Dataclass coercion

[eyurtsev]

Privileged issue

• I am a LangChain maintainer, or was asked directly by a LangChain maintainer to create an issue here.

Issue Content

from dataclasses import dataclass
from typing import List

@dataclass
class Foo:
    """Represents an item with an index."""
    index: int

@dataclass
class State:
    foos: List[Foo]

def map_to_node(state: State):
    """Prepare all items in the state for processing."""
    return [describe_foo(foo) for foo in state.foos]

def describe_foo(foo: Foo): # <-- foo is a DICT here instead of a dataclass
    """Raise a TypeError if foo is not a dataclass instance."""
    raise TypeError(f"Expected Foo, got {type(foo).__name__}")  # Assume foo is a dict

---

System Information

OS: Linux
OS Version: #49~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Nov 6 17:42:15 UTC 2
Python Version: 3.11.4 (main, Sep 25 2023, 10:06:23) [GCC 11.4.0]

Package Information

langchain_core: 0.3.19
langsmith: 0.1.144
langchain_openai: 0.2.9
langgraph: 0.2.53

Optional packages not installed

langserve

Other Dependencies

httpx: 0.27.2
jsonpatch: 1.33
langgraph-checkpoint: 2.0.5
langgraph-sdk: 0.1.36
openai: 1.55.0
orjson: 3.10.11
packaging: 24.2
pydantic: 2.10.0
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
tenacity: 9.0.0
tiktoken: 0.8.0
typing-extensions: 4.12.2