Pydantic AI sends wrong JSON payload to Gemini in v0.0.53 but not in v0.0.52

[dldx]

Initial Checks

• I confirm that I'm using the latest version of Pydantic AI
• I confirm that I searched for my issue in https://github.com/pydantic/pydantic-ai/issues before opening this issue

Description

In v0.0.53 of pydantic ai, when using structured outputs and the instrument=True argument when creating a gemini Agent, the wrong JSON schema is generated and sent to the Gemini API, resulting in the following error:

pydantic_ai.exceptions.ModelHTTPError: status_code: 400, model_name: gemini-2.0-flash, body: {
  "error": {
    "code": 400,
    "message": "Invalid JSON payload received. Unknown name \"$defs\" at 'tools.function_declarations[0].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name \"$ref\" at 'tools.function_declarations[0].parameters.properties[0].value.items': Cannot find field.",
    "status": "INVALID_ARGUMENT",
    "details": [
      {
        "@type": "type.googleapis.com/google.rpc.BadRequest",
        "fieldViolations": [
          {
            "field": "tools.function_declarations[0].parameters",
            "description": "Invalid JSON payload received. Unknown name \"$defs\" at 'tools.function_declarations[0].parameters': Cannot find field."
          },
          {
            "field": "tools.function_declarations[0].parameters.properties[0].value.items",
            "description": "Invalid JSON payload received. Unknown name \"$ref\" at 'tools.function_declarations[0].parameters.properties[0].value.items': Cannot find field."
          }
        ]
      }
    ]
  }
}

This error does not occur in v0.0.52 or below.

Change the pydantic-ai version to v0.0.52 in the example code to see the difference. Run the script with uv run script.py

Example Code

# /// script
# requires-python = ">=3.11"
# dependencies = [
#     "google-genai",
#     "python-dotenv",
#     "pydantic-ai-slim[vertexai]==v0.0.53",
#     "pydantic",
# ]
# ///

from pydantic_ai import Agent, RunContext
from pydantic_ai.models.gemini import GeminiModel
from pydantic import BaseModel, Field
from typing import Optional
import dotenv
dotenv.load_dotenv()

model = GeminiModel(
    "gemini-2.0-flash",
    provider="google-vertex",
    # GoogleVertexProvider(service_account_file=os.getenv("GOOGLE_APPLICATION_CREDENTIALS")),
)

class PowerSaleEntry(BaseModel):
    source_document: str = Field(alias="Source document", description="URL of source document that contains this data")
    year_month: str = Field(alias="Year-Month", description="Month and year of the data in yyyy-mm format")
    source: str = Field(alias="Source", description="Source of the electricity bought")
    kwh_purchased: float = Field(alias="kWh purchased")
    basic_generation_cost: Optional[float] = Field(alias="Basic generation cost (PHP)")
    total_generation_cost: float = Field(alias="Total generation cost for the month (PHP)")
    price_per_kwh: Optional[float] = Field(
        alias="Price per kWh",
        description="Price of electricity bought, or alternatively, average generation cost (PHP/kWh)",
        default=None,
    )

class PowerSaleEntries(BaseModel):
    entries: list[PowerSaleEntry] = Field(alias="Entries", description="List of electricity sales entries")

class Deps(BaseModel):
    text: str = Field(description="Raw text containing electricity sales data")

extraction_agent = Agent(
    model,
    result_type=PowerSaleEntries,
    system_prompt="You are an expert in electricity data.",
    deps_type=Deps,
    instrument=True
)

@extraction_agent.system_prompt
async def system_prompt(context: RunContext[Deps]) -> str:
    return f"""
    You are an expert in electricity data. Your task is to extract the electricity sales data from the text.
    The text contains multiple entries, each with the following fields:
    - Source document
    - Year-Month
    - Source
    - kWh purchased
    - Basic generation cost (PHP)
    - Total generation cost for the month (PHP)

    Please extract these fields and return them in a structured format.

    This is the text you need to process:
    {context.deps.text}
    """

async def extract_power_sales(text: str) -> PowerSaleEntries:
    context = "Please extract the electricity sales data from the text."
    result = await extraction_agent.run(context, deps=Deps(text=text))
    return result

if __name__ == "__main__":
    import asyncio

    sample_text = """
    Source document: https://example.com/doc1
    Year-Month: 2023-01
    Source: Coal Plant A
    kWh purchased: 1000000
    Basic generation cost (PHP): 500000
    Total generation cost for the month (PHP): 550000

    Source document: https://example.com/doc2
    Year-Month: 2023-01
    Source: Wind Farm B
    kWh purchased: 200000
    Basic generation cost (PHP): 100000
    Total generation cost for the month (PHP): 120000

    Source document: https://example.com/doc3
    Year-Month: 2023-01
    Source: Solar Plant C
    kWh purchased: 300000
    Basic generation cost (PHP): 150000
    Total generation cost for the month (PHP): 180000
    """

    result = asyncio.run(extract_power_sales(sample_text))

    print(result.data)

Python, Pydantic AI & LLM client version

python 3.11
pydantic_ai 0.0.53

[fabioscantamburlo]

Same here. I'm experiencing this issue only for 0.0.53

[xxxpsyduck]

I got similar issue

pydantic_ai.exceptions.ModelHTTPError: status_code: 400, model_name: google-gla:gemini-2.0-flash, body: [{
  "error": {
    "code": 400,
    "message": "Invalid JSON payload received. Unknown name \"additionalProperties\" at 'tools.function_declarations[0].parameters': Cannot find field.",
    "status": "INVALID_ARGUMENT",
    "details": [
      {
        "@type": "type.googleapis.com/google.rpc.BadRequest",
        "fieldViolations": [
          {
            "field": "tools.function_declarations[0].parameters",
            "description": "Invalid JSON payload received. Unknown name \"additionalProperties\" at 'tools.function_declarations[0].parameters': Cannot find field."
          }
        ]
      }
    ]
  }
}
]

[IngLP]

I have the same problem with pydantic-ai 0.0.55

        async with self.client.stream(
            'POST',
            url,
            content=request_json,
            headers=headers,
            timeout=model_settings.get('timeout', USE_CLIENT_DEFAULT),
        ) as r:
            if (status_code := r.status_code) != 200:
                await r.aread()
                if status_code >= 400:
>                   raise ModelHTTPError(status_code=status_code, model_name=self.model_name, body=r.text)
E                   pydantic_ai.exceptions.ModelHTTPError: status_code: 400, model_name: gemini-2.5-pro-exp-03-25, body: [{
E                     "error": {
E                       "code": 400,
E                       "message": "Invalid JSON payload received. Unknown name \"additionalProperties\" at 'tools.function_declarations[0].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name \"additionalProperties\" at 'tools.function_declarations[1].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name \"additionalProperties\" at 'tools.function_declarations[2].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name \"$defs\" at 'tools.function_declarations[3].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name \"$ref\" at 'tools.function_declarations[3].parameters.properties[1].value.items': Cannot find field.",
E                       "status": "INVALID_ARGUMENT",
E                       "details": [
E                         {
E                           "@type": "type.googleapis.com/google.rpc.BadRequest",
E                           "fieldViolations": [
E                             {
E                               "field": "tools.function_declarations[0].parameters",
E                               "description": "Invalid JSON payload received. Unknown name \"additionalProperties\" at 'tools.function_declarations[0].parameters': Cannot find field."
E                             },
E                             {
E                               "field": "tools.function_declarations[1].parameters",
E                               "description": "Invalid JSON payload received. Unknown name \"additionalProperties\" at 'tools.function_declarations[1].parameters': Cannot find field."
E                             },
E                             {
E                               "field": "tools.function_declarations[2].parameters",
E                               "description": "Invalid JSON payload received. Unknown name \"additionalProperties\" at 'tools.function_declarations[2].parameters': Cannot find field."
E                             },
E                             {
E                               "field": "tools.function_declarations[3].parameters",
E                               "description": "Invalid JSON payload received. Unknown name \"$defs\" at 'tools.function_declarations[3].parameters': Cannot find field."
E                             },
E                             {
E                               "field": "tools.function_declarations[3].parameters.properties[1].value.items",
E                               "description": "Invalid JSON payload received. Unknown name \"$ref\" at 'tools.function_declarations[3].parameters.properties[1].value.items': Cannot find field."
E                             }
E                           ]
E                         }
E                       ]
E                     }
E                   }
E                   ]

[IngLP]

@dmontagu can you please reopen the issue?

[IngLP]

@dmontagu or should I open another issue?

[Kludex]

Can you provide an MRE?

[IngLP]

I can confirm that going back to 0.0.52 solves the problem.
Here is an MRE:

import asyncio
import logging
import os
from dataclasses import dataclass, field
from typing import List, Optional, Dict, Any

from pydantic import BaseModel, Field, HttpUrl
from pydantic_ai import Agent, RunContext, ModelRetry
from pydantic_ai.settings import ModelSettings

logger = logging.getLogger(__name__)

# --- Pydantic Schemas ---


class BrowserTask(BaseModel):
    """Input request for the browser agent."""

    query: str = Field(..., description="The main research query or question.")
    target_url: Optional[HttpUrl] = Field(
        None,
        description="Optional specific URL to focus the search on (e.g., a specific website).",
    )


class Citation(BaseModel):
    """Represents a single piece of evidence found."""

    url: HttpUrl = Field(..., description="The source URL of the quote.")
    quote: str = Field(
        ..., description="The specific text snippet (quote) supporting the findings."
    )


class BrowserResult(BaseModel):
    """Structured output of the browser agent's research."""

    reasoning: str = Field(
        ...,
        description="A detailed step-by-step explanation of the agent's research process, including search strategy, sites visited, information found, and synthesis of results.",
    )
    citations: List[Citation] = Field(
        default_factory=list,
        description="A list of relevant quotes/snippets found, each linked to its source URL.",
    )


class SearchResultSummary(BaseModel):
    """Simplified summary of a search result returned by the search tool."""

    rank: int
    url: HttpUrl
    title: str
    content_preview: str
    initial_snippets: List[str] = Field(default_factory=list)
    error: Optional[str] = None


# --- Dependency Definition ---


@dataclass
class BrowserAgentDeps:
    """Dependencies required by the Browser Agent."""

    pass


# --- Agent Initialization ---

BROWSER_LLM_IDENTIFIER = os.getenv(
    "BROWSER_LLM_IDENTIFIER",
    "google-gla:gemini-2.5-pro-exp-03-25",
)

browser_agent: Agent[BrowserAgentDeps, BrowserResult] = Agent(
    BROWSER_LLM_IDENTIFIER,
    result_type=BrowserResult,
    deps_type=BrowserAgentDeps,
    retries=3,
    model_settings=ModelSettings(max_tokens=8192, temperature=0.0),
    # System prompt and tools are added below using decorators
)

# --- System Prompt ---


@browser_agent.system_prompt
async def get_system_prompt(ctx: RunContext[BrowserAgentDeps]) -> str:
    return """
You are an expert AI research assistant equipped with web browsing capabilities.
Your task is to gather and synthesize information from the web to answer complex queries.
"""


# --- Tools ---


@browser_agent.tool
async def perform_web_search(
    ctx: RunContext[BrowserAgentDeps], query: str, target_url: Optional[HttpUrl] = None
) -> List[SearchResultSummary]:
    """Perform a web search."""
    pass


@browser_agent.tool
async def get_relevant_snippets(
    ctx: RunContext[BrowserAgentDeps],
    url: HttpUrl,
    query: str,
) -> List[str]:
    """Get relevant snippets from a web page."""
    pass


@browser_agent.tool
async def read_full_page_content(
    ctx: RunContext[BrowserAgentDeps], url: HttpUrl
) -> str:

    """Read the full content of a web page."""
    pass

async def test_agent():
    async with browser_agent.run_stream(
        "Find the Unique selling proposition of Apple.",
        deps=BrowserAgentDeps(),
    ) as result:
        async for msg in result.stream(debounce_by=1):
            print(msg)

if __name__ == "__main__":
    asyncio.run(test_agent())