QA: ensure all bedrock regional models have same supported_ as base + Anthropic nested pydantic object support (#7844)

* build: ensure all regional bedrock models have same supported values as base bedrock model

prevents drift

* test(base_llm_unit_tests.py): add testing for nested pydantic objects

* fix(test_utils.py): add test_get_potential_model_names

* fix(anthropic/chat/transformation.py): support nested pydantic objects

Fixes https://github.com/BerriAI/litellm/issues/7755

litellm/llms/base_llm/chat/transformation.py

@@ -4,13 +4,25 @@ Common base config for all LLM providers
 
 import types
 from abc import ABC, abstractmethod
-from typing import TYPE_CHECKING, Any, AsyncIterator, Iterator, List, Optional, Union
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    AsyncIterator,
+    Iterator,
+    List,
+    Optional,
+    Type,
+    Union,
+)
 
 import httpx
+from pydantic import BaseModel
 
 from litellm.types.llms.openai import AllMessageValues
 from litellm.types.utils import ModelResponse
 
+from ..base_utils import type_to_response_format_param
+
 if TYPE_CHECKING:
     from litellm.litellm_core_utils.litellm_logging import Logging as _LiteLLMLoggingObj
 
@@ -71,6 +83,11 @@ class BaseConfig(ABC):
             and v is not None
         }
 
+    def get_json_schema_from_pydantic_object(
+        self, response_format: Optional[Union[Type[BaseModel], dict]]
+    ) -> Optional[dict]:
+        return type_to_response_format_param(response_format=response_format)
+
     def should_fake_stream(
         self,
         model: Optional[str],