test_create_agent_invoke() — langchain Function Reference
Architecture documentation for the test_create_agent_invoke() function in test_framework.py from the langchain codebase.
Entity Profile
Dependency Diagram
graph TD 6e11109d_74e3_2b16_91b1_82e90d0e2d6c["test_create_agent_invoke()"] 8310d669_2524_e019_e333_8473b50a4990["test_framework.py"] 6e11109d_74e3_2b16_91b1_82e90d0e2d6c -->|defined in| 8310d669_2524_e019_e333_8473b50a4990 83f90d06_bd5d_f90c_8a51_2e1292bd1cfc["after_model()"] 6e11109d_74e3_2b16_91b1_82e90d0e2d6c -->|calls| 83f90d06_bd5d_f90c_8a51_2e1292bd1cfc style 6e11109d_74e3_2b16_91b1_82e90d0e2d6c fill:#6366f1,stroke:#818cf8,color:#fff
Relationship Graph
Source Code
libs/langchain_v1/tests/unit_tests/agents/middleware/core/test_framework.py lines 39–137
def test_create_agent_invoke(
snapshot: SnapshotAssertion,
sync_checkpointer: BaseCheckpointSaver[str],
) -> None:
calls = []
class NoopSeven(AgentMiddleware):
def before_model(self, state: AgentState[Any], runtime: Runtime) -> None:
calls.append("NoopSeven.before_model")
def wrap_model_call(
self,
request: ModelRequest,
handler: Callable[[ModelRequest], ModelResponse],
) -> ModelCallResult:
calls.append("NoopSeven.wrap_model_call")
return handler(request)
def after_model(self, state: AgentState[Any], runtime: Runtime) -> None:
calls.append("NoopSeven.after_model")
class NoopEight(AgentMiddleware):
def before_model(self, state: AgentState[Any], runtime: Runtime) -> None:
calls.append("NoopEight.before_model")
def wrap_model_call(
self,
request: ModelRequest,
handler: Callable[[ModelRequest], ModelResponse],
) -> ModelCallResult:
calls.append("NoopEight.wrap_model_call")
return handler(request)
def after_model(self, state: AgentState[Any], runtime: Runtime) -> None:
calls.append("NoopEight.after_model")
@tool
def my_tool(value: str) -> str:
"""A great tool."""
calls.append("my_tool")
return value.upper()
agent_one = create_agent(
model=FakeToolCallingModel(
tool_calls=[
[
{"args": {"value": "yo"}, "id": "1", "name": "my_tool"},
],
[],
]
),
tools=[my_tool],
system_prompt="You are a helpful assistant.",
middleware=[NoopSeven(), NoopEight()],
checkpointer=sync_checkpointer,
)
thread1 = {"configurable": {"thread_id": "1"}}
assert agent_one.invoke({"messages": ["hello"]}, thread1) == {
"messages": [
_AnyIdHumanMessage(content="hello"),
AIMessage(
content="You are a helpful assistant.-hello",
additional_kwargs={},
response_metadata={},
id="0",
tool_calls=[
{
"name": "my_tool",
"args": {"value": "yo"},
"id": "1",
"type": "tool_call",
}
],
),
_AnyIdToolMessage(content="YO", name="my_tool", tool_call_id="1"),
AIMessage(
content="You are a helpful assistant.-hello-You are a helpful assistant.-hello-YO",
additional_kwargs={},
response_metadata={},
id="1",
Domain
Subdomains
Calls
Source
Frequently Asked Questions
What does test_create_agent_invoke() do?
test_create_agent_invoke() is a function in the langchain codebase, defined in libs/langchain_v1/tests/unit_tests/agents/middleware/core/test_framework.py.
Where is test_create_agent_invoke() defined?
test_create_agent_invoke() is defined in libs/langchain_v1/tests/unit_tests/agents/middleware/core/test_framework.py at line 39.
What does test_create_agent_invoke() call?
test_create_agent_invoke() calls 1 function(s): after_model.
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free