wrap_model_call() — langchain Function Reference

Source Code

libs/langchain_v1/tests/unit_tests/agents/middleware/core/test_wrap_model_call.py lines 505–519

            def wrap_model_call(
                self,
                request: ModelRequest,
                handler: Callable[[ModelRequest], ModelResponse],
            ) -> ModelCallResult:
                # Simple cache key based on last message
                cache_key = str(request.messages[-1].content) if request.messages else ""

                if cache_key in cache:
                    # Short-circuit with cached result
                    return cache[cache_key]
                # Execute and cache
                result = handler(request)
                cache[cache_key] = result
                return result