test_todo_middleware_on_model_call() — langchain Function Reference
Architecture documentation for the test_todo_middleware_on_model_call() function in test_todo.py from the langchain codebase.
Entity Profile
Dependency Diagram
graph TD c6d17951_b7d2_9059_963f_911b0079a0d3["test_todo_middleware_on_model_call()"] d2f3bc2a_72aa_59d0_8558_330793eda010["test_todo.py"] c6d17951_b7d2_9059_963f_911b0079a0d3 -->|defined in| d2f3bc2a_72aa_59d0_8558_330793eda010 style c6d17951_b7d2_9059_963f_911b0079a0d3 fill:#6366f1,stroke:#818cf8,color:#fff
Relationship Graph
Source Code
libs/langchain_v1/tests/unit_tests/agents/middleware/implementations/test_todo.py lines 136–171
def test_todo_middleware_on_model_call(
original_prompt: str | None, expected_prompt_prefix: str
) -> None:
"""Test that wrap_model_call handles system prompts correctly."""
middleware = TodoListMiddleware()
model = FakeToolCallingModel()
state: PlanningState = {"messages": [HumanMessage(content="Hello")]}
request = ModelRequest(
model=model,
system_prompt=original_prompt,
messages=[HumanMessage(content="Hello")],
tool_choice=None,
tools=[],
response_format=None,
state=state,
runtime=cast("Runtime", object()),
model_settings={},
)
captured_request = None
def mock_handler(req: ModelRequest) -> ModelResponse:
nonlocal captured_request
captured_request = req
return ModelResponse(result=[AIMessage(content="mock response")])
# Call wrap_model_call to trigger the middleware logic
middleware.wrap_model_call(request, mock_handler)
# Check that the modified request passed to handler has the expected prompt
assert captured_request is not None
assert captured_request.system_prompt is not None
assert captured_request.system_prompt.startswith(expected_prompt_prefix)
# Original request should be unchanged
assert request.system_prompt == original_prompt
Domain
Subdomains
Source
Frequently Asked Questions
What does test_todo_middleware_on_model_call() do?
test_todo_middleware_on_model_call() is a function in the langchain codebase, defined in libs/langchain_v1/tests/unit_tests/agents/middleware/implementations/test_todo.py.
Where is test_todo_middleware_on_model_call() defined?
test_todo_middleware_on_model_call() is defined in libs/langchain_v1/tests/unit_tests/agents/middleware/implementations/test_todo.py at line 136.
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free