIs
ICJyb2xlIjogIlNjb3JlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1h
eF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8t
bWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlv
bj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K+wEK
CmNyZXdfdGFza3MS7AEK6QFbeyJrZXkiOiAiMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFi
ODYiLCAiaWQiOiAiYTNiODU1ODAtZTVjNC00YmU2LWI0ZmItMDU1NDU2Y2RkZWJkIiwgImFzeW5j
X2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6
ICJTY29yZXIiLCAiYWdlbnRfa2V5IjogIjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRk
IiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASgAQKED9XhldOUhgSlcVbrT/HuRwSCCF7
8YboEaZnKgxUYXNrIENyZWF0ZWQwATlYmeU5gys3GEHwx+c5gys3GEouCghjcmV3X2tleRIiCiA1
ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0oxCgdjcmV3X2lkEiYKJDMyODM2YTk3LTBi
MmItNDEwMC04MWQ2LWJiMGViY2NiNmQ2MkouCgh0YXNrX2tleRIiCiAyN2VmMzhjYzk5ZGE0YThk
ZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0YXNrX2lkEiYKJGEzYjg1NTgwLWU1YzQtNGJlNi1iNGZiLTA1
NTQ1NmNkZGViZEo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJGQ5YmEwZDE3LTE5YjMtNGQ5Yi04ZTNm
LThiMjNhOGM0YzgyM0o6ChB0YXNrX2ZpbmdlcnByaW50EiYKJDc0OTEwMDcxLTM1MWQtNDljNy1h
YmZlLTJmMWZhNWUzZTEyYko7Cht0YXNrX2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0w
NC0xN1QxNDozMzo0My4yMzg4MDFKOwoRYWdlbnRfZmluZ2VycHJpbnQSJgokYzMyNmIyMWUtYWJh
YS00N2ZjLWE0NGQtMzk2NTQ4ZjczZTRiegIYAYUBAAEAABKYCAoQH3AbYnQyty/P5gHiJzrjLxII
PR8P3tNCS74qDENyZXcgQ3JlYXRlZDABOYgCyj6DKzcYQSD71D6DKzcYShsKDmNyZXdhaV92ZXJz
aW9uEgkKBzAuMTE0LjBKGwoOcHl0aG9uX3ZlcnNpb24SCQoHMy4xMS4xMkouCghjcmV3X2tleRIi
CiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0oxCgdjcmV3X2lkEiYKJDBkY2JhOGY4
LTdhYzQtNDdmMC04ZWIxLWE0ZTJkODFjOGZkYkoeCgxjcmV3X3Byb2Nlc3MSDgoMaGllcmFyY2hp
Y2FsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jl
d19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJDJiYzYzYWE1LWU5
YzYtNDAxNi1hMTdiLWFmZDM5ZWJlYmEwNko7ChtjcmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQS
HAoaMjAyNS0wNC0xN1QxNDozMzo0My4zMjI3OTlKzQIKC2NyZXdfYWdlbnRzEr0CCroCW3sia2V5
IjogIjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgImlkIjogImYyY2Y4YWRlLTdj
YmYtNDkwMS1hODMwLWE3ZDkxODA4NjI3NCIsICJyb2xlIjogIlNjb3JlciIsICJ2ZXJib3NlPyI6
IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGlu
Z19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/Ijog
ZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6
IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K+wEKCmNyZXdfdGFza3MS7AEK6QFbeyJrZXkiOiAiMjdl
ZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODYiLCAiaWQiOiAiMWY3MTljNTktOTJjMC00NGU1
LWFmMjUtNzIwYjE1NWE1Njg1IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lu
cHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJTY29yZXIiLCAiYWdlbnRfa2V5IjogIjkyZTdl
YjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQAB
AAASgAQKEIVZhLW3PhEOxntJYQn8IYkSCDNELyrmM+eYKgxUYXNrIENyZWF0ZWQwATlYr+0+gys3
GEGIJO4+gys3GEouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2Zh
M0oxCgdjcmV3X2lkEiYKJDBkY2JhOGY4LTdhYzQtNDdmMC04ZWIxLWE0ZTJkODFjOGZkYkouCgh0
YXNrX2tleRIiCiAyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0YXNrX2lkEiYK
JDFmNzE5YzU5LTkyYzAtNDRlNS1hZjI1LTcyMGIxNTVhNTY4NUo6ChBjcmV3X2ZpbmdlcnByaW50
EiYKJDJiYzYzYWE1LWU5YzYtNDAxNi1hMTdiLWFmZDM5ZWJlYmEwNko6ChB0YXNrX2ZpbmdlcnBy
aW50EiYKJGJmMDU5YjBiLWFlYmYtNGIzMS04YTc4LTA2ZTlmMjcyZDQ2MEo7Cht0YXNrX2Zpbmdl
cnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0My4zMjI3NTVKOwoRYWdlbnRf
ZmluZ2VycHJpbnQSJgokY2IzZWQ2ZGQtNzEzNC00YTc3LThiMjctZWIwZGRkZGZlMjdiegIYAYUB
AAEAABKdAQoQ6S1CnqyOxKwRN/Vq7X81HRIIso7ugOmXnjEqClRvb2wgVXNhZ2UwATnAIk4/gys3
GEE4YlU/gys3GEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjExNC4wSigKCXRvb2xfbmFtZRIbChlE
ZWxlZ2F0ZSB3b3JrIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASlggKENaM
zYnzHCL03v+Ihe5ZidsSCIXobzKG03Z6KgxDcmV3IENyZWF0ZWQwATlQ8uM/gys3GEFIfOk/gys3
GEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjExNC4wShsKDnB5dGhvbl92ZXJzaW9uEgkKBzMuMTEu
MTJKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4MGE1ZDk3ZGMzODczYjE0ODI1Y2NmYTNKMQoHY3Jl
d19pZBImCiQ5ZmYzZmU1ZC01YmYyLTRlNzEtODU0ZS05OTAyZGYxYzIxYTRKHAoMY3Jld19wcm9j
ZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rh
c2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSjoKEGNyZXdfZmluZ2VycHJpbnQS
JgokOTkwOTQ1YmUtOTczMS00ZTQxLTg5ZDAtYzEzMjljNGQ3NjQ5SjsKG2NyZXdfZmluZ2VycHJp
bnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjM0MTIyM0rNAgoLY3Jld19hZ2Vu
dHMSvQIKugJbeyJrZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQiLCAiaWQi
OiAiMGM3NDhlNDgtOGNmNC00ZDJhLWFlYWMtZDY5OTUzMDkwZThmIiwgInJvbGUiOiAiU2NvcmVy
IiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDI1LCAibWF4X3JwbSI6IG51bGwsICJm
dW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRp
b25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4
X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUr7AQoKY3Jld190YXNrcxLsAQrp
AVt7ImtleSI6ICIyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NiIsICJpZCI6ICI2NzBj
MjdhOS1kYTc3LTRhNTQtYmYxYS1mM2M0YjVlNTcwNDkiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZh
bHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIlNjb3JlciIsICJhZ2Vu
dF9rZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQiLCAidG9vbHNfbmFtZXMi
OiBbXX1degIYAYUBAAEAABKABAoQ0PunZB/jswUd8i8ahTz20BIIFtRhrWbDsGIqDFRhc2sgQ3Jl
YXRlZDABOejM8z+DKzcYQZAu9D+DKzcYSi4KCGNyZXdfa2V5EiIKIDVlNmVmZmU2ODBhNWQ5N2Rj
Mzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokOWZmM2ZlNWQtNWJmMi00ZTcxLTg1NGUtOTkw
MmRmMWMyMWE0Si4KCHRhc2tfa2V5EiIKIDI3ZWYzOGNjOTlkYTRhOGRlZDcwZWQ0MDZlNDRhYjg2
SjEKB3Rhc2tfaWQSJgokNjcwYzI3YTktZGE3Ny00YTU0LWJmMWEtZjNjNGI1ZTU3MDQ5SjoKEGNy
ZXdfZmluZ2VycHJpbnQSJgokOTkwOTQ1YmUtOTczMS00ZTQxLTg5ZDAtYzEzMjljNGQ3NjQ5SjoK
EHRhc2tfZmluZ2VycHJpbnQSJgokMjczZmM3YjYtZGJmYS00MzYyLWEwZTEtNzhhNjJjNDY0OTlh
SjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjM0
MTE5NUo7ChFhZ2VudF9maW5nZXJwcmludBImCiQwNTc3MWI4Ny04ZGIzLTRhZGYtOWJhZC0yNzcw
ZjgzYTZiYTN6AhgBhQEAAQAAEpgIChA5RacttE9X5amPuTPHLuYDEgiZ/RIthMTU5yoMQ3JldyBD
cmVhdGVkMAE5EC+lQIMrNxhBsJGsQIMrNxhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMTQuMEob
Cg5weXRob25fdmVyc2lvbhIJCgczLjExLjEySi4KCGNyZXdfa2V5EiIKIDVlNmVmZmU2ODBhNWQ5
N2RjMzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokMTc5MzYxNTItNDJmMi00YmY3LWIzOTEt
ZTU0MDU1ZTY2NGU4Sh4KDGNyZXdfcHJvY2VzcxIOCgxoaWVyYXJjaGljYWxKEQoLY3Jld19tZW1v
cnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2Vu
dHMSAhgBSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokNjI0ZTI1NjEtMDFkOC00YmNkLWJhMjEtZDcx
ZTQ0MTZkNGJiSjsKG2NyZXdfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0LTE3VDE0
OjMzOjQzLjM1Mzg3M0rNAgoLY3Jld19hZ2VudHMSvQIKugJbeyJrZXkiOiAiOTJlN2ViMTkxNjY0
YzkzNTc4NWVkN2Q0MjQwYTI5NGQiLCAiaWQiOiAiYTEyMTFiNmYtMzFhMy00MzY4LWI5YzItZDNh
NjA1NTZlOTk2IiwgInJvbGUiOiAiU2NvcmVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRl
ciI6IDI1LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxt
IjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2Nv
ZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVz
IjogW119XUr7AQoKY3Jld190YXNrcxLsAQrpAVt7ImtleSI6ICIyN2VmMzhjYzk5ZGE0YThkZWQ3
MGVkNDA2ZTQ0YWI4NiIsICJpZCI6ICI3ZjJjNGIxMi00MjNhLTRmMTctOTZiMS0zZmEyNmUzMDM3
MmMiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJh
Z2VudF9yb2xlIjogIlNjb3JlciIsICJhZ2VudF9rZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVk
N2Q0MjQwYTI5NGQiLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQG2i2Mf2AK81I
gFDuyTZ4hxIIGTCH8bEW9REqDFRhc2sgQ3JlYXRlZDABOajZvECDKzcYQbArvUCDKzcYSi4KCGNy
ZXdfa2V5EiIKIDVlNmVmZmU2ODBhNWQ5N2RjMzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgok
MTc5MzYxNTItNDJmMi00YmY3LWIzOTEtZTU0MDU1ZTY2NGU4Si4KCHRhc2tfa2V5EiIKIDI3ZWYz
OGNjOTlkYTRhOGRlZDcwZWQ0MDZlNDRhYjg2SjEKB3Rhc2tfaWQSJgokN2YyYzRiMTItNDIzYS00
ZjE3LTk2YjEtM2ZhMjZlMzAzNzJjSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokNjI0ZTI1NjEtMDFk
OC00YmNkLWJhMjEtZDcxZTQ0MTZkNGJiSjoKEHRhc2tfZmluZ2VycHJpbnQSJgokZjViNmU5YjUt
ZjcxMi00YzM3LTkyYjAtMWFjNzQ2ZTYzYWJjSjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9h
dBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjM1Mzg0M0o7ChFhZ2VudF9maW5nZXJwcmludBImCiQ1
ZjhkM2YwYS1lODZhLTRiMmUtYWFmMC1jOWMyMDg2N2M1ODR6AhgBhQEAAQAAEpwBChBCoZs2F2Pk
GqD1dlo+B0jIEgh/8w+r7HLXDioKVG9vbCBVc2FnZTABOfhQHUGDKzcYQeChJUGDKzcYShsKDmNy
ZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKJwoJdG9vbF9uYW1lEhoKGEFzayBxdWVzdGlvbiB0byBj
b3dvcmtlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpYIChAtKHG1/6WFVXbuKiUU/tulEggA
5PFku/BBtSoMQ3JldyBDcmVhdGVkMAE5qOuzQYMrNxhBYNO5QYMrNxhKGwoOY3Jld2FpX3ZlcnNp
b24SCQoHMC4xMTQuMEobCg5weXRob25fdmVyc2lvbhIJCgczLjExLjEySi4KCGNyZXdfa2V5EiIK
IDVlNmVmZmU2ODBhNWQ5N2RjMzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokNWQzODQyMmQt
NTk2MC00NGQ0LWFmZjctYWM5MDFiMjU1NzM5ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFs
ShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19u
dW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJGZhNWYxODc1LWRiYTQt
NDc2MS04ZDk4LTliNzlmNDg2ZTNlY0o7ChtjcmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoa
MjAyNS0wNC0xN1QxNDozMzo0My4zNzE2MzZKzQIKC2NyZXdfYWdlbnRzEr0CCroCW3sia2V5Ijog
IjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgImlkIjogIjgwZDg1ZDY3LTg3M2Qt
NDFhNi05MzY1LWJkODVjYTc5MGI2MyIsICJyb2xlIjogIlNjb3JlciIsICJ2ZXJib3NlPyI6IGZh
bHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19s
bG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFs
c2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIs
ICJ0b29sc19uYW1lcyI6IFtdfV1K+wEKCmNyZXdfdGFza3MS7AEK6QFbeyJrZXkiOiAiMjdlZjM4
Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODYiLCAiaWQiOiAiZWYwNmQ3NTEtZWY2Yy00YjJiLWI2
MTQtMmVhMmU1NGM0MjVlIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0
PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJTY29yZXIiLCAiYWdlbnRfa2V5IjogIjkyZTdlYjE5
MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAAS
gAQKEJUYH+zYJdlQxAU/SEz07wwSCHIyR0YIxKoQKgxUYXNrIENyZWF0ZWQwATnYg8NBgys3GEFQ
7cNBgys3GEouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0ox
CgdjcmV3X2lkEiYKJDVkMzg0MjJkLTU5NjAtNDRkNC1hZmY3LWFjOTAxYjI1NTczOUouCgh0YXNr
X2tleRIiCiAyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0YXNrX2lkEiYKJGVm
MDZkNzUxLWVmNmMtNGIyYi1iNjE0LTJlYTJlNTRjNDI1ZUo6ChBjcmV3X2ZpbmdlcnByaW50EiYK
JGZhNWYxODc1LWRiYTQtNDc2MS04ZDk4LTliNzlmNDg2ZTNlY0o6ChB0YXNrX2ZpbmdlcnByaW50
EiYKJDA1ZTU2ZTIzLWI5YjgtNDIwMy05MWYwLTY2ZmE5MDgzNzYzNUo7Cht0YXNrX2ZpbmdlcnBy
aW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0My4zNzE2MDJKOwoRYWdlbnRfZmlu
Z2VycHJpbnQSJgokZGZiMDEzYTItNzg0MC00NDFhLTg1YzMtMzI0OWQ1OGJhNmIzegIYAYUBAAEA
ABKWCAoQ67KSQgBBFIpwJAjqKwKTNxIIPHptHAGKIGYqDENyZXcgQ3JlYXRlZDABOeB7T0KDKzcY
QVhEVUKDKzcYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKGwoOcHl0aG9uX3ZlcnNpb24S
CQoHMy4xMS4xMkouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2Zh
M0oxCgdjcmV3X2lkEiYKJDRmOTE0YWZhLTVlMTAtNDU3Ni1hYjJjLWVkZmNlZWQzYTZiYkocCgxj
cmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1i
ZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFKOgoQY3Jld19maW5n
ZXJwcmludBImCiQzODFkOTIwYi1iMGE1LTRiNGUtYTQ0OS1kZjg5OGNjZjVmZDdKOwobY3Jld19m
aW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIwMjUtMDQtMTdUMTQ6MzM6NDMuMzgxODc1Ss0CCgtj
cmV3X2FnZW50cxK9Agq6Alt7ImtleSI6ICI5MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0
ZCIsICJpZCI6ICI5ZjVhZTRmOC02MjkwLTQ5NTUtOGI2OC00YmNjOTM5ZjhhMDkiLCAicm9sZSI6
ICJTY29yZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJtYXhfcnBtIjog
bnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAi
ZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFs
c2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSvsBCgpjcmV3X3Rh
c2tzEuwBCukBW3sia2V5IjogIjI3ZWYzOGNjOTlkYTRhOGRlZDcwZWQ0MDZlNDRhYjg2IiwgImlk
IjogIjViODI1OWU3LWI2Y2YtNGJlYi1iYTRiLWY3MDg4Y2E4YWM3NiIsICJhc3luY19leGVjdXRp
b24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiU2NvcmVy
IiwgImFnZW50X2tleSI6ICI5MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJ0b29s
c19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChCDE114uxBCLFPLICeD1DCNEgiFJ3IambqX4yoM
VGFzayBDcmVhdGVkMAE5+P9iQoMrNxhBcGljQoMrNxhKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4
MGE1ZDk3ZGMzODczYjE0ODI1Y2NmYTNKMQoHY3Jld19pZBImCiQ0ZjkxNGFmYS01ZTEwLTQ1NzYt
YWIyYy1lZGZjZWVkM2E2YmJKLgoIdGFza19rZXkSIgogMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQw
NmU0NGFiODZKMQoHdGFza19pZBImCiQ1YjgyNTllNy1iNmNmLTRiZWItYmE0Yi1mNzA4OGNhOGFj
NzZKOgoQY3Jld19maW5nZXJwcmludBImCiQzODFkOTIwYi1iMGE1LTRiNGUtYTQ0OS1kZjg5OGNj
ZjVmZDdKOgoQdGFza19maW5nZXJwcmludBImCiRmZWIzZDVjYy0yMzEwLTRhNDgtOWQ5My1jMzQ5
MTI0MGU3NTlKOwobdGFza19maW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIwMjUtMDQtMTdUMTQ6
MzM6NDMuMzgxODQ4SjsKEWFnZW50X2ZpbmdlcnByaW50EiYKJDdhYzY3YTkzLTkwNjctNGJjNC1i
NmFmLTcxZWVjZmRjNzEzOHoCGAGFAQABAAASmAgKEGmCIFMw9GayxClAketnXWsSCPvb3mKDZYhn
KgxDcmV3IENyZWF0ZWQwATkA88JGgys3GEGAhMpGgys3GEobCg5jcmV3YWlfdmVyc2lvbhIJCgcw
LjExNC4wShsKDnB5dGhvbl92ZXJzaW9uEgkKBzMuMTEuMTJKLgoIY3Jld19rZXkSIgogNWU2ZWZm
ZTY4MGE1ZDk3ZGMzODczYjE0ODI1Y2NmYTNKMQoHY3Jld19pZBImCiRmNmE1MGVkMy02ODk5LTQ4
MTItODVkNy1iNDZlYTQyNzUwN2FKHgoMY3Jld19wcm9jZXNzEg4KDGhpZXJhcmNoaWNhbEoRCgtj
cmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVy
X29mX2FnZW50cxICGAFKOgoQY3Jld19maW5nZXJwcmludBImCiQzYzRlM2VmZS01YmQ0LTRkNDgt
YThmNS0yOGY0NDdhNDI0OGRKOwobY3Jld19maW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIwMjUt
MDQtMTdUMTQ6MzM6NDMuNDU2MDg4Ss0CCgtjcmV3X2FnZW50cxK9Agq6Alt7ImtleSI6ICI5MmU3
ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJpZCI6ICJmNzMwNTE0Mi1jOTViLTQ0MmQt
YjJiOS1jYTVhN2IzMzZlYjMiLCAicm9sZSI6ICJTY29yZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwg
Im1heF9pdGVyIjogMjUsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjog
IiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAi
YWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9v
bHNfbmFtZXMiOiBbXX1dSvsBCgpjcmV3X3Rhc2tzEuwBCukBW3sia2V5IjogIjI3ZWYzOGNjOTlk
YTRhOGRlZDcwZWQ0MDZlNDRhYjg2IiwgImlkIjogIjU5MDRiMDg5LTMzNzYtNDZhMy04NWU1LTRk
ZTc0NDQyYTljYyIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBm
YWxzZSwgImFnZW50X3JvbGUiOiAiU2NvcmVyIiwgImFnZW50X2tleSI6ICI5MmU3ZWIxOTE2NjRj
OTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChD9
DkCz0iVsHA4a1S3+yN8lEgjsMseCiYSvFioMVGFzayBDcmVhdGVkMAE5+ATcRoMrNxhB0F7cRoMr
NxhKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4MGE1ZDk3ZGMzODczYjE0ODI1Y2NmYTNKMQoHY3Jl
d19pZBImCiRmNmE1MGVkMy02ODk5LTQ4MTItODVkNy1iNDZlYTQyNzUwN2FKLgoIdGFza19rZXkS
IgogMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFza19pZBImCiQ1OTA0YjA4
OS0zMzc2LTQ2YTMtODVlNS00ZGU3NDQ0MmE5Y2NKOgoQY3Jld19maW5nZXJwcmludBImCiQzYzRl
M2VmZS01YmQ0LTRkNDgtYThmNS0yOGY0NDdhNDI0OGRKOgoQdGFza19maW5nZXJwcmludBImCiQ3
MjExMmY3OS1iMWU3LTRkYTctYTg4YS00NjU3NTJiZTIwZDdKOwobdGFza19maW5nZXJwcmludF9j
cmVhdGVkX2F0EhwKGjIwMjUtMDQtMTdUMTQ6MzM6NDMuNDU2MDU5SjsKEWFnZW50X2ZpbmdlcnBy
aW50EiYKJGJiMzQ0NzIxLTE3M2QtNGRmNS1iMWRmLWQ2NjBkZjZlZmVjZnoCGAGFAQABAAASnAEK
EOg/b+TBCd7kQOaEdNwvgZoSCGYJctohLuuaKgpUb29sIFVzYWdlMAE58JA0R4MrNxhBqOM9R4Mr
NxhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMTQuMEonCgl0b29sX25hbWUSGgoYQXNrIHF1ZXN0
aW9uIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASlwoKEMn/aYwi4Jc7AohP
Y7puRXsSCB83OjVnCZfLKgxDcmV3IENyZWF0ZWQwATlw8dVHgys3GEGA9NtHgys3GEobCg5jcmV3
YWlfdmVyc2lvbhIJCgcwLjExNC4wShsKDnB5dGhvbl92ZXJzaW9uEgkKBzMuMTEuMTJKLgoIY3Jl
d19rZXkSIgogZDQyNjA4MzNhYjBjMjBiYjQ0OTIyYzc5OWFhOTZiNGFKMQoHY3Jld19pZBImCiQx
ZjA0NjU0YS05ODE5LTQ0MTEtOTVlZC1kMmMwMTJlNWU3YjJKHAoMY3Jld19wcm9jZXNzEgwKCnNl
cXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAkob
ChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokYjhhYjU0
YzEtYjFjZS00OGIyLTlkODMtNDVkNzkyMTkxOWQ0SjsKG2NyZXdfZmluZ2VycHJpbnRfY3JlYXRl
ZF9hdBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjQ3NDIyN0rlAgoLY3Jld19hZ2VudHMS1QIK0gJb
eyJrZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQiLCAiaWQiOiAiMjg5YzIz
NzgtNWUxOC00YzJiLWE1NDMtNzVkOTk5YWUyYWQyIiwgInJvbGUiOiAiU2NvcmVyIiwgInZlcmJv
c2U/IjogdHJ1ZSwgIm1heF9pdGVyIjogMjUsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2Nh
bGxpbmdfbGxtIjogImdwdC0zLjUtdHVyYm8tMDEyNSIsICJsbG0iOiAiZ3B0LTQtMDEyNS1wcmV2
aWV3IiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9u
PyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUrkAwoK
Y3Jld190YXNrcxLVAwrSA1t7ImtleSI6ICIyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4
NiIsICJpZCI6ICJiNTAxMWUwNi02YTdmLTQzYWItYWQzNy1mNGI4ODBhMmJlYjgiLCAiYXN5bmNf
ZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjog
IlNjb3JlciIsICJhZ2VudF9rZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQi
LCAidG9vbHNfbmFtZXMiOiBbXX0sIHsia2V5IjogIjYwOWRlZTM5MTA4OGNkMWM4N2I4ZmE2NmFh
NjdhZGJlIiwgImlkIjogIjRiODE5NjQ5LTYyMjQtNGQ3Mi1hZDFkLTM0ODZhYzBkODQwNSIsICJh
c3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3Jv
bGUiOiAiU2NvcmVyIiwgImFnZW50X2tleSI6ICI5MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBh
Mjk0ZCIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChCdiwcYoV5twj//vpjaNfMl
EghUv7y5H7+dXioMVGFzayBDcmVhdGVkMAE5wN3kR4MrNxhBsDPlR4MrNxhKLgoIY3Jld19rZXkS
IgogZDQyNjA4MzNhYjBjMjBiYjQ0OTIyYzc5OWFhOTZiNGFKMQoHY3Jld19pZBImCiQxZjA0NjU0
YS05ODE5LTQ0MTEtOTVlZC1kMmMwMTJlNWU3YjJKLgoIdGFza19rZXkSIgogMjdlZjM4Y2M5OWRh
NGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFza19pZBImCiRiNTAxMWUwNi02YTdmLTQzYWItYWQz
Ny1mNGI4ODBhMmJlYjhKOgoQY3Jld19maW5nZXJwcmludBImCiRiOGFiNTRjMS1iMWNlLTQ4YjIt
OWQ4My00NWQ3OTIxOTE5ZDRKOgoQdGFza19maW5nZXJwcmludBImCiQ3NDcyMTM3Yi0wYzBkLTRi
OTEtYTgwYy01YzZkYWQwZmM3YTBKOwobdGFza19maW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIw
MjUtMDQtMTdUMTQ6MzM6NDMuNDc0MTc1SjsKEWFnZW50X2ZpbmdlcnByaW50EiYKJDVlMWU1Nzdh
LWY5N2QtNDA2OS04NzNmLTc1ZjYyMDE0ZWJlNnoCGAGFAQABAAASgAQKEA6OsjCwXi+o2MUfKyS+
TmgSCOIWlM7TtxNCKgxUYXNrIENyZWF0ZWQwATmQ915Igys3GEHYaF9Igys3GEouCghjcmV3X2tl
eRIiCiBkNDI2MDgzM2FiMGMyMGJiNDQ5MjJjNzk5YWE5NmI0YUoxCgdjcmV3X2lkEiYKJDFmMDQ2
NTRhLTk4MTktNDQxMS05NWVkLWQyYzAxMmU1ZTdiMkouCgh0YXNrX2tleRIiCiA2MDlkZWUzOTEw
ODhjZDFjODdiOGZhNjZhYTY3YWRiZUoxCgd0YXNrX2lkEiYKJDRiODE5NjQ5LTYyMjQtNGQ3Mi1h
ZDFkLTM0ODZhYzBkODQwNUo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJGI4YWI1NGMxLWIxY2UtNDhi
Mi05ZDgzLTQ1ZDc5MjE5MTlkNEo6ChB0YXNrX2ZpbmdlcnByaW50EiYKJGYwZWUxMjY2LWExNzIt
NDhiMi1iMTM2LTczN2I3YWNkYWYwNko7Cht0YXNrX2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoa
MjAyNS0wNC0xN1QxNDozMzo0My40NzQyMDVKOwoRYWdlbnRfZmluZ2VycHJpbnQSJgokNWUxZTU3
N2EtZjk3ZC00MDY5LTg3M2YtNzVmNjIwMTRlYmU2egIYAYUBAAEAABL/CQoQOon8z16iVXeCtEnr
visR+hII1ztFvfUBPyAqDENyZXcgQ3JlYXRlZDABOYC2CUmDKzcYQVhjEUmDKzcYShsKDmNyZXdh
aV92ZXJzaW9uEgkKBzAuMTE0LjBKGwoOcHl0aG9uX3ZlcnNpb24SCQoHMy4xMS4xMkouCghjcmV3
X2tleRIiCiBhOTU0MGNkMGVhYTUzZjY3NTQzN2U5YmQ0ZmE1ZTQ0Y0oxCgdjcmV3X2lkEiYKJDFh
MDA5NjZhLTcwYmQtNDc4OS1hZmQxLTY5NjgzMzZjYjc2NkocCgxjcmV3X3Byb2Nlc3MSDAoKc2Vx
dWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgCShsK
FWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFKOgoQY3Jld19maW5nZXJwcmludBImCiRjOGI1ZDUx
My0xNzY0LTQyYWQtOGVlYS0wYWU0MDAzZTRmNTRKOwobY3Jld19maW5nZXJwcmludF9jcmVhdGVk
X2F0EhwKGjIwMjUtMDQtMTdUMTQ6MzM6NDMuNDk0ODMySs0CCgtjcmV3X2FnZW50cxK9Agq6Alt7
ImtleSI6ICI5MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJpZCI6ICIwZTg1MzFl
YS05MmM4LTQzMGQtYmE0Yy1jMmIxYzkwZDBlMWQiLCAicm9sZSI6ICJTY29yZXIiLCAidmVyYm9z
ZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2Nh
bGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVk
PyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGlt
aXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSuQDCgpjcmV3X3Rhc2tzEtUDCtIDW3sia2V5Ijog
IjI3ZWYzOGNjOTlkYTRhOGRlZDcwZWQ0MDZlNDRhYjg2IiwgImlkIjogImI2NWQ1ZGUzLWY5MjAt
NDVhZi1hOTgwLTA2NjBkMDU5YzdiZiIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1h
bl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiU2NvcmVyIiwgImFnZW50X2tleSI6ICI5
MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJr
ZXkiOiAiYjBkMzRhNmY2MjFhN2IzNTgwZDVkMWY0ZTI2NjViOTIiLCAiaWQiOiAiZjk2MDU5NzMt
YzYyMi00NzRjLWFhZjktYWJiOWMwZWZhYmQ0IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwg
Imh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJTY29yZXIiLCAiYWdlbnRfa2V5
IjogIjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgInRvb2xzX25hbWVzIjogW119
XXoCGAGFAQABAAASgAQKEGysuSY/RpRwwsmMtZmmkLgSCB3RCKVN5vMGKgxUYXNrIENyZWF0ZWQw
ATmYyRpJgys3GEFwIxtJgys3GEouCghjcmV3X2tleRIiCiBhOTU0MGNkMGVhYTUzZjY3NTQzN2U5
YmQ0ZmE1ZTQ0Y0oxCgdjcmV3X2lkEiYKJDFhMDA5NjZhLTcwYmQtNDc4OS1hZmQxLTY5NjgzMzZj
Yjc2NkouCgh0YXNrX2tleRIiCiAyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0
YXNrX2lkEiYKJGI2NWQ1ZGUzLWY5MjAtNDVhZi1hOTgwLTA2NjBkMDU5YzdiZko6ChBjcmV3X2Zp
bmdlcnByaW50EiYKJGM4YjVkNTEzLTE3NjQtNDJhZC04ZWVhLTBhZTQwMDNlNGY1NEo6ChB0YXNr
X2ZpbmdlcnByaW50EiYKJDZjNDhlMTkxLTViMjEtNDBmNi1iNmQwLWRjMWY3ZmM2YWQzN0o7Cht0
YXNrX2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0My40OTQ3NzdK
OwoRYWdlbnRfZmluZ2VycHJpbnQSJgokNTZmYTQ1MTYtM2RiNS00Mjk3LTg3NzUtOTI2MWVhNWI4
OWI2egIYAYUBAAEAABKABAoQJRURFvAOz5/5e2bQNRT4ChIIpSiy2tnBCrsqDFRhc2sgQ3JlYXRl
ZDABOdgreEmDKzcYQSCdeEmDKzcYSi4KCGNyZXdfa2V5EiIKIGE5NTQwY2QwZWFhNTNmNjc1NDM3
ZTliZDRmYTVlNDRjSjEKB2NyZXdfaWQSJgokMWEwMDk2NmEtNzBiZC00Nzg5LWFmZDEtNjk2ODMz
NmNiNzY2Si4KCHRhc2tfa2V5EiIKIGIwZDM0YTZmNjIxYTdiMzU4MGQ1ZDFmNGUyNjY1YjkySjEK
B3Rhc2tfaWQSJgokZjk2MDU5NzMtYzYyMi00NzRjLWFhZjktYWJiOWMwZWZhYmQ0SjoKEGNyZXdf
ZmluZ2VycHJpbnQSJgokYzhiNWQ1MTMtMTc2NC00MmFkLThlZWEtMGFlNDAwM2U0ZjU0SjoKEHRh
c2tfZmluZ2VycHJpbnQSJgokMWI0YzI5NTYtMDZkOC00NWNjLWFmYWMtNmZhZDk0MzdkNTZmSjsK
G3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjQ5NDgw
OEo7ChFhZ2VudF9maW5nZXJwcmludBImCiQ1NmZhNDUxNi0zZGI1LTQyOTctODc3NS05MjYxZWE1
Yjg5YjZ6AhgBhQEAAQAAEpYIChCt1KD2VBrK6+JIjPGbSQYWEghyEaRdKejivSoMQ3JldyBDcmVh
dGVkMAE54Fn7SYMrNxhBMPkBSoMrNxhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMTQuMEobCg5w
eXRob25fdmVyc2lvbhIJCgczLjExLjEySi4KCGNyZXdfa2V5EiIKIDVlNmVmZmU2ODBhNWQ5N2Rj
Mzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokMDQ4ZDQ5MzctNmU3OC00OWFkLTllZDMtYzVi
MjdlNDgyNThlShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQ
AEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIY
AUo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJDIxYjViOWQ3LWVjNTktNDBhYi1iZjY1LTk1NzM2M2Fl
ZDRkZEo7ChtjcmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0
My41MTA0NjZKzQIKC2NyZXdfYWdlbnRzEr0CCroCW3sia2V5IjogIjkyZTdlYjE5MTY2NGM5MzU3
ODVlZDdkNDI0MGEyOTRkIiwgImlkIjogImFkN2ExMTJiLWY5NDQtNDViYy05YzE4LWJjOWQzMDE4
NjE1OCIsICJyb2xlIjogIlNjb3JlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAy
NSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJn
cHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4
ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtd
fV1K+wEKCmNyZXdfdGFza3MS7AEK6QFbeyJrZXkiOiAiMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQw
NmU0NGFiODYiLCAiaWQiOiAiZTJmMDI3YzItZWQ2NC00MDU4LThkNzUtNjQ1OWMzYTllYWIwIiwg
ImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRf
cm9sZSI6ICJTY29yZXIiLCAiYWdlbnRfa2V5IjogIjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0
MGEyOTRkIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASgAQKELdQRmZyaC0pfEDI4tAa
vRsSCCE13pISM1wEKgxUYXNrIENyZWF0ZWQwATmwBwpKgys3GEG4WQpKgys3GEouCghjcmV3X2tl
eRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0oxCgdjcmV3X2lkEiYKJDA0OGQ0
OTM3LTZlNzgtNDlhZC05ZWQzLWM1YjI3ZTQ4MjU4ZUouCgh0YXNrX2tleRIiCiAyN2VmMzhjYzk5
ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0YXNrX2lkEiYKJGUyZjAyN2MyLWVkNjQtNDA1OC04
ZDc1LTY0NTljM2E5ZWFiMEo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJDIxYjViOWQ3LWVjNTktNDBh
Yi1iZjY1LTk1NzM2M2FlZDRkZEo6ChB0YXNrX2ZpbmdlcnByaW50EiYKJDNmMDU4NDE1LTNkNzUt
NDZhNi05OWFjLTIyZmM5OWM4OTBmM0o7Cht0YXNrX2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoa
MjAyNS0wNC0xN1QxNDozMzo0My41MTA0NDBKOwoRYWdlbnRfZmluZ2VycHJpbnQSJgokMjViMTgx
NjYtYjk3My00ZDM3LWI0OTUtMTI4YmIyMzQyNjhmegIYAYUBAAEAABKWCAoQuKzLEfp7NclRHh6f
Sm2/nxIIucJxIhUlkkwqDENyZXcgQ3JlYXRlZDABOfDOa0qDKzcYQfh/cUqDKzcYShsKDmNyZXdh
aV92ZXJzaW9uEgkKBzAuMTE0LjBKGwoOcHl0aG9uX3ZlcnNpb24SCQoHMy4xMS4xMkouCghjcmV3
X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0oxCgdjcmV3X2lkEiYKJDhl
YzE2ZWQ3LTNiYjItNDkxZC04YjYxLTI3MWYxNmZlOGFlMUocCgxjcmV3X3Byb2Nlc3MSDAoKc2Vx
dWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsK
FWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFKOgoQY3Jld19maW5nZXJwcmludBImCiQxN2MxN2Qz
NC1mZWZkLTQ1ZTktYWM2NS00ODY2ZTBlNTgwYTBKOwobY3Jld19maW5nZXJwcmludF9jcmVhdGVk
X2F0EhwKGjIwMjUtMDQtMTdUMTQ6MzM6NDMuNTE4MDI0Ss0CCgtjcmV3X2FnZW50cxK9Agq6Alt7
ImtleSI6ICI5MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJpZCI6ICJhODk2OTRm
ZS1lNjE1LTQzOWItOTQ4MC02MmVmZTRiNGY4ODUiLCAicm9sZSI6ICJTY29yZXIiLCAidmVyYm9z
ZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2Nh
bGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVk
PyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGlt
aXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSvsBCgpjcmV3X3Rhc2tzEuwBCukBW3sia2V5Ijog
IjI3ZWYzOGNjOTlkYTRhOGRlZDcwZWQ0MDZlNDRhYjg2IiwgImlkIjogIjMwYjNmYmQ4LWM0MmMt
NDhlYi1hNDdlLTAzNzFlOTFmYTAxYiIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1h
bl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiU2NvcmVyIiwgImFnZW50X2tleSI6ICI5
MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgB
hQEAAQAAEoAEChBSqrS4nl90w/7Z/EGzEvYpEgj54GNjf+XWQyoMVGFzayBDcmVhdGVkMAE5GJ55
SoMrNxhBOOx5SoMrNxhKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4MGE1ZDk3ZGMzODczYjE0ODI1
Y2NmYTNKMQoHY3Jld19pZBImCiQ4ZWMxNmVkNy0zYmIyLTQ5MWQtOGI2MS0yNzFmMTZmZThhZTFK
LgoIdGFza19rZXkSIgogMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFza19p
ZBImCiQzMGIzZmJkOC1jNDJjLTQ4ZWItYTQ3ZS0wMzcxZTkxZmEwMWJKOgoQY3Jld19maW5nZXJw
cmludBImCiQxN2MxN2QzNC1mZWZkLTQ1ZTktYWM2NS00ODY2ZTBlNTgwYTBKOgoQdGFza19maW5n
ZXJwcmludBImCiQ5MGYyODZhZC1lOWQ4LTRkOWUtYjA5MC05YTQyY2I3ZjYzNDhKOwobdGFza19m
aW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIwMjUtMDQtMTdUMTQ6MzM6NDMuNTE3OTk4SjsKEWFn
ZW50X2ZpbmdlcnByaW50EiYKJDhhMTliOTQxLWI4MTgtNDU3MC05NmJjLWZlYWQ4MWNkMjk1NXoC
GAGFAQABAAASlggKEFFBQgm1QyQTSqKMpRKbGjwSCCoFcjlB3aOLKgxDcmV3IENyZWF0ZWQwATlY
/RVLgys3GEEwLR1Lgys3GEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjExNC4wShsKDnB5dGhvbl92
ZXJzaW9uEgkKBzMuMTEuMTJKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4MGE1ZDk3ZGMzODczYjE0
ODI1Y2NmYTNKMQoHY3Jld19pZBImCiQ5NDYyMGE5YS1jMjc1LTRjMjItYjk1OC0zZmZlYWRiOGFl
ZGJKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNy
ZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSjoKEGNy
ZXdfZmluZ2VycHJpbnQSJgokNzQzZDgxNDYtZTM0My00Njk0LTljODUtMmVmZWRkMzZhYTlkSjsK
G2NyZXdfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjUyOTAz
MkrNAgoLY3Jld19hZ2VudHMSvQIKugJbeyJrZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0
MjQwYTI5NGQiLCAiaWQiOiAiZWE5NTMyZDktZDczNy00ZTIyLWE3MjItMDg2ODQ4NGViMmY5Iiwg
InJvbGUiOiAiU2NvcmVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDI1LCAibWF4
X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1t
aW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9u
PyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUr7AQoK
Y3Jld190YXNrcxLsAQrpAVt7ImtleSI6ICIyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4
NiIsICJpZCI6ICIyMmUyMjZiNC1kNmI5LTRiMzgtOTQwMi05NDY0NTBhOWExZjUiLCAiYXN5bmNf
ZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjog
IlNjb3JlciIsICJhZ2VudF9rZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQi
LCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQBNXlZK0H3tATZKP2Uw7bBxII0nvw
9UluHcgqDFRhc2sgQ3JlYXRlZDABOXhiJ0uDKzcYQZiwJ0uDKzcYSi4KCGNyZXdfa2V5EiIKIDVl
NmVmZmU2ODBhNWQ5N2RjMzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokOTQ2MjBhOWEtYzI3
NS00YzIyLWI5NTgtM2ZmZWFkYjhhZWRiSi4KCHRhc2tfa2V5EiIKIDI3ZWYzOGNjOTlkYTRhOGRl
ZDcwZWQ0MDZlNDRhYjg2SjEKB3Rhc2tfaWQSJgokMjJlMjI2YjQtZDZiOS00YjM4LTk0MDItOTQ2
NDUwYTlhMWY1SjoKEGNyZXdfZmluZ2VycHJpbnQSJgokNzQzZDgxNDYtZTM0My00Njk0LTljODUt
MmVmZWRkMzZhYTlkSjoKEHRhc2tfZmluZ2VycHJpbnQSJgokYjI3M2Q1OTMtYzcxZC00ZWRmLWI0
NmMtMTkyMmIxY2ZmZjY1SjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA0
LTE3VDE0OjMzOjQzLjUyOTAwMko7ChFhZ2VudF9maW5nZXJwcmludBImCiQ5ZWYxZjc4Ny1lZTIz
LTRlNGUtOGJkYi04NGJiNjkwZjlkZjV6AhgBhQEAAQAAEpYIChCLERZYyvqc04xX3gWXPO59EggU
L4MaGDu+FyoMQ3JldyBDcmVhdGVkMAE54NLGS4MrNxhBeGbNS4MrNxhKGwoOY3Jld2FpX3ZlcnNp
b24SCQoHMC4xMTQuMEobCg5weXRob25fdmVyc2lvbhIJCgczLjExLjEySi4KCGNyZXdfa2V5EiIK
IDVlNmVmZmU2ODBhNWQ5N2RjMzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokZWI4MDdlMzEt
MGFiZS00NjQ0LWEwZjEtMDM4N2ZkZTYzYWQ1ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFs
ShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19u
dW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJDBkZDRmNDNlLTEzNzEt
NDVlNS1iMGNmLWY2ZDE5YTNjNzZkOUo7ChtjcmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoa
MjAyNS0wNC0xN1QxNDozMzo0My41NDA2MzhKzQIKC2NyZXdfYWdlbnRzEr0CCroCW3sia2V5Ijog
IjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgImlkIjogImY0ZDM5NzdlLTg4YjAt
NDQ2Zi04YzQ5LThkMjc0NDgwOGQ4NiIsICJyb2xlIjogIlNjb3JlciIsICJ2ZXJib3NlPyI6IGZh
bHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19s
bG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFs
c2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIs
ICJ0b29sc19uYW1lcyI6IFtdfV1K+wEKCmNyZXdfdGFza3MS7AEK6QFbeyJrZXkiOiAiMjdlZjM4
Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODYiLCAiaWQiOiAiYjA4MTZmY2QtYjcyMS00YTZkLTk0
ODQtNDc4YWM4ZDdkYTg4IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0
PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJTY29yZXIiLCAiYWdlbnRfa2V5IjogIjkyZTdlYjE5
MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAAS
gAQKEB0emJtWTE8969Cle2pbw8QSCFZbdjoOT655KgxUYXNrIENyZWF0ZWQwATlgt9VLgys3GEFo
CdZLgys3GEouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0ox
CgdjcmV3X2lkEiYKJGViODA3ZTMxLTBhYmUtNDY0NC1hMGYxLTAzODdmZGU2M2FkNUouCgh0YXNr
X2tleRIiCiAyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0YXNrX2lkEiYKJGIw
ODE2ZmNkLWI3MjEtNGE2ZC05NDg0LTQ3OGFjOGQ3ZGE4OEo6ChBjcmV3X2ZpbmdlcnByaW50EiYK
JDBkZDRmNDNlLTEzNzEtNDVlNS1iMGNmLWY2ZDE5YTNjNzZkOUo6ChB0YXNrX2ZpbmdlcnByaW50
EiYKJGM1ODIyZGM4LWIyYmYtNDUyZS04YjQ2LWRkNjAyMDNkNTA0Zko7Cht0YXNrX2ZpbmdlcnBy
aW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0My41NDA2MDlKOwoRYWdlbnRfZmlu
Z2VycHJpbnQSJgokZjZhMjA0MDYtOTM0Yy00ZjVmLWI1MzMtMDYwMTQwMGUxMTM1egIYAYUBAAEA
ABL4BwoQxJQoNY/stf/qihFVNGkp1hII9x5mkc7Cz5AqDENyZXcgQ3JlYXRlZDABOcB+REyDKzcY
QYA7SkyDKzcYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjBKGwoOcHl0aG9uX3ZlcnNpb24S
CQoHMy4xMS4xMkouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2Zh
M0oxCgdjcmV3X2lkEiYKJDY3NmIxNjlhLTI5YTYtNDVhOC05NmNjLTY4MjMyNzgzYmU3NUoeCgxj
cmV3X3Byb2Nlc3MSDgoMaGllcmFyY2hpY2FsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251
bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3X2Zp
bmdlcnByaW50EiYKJDMzZDRkZWU1LWIxOTEtNDAzYy04OWEwLTYyNWJiNjVmMmYxOUo7ChtjcmV3
X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNC0xN1QxNDozMzo0My41NDg4OThKzQIK
C2NyZXdfYWdlbnRzEr0CCroCW3sia2V5IjogIjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEy
OTRkIiwgImlkIjogImE0Mzc1OWYyLTY0NDEtNDNiMy1hOGRjLWYxYmQzMTU3MDdlZiIsICJyb2xl
IjogIlNjb3JlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0i
OiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIs
ICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBm
YWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K2wEKCmNyZXdf
dGFza3MSzAEKyQFbeyJrZXkiOiAiMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODYiLCAi
aWQiOiAiMDVmYzk4OWItMDY5Mi00ODAzLTgyMTMtMWQ2ODY5YTYwMTBlIiwgImFzeW5jX2V4ZWN1
dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJOb25l
IiwgImFnZW50X2tleSI6IG51bGwsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChDT
QOB/rAOBZumhFuP0yYFYEggS6cvMoHzBYioMVGFzayBDcmVhdGVkMAE5cB9dTIMrNxhBeHFdTIMr
NxhKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4MGE1ZDk3ZGMzODczYjE0ODI1Y2NmYTNKMQoHY3Jl
d19pZBImCiQ2NzZiMTY5YS0yOWE2LTQ1YTgtOTZjYy02ODIzMjc4M2JlNzVKLgoIdGFza19rZXkS
IgogMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFza19pZBImCiQwNWZjOTg5
Yi0wNjkyLTQ4MDMtODIxMy0xZDY4NjlhNjAxMGVKOgoQY3Jld19maW5nZXJwcmludBImCiQzM2Q0
ZGVlNS1iMTkxLTQwM2MtODlhMC02MjViYjY1ZjJmMTlKOgoQdGFza19maW5nZXJwcmludBImCiQ2
MGIzYTVkNi04MWUxLTQzOGYtOTE3Yy0yNjU4MzU4NjdmNzZKOwobdGFza19maW5nZXJwcmludF9j
cmVhdGVkX2F0EhwKGjIwMjUtMDQtMTdUMTQ6MzM6NDMuNTQ4ODcwSjsKEWFnZW50X2ZpbmdlcnBy
aW50EiYKJDgwZjQ2NDkxLWM0YjItNDExNy05MTM2LTZhOTQxZjI5ODBiZHoCGAGFAQABAAASnAEK
EObnhSrs8UQiBg/0Bricu2cSCMFW2rX4WlIFKgpUb29sIFVzYWdlMAE5CJ26TIMrNxhBmE/DTIMr
NxhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMTQuMEonCgl0b29sX25hbWUSGgoYQXNrIHF1ZXN0
aW9uIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAAS0AoKEBk04hfXjSFQOWWK
xJFMHB8SCLGFr6R51/OhKgxDcmV3IENyZWF0ZWQwATl4TzNNgys3GEFIMzlNgys3GEobCg5jcmV3
YWlfdmVyc2lvbhIJCgcwLjExNC4wShsKDnB5dGhvbl92ZXJzaW9uEgkKBzMuMTEuMTJKLgoIY3Jl
d19rZXkSIgogNzQyNzU3MzEyZWY3YmI0ZWUwYjA2NjJkMWMyZTIxNzlKMQoHY3Jld19pZBImCiQ2
MWRiMTdjYi0xODQ3LTRmYzktOWNkMy1hMDY3ZjRkOGExMzRKHAoMY3Jld19wcm9jZXNzEgwKCnNl
cXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUob
ChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokNjQ3OGY2
MjItZGVlOC00OWYyLTljMDktOGNiOTBjMjEwYzNjSjsKG2NyZXdfZmluZ2VycHJpbnRfY3JlYXRl
ZF9hdBIcChoyMDI1LTA0LTE3VDE0OjMzOjQzLjU2NDI2NEqGBQoLY3Jld19hZ2VudHMS9gQK8wRb
eyJrZXkiOiAiODljZjMxMWI0OGI1MjE2OWQ0MmYzOTI1YzViZTFjNWEiLCAiaWQiOiAiM2E3YjUx
ZGItYzhhZC00ZDU3LWE1OGUtOGIzY2EyYzIxZTI2IiwgInJvbGUiOiAiTWFuYWdlciIsICJ2ZXJi
b3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25f
Y2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJs
ZWQ/IjogdHJ1ZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xp
bWl0IjogMiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICI5MmU3ZWIxOTE2NjRjOTM1Nzg1
ZWQ3ZDQyNDBhMjk0ZCIsICJpZCI6ICIxNWZiMjExOC0zOTE0LTQ2ZTctODRkZi05M2E5ZDA0ZWVj
M2YiLCAicm9sZSI6ICJTY29yZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUs
ICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0
LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IHRydWUsICJhbGxvd19jb2RlX2V4ZWN1
dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K
/AEKCmNyZXdfdGFza3MS7QEK6gFbeyJrZXkiOiAiMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0
NGFiODYiLCAiaWQiOiAiMzcwNTE2YzQtNWNhMC00NDBjLWE3YTctNWFhMjZiMDQ4MmFmIiwgImFz
eW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9s
ZSI6ICJNYW5hZ2VyIiwgImFnZW50X2tleSI6ICI4OWNmMzExYjQ4YjUyMTY5ZDQyZjM5MjVjNWJl
MWM1YSIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEoAEChBGCATWQjaQu6Zpx66QI8ik
Egg05IWKCa/6oyoMVGFzayBDcmVhdGVkMAE54CVFTYMrNxhB0HtFTYMrNxhKLgoIY3Jld19rZXkS
IgogNzQyNzU3MzEyZWY3YmI0ZWUwYjA2NjJkMWMyZTIxNzlKMQoHY3Jld19pZBImCiQ2MWRiMTdj
Yi0xODQ3LTRmYzktOWNkMy1hMDY3ZjRkOGExMzRKLgoIdGFza19rZXkSIgogMjdlZjM4Y2M5OWRh
NGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFza19pZBImCiQzNzA1MTZjNC01Y2EwLTQ0MGMtYTdh
Ny01YWEyNmIwNDgyYWZKOgoQY3Jld19maW5nZXJwcmludBImCiQ2NDc4ZjYyMi1kZWU4LTQ5ZjIt
OWMwOS04Y2I5MGMyMTBjM2NKOgoQdGFza19maW5nZXJwcmludBImCiQxMWU1ZDRhNi04ODc5LTQx
ZDktYWE3ZS04OTdhNDMzMDhlZWVKOwobdGFza19maW5nZXJwcmludF9jcmVhdGVkX2F0EhwKGjIw
MjUtMDQtMTdUMTQ6MzM6NDMuNTY0MjMzSjsKEWFnZW50X2ZpbmdlcnByaW50EiYKJGUyMzRlYzA5
LTk3MzktNGE3Zi04MDgxLTBhNjJkYzNlNzY1ZHoCGAGFAQABAAASnQEKEFjGvzVUde99Ey+6qDaD
oG4SCFWLiXG8McaKKgpUb29sIFVzYWdlMAE5kI2lTYMrNxhBMG2tTYMrNxhKGwoOY3Jld2FpX3Zl
cnNpb24SCQoHMC4xMTQuMEooCgl0b29sX25hbWUSGwoZRGVsZWdhdGUgd29yayB0byBjb3dvcmtl
ckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEooIChCB+QR8dk6jPImbeJiKh5UYEgj00bY0zkAX
LSoMQ3JldyBDcmVhdGVkMAE5cAkrToMrNxhBKNM1ToMrNxhKGwoOY3Jld2FpX3ZlcnNpb24SCQoH
MC4xMTQuMEobCg5weXRob25fdmVyc2lvbhIJCgczLjExLjEySi4KCGNyZXdfa2V5EiIKIDMwM2I4
ZWRkNWIwMDg3MTBkNzZhYWY4MjVhNzA5ZTU1SjEKB2NyZXdfaWQSJgokNmUzM2ZiOTItNTZjMC00
OTY3LTk1MjItZGQ3ZWFhOWY5NjFlSh4KDGNyZXdfcHJvY2VzcxIOCgxoaWVyYXJjaGljYWxKEQoL
Y3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJl
cl9vZl9hZ2VudHMSAhgBSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokNDY5MjUyODctOTY2OS00MTRl
LWEwNzctZGVjNDE2ZTE3NDRlSjsKG2NyZXdfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1
LTA0LTE3VDE0OjMzOjQzLjU4MDUyM0rfAgoLY3Jld19hZ2VudHMSzwIKzAJbeyJrZXkiOiAiOTJl
N2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQiLCAiaWQiOiAiNzllZTU5MjktNjdlMy00NjNi
LTljYjEtMjFlNTdjNjZlNGQ4IiwgInJvbGUiOiAiU2NvcmVyIiwgInZlcmJvc2U/IjogZmFsc2Us
ICJtYXhfaXRlciI6IDI1LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6
ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwg
ImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRv
b2xzX25hbWVzIjogWyJzY29yaW5nX2V4YW1wbGVzIl19XUrbAQoKY3Jld190YXNrcxLMAQrJAVt7
ImtleSI6ICJmMzU3NWIwMTNjMjI5NGI3Y2M4ZTgwMzE1NWM4YmE0NiIsICJpZCI6ICJhZTlmMjgz
MC1hY2NhLTRiNmQtOGRjNy01MjMzZmZlYmJhM2QiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNl
LCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIk5vbmUiLCAiYWdlbnRfa2V5
IjogbnVsbCwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASgAQKEHOf6gKzlTQXpW3qTaF+
AlQSCIXd9+wt3hyiKgxUYXNrIENyZWF0ZWQwATkws0hOgys3GEE4BUlOgys3GEouCghjcmV3X2tl
eRIiCiAzMDNiOGVkZDViMDA4NzEwZDc2YWFmODI1YTcwOWU1NUoxCgdjcmV3X2lkEiYKJDZlMzNm
YjkyLTU2YzAtNDk2Ny05NTIyLWRkN2VhYTlmOTYxZUouCgh0YXNrX2tleRIiCiBmMzU3NWIwMTNj
MjI5NGI3Y2M4ZTgwMzE1NWM4YmE0NkoxCgd0YXNrX2lkEiYKJGFlOWYyODMwLWFjY2EtNGI2ZC04
ZGM3LTUyMzNmZmViYmEzZEo6ChBjcmV3X2ZpbmdlcnByaW50EiYKJDQ2OTI1Mjg3LTk2NjktNDE0
ZS1hMDc3LWRlYzQxNmUxNzQ0ZUo6ChB0YXNrX2ZpbmdlcnByaW50EiYKJDU4ZGVjODNjLWFjZTQt
NGI1Ni05YzhjLWQyZGQ1YjVlMWYyNUo7Cht0YXNrX2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoa
MjAyNS0wNC0xN1QxNDozMzo0My41ODA0OTNKOwoRYWdlbnRfZmluZ2VycHJpbnQSJgokMGVjNzAw
NWEtOGMzOC00N2RlLWI5YzctNjc3ZmFkOTU2ZmMzegIYAYUBAAEAABJpChDdogUTH/ocvPeyU/F2
dgcNEghEqOA/7aEsiyoQVG9vbCBVc2FnZSBFcnJvcjABOVBbt06DKzcYQajPvU6DKzcYShsKDmNy
ZXdhaV92ZXJzaW9uEgkKBzAuMTE0LjB6AhgBhQEAAQAAEp0BChD7kRw1jX3K2nusXZXPvHyGEghl
QFQp8mFhuCoKVG9vbCBVc2FnZTABORCS/E6DKzcYQXDPBE+DKzcYShsKDmNyZXdhaV92ZXJzaW9u
EgkKBzAuMTE0LjBKKAoJdG9vbF9uYW1lEhsKGURlbGVnYXRlIHdvcmsgdG8gY293b3JrZXJKDgoI
YXR0ZW1wdHMSAhgBegIYAYUBAAEAAA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '27952'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.31.1
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Thu, 17 Apr 2025 17:33:47 GMT
status:
code: 200
message: OK
version: 1

81
tests/cassettes/test_task_with_max_execution_time_exceeded.yaml Normal file
View File

@@ -0,0 +1,81 @@
interactions:
- request:
body: '{"contents": [{"role": "user", "parts": [{"text": "\nCurrent Task: Give
me a list of 5 interesting ideas to explore for an article, what makes them
unique and interesting.\n\nThis is the expected criteria for your final answer:
Bullet point list of 5 interesting ideas.\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:"}]}], "system_instruction": {"parts": [{"text": "You are
Researcher. You''re an expert researcher, specialized in technology, software
engineering, AI and startups. You work as a freelancer and are now working on
doing research and analysis for a new customer.\nYour personal goal is: Make
the best research and analysis on content about AI and AI agents. Use the tool
provided to you.\nYou ONLY have access to the following tools, and should NEVER
make up tools that are not listed here:\n\nTool Name: what amazing tool\nTool
Arguments: {}\nTool Description: My tool\n\nIMPORTANT: Use the following format
in your response:\n\n```\nThought: you should always think about what to do\nAction:
the action to take, only one name of [what amazing tool], just the name, exactly
as it''s written.\nAction Input: the input to the action, just a simple JSON
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\n```\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n```"}]}, "generationConfig":
{"temperature": 0.7, "stop_sequences": ["\nObservation:"]}}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1718'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
user-agent:
- litellm/1.60.2
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-pro-latest:generateContent
response:
body:
string: !!binary |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=
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Encoding:
- gzip
Content-Type:
- application/json; charset=UTF-8
Date:
- Thu, 17 Apr 2025 19:00:14 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=1972
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- nosniff
X-Frame-Options:
- SAMEORIGIN
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
version: 1

209
tests/cassettes/test_using_contextual_memory_with_long_term_memory.yaml Normal file
View File

@@ -0,0 +1,209 @@
interactions:
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1635'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.31.1
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Sat, 12 Apr 2025 20:52:35 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
an expert in research and you love to learn new things.\nYour personal goal
is: You research about math.\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: Research a topic
to teach a kid aged 6 about math.\n\nThis is the expected criteria for your
final answer: A topic, explanation, angle, and examples.\nyou MUST return the
actual complete content as the final answer, not a summary.\n\n# Useful context:
\n<MagicMock name=''build_context_for_task()'' id=''13586043616''>\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-mini", "stop":
["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1031'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-BLc7zvaXoFAArOIDK9TrMtdq8kKY0\",\n \"object\":
\"chat.completion\",\n \"created\": 1744491151,\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: \\n\\n**Topic: Introduction to Addition with Fun Objects**\\n\\n**Explanation:**
\ \\nAt its core, addition is all about combining two or more groups of things
to find out how many there are in total. We can think of addition as a way to
bring friends together! Imagine if you have some apples and your friend brings
some more apples; together, you want to find out how many apples there are altogether.
This is the foundation of addition, and it can be made fun and engaging for
a 6-year-old.\\n\\n**Angle:** \\nTo make this relatable and enjoyable, we can
use everyday objects that kids love, such as toys, fruits, or even drawings.
We can create little stories or scenarios that involve addition, turning it
into a game where they get to count and add things together. By using real items,
children can see and feel what addition means, making it easier to grasp the
concept.\\n\\n**Examples:** \\n1. **Using Fruits:** \\n Let's say you have
3 oranges. You can say, \\\"I have 3 oranges.\\\" Then, if your friend brings
you 2 more oranges, you can introduce the addition by saying, \\\"Now, how many
do we have all together?\\\" \\n - So you would show it as: 3 (oranges you
have) + 2 (oranges your friend brought) = ? \\n To find the answer, you can
count all the oranges together: 1, 2, 3 (your oranges) and 4, 5 (your friend's
oranges). \\n - The answer is 5 oranges in total!\\n\\n2. **Using Toys:**
\ \\n If a child has 4 toy cars and finds 3 more under the couch, we can ask,
\\\"How many cars do you have now?\\\" \\n - Write it down: 4 (toy cars)
+ 3 (found cars) = ? \\n Then, count the toy cars together: 1, 2, 3, 4 (original
cars), 5, 6, 7. \\n - The answer is 7 toy cars!\\n\\n3. **Story Scenario:**
\ \\n Create an engaging story: \\\"Once upon a time, there were 2 friendly
puppies. One day, 3 more puppies came to play. How many puppies are playing
now?\\\" \\n - Present it as: 2 (original puppies) + 3 (new puppies) = ?
\ \\n Count the puppies: 1, 2 (the first two) and then 3, 4, 5 (the new ones).
\ \\n - The answer is 5 puppies playing!\\n\\nBy presenting addition through
fun scenarios and interactive counting, a 6-year-old can learn and understand
addition while enjoying the process. They can even use crayons to draw the items
or fruit to count in a playful, hands-on approach. This makes math not just
a subject, but also a delightful adventure!\",\n \"refusal\": null,\n
\ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 206,\n \"completion_tokens\":
609,\n \"total_tokens\": 815,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_44added55e\"\n}\n"
headers:
CF-RAY:
- 92f59ba1fa19572a-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 12 Apr 2025 20:52:44 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=C7ejNhC7vNTBO9VtBqzN_ce__mP2Dz8noDo2lIcNBn0-1744491164-1.0.1.1-kQgWk4d54JIGxg_yCJ.7uV9HkU8JXrhpfIth0WHDdqf9ESzAsQyDu0xKVLYnga.xswBnm5kePpuFCcnIqGKgyag31cEyuiFFf6JHTvQcvWI;
path=/; expires=Sat, 12-Apr-25 21:22:44 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=QuvcyYK0MZfY9dNclglrzesXcplWfoZN.rd4J57.xtY-1744491164641-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '12806'
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:
- '149999777'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_49f3c203229149ce08c0813ac4071355
http_version: HTTP/1.1
status_code: 200
version: 1

335
tests/cassettes/test_using_contextual_memory_with_short_term_memory.yaml Normal file
View File

File diff suppressed because one or more lines are too long

205
tests/cassettes/test_warning_long_term_memory_without_entity_memory.yaml Normal file
View File

@@ -0,0 +1,205 @@
interactions:
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1635'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.31.1
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Sat, 12 Apr 2025 21:26:32 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
an expert in research and you love to learn new things.\nYour personal goal
is: You research about math.\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: Research a topic
to teach a kid aged 6 about math.\n\nThis is the expected criteria for your
final answer: A topic, explanation, angle, and examples.\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-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '947'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-BLceqFO97kLaTEPUSKGHkGlckpxLe\",\n \"object\":
\"chat.completion\",\n \"created\": 1744493188,\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: \\n\\n**Topic:** Introduction to Addition\\n\\n**Explanation:** \\nAddition
is a fundamental concept in math that means putting together two or more numbers
to find out how many there are in total. When we add, we combine quantities
to see the total amount we have. The symbol for addition is \\\"+\\\". \\n\\nLet's
break it down so it's easy to understand. If you have a small group of apples
and then you get more apples, to find out how many apples you have altogether,
you add them up! \\n\\n**Angle:** \\nTo teach this concept to a 6-year-old,
we can use tangible objects they can relate to, such as fruits, toys, or stickers.
Kids learn best through play and visual representation, so using real-life examples
will make the concept of addition exciting and engaging!\\n\\n**Examples:**
\ \\n1. **Using Fruits:** \\n - Start with 2 apples. \\n\\n \U0001F34F\U0001F34F
(2 apples)\\n\\n - Then, you receive 3 more apples. \\n\\n \U0001F34F\U0001F34F\U0001F34F
(3 apples)\\n\\n - To find out how many apples you have now, we add them together:
\\n\\n 2 + 3 = 5 \\n\\n - Show them the total by counting all the apples
together: \\n\\n \U0001F34F\U0001F34F\U0001F34F\U0001F34F\U0001F34F (5 apples)\\n\\n2.
**Using Toys:** \\n - Let\u2019s say there are 4 toy cars. \\n\\n \U0001F697\U0001F697\U0001F697\U0001F697
(4 toy cars)\\n\\n - If you get 2 more toy cars. \\n\\n \U0001F697\U0001F697
(2 toy cars)\\n\\n - How many do we have in total? \\n\\n 4 + 2 = 6 \\n\\n
\ - Count them all together: \\n\\n \U0001F697\U0001F697\U0001F697\U0001F697\U0001F697\U0001F697
(6 toy cars)\\n\\n3. **Using Stickers:** \\n - You have 5 stickers. \\n\\n
\ \U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F (5 stickers)\\n\\n -
Your friend gives you 4 more stickers. \\n\\n \U0001F31F\U0001F31F\U0001F31F\U0001F31F
(4 stickers)\\n\\n - Now, let\u2019s see how many stickers you have in total:
\\n\\n 5 + 4 = 9 \\n\\n - Count them together: \\n\\n \U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F\U0001F31F
(9 stickers)\\n\\n**Conclusion:** \\nTry to make addition fun! Use snacks or
play time to practice addition. Ask questions during snack time, such as \u201CIf
you eat one of your 5 cookies, how many will you have left?\u201D This approach
makes learning relatable and enjoyable, enhancing their understanding of math
in everyday situations. Happy adding!\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 182,\n \"completion_tokens\":
561,\n \"total_tokens\": 743,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_44added55e\"\n}\n"
headers:
CF-RAY:
- 92f5cd5a19257e0f-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 12 Apr 2025 21:26:36 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=RJADJOyAKqFS8232yM1dbM71E3ODRyiAty_s9rGvM0Y-1744493196-1.0.1.1-f4yxtdxM2DD78r7TOvv1J75SF6jkKDecDiDNH3cGysXRR3R.QycZfAzjKzWFkncqaQY4jeqGFYZlVR06qIdq2Gw178QxYpOC6MrJT1eqduw;
path=/; expires=Sat, 12-Apr-25 21:56:36 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=l0OvqELD24_KHHDhiAwih_bsqFrop1327mHak9Y_Ovk-1744493196966-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '8640'
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:
- '149999797'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_dda2c2217b856a9012403aeb7378a9e2
http_version: HTTP/1.1
status_code: 200
version: 1

23
tests/cli/test_constants.py Normal file
View File

@@ -0,0 +1,23 @@
import pytest
from crewai.cli.constants import ENV_VARS, MODELS, PROVIDERS
def test_huggingface_in_providers():
"""Test that Huggingface is in the PROVIDERS list."""
assert "huggingface" in PROVIDERS
def test_huggingface_env_vars():
"""Test that Huggingface environment variables are properly configured."""
assert "huggingface" in ENV_VARS
assert any(
detail.get("key_name") == "HF_TOKEN"
for detail in ENV_VARS["huggingface"]
)
def test_huggingface_models():
"""Test that Huggingface models are properly configured."""
assert "huggingface" in MODELS
assert len(MODELS["huggingface"]) > 0

26
tests/conftest.py
View File

@@ -8,6 +8,7 @@ from dotenv import load_dotenv
load_result = load_dotenv(override=True)
@pytest.fixture(autouse=True)
def setup_test_environment():
"""Set up test environment with a temporary directory for SQLite storage."""
@@ -15,11 +16,13 @@ def setup_test_environment():
# Create the directory with proper permissions
storage_dir = Path(temp_dir) / "crewai_test_storage"
storage_dir.mkdir(parents=True, exist_ok=True)
# Validate that the directory was created successfully
if not storage_dir.exists() or not storage_dir.is_dir():
raise RuntimeError(f"Failed to create test storage directory: {storage_dir}")
raise RuntimeError(
f"Failed to create test storage directory: {storage_dir}"
)
# Verify directory permissions
try:
# Try to create a test file to verify write permissions
@@ -27,11 +30,20 @@ def setup_test_environment():
test_file.touch()
test_file.unlink()
except (OSError, IOError) as e:
raise RuntimeError(f"Test storage directory {storage_dir} is not writable: {e}")
raise RuntimeError(
f"Test storage directory {storage_dir} is not writable: {e}"
)
# Set environment variable to point to the test storage directory
os.environ["CREWAI_STORAGE_DIR"] = str(storage_dir)
yield
# Cleanup is handled automatically when tempfile context exits
@pytest.fixture(scope="module")
def vcr_config(request) -> dict:
return {
"cassette_library_dir": "tests/cassettes",
}

244
tests/crew_test.py
View File

@@ -4,6 +4,7 @@ import hashlib
import json
import os
import sys
import tempfile
from concurrent.futures import Future
from unittest import mock
from unittest.mock import MagicMock, Mock, patch
@@ -19,6 +20,8 @@ from crewai.crews.crew_output import CrewOutput
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
from crewai.llm import LLM
from crewai.memory.contextual.contextual_memory import ContextualMemory
from crewai.memory.long_term.long_term_memory import LongTermMemory
from crewai.memory.short_term.short_term_memory import ShortTermMemory
from crewai.process import Process
from crewai.task import Task
from crewai.tasks.conditional_task import ConditionalTask
@@ -39,11 +42,6 @@ from crewai.utilities.events.event_listener import EventListener
from crewai.utilities.rpm_controller import RPMController
from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
# Skip streaming tests when running in CI/CD environments
skip_streaming_in_ci = pytest.mark.skipif(
os.getenv("CI") is not None, reason="Skipping streaming tests in CI/CD environments"
)
ceo = Agent(
role="CEO",
goal="Make sure the writers in your company produce amazing content.",
@@ -960,7 +958,6 @@ def test_api_calls_throttling(capsys):
moveon.assert_called()
@skip_streaming_in_ci
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_kickoff_usage_metrics():
inputs = [
@@ -996,7 +993,6 @@ def test_crew_kickoff_usage_metrics():
assert result.token_usage.cached_prompt_tokens == 0
@skip_streaming_in_ci
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_kickoff_streaming_usage_metrics():
inputs = [
@@ -2404,6 +2400,136 @@ def test_using_contextual_memory():
contextual_mem.assert_called_once()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_using_contextual_memory_with_long_term_memory():
from unittest.mock import patch
math_researcher = Agent(
role="Researcher",
goal="You research about math.",
backstory="You're an expert in research and you love to learn new things.",
allow_delegation=False,
)
task1 = Task(
description="Research a topic to teach a kid aged 6 about math.",
expected_output="A topic, explanation, angle, and examples.",
agent=math_researcher,
)
crew = Crew(
agents=[math_researcher],
tasks=[task1],
long_term_memory=LongTermMemory(),
)
with patch.object(ContextualMemory, "build_context_for_task") as contextual_mem:
crew.kickoff()
contextual_mem.assert_called_once()
assert crew.memory is False
@pytest.mark.vcr(filter_headers=["authorization"])
def test_warning_long_term_memory_without_entity_memory():
from unittest.mock import patch
math_researcher = Agent(
role="Researcher",
goal="You research about math.",
backstory="You're an expert in research and you love to learn new things.",
allow_delegation=False,
)
task1 = Task(
description="Research a topic to teach a kid aged 6 about math.",
expected_output="A topic, explanation, angle, and examples.",
agent=math_researcher,
)
crew = Crew(
agents=[math_researcher],
tasks=[task1],
long_term_memory=LongTermMemory(),
)
with (
patch("crewai.utilities.printer.Printer.print") as mock_print,
patch(
"crewai.memory.long_term.long_term_memory.LongTermMemory.save"
) as save_memory,
):
crew.kickoff()
mock_print.assert_called_with(
content="Long term memory is enabled, but entity memory is not enabled. Please configure entity memory or set memory=True to automatically enable it.",
color="bold_yellow",
)
save_memory.assert_not_called()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_long_term_memory_with_memory_flag():
from unittest.mock import patch
math_researcher = Agent(
role="Researcher",
goal="You research about math.",
backstory="You're an expert in research and you love to learn new things.",
allow_delegation=False,
)
task1 = Task(
description="Research a topic to teach a kid aged 6 about math.",
expected_output="A topic, explanation, angle, and examples.",
agent=math_researcher,
)
crew = Crew(
agents=[math_researcher],
tasks=[task1],
memory=True,
long_term_memory=LongTermMemory(),
)
with (
patch("crewai.utilities.printer.Printer.print") as mock_print,
patch(
"crewai.memory.long_term.long_term_memory.LongTermMemory.save"
) as save_memory,
):
crew.kickoff()
mock_print.assert_not_called()
save_memory.assert_called_once()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_using_contextual_memory_with_short_term_memory():
from unittest.mock import patch
math_researcher = Agent(
role="Researcher",
goal="You research about math.",
backstory="You're an expert in research and you love to learn new things.",
allow_delegation=False,
)
task1 = Task(
description="Research a topic to teach a kid aged 6 about math.",
expected_output="A topic, explanation, angle, and examples.",
agent=math_researcher,
)
crew = Crew(
agents=[math_researcher],
tasks=[task1],
short_term_memory=ShortTermMemory(),
)
with patch.object(ContextualMemory, "build_context_for_task") as contextual_mem:
crew.kickoff()
contextual_mem.assert_called_once()
assert crew.memory is False
@pytest.mark.vcr(filter_headers=["authorization"])
def test_disabled_memory_using_contextual_memory():
from unittest.mock import patch
@@ -3935,11 +4061,17 @@ def test_crew_guardrail_feedback_in_context():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_before_kickoff_callback():
from crewai.project import CrewBase, agent, before_kickoff, task
from crewai.project import CrewBase
@CrewBase
class TestCrewClass:
from crewai.project import crew
from typing import List
from crewai.agents.agent_builder.base_agent import BaseAgent
from crewai.project import CrewBase, agent, before_kickoff, crew, task
agents: List[BaseAgent]
tasks: List[Task]
agents_config = None
tasks_config = None
@@ -4115,9 +4247,97 @@ def test_crew_kickoff_for_each_works_with_manager_agent_copy():
assert crew_copy.manager_agent.id != crew.manager_agent.id
assert crew_copy.manager_agent.role == crew.manager_agent.role
assert crew_copy.manager_agent.goal == crew.manager_agent.goal
assert crew_copy.manager_agent.backstory == crew.manager_agent.backstory
assert isinstance(crew_copy.manager_agent.agent_executor, CrewAgentExecutor)
assert isinstance(crew_copy.manager_agent.cache_handler, CacheHandler)
def test_crew_copy_with_memory():
"""Test that copying a crew with memory enabled does not raise validation errors and copies memory correctly."""
agent = Agent(role="Test Agent", goal="Test Goal", backstory="Test Backstory")
task = Task(description="Test Task", expected_output="Test Output", agent=agent)
crew = Crew(agents=[agent], tasks=[task], memory=True)
original_short_term_id = (
id(crew._short_term_memory) if crew._short_term_memory else None
)
original_long_term_id = (
id(crew._long_term_memory) if crew._long_term_memory else None
)
original_entity_id = id(crew._entity_memory) if crew._entity_memory else None
original_external_id = id(crew._external_memory) if crew._external_memory else None
original_user_id = id(crew._user_memory) if crew._user_memory else None
try:
crew_copy = crew.copy()
assert hasattr(
crew_copy, "_short_term_memory"
), "Copied crew should have _short_term_memory"
assert (
crew_copy._short_term_memory is not None
), "Copied _short_term_memory should not be None"
assert (
id(crew_copy._short_term_memory) != original_short_term_id
), "Copied _short_term_memory should be a new object"
assert hasattr(
crew_copy, "_long_term_memory"
), "Copied crew should have _long_term_memory"
assert (
crew_copy._long_term_memory is not None
), "Copied _long_term_memory should not be None"
assert (
id(crew_copy._long_term_memory) != original_long_term_id
), "Copied _long_term_memory should be a new object"
assert hasattr(
crew_copy, "_entity_memory"
), "Copied crew should have _entity_memory"
assert (
crew_copy._entity_memory is not None
), "Copied _entity_memory should not be None"
assert (
id(crew_copy._entity_memory) != original_entity_id
), "Copied _entity_memory should be a new object"
if original_external_id:
assert hasattr(
crew_copy, "_external_memory"
), "Copied crew should have _external_memory"
assert (
crew_copy._external_memory is not None
), "Copied _external_memory should not be None"
assert (
id(crew_copy._external_memory) != original_external_id
), "Copied _external_memory should be a new object"
else:
assert (
not hasattr(crew_copy, "_external_memory")
or crew_copy._external_memory is None
), "Copied _external_memory should be None if not originally present"
if original_user_id:
assert hasattr(
crew_copy, "_user_memory"
), "Copied crew should have _user_memory"
assert (
crew_copy._user_memory is not None
), "Copied _user_memory should not be None"
assert (
id(crew_copy._user_memory) != original_user_id
), "Copied _user_memory should be a new object"
else:
assert (
not hasattr(crew_copy, "_user_memory") or crew_copy._user_memory is None
), "Copied _user_memory should be None if not originally present"
except pydantic_core.ValidationError as e:
if "Input should be an instance of" in str(e) and ("Memory" in str(e)):
pytest.fail(
f"Copying with memory raised Pydantic ValidationError, likely due to incorrect memory copy: {e}"
)
else:
raise e # Re-raise other validation errors
except Exception as e:
pytest.fail(f"Copying crew raised an unexpected exception: {e}")
@patch.dict(os.environ, {}, clear=True) # Ensure AGENTOPS_API_KEY is not set

142
tests/llm_test.py
View File

@@ -2,13 +2,16 @@ import os
from time import sleep
from unittest.mock import MagicMock, patch
import litellm
import pytest
from pydantic import BaseModel
from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
from crewai.llm import CONTEXT_WINDOW_USAGE_RATIO, LLM
from crewai.utilities.events import crewai_event_bus
from crewai.utilities.events.tool_usage_events import ToolExecutionErrorEvent
from crewai.utilities.events import (
LLMCallCompletedEvent,
LLMStreamChunkEvent,
)
from crewai.utilities.token_counter_callback import TokenCalcHandler
@@ -304,6 +307,27 @@ def test_context_window_validation():
assert "must be between 1024 and 2097152" in str(excinfo.value)
@pytest.fixture
def get_weather_tool_schema():
return {
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
}
},
"required": ["location"],
},
},
}
@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.fixture
def anthropic_llm():
@@ -395,3 +419,117 @@ def test_deepseek_r1_with_open_router():
result = llm.call("What is the capital of France?")
assert isinstance(result, str)
assert "Paris" in result
def assert_event_count(
mock_emit,
expected_completed_tool_call: int = 0,
expected_stream_chunk: int = 0,
expected_completed_llm_call: int = 0,
expected_final_chunk_result: str = "",
):
event_count = {
"completed_tool_call": 0,
"stream_chunk": 0,
"completed_llm_call": 0,
}
final_chunk_result = ""
for _call in mock_emit.call_args_list:
event = _call[1]["event"]
if (
isinstance(event, LLMCallCompletedEvent)
and event.call_type.value == "tool_call"
):
event_count["completed_tool_call"] += 1
elif isinstance(event, LLMStreamChunkEvent):
event_count["stream_chunk"] += 1
final_chunk_result += event.chunk
elif (
isinstance(event, LLMCallCompletedEvent)
and event.call_type.value == "llm_call"
):
event_count["completed_llm_call"] += 1
else:
continue
assert event_count["completed_tool_call"] == expected_completed_tool_call
assert event_count["stream_chunk"] == expected_stream_chunk
assert event_count["completed_llm_call"] == expected_completed_llm_call
assert final_chunk_result == expected_final_chunk_result
@pytest.fixture
def mock_emit() -> MagicMock:
from crewai.utilities.events.crewai_event_bus import CrewAIEventsBus
with patch.object(CrewAIEventsBus, "emit") as mock_emit:
yield mock_emit
@pytest.mark.vcr(filter_headers=["authorization"])
def test_handle_streaming_tool_calls(get_weather_tool_schema, mock_emit):
llm = LLM(model="openai/gpt-4o", stream=True)
response = llm.call(
messages=[
{"role": "user", "content": "What is the weather in New York?"},
],
tools=[get_weather_tool_schema],
available_functions={
"get_weather": lambda location: f"The weather in {location} is sunny"
},
)
assert response == "The weather in New York, NY is sunny"
expected_final_chunk_result = (
'{"location":"New York, NY"}The weather in New York, NY is sunny'
)
assert_event_count(
mock_emit=mock_emit,
expected_completed_tool_call=1,
expected_stream_chunk=10,
expected_completed_llm_call=1,
expected_final_chunk_result=expected_final_chunk_result,
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_handle_streaming_tool_calls_no_available_functions(
get_weather_tool_schema, mock_emit
):
llm = LLM(model="openai/gpt-4o", stream=True)
response = llm.call(
messages=[
{"role": "user", "content": "What is the weather in New York?"},
],
tools=[get_weather_tool_schema],
)
assert response == ""
assert_event_count(
mock_emit=mock_emit,
expected_stream_chunk=9,
expected_completed_llm_call=1,
expected_final_chunk_result='{"location":"New York, NY"}',
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_handle_streaming_tool_calls_no_tools(mock_emit):
llm = LLM(model="openai/gpt-4o", stream=True)
response = llm.call(
messages=[
{"role": "user", "content": "What is the weather in New York?"},
],
)
assert (
response
== "I'm unable to provide real-time information or current weather updates. For the latest weather information in New York, I recommend checking a reliable weather website or app, such as the National Weather Service, Weather.com, or a similar service."
)
assert_event_count(
mock_emit=mock_emit,
expected_stream_chunk=46,
expected_completed_llm_call=1,
expected_final_chunk_result=response,
)

270
tests/memory/cassettes/test_save_and_search_with_provider.yaml
View File

@@ -1,270 +0,0 @@
interactions:
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
host:
- api.mem0.ai
user-agent:
- python-httpx/0.27.0
method: GET
uri: https://api.mem0.ai/v1/memories/?user_id=test
response:
body:
string: '[]'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8b477138bad847b9-BOM
Connection:
- keep-alive
Content-Length:
- '2'
Content-Type:
- application/json
Date:
- Sat, 17 Aug 2024 06:00:11 GMT
NEL:
- '{"success_fraction":0,"report_to":"cf-nel","max_age":604800}'
Report-To:
- '{"endpoints":[{"url":"https:\/\/a.nel.cloudflare.com\/report\/v4?s=uuyH2foMJVDpV%2FH52g1q%2FnvXKe3dBKVzvsK0mqmSNezkiszNR9OgrEJfVqmkX%2FlPFRP2sH4zrOuzGo6k%2FjzsjYJczqSWJUZHN2pPujiwnr1E9W%2BdLGKmG6%2FqPrGYAy2SBRWkkJVWsTO3OQ%3D%3D"}],"group":"cf-nel","max_age":604800}'
Server:
- cloudflare
allow:
- GET, POST, DELETE, OPTIONS
alt-svc:
- h3=":443"; ma=86400
cross-origin-opener-policy:
- same-origin
referrer-policy:
- same-origin
vary:
- Accept, origin, Cookie
x-content-type-options:
- nosniff
x-frame-options:
- DENY
status:
code: 200
message: OK
- request:
body: '{"batch": [{"properties": {"python_version": "3.12.4 (v3.12.4:8e8a4baf65,
Jun 6 2024, 17:33:18) [Clang 13.0.0 (clang-1300.0.29.30)]", "os": "darwin",
"os_version": "Darwin Kernel Version 23.4.0: Wed Feb 21 21:44:54 PST 2024; root:xnu-10063.101.15~2/RELEASE_ARM64_T6030",
"os_release": "23.4.0", "processor": "arm", "machine": "arm64", "function":
"mem0.client.main.MemoryClient", "$lib": "posthog-python", "$lib_version": "3.5.0",
"$geoip_disable": true}, "timestamp": "2024-08-17T06:00:11.526640+00:00", "context":
{}, "distinct_id": "fd411bd3-99a2-42d6-acd7-9fca8ad09580", "event": "client.init"}],
"historical_migration": false, "sentAt": "2024-08-17T06:00:11.701621+00:00",
"api_key": "phc_hgJkUVJFYtmaJqrvf6CYN67TIQ8yhXAkWzUn9AMU4yX"}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '740'
Content-Type:
- application/json
User-Agent:
- posthog-python/3.5.0
method: POST
uri: https://us.i.posthog.com/batch/
response:
body:
string: '{"status":"Ok"}'
headers:
Connection:
- keep-alive
Content-Length:
- '15'
Content-Type:
- application/json
Date:
- Sat, 17 Aug 2024 06:00:12 GMT
access-control-allow-credentials:
- 'true'
server:
- envoy
vary:
- origin, access-control-request-method, access-control-request-headers
x-envoy-upstream-service-time:
- '69'
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "Remember the following insights
from Agent run: test value with provider"}], "metadata": {"task": "test_task_provider",
"agent": "test_agent_provider"}, "app_id": "Researcher"}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '219'
content-type:
- application/json
host:
- api.mem0.ai
user-agent:
- python-httpx/0.27.0
method: POST
uri: https://api.mem0.ai/v1/memories/
response:
body:
string: '{"message":"ok"}'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8b477140282547b9-BOM
Connection:
- keep-alive
Content-Length:
- '16'
Content-Type:
- application/json
Date:
- Sat, 17 Aug 2024 06:00:13 GMT
NEL:
- '{"success_fraction":0,"report_to":"cf-nel","max_age":604800}'
Report-To:
- '{"endpoints":[{"url":"https:\/\/a.nel.cloudflare.com\/report\/v4?s=FRjJKSk3YxVj03wA7S05H8ts35KnWfqS3wb6Rfy4kVZ4BgXfw7nJbm92wI6vEv5fWcAcHVnOlkJDggs11B01BMuB2k3a9RqlBi0dJNiMuk%2Bgm5xE%2BODMPWJctYNRwQMjNVbteUpS%2Fad8YA%3D%3D"}],"group":"cf-nel","max_age":604800}'
Server:
- cloudflare
allow:
- GET, POST, DELETE, OPTIONS
alt-svc:
- h3=":443"; ma=86400
cross-origin-opener-policy:
- same-origin
referrer-policy:
- same-origin
vary:
- Accept, origin, Cookie
x-content-type-options:
- nosniff
x-frame-options:
- DENY
status:
code: 200
message: OK
- request:
body: '{"query": "test value with provider", "limit": 3, "app_id": "Researcher"}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '73'
content-type:
- application/json
host:
- api.mem0.ai
user-agent:
- python-httpx/0.27.0
method: POST
uri: https://api.mem0.ai/v1/memories/search/
response:
body:
string: '[]'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8b47714d083b47b9-BOM
Connection:
- keep-alive
Content-Length:
- '2'
Content-Type:
- application/json
Date:
- Sat, 17 Aug 2024 06:00:14 GMT
NEL:
- '{"success_fraction":0,"report_to":"cf-nel","max_age":604800}'
Report-To:
- '{"endpoints":[{"url":"https:\/\/a.nel.cloudflare.com\/report\/v4?s=2DRWL1cdKdMvnE8vx1fPUGeTITOgSGl3N5g84PS6w30GRqpfz79BtSx6REhpnOiFV8kM6KGqln0iCZ5yoHc2jBVVJXhPJhQ5t0uerD9JFnkphjISrJOU1MJjZWneT9PlNABddxvVNCmluA%3D%3D"}],"group":"cf-nel","max_age":604800}'
Server:
- cloudflare
allow:
- POST, OPTIONS
alt-svc:
- h3=":443"; ma=86400
cross-origin-opener-policy:
- same-origin
referrer-policy:
- same-origin
vary:
- Accept, origin, Cookie
x-content-type-options:
- nosniff
x-frame-options:
- DENY
status:
code: 200
message: OK
- request:
body: '{"batch": [{"properties": {"python_version": "3.12.4 (v3.12.4:8e8a4baf65,
Jun 6 2024, 17:33:18) [Clang 13.0.0 (clang-1300.0.29.30)]", "os": "darwin",
"os_version": "Darwin Kernel Version 23.4.0: Wed Feb 21 21:44:54 PST 2024; root:xnu-10063.101.15~2/RELEASE_ARM64_T6030",
"os_release": "23.4.0", "processor": "arm", "machine": "arm64", "function":
"mem0.client.main.MemoryClient", "$lib": "posthog-python", "$lib_version": "3.5.0",
"$geoip_disable": true}, "timestamp": "2024-08-17T06:00:13.593952+00:00", "context":
{}, "distinct_id": "fd411bd3-99a2-42d6-acd7-9fca8ad09580", "event": "client.add"}],
"historical_migration": false, "sentAt": "2024-08-17T06:00:13.858277+00:00",
"api_key": "phc_hgJkUVJFYtmaJqrvf6CYN67TIQ8yhXAkWzUn9AMU4yX"}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '739'
Content-Type:
- application/json
User-Agent:
- posthog-python/3.5.0
method: POST
uri: https://us.i.posthog.com/batch/
response:
body:
string: '{"status":"Ok"}'
headers:
Connection:
- keep-alive
Content-Length:
- '15'
Content-Type:
- application/json
Date:
- Sat, 17 Aug 2024 06:00:13 GMT
access-control-allow-credentials:
- 'true'
server:
- envoy
vary:
- origin, access-control-request-method, access-control-request-headers
x-envoy-upstream-service-time:
- '33'
status:
code: 200
message: OK
version: 1

650
tests/memory/external/cassettes/test_crew_external_memory_save[save].yaml vendored
View File

File diff suppressed because one or more lines are too long

836
tests/memory/external/cassettes/test_crew_external_memory_save[search].yaml vendored
View File

File diff suppressed because one or more lines are too long

45
tests/memory/external/external_memory_test.py → tests/memory/external_memory_test.py
View File

@@ -61,6 +61,35 @@ def crew_with_external_memory(external_memory_with_mocked_config, patch_configur
return crew
@pytest.fixture
def crew_with_external_memory_without_memory_flag(
external_memory_with_mocked_config, patch_configure_mem0
):
agent = Agent(
role="Researcher",
goal="Search relevant data and provide results",
backstory="You are a researcher at a leading tech think tank.",
tools=[],
verbose=True,
)
task = Task(
description="Perform a search on specific topics.",
expected_output="A list of relevant URLs based on the search query.",
agent=agent,
)
crew = Crew(
agents=[agent],
tasks=[task],
verbose=True,
process=Process.sequential,
external_memory=external_memory_with_mocked_config,
)
return crew
def test_external_memory_initialization(external_memory_with_mocked_config):
assert external_memory_with_mocked_config is not None
assert isinstance(external_memory_with_mocked_config, ExternalMemory)
@@ -137,7 +166,9 @@ def test_crew_external_memory_reset(mem_type, crew_with_external_memory):
@pytest.mark.parametrize("mem_method", ["search", "save"])
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_external_memory_save(mem_method, crew_with_external_memory):
def test_crew_external_memory_save_with_memory_flag(
mem_method, crew_with_external_memory
):
with patch(
f"crewai.memory.external.external_memory.ExternalMemory.{mem_method}"
) as mock_method:
@@ -145,6 +176,18 @@ def test_crew_external_memory_save(mem_method, crew_with_external_memory):
assert mock_method.call_count > 0
@pytest.mark.parametrize("mem_method", ["search", "save"])
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_external_memory_save_using_crew_without_memory_flag(
mem_method, crew_with_external_memory_without_memory_flag
):
with patch(
f"crewai.memory.external.external_memory.ExternalMemory.{mem_method}"
) as mock_method:
crew_with_external_memory_without_memory_flag.kickoff()
assert mock_method.call_count > 0
def test_external_memory_custom_storage(crew_with_external_memory):
class CustomStorage(Storage):
def __init__(self):

30
tests/project_test.py
View File

@@ -1,6 +1,9 @@
from typing import List
import pytest
from crewai.agent import Agent
from crewai.agents.agent_builder.base_agent import BaseAgent
from crewai.crew import Crew
from crewai.llm import LLM
from crewai.project import (
@@ -40,28 +43,32 @@ class InternalCrew:
agents_config = "config/agents.yaml"
tasks_config = "config/tasks.yaml"
agents: List[BaseAgent]
tasks: List[Task]
@llm
def local_llm(self):
return LLM(
model='openai/model_name',
model="openai/model_name",
api_key="None",
base_url="http://xxx.xxx.xxx.xxx:8000/v1")
base_url="http://xxx.xxx.xxx.xxx:8000/v1",
)
@agent
def researcher(self):
return Agent(config=self.agents_config["researcher"])
return Agent(config=self.agents_config["researcher"]) # type: ignore[index]
@agent
def reporting_analyst(self):
return Agent(config=self.agents_config["reporting_analyst"])
return Agent(config=self.agents_config["reporting_analyst"]) # type: ignore[index]
@task
def research_task(self):
return Task(config=self.tasks_config["research_task"])
return Task(config=self.tasks_config["research_task"]) # type: ignore[index]
@task
def reporting_task(self):
return Task(config=self.tasks_config["reporting_task"])
return Task(config=self.tasks_config["reporting_task"]) # type: ignore[index]
@before_kickoff
def modify_inputs(self, inputs):
@@ -165,24 +172,27 @@ def test_before_kickoff_with_none_input():
def test_multiple_before_after_kickoff():
@CrewBase
class MultipleHooksCrew:
agents: List[BaseAgent]
tasks: List[Task]
agents_config = "config/agents.yaml"
tasks_config = "config/tasks.yaml"
@agent
def researcher(self):
return Agent(config=self.agents_config["researcher"])
return Agent(config=self.agents_config["researcher"]) # type: ignore[index]
@agent
def reporting_analyst(self):
return Agent(config=self.agents_config["reporting_analyst"])
return Agent(config=self.agents_config["reporting_analyst"]) # type: ignore[index]
@task
def research_task(self):
return Task(config=self.tasks_config["research_task"])
return Task(config=self.tasks_config["research_task"]) # type: ignore[index]
@task
def reporting_task(self):
return Task(config=self.tasks_config["reporting_task"])
return Task(config=self.tasks_config["reporting_task"]) # type: ignore[index]
@before_kickoff
def first_before(self, inputs):

10
tests/storage/test_mem0_storage.py
View File

@@ -29,7 +29,7 @@ def mem0_storage_with_mocked_config(mock_mem0_memory):
"""Fixture to create a Mem0Storage instance with mocked dependencies"""
# Patch the Memory class to return our mock
with patch("mem0.memory.main.Memory.from_config", return_value=mock_mem0_memory):
with patch("mem0.memory.main.Memory.from_config", return_value=mock_mem0_memory) as mock_from_config:
config = {
"vector_store": {
"provider": "mock_vector_store",
@@ -66,13 +66,15 @@ def mem0_storage_with_mocked_config(mock_mem0_memory):
)
mem0_storage = Mem0Storage(type="short_term", crew=crew)
return mem0_storage
return mem0_storage, mock_from_config, config
def test_mem0_storage_initialization(mem0_storage_with_mocked_config, mock_mem0_memory):
"""Test that Mem0Storage initializes correctly with the mocked config"""
assert mem0_storage_with_mocked_config.memory_type == "short_term"
assert mem0_storage_with_mocked_config.memory is mock_mem0_memory
mem0_storage, mock_from_config, config = mem0_storage_with_mocked_config
assert mem0_storage.memory_type == "short_term"
assert mem0_storage.memory is mock_mem0_memory
mock_from_config.assert_called_once_with(config)
@pytest.fixture

88
tests/task_test.py
View File

@@ -3,6 +3,7 @@
import hashlib
import json
import os
import time
from functools import partial
from typing import Tuple, Union
from unittest.mock import MagicMock, patch
@@ -1368,3 +1369,90 @@ def test_interpolate_valid_types():
assert parsed["optional"] is None
assert parsed["nested"]["flag"] is True
assert parsed["nested"]["empty"] is None
def test_task_with_no_max_execution_time():
researcher = Agent(
role="Researcher",
goal="Make the best research and analysis on content about AI and AI agents",
backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
allow_delegation=False,
max_execution_time=None
)
task = Task(
description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
expected_output="Bullet point list of 5 interesting ideas.",
agent=researcher,
)
with patch.object(Agent, "_execute_without_timeout", return_value = "ok") as execute:
result = task.execute_sync(agent=researcher)
assert result.raw == "ok"
execute.assert_called_once()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_task_with_max_execution_time():
from crewai.tools import tool
"""Test that execution raises TimeoutError when max_execution_time is exceeded."""
@tool("what amazing tool", result_as_answer=True)
def my_tool() -> str:
"My tool"
time.sleep(1)
return "okay"
researcher = Agent(
role="Researcher",
goal="Make the best research and analysis on content about AI and AI agents. Use the tool provided to you.",
backstory=(
"You're an expert researcher, specialized in technology, software engineering, AI and startups. "
"You work as a freelancer and are now working on doing research and analysis for a new customer."
),
allow_delegation=False,
tools=[my_tool],
max_execution_time=4
)
task = Task(
description="Give me a list of 5 interesting ideas to explore for an article, what makes them unique and interesting.",
expected_output="Bullet point list of 5 interesting ideas.",
agent=researcher,
)
result = task.execute_sync(agent=researcher)
assert result.raw == "okay"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_task_with_max_execution_time_exceeded():
from crewai.tools import tool
"""Test that execution raises TimeoutError when max_execution_time is exceeded."""
@tool("what amazing tool", result_as_answer=True)
def my_tool() -> str:
"My tool"
time.sleep(10)
return "okay"
researcher = Agent(
role="Researcher",
goal="Make the best research and analysis on content about AI and AI agents. Use the tool provided to you.",
backstory=(
"You're an expert researcher, specialized in technology, software engineering, AI and startups. "
"You work as a freelancer and are now working on doing research and analysis for a new customer."
),
allow_delegation=False,
tools=[my_tool],
max_execution_time=1
)
task = Task(
description="Give me a list of 5 interesting ideas to explore for an article, what makes them unique and interesting.",
expected_output="Bullet point list of 5 interesting ideas.",
agent=researcher,
)
with pytest.raises(TimeoutError):
task.execute_sync(agent=researcher)

7
tests/tools/agent_tools/agent_tools_test.py
View File

@@ -16,6 +16,13 @@ delegate_tool = tools[0]
ask_tool = tools[1]
@pytest.fixture(scope="module")
def vcr_config(request) -> dict:
return {
"cassette_library_dir": "tests/tools/agent_tools/cassettes",
}
@pytest.mark.vcr(filter_headers=["authorization"])
def test_delegate_work():
result = delegate_tool.run(

7
tests/utilities/test_converter.py
View File

@@ -21,6 +21,13 @@ from crewai.utilities.converter import (
from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
@pytest.fixture(scope="module")
def vcr_config(request) -> dict:
return {
"cassette_library_dir": "tests/utilities/cassettes",
}
# Sample Pydantic models for testing
class EmailResponse(BaseModel):
previous_message_content: str

13
tests/utilities/test_events.py
View File

@@ -50,10 +50,13 @@ from crewai.utilities.events.tool_usage_events import (
ToolUsageErrorEvent,
)
# Skip streaming tests when running in CI/CD environments
skip_streaming_in_ci = pytest.mark.skipif(
os.getenv("CI") is not None, reason="Skipping streaming tests in CI/CD environments"
)
@pytest.fixture(scope="module")
def vcr_config(request) -> dict:
return {
"cassette_library_dir": "tests/utilities/cassettes",
}
base_agent = Agent(
role="base_agent",
@@ -625,7 +628,6 @@ def test_llm_emits_call_failed_event():
assert received_events[0].error == error_message
@skip_streaming_in_ci
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_emits_stream_chunk_events():
"""Test that LLM emits stream chunk events when streaming is enabled."""
@@ -650,7 +652,6 @@ def test_llm_emits_stream_chunk_events():
assert "".join(received_chunks) == response
@skip_streaming_in_ci
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_no_stream_chunks_when_streaming_disabled():
"""Test that LLM doesn't emit stream chunk events when streaming is disabled."""