From eb25d7472d969976859d677c74a2188dcec85ac4 Mon Sep 17 00:00:00 2001
From: OysterMax <sma@esri.com>
Date: Fri, 16 May 2025 13:20:32 -0700
Subject: [PATCH] core: support `Union` type args in strict mode of OpenAI
 function calling / structured output (#30971)

**Issue:**[
#309070](https://github.com/langchain-ai/langchain/issues/30970)

**Cause**
Arg type in python code
```
arg: Union[SubSchema1, SubSchema2]
```
is translated to `anyOf` in **json schema**
```
"anyOf" : [{sub schema 1 ...}, {sub schema 1 ...}]
```
The value of anyOf is a list sub schemas.
The bug is caused since the sub schemas inside `anyOf` list is not taken
care of.
The location where the issue happens is `convert_to_openai_function`
function -> `_recursive_set_additional_properties_false` function, that
recursively adds `"additionalProperties": false` to json schema which is
[required by OpenAI's strict function
calling](https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses#additionalproperties-false-must-always-be-set-in-objects)

**Solution:**
This PR fixes this issue by iterating each sub schema inside `anyOf`
list.
A unit test is added.

**Twitter handle:** shengboma


If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.

---------

Co-authored-by: ccurme <chester.curme@gmail.com>
---
 .../langchain_core/utils/function_calling.py  |  7 ++-
 .../unit_tests/utils/test_function_calling.py | 55 +++++++++++++++++++
 2 files changed, 60 insertions(+), 2 deletions(-)

diff --git a/libs/core/langchain_core/utils/function_calling.py b/libs/core/langchain_core/utils/function_calling.py
index c664ec03e3d..aa288bedc53 100644
--- a/libs/core/langchain_core/utils/function_calling.py
+++ b/libs/core/langchain_core/utils/function_calling.py
@@ -788,9 +788,12 @@ def _recursive_set_additional_properties_false(
             schema["additionalProperties"] = False
 
         # Recursively check 'properties' and 'items' if they exist
+        if "anyOf" in schema:
+            for sub_schema in schema["anyOf"]:
+                _recursive_set_additional_properties_false(sub_schema)
         if "properties" in schema:
-            for value in schema["properties"].values():
-                _recursive_set_additional_properties_false(value)
+            for sub_schema in schema["properties"].values():
+                _recursive_set_additional_properties_false(sub_schema)
         if "items" in schema:
             _recursive_set_additional_properties_false(schema["items"])
 
diff --git a/libs/core/tests/unit_tests/utils/test_function_calling.py b/libs/core/tests/unit_tests/utils/test_function_calling.py
index 126c1753f4e..f75ae304937 100644
--- a/libs/core/tests/unit_tests/utils/test_function_calling.py
+++ b/libs/core/tests/unit_tests/utils/test_function_calling.py
@@ -497,6 +497,61 @@ def test_convert_to_openai_function_nested_strict() -> None:
     assert actual == expected
 
 
+def test_convert_to_openai_function_strict_union_of_objects_arg_type() -> None:
+    class NestedA(BaseModel):
+        foo: str
+
+    class NestedB(BaseModel):
+        bar: int
+
+    class NestedC(BaseModel):
+        baz: bool
+
+    def my_function(my_arg: Union[NestedA, NestedB, NestedC]) -> None:
+        """Dummy function."""
+
+    expected = {
+        "name": "my_function",
+        "description": "Dummy function.",
+        "parameters": {
+            "properties": {
+                "my_arg": {
+                    "anyOf": [
+                        {
+                            "properties": {"foo": {"title": "Foo", "type": "string"}},
+                            "required": ["foo"],
+                            "title": "NestedA",
+                            "type": "object",
+                            "additionalProperties": False,
+                        },
+                        {
+                            "properties": {"bar": {"title": "Bar", "type": "integer"}},
+                            "required": ["bar"],
+                            "title": "NestedB",
+                            "type": "object",
+                            "additionalProperties": False,
+                        },
+                        {
+                            "properties": {"baz": {"title": "Baz", "type": "boolean"}},
+                            "required": ["baz"],
+                            "title": "NestedC",
+                            "type": "object",
+                            "additionalProperties": False,
+                        },
+                    ]
+                }
+            },
+            "required": ["my_arg"],
+            "type": "object",
+            "additionalProperties": False,
+        },
+        "strict": True,
+    }
+
+    actual = convert_to_openai_function(my_function, strict=True)
+    assert actual == expected
+
+
 json_schema_no_description_no_params = {
     "title": "dummy_function",
 }