langchain-typesafe: ModelRouterMiddleware raises an opaque RuntimeError when state has no human message

### Submission checklist - [x] This is a bug, not a usage question. - [x] I added a clear and descriptive title that summarizes this issue. - [x] I used the GitHub search to find a similar question and didn't find it. - [x] I am sure that this is a bug in LangChain rather than my code. - [x] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package). - [x] This is not related to the langchain-community package. - [x] I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS. ### Package (Required) - [ ] langchain - [ ] langchain-openai - [ ] langchain-anthropic - [ ] langchain-classic - [ ] langchain-core - [ ] langchain-model-profiles - [ ] langchain-tests - [ ] langchain-text-splitters - [ ] langchain-chroma - [ ] langchain-deepseek - [ ] langchain-exa - [ ] langchain-fireworks - [ ] langchain-groq - [ ] langchain-huggingface - [ ] langchain-mistralai - [ ] langchain-nomic - [ ] langchain-ollama - [ ] langchain-openrouter - [ ] langchain-perplexity - [ ] langchain-qdrant - [x] langchain-typesafe - [ ] langchain-xai - [ ] Other / not sure / general ### Related Issues / PRs #40648 (PR with the fix and test, auto-closed for missing an approved issue) #40650 (same report, auto-closed for being submitted through the API) ### Reproduction Steps / Example Code (Python) ```python import asyncio import os # The classifier validates the key at construction. No request is made. os.environ.setdefault("TYPESAFE_API_KEY", "not-used-no-request-is-made") from langchain.agents import create_agent from langchain_core.language_models.fake_chat_models import GenericFakeChatModel from langchain_core.messages import AIMessage from langchain_typesafe.experimental.middleware import ModelChoice, ModelRouterMiddleware model = GenericFakeChatModel(messages=iter([AIMessage("response")])) router = ModelRouterMiddleware( choices={ "fast": ModelChoice(model=model, criteria="Simple task…