langchain-ai/langchain-google

Attempting to use pydantic models as tool args causes `ParseError` in `ChatVertexAI`

Open

#1,076 opened on Aug 5, 2025

View on GitHub
 (4 comments) (3 reactions) (0 assignees)Python (461 forks)auto 404
help wantedvertexai

Repository metrics

Stars
 (392 stars)
PR merge metrics
 (PR metrics pending)

Description

Example Pydantic schema:

class IntOrFloat(BaseModel):
    """A type that can be either an int or a float."""

    number: int | float

and tool:

@tool
def add(a: IntOrFloat, b: IntOrFloat) -> IntOrFloat:
    """Adds a and b."""
    return IntOrFloat(number=a.number + b.number)

Attempting to use this tool in a tool-calling agent with ChatVertexAI causes the following error:

ParseError: Failed to parse properties field: Failed to parse properties field: Failed to parse anyOf field: Failed to parse type field: Invalid enum value integer for enum type google.cloud.aiplatform.v1beta1.Type at Schema.properties[a].properties[number].anyOf[0].type....

Contributor guide

Research direction
Tech stack
Domain
Issue type
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Prerequisites
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.