Merge pull request #19565 from BerriAI/litellm_staging_01_21_2026_fixes

Litellm staging 01 21 2026 fixes

litellm/llms/bedrock/common_utils.py

@@ -10,7 +10,6 @@ from typing import TYPE_CHECKING, Dict, List, Literal, Optional, Union
 
 if TYPE_CHECKING:
     from litellm.types.llms.bedrock import BedrockCreateBatchRequest
-    from litellm.types.utils import ProviderSpecificModelInfo
 
 import httpx
 
@@ -486,21 +485,21 @@ class BedrockModelInfo(BaseLLMModelInfo):
     ) -> List[str]:
         return []
 
-    def get_provider_info(self, model: str) -> Optional[ProviderSpecificModelInfo]:
-        """
-        Handles Bedrock throughput suffixes like ":28k", ":51k".
-        """
-        import re
+    # def get_provider_info(self, model: str) -> Optional[ProviderSpecificModelInfo]:
+    #     """
+    #     Handles Bedrock throughput suffixes like ":28k", ":51k".
+    #     """
+    #     import re
 
-        overrides: ProviderSpecificModelInfo = {}
+    #     overrides: ProviderSpecificModelInfo = {}
 
-        # Parse context window suffix (e.g., :28k, :51k)
-        match = re.search(r":(\d+)k$", model)
-        if match:
-            throughput_value = int(match.group(1)) * 1000
-            overrides["max_input_tokens"] = throughput_value
+    #     # Parse context window suffix (e.g., :28k, :51k)
+    #     match = re.search(r":(\d+)k$", model)
+    #     if match:
+    #         throughput_value = int(match.group(1)) * 1000
+    #         overrides["max_input_tokens"] = throughput_value
 
-        return overrides if overrides else None
+    #     return overrides if overrides else None
 
     def get_token_counter(self) -> Optional[BaseTokenCounter]:
         """

litellm/main.py

@@ -599,9 +599,8 @@ async def acompletion( # noqa: PLR0915
         ctx = contextvars.copy_context()
         func_with_context = partial(ctx.run, func)
 
-        # Wrap with timeout if specified
-        if timeout is not None:
-            timeout_value = float(timeout) if not isinstance(timeout, (int, float)) else timeout
+        if timeout is not None and isinstance(timeout, (int, float)):
+            timeout_value = float(timeout)
             init_response = await asyncio.wait_for(
                 loop.run_in_executor(None, func_with_context),
                 timeout=timeout_value
@@ -616,8 +615,8 @@ async def acompletion( # noqa: PLR0915
                 response = ModelResponse(**init_response)
             response = init_response
         elif asyncio.iscoroutine(init_response):
-            if timeout is not None:
-                timeout_value = float(timeout) if not isinstance(timeout, (int, float)) else timeout
+            if timeout is not None and isinstance(timeout, (int, float)):
+                timeout_value = float(timeout)
                 response = await asyncio.wait_for(init_response, timeout=timeout_value)
             else:
                 response = await init_response

litellm/types/llms/openai.py

@@ -71,7 +71,7 @@ from openai.types.responses.response_create_params import (
     ToolParam,
 )
 from openai.types.responses.response_function_tool_call import ResponseFunctionToolCall
-from pydantic import BaseModel, ConfigDict, Discriminator, PrivateAttr
+from pydantic import BaseModel, ConfigDict, Discriminator, PrivateAttr, field_validator
 from typing_extensions import Annotated, Dict, Required, TypedDict, override
 
 from litellm.types.llms.base import BaseLiteLLMOpenAIResponseObject
@@ -1199,6 +1199,16 @@ class ResponsesAPIResponse(BaseLiteLLMOpenAIResponseObject):
     # Define private attributes using PrivateAttr
     _hidden_params: dict = PrivateAttr(default_factory=dict)
 
+    @field_validator("usage", mode="before")
+    @classmethod
+    def validate_usage(cls, value):
+        """Convert usage dict to ResponseAPIUsage object if needed"""
+        if value is None:
+            return value
+        if isinstance(value, dict):
+            return ResponseAPIUsage(**value)
+        return value
+
     @property
     def output_text(self) -> str:
         """

tests/image_gen_tests/test_image_generation.py

@@ -112,7 +112,7 @@ class TestVertexImageGeneration(BaseImageGenTest):
 
         litellm.in_memory_llm_clients_cache = InMemoryCache()
         return {
-            "model": "vertex_ai/imagegeneration@006",
+            "model": "vertex_ai/imagen-3.0-fast-generate-001",
             "vertex_ai_project": "pathrise-convert-1606954137718",
             "vertex_ai_location": "us-central1",
             "n": 1,

tests/llm_translation/test_anthropic_completion.py

@@ -1594,7 +1594,6 @@ def test_anthropic_via_responses_api():
         ResponsesAPIStreamEvents.RESPONSE_CREATED,
         ResponsesAPIStreamEvents.RESPONSE_IN_PROGRESS,
         ResponsesAPIStreamEvents.OUTPUT_ITEM_ADDED,
-        ResponsesAPIStreamEvents.CONTENT_PART_ADDED,
         ResponsesAPIStreamEvents.OUTPUT_TEXT_DELTA,  # Can occur multiple times
         ResponsesAPIStreamEvents.OUTPUT_TEXT_DONE,
         ResponsesAPIStreamEvents.CONTENT_PART_DONE,