ADK 1.18.0 spams the log with note about Field conversion for JSON Schema

[flansen]

** Please make sure you read the contribution guide and file the issues in the right place. **
Contribution guide.

Describe the bug
With the upgrade to 1.18.0 the ADK logs the following statement on INFO level over and over.
We use various McpToolsets that are connected to FastMCP servers.
Furthermore, we have two FunctionTools.

I have no clue what the log is supposed to tell me; we do not use Vertex and/or Gemini API.
It looks like a DEBUG/TRACE log to me, especially because it is logged ~10 times per agent interaction.

this comes from google.genai.types.py:

2025-11-11 08:03:18 - google_genai.types - INFO - 
Note: Conversion of fields that are not included in the JSONSchema class are ignored. Json Schema is now supported natively by both Vertex AI and Gemini API. Users are recommended to pass/receive Json Schema directly to/from the API. For example:
1. the counter part of GenerateContentConfig.response_schema is GenerateContentConfig.response_json_schema, which accepts [JSON Schema](https://json-schema.org/)
2. the counter part of FunctionDeclaration.parameters is FunctionDeclaration.parameters_json_schema, which accepts [JSON Schema](https://json-schema.org/)
3. the counter part of FunctionDeclaration.response is FunctionDeclaration.response_json_schema, which accepts [JSON Schema](https://json-schema.org/)

To Reproduce

1. interact with an agent in adk

Not sure which part of our setup causes it.

Expected behavior

Log is not spammed.

Screenshots
%

Desktop (please complete the following information):

• OS: MacOS
• Python version(python -V): 3.17
• ADK version(pip show google-adk): 1.18.0

Model Information:

• Are you using LiteLLM: Yes
• Which model is being used(e.g. gemini-2.5-pro): azure/gpt5

[gioboa]

Hi @Jacksunwei I tried to reproduce the issue on a fresh project, but I can't.
Can you list your steps please?

[plotic]

@gioboa
i encounter it as well, if i configure llm agent with :
LlmAgent(
..
generate_content_config=
output_key=
output_schema=
tools=
...
)
i start receiving that message

[surajksharma07]

@flansen The log spam comes from the google-genai package (external dependency) at INFO level.
It's triggered when agents have output_schema + multiple tools, logging once per tool per interaction.

Workaround: Suppress google-genai INFO logs by adding logging.getLogger('google_genai').setLevel(logging.WARNING) to your code.
Thanks!

[flansen]

I think the log should then not be logged on INFO as the approach we use is the automated tool integration between adk and FastMCP/McpToolset.

[surajksharma07]

@flansen You're right - INFO level is too verbose for this conversion note, especially for standard MCP/FastMCP usage patterns.

This is in the google-genai package (external to ADK), so we'll raise this with that team to lower the log level to DEBUG.
In the meantime, you can add the suppression in your app's entry point.
We're also loooking more into it for considering having ADK set this log level automatically to avoid this friction for users.

[flansen]

Nice, thank so you so much. For now, I have applied the suggested suppression!