Incorrect state validation when there's generic types in pydantic.BaseModel state schema

[hon-gyu]

Checked other resources

• This is a bug, not a usage question. For questions, please use GitHub Discussions.
• I added a clear and detailed title that summarizes the issue.
• I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
• I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue.

Example Code

from pydantic import BaseModel
from langgraph.graph import StateGraph, START, END

class A(BaseModel):
    a: str

class B(BaseModel):
    b: str

class C[AorB](BaseModel):
    c: AorB

class State(BaseModel):
    text: str
    count: int
    c: C[A]
    
def process_node(state: State):
    new_text = ", the type of c is " + str(type(state.c.c))
    print(state.c.c)

    return {"text": state.text + new_text, "count": state.count + 1}


builder = StateGraph(State)
builder.add_node("process", process_node)
builder.add_edge(START, "process")
builder.add_edge("process", END)
g = builder.compile()

input_state = {'text': '1', 'count': 0, 'c': {'c': {'a': '1'}}}

g.invoke(input_state)

# output
# {'a': '1'}
# .../pydantic/main.py:426: UserWarning: Pydantic serializer warnings:
#   Expected `A` but got `dict` with value `{'a': '1'}` - serialized value may not be as expected
#   return self.__pydantic_serializer__.to_python(

# {'text': "1, the type of c is <class 'dict'>",
#  'count': 1,
#  'c': {'c': {'a': '1'}}}

g.invoke(State.model_validate(input_state))
# output
# a='1'

Error Message and Stack Trace (if applicable)

pydantic/main.py:426: UserWarning: Pydantic serializer warnings:
  Expected `A` but got `dict` with value `{'a': '1'}` - serialized value may not be as expected
  return self.__pydantic_serializer__.to_python(

Description

When graph state schema has pydantic.BaseModel with generic types invovled. The validation does not perform correctly.

In the repro example provided, C instead of C[A] is used in validation, resulting in the type of state.c.c being dict instead of A.

Manual validation (g.invoke(State.model_validate(input_state))) gives the correct result.

The output of g.invoke(input_state) should be consistent with g.invoke(State.model_validate(input_state))

System Info

System Information

OS: Darwin
OS Version: Darwin Kernel Version 23.1.0: Mon Oct 9 21:33:00 PDT 2023; root:xnu-10002.41.9~7/RELEASE_ARM64_T6031
Python Version: 3.12.8 (main, Dec 19 2024, 14:22:58) [Clang 18.1.8 ]

Package Information

langchain_core: 0.3.48
langchain: 0.3.21
langchain_community: 0.3.20
langsmith: 0.3.19
langchain_anthropic: 0.3.10
langchain_google_vertexai: 2.0.17
langchain_neo4j: 0.4.0
langchain_openai: 0.3.10
langchain_text_splitters: 0.3.7
langgraph_api: 0.0.34
langgraph_cli: 0.1.80
langgraph_license: Installed. No version info available.
langgraph_sdk: 0.1.59
langgraph_storage: Installed. No version info available.

Optional packages not installed

langserve

Other Dependencies

aiohttp<4.0.0,>=3.8.3: Installed. No version info available.
anthropic<1,>=0.49.0: Installed. No version info available.
anthropic[vertexai]: Installed. No version info available.
async-timeout<5.0.0,>=4.0.0;: Installed. No version info available.
click: 8.1.8
cryptography: 43.0.3
dataclasses-json<0.7,>=0.5.7: Installed. No version info available.
google-cloud-aiplatform: 1.85.0
google-cloud-storage: 2.19.0
httpx: 0.28.1
httpx-sse: 0.4.0
httpx-sse<1.0.0,>=0.4.0: Installed. No version info available.
jsonpatch<2.0,>=1.33: Installed. No version info available.
jsonschema-rs: 0.29.1
langchain-anthropic;: Installed. No version info available.
langchain-aws;: Installed. No version info available.
langchain-azure-ai;: Installed. No version info available.
langchain-cohere;: Installed. No version info available.
langchain-community;: Installed. No version info available.
langchain-core<1.0.0,>=0.3.45: Installed. No version info available.
langchain-core<1.0.0,>=0.3.48: Installed. No version info available.
langchain-deepseek;: Installed. No version info available.
langchain-fireworks;: Installed. No version info available.
langchain-google-genai;: Installed. No version info available.
langchain-google-vertexai;: Installed. No version info available.
langchain-groq;: Installed. No version info available.
langchain-huggingface;: Installed. No version info available.
langchain-mistralai: Installed. No version info available.
langchain-mistralai;: Installed. No version info available.
langchain-ollama;: Installed. No version info available.
langchain-openai;: Installed. No version info available.
langchain-text-splitters<1.0.0,>=0.3.7: Installed. No version info available.
langchain-together;: Installed. No version info available.
langchain-xai;: Installed. No version info available.
langchain<1.0.0,>=0.3.21: Installed. No version info available.
langgraph: 0.3.20
langgraph-checkpoint: 2.0.23
langsmith-pyo3: Installed. No version info available.
langsmith<0.4,>=0.1.125: Installed. No version info available.
langsmith<0.4,>=0.1.17: Installed. No version info available.
neo4j: 5.28.1
neo4j-graphrag: 1.6.1
numpy<3,>=1.26.2: Installed. No version info available.
openai-agents: Installed. No version info available.
openai<2.0.0,>=1.68.2: Installed. No version info available.
opentelemetry-api: 1.31.1
opentelemetry-exporter-otlp-proto-http: 1.31.1
opentelemetry-sdk: 1.31.1
orjson: 3.10.16
packaging: 24.2
packaging<25,>=23.2: Installed. No version info available.
pydantic: 2.10.6
pydantic-settings<3.0.0,>=2.4.0: Installed. No version info available.
pydantic<3.0.0,>=2.5.2;: Installed. No version info available.
pydantic<3.0.0,>=2.7.4: Installed. No version info available.
pydantic<3.0.0,>=2.7.4;: Installed. No version info available.
pyjwt: 2.10.1
pytest: 8.3.5
python-dotenv: 1.1.0
PyYAML>=5.3: Installed. No version info available.
requests: 2.32.3
requests-toolbelt: 1.0.0
requests<3,>=2: Installed. No version info available.
rich: 13.9.4
SQLAlchemy<3,>=1.4: Installed. No version info available.
sse-starlette: 2.1.3
starlette: 0.46.1
structlog: 25.2.0
tenacity: 9.0.0
tenacity!=8.4.0,<10,>=8.1.0: Installed. No version info available.
tenacity!=8.4.0,<10.0.0,>=8.1.0: Installed. No version info available.
tiktoken<1,>=0.7: Installed. No version info available.
typing-extensions>=4.7: Installed. No version info available.
uvicorn: 0.34.0
validators: 0.34.0
watchfiles: 1.0.4
zstandard: 0.23.0

[gbaian10]

I get the same output, but without the UserWarning.

[NathanAP]

I'm not sure this is closely related to what I posted in #4058 , but it seems that something changed in States that uses Pydantic model and broke it...

Edit: it seems my problem is related to the supervisor.

[hon-gyu]

@gbaian10 the UserWarning shows when using a deployed graph (in my case, via langgraph dev)

[gbaian10]

I think this is the same issue as the one mentioned in #4074 (comment).
Langgraph currently only validates content without modifying the values.

[hon-gyu]

@gbaian10 thanks for looking into this. But I believe this is a different issue. The serialization itself is incorrect. It's using the incorrect type (C instead of C[A]) to serialize python dict into pydantic BaseModel. There's no modification involved.