fix: Apply strict JSON schema validation in FunctionTool constructor#1041

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Jump to bottom

Merged

rm-openai merged 1 commit intoopenai:mainfromhabema:fix/function-tool-strict-schema

Jul 18, 2025

Merged

fix: Apply strict JSON schema validation in FunctionTool constructor#1041

rm-openai merged 1 commit intoopenai:mainfromhabema:fix/function-tool-strict-schema

Jul 18, 2025

+5 −0

Conversation

Copy link

Contributor

habema commentedJul 8, 2025

Summary

Fixes an issue where directly createdFunctionTool objects fail with OpenAI's Responses API due to missingadditionalProperties: false in the JSON schema, while the@function_tool decorator works correctly.

Problem

The documentation example for creatingFunctionTool objects directly fails with:

Error code: 400 - {'error': {'message': "Invalid schema for function 'process_user': In context=(), 'additionalProperties' is required to be supplied and to be false.", 'type': 'invalid_request_error', 'param': 'tools[0].parameters', 'code': 'invalid_function_parameters'}}

This creates an inconsistency betweenFunctionTool and@function_tool behavior, both of which havestrict_json_schema=True by default.

Solution

Added__post_init__ method toFunctionTool dataclass
Automatically appliesensure_strict_json_schema() whenstrict_json_schema=True
Makes behavior consistent with@function_tool decorator
Maintains backward compatibility

Testing

The fix can be verified by running the reproduction case from the issue:

fromtypingimportAnyfrompydanticimportBaseModelfromagentsimportRunContextWrapper,FunctionTool,Agent,RunnerclassFunctionArgs(BaseModel):username:strage:intasyncdefrun_function(ctx:RunContextWrapper[Any],args:str)->str:parsed=FunctionArgs.model_validate_json(args)returnf"{parsed.username} is{parsed.age} years old"# This now works without manual ensure_strict_json_schema() calltool=FunctionTool(name="process_user",description="Processes extracted user data",params_json_schema=FunctionArgs.model_json_schema(),on_invoke_tool=run_function,)agent=Agent(name="Test Agent",instructions="You are a test agent",tools=[tool])result=Runner.run_sync(agent,"Process user data for John who is 30 years old")