Summary

• Fixes issue where Pydantic default values fromargs_schema were not passed to tool functions when the caller omits optional arguments
• Modified_parse_input() inlibs/core/langchain_core/tools/base.py to include fields with non-None defaults
• Added unit tests to verify default args behavior for both sync and async tools

Problem

When a tool has anargs_schema with default values:

classSearchArgs(BaseModel):query:str=Field(...,description="Search query")page:int=Field(default=1,description="Page number")size:int=Field(default=10,description="Results per page")@tool("search",args_schema=SearchArgs)defsearch_tool(query:str,page:int,size:int)->str:returnf"query={query}, page={page}, size={size}"# This threw: TypeError: search_tool() missing 2 required positional argumentssearch_tool.invoke({"query":"test"})

The defaults fromargs_schema were being discarded because_parse_input() filtered validated results to only include keys from the original input.

Solution

Changed the filtering logic to:

1. Include all fields that were in the original input (validated)
2. Also include fields with non-None defaults from the Pydantic schema

This applies user-defined defaults (likeField(default=1)) while excluding synthetic fields from*args/**kwargs which havedefault=None.

Test plan

• Addedtest_tool_args_schema_default_values - tests sync tool with defaults
• Addedtest_tool_args_schema_default_values_async - tests async tool with defaults
• All existing tests pass (150 passed, 4 skipped)
• Lint passes

Fixes#34384