langchain Architecture Docs
Home / Function/ test_decorator_retry_logic() — langchain Function Reference

test_decorator_retry_logic() — langchain Function Reference

Architecture documentation for the test_decorator_retry_logic() function in test_wrap_model_call.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

Dependency Diagram

graph TD
  dcca7157_a2ad_53e7_46e8_ba7561164079["test_decorator_retry_logic()"]
  5a3c6db0_0302_046a_d217_22fb3d4e632e["TestWrapModelCallDecorator"]
  dcca7157_a2ad_53e7_46e8_ba7561164079 -->|defined in| 5a3c6db0_0302_046a_d217_22fb3d4e632e
  style dcca7157_a2ad_53e7_46e8_ba7561164079 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain_v1/tests/unit_tests/agents/middleware/core/test_wrap_model_call.py lines 1042–1078

    def test_decorator_retry_logic(self) -> None:
        """Test decorator for implementing retry logic."""
        call_count = {"value": 0}

        class FailOnceThenSucceed(GenericFakeChatModel):
            @override
            def _generate(
                self,
                messages: list[BaseMessage],
                stop: list[str] | None = None,
                run_manager: CallbackManagerForLLMRun | None = None,
                **kwargs: Any,
            ) -> ChatResult:
                call_count["value"] += 1
                if call_count["value"] == 1:
                    msg = "First call fails"
                    raise ValueError(msg)
                return super()._generate(messages, **kwargs)

        @wrap_model_call
        def retry_once(
            request: ModelRequest,
            handler: Callable[[ModelRequest], ModelResponse],
        ) -> ModelCallResult:
            try:
                return handler(request)
            except Exception:
                # Retry once
                return handler(request)

        model = FailOnceThenSucceed(messages=iter([AIMessage(content="Success")]))
        agent = create_agent(model=model, middleware=[retry_once])

        result = agent.invoke({"messages": [HumanMessage("Test")]})

        assert call_count["value"] == 2
        assert result["messages"][1].content == "Success"

Domain

Subdomains

Defined In

Source

Frequently Asked Questions

What does test_decorator_retry_logic() do?
test_decorator_retry_logic() is a function in the langchain codebase, defined in libs/langchain_v1/tests/unit_tests/agents/middleware/core/test_wrap_model_call.py.
Where is test_decorator_retry_logic() defined?
test_decorator_retry_logic() is defined in libs/langchain_v1/tests/unit_tests/agents/middleware/core/test_wrap_model_call.py at line 1042.

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free