fix(adapters,vertex): pass output_config through to backends that accept it (closes #23380, supersedes #23475/#23396/#23706/#22727)

litellm/llms/anthropic/experimental_pass_through/adapters/handler.py

@@ -27,6 +27,16 @@
 if TYPE_CHECKING:
     pass
 
+
+# Anthropic-only fields that the translator above already maps into the
+# OpenAI-format completion_kwargs (output_config → reasoning_effort /
+# response_format, etc.). They must be filtered out of the raw
+# extra_kwargs re-merge below or non-Anthropic backends reject the call
+# with 400 "Extra inputs are not permitted". Add new entries here when
+# extending AnthropicMessagesRequestOptionalParams with another Anthropic-
+# specific key.
+ANTHROPIC_ONLY_REQUEST_KEYS: frozenset[str] = frozenset({"output_config"})
+
 ########################################################
 # init adapter
 ANTHROPIC_ADAPTER = AnthropicAdapter()
@@ -202,8 +212,12 @@ def _prepare_completion_kwargs(
             request_data["output_format"] = output_format
 
         # Extract output_config from extra_kwargs so the translator can use it
-        # (e.g. output_config.effort for adaptive thinking → reasoning_effort)
-        extra_kwargs = extra_kwargs or {}
+        # (e.g. output_config.effort for adaptive thinking → reasoning_effort,
+        # output_config.format → response_format for structured outputs).
+        # Use explicit None check rather than `or {}` so an explicit empty dict
+        # caller-passed argument is preserved (matters for tests that drive
+        # the fallback inference path).
+        extra_kwargs = extra_kwargs if extra_kwargs is not None else {}
         if "output_config" in extra_kwargs:
             request_data["output_config"] = extra_kwargs["output_config"]
 
@@ -225,8 +239,23 @@ def _prepare_completion_kwargs(
                 "include_usage": True,
             }
 
-        excluded_keys = {"anthropic_messages"}
-        extra_kwargs = extra_kwargs or {}
+        # Keys that must NOT be forwarded as raw extras into the OpenAI-format
+        # ``completion_kwargs`` after translation. The translator above has
+        # already consumed the meaningful parts of these inputs (e.g.
+        # ``output_config.format`` → ``response_format``, ``output_config.effort``
+        # → ``reasoning_effort`` for non-Claude targets). Re-adding the raw
+        # Anthropic-shaped key here causes 400 "Extra inputs are not permitted"
+        # on non-Anthropic backends (Azure OpenAI, Fireworks, Bedrock Nova,
+        # etc.) and is silently lossy on Anthropic-family targets, which would
+        # see the translated key ``response_format`` AND a duplicate, conflicting
+        # ``output_config``.
+        #
+        # Maintainability: when adding a new Anthropic-only request param to
+        # ``AnthropicMessagesRequestOptionalParams``, also extend
+        # ``ANTHROPIC_ONLY_REQUEST_KEYS`` here so it doesn't silently leak.
+        excluded_keys = ANTHROPIC_ONLY_REQUEST_KEYS | {"anthropic_messages"}
+        # NOTE: extra_kwargs was already coerced from None to {} at the top of
+        # this method (line ~220). It is guaranteed to be a dict here.
         for key, value in extra_kwargs.items():
             if (
                 key == "litellm_logging_obj"

litellm/llms/anthropic/experimental_pass_through/adapters/transformation.py

@@ -664,7 +664,7 @@ def translate_anthropic_messages_to_openai(  # noqa: PLR0915
 
     @staticmethod
     def translate_anthropic_thinking_to_reasoning_effort(
-        thinking: Dict[str, Any]
+        thinking: Dict[str, Any],
     ) -> Optional[str]:
         """
         Translate Anthropic's thinking parameter to OpenAI's reasoning_effort.
@@ -1081,10 +1081,23 @@ def _translate_output_format_to_openai(
         anthropic_message_request: AnthropicMessagesRequest,
         new_kwargs: ChatCompletionRequest,
     ) -> None:
-        """Translate output_format to response_format when applicable."""
-        if "output_format" not in anthropic_message_request:
-            return
-        output_format = anthropic_message_request["output_format"]
+        """Translate Anthropic structured-output config to OpenAI ``response_format``.
+
+        Accepts either the legacy top-level ``output_format`` field OR the
+        newer ``output_config.format`` (sub-key on ``output_config``) so that
+        both shapes flow through to non-Anthropic backends as
+        ``response_format``. Without the ``output_config.format`` branch,
+        callers using the new Anthropic Structured Outputs API would have
+        their schema silently dropped on the adapter path — only the legacy
+        top-level ``output_format`` was being mapped.
+
+        ``output_format`` takes precedence when both are provided.
+        """
+        output_format: Any = anthropic_message_request.get("output_format")
+        if not output_format:
+            output_config = anthropic_message_request.get("output_config")
+            if isinstance(output_config, dict):
+                output_format = output_config.get("format")
         if not output_format:
             return
         response_format = self.translate_anthropic_output_format_to_openai(

litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/experimental_pass_through/transformation.py

@@ -13,6 +13,7 @@
 from litellm.types.router import GenericLiteLLMParams
 
 from ....vertex_llm_base import VertexBase
+from ..output_params_utils import sanitize_vertex_anthropic_output_params
 
 
 class VertexAIPartnerModelsAnthropicMessagesConfig(AnthropicMessagesConfig, VertexBase):
@@ -158,12 +159,10 @@ def transform_anthropic_messages_request(
             "model", None
         )  # do not pass model in request body to vertex ai
 
-        anthropic_messages_request.pop(
-            "output_format", None
-        )  # do not pass output_format in request body to vertex ai - vertex ai does not support output_format as yet
-
-        anthropic_messages_request.pop(
-            "output_config", None
-        )  # do not pass output_config in request body to vertex ai - vertex ai does not support output_config
+        # Vertex AI Claude accepts ``output_config.format`` (structured outputs)
+        # and ``output_format``, but rejects ``output_config.effort`` with 400
+        # "Extra inputs are not permitted". Sanitize in place so the supported
+        # bits flow through.
+        sanitize_vertex_anthropic_output_params(anthropic_messages_request)
 
         return anthropic_messages_request

litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/output_params_utils.py

@@ -0,0 +1,50 @@
+"""
+Shared sanitization for ``output_config`` / ``output_format`` on Vertex AI
+Claude. Lives in its own module so both the chat-completion transformation
+(``transformation.py``) and the Messages pass-through transformation
+(``experimental_pass_through/transformation.py``) can import it without
+forming a cycle through the parent module's heavier imports.
+
+CodeQL flagged the ``..transformation`` import path as a potential cyclic
+import; extracting the helper into a leaf module resolves the warning and
+keeps the parent module's import surface narrow.
+"""
+
+# Keys inside ``output_config`` that Vertex AI Claude does not accept.
+# Today only ``effort`` triggers "Extra inputs are not permitted"; add new
+# entries here as Vertex parity drifts. Keep this list narrow — anything
+# Vertex DOES accept (e.g. ``format`` for structured outputs) must be
+# preserved so callers can rely on Anthropic-native features.
+VERTEX_UNSUPPORTED_OUTPUT_CONFIG_KEYS: frozenset = frozenset({"effort"})
+
+
+def sanitize_vertex_anthropic_output_params(data: dict) -> None:
+    """
+    Strip Vertex-unsupported keys from ``output_config`` /
+    ``output_format`` in-place; forward whatever remains.
+
+    Behavior:
+      * ``output_config`` containing only unsupported keys (e.g. ``effort``
+        alone) is removed entirely so the request body has no empty dict.
+      * ``output_config`` containing a mix of supported + unsupported keys
+        has the unsupported subset filtered out and the rest forwarded.
+      * ``output_config`` that is supported in full passes through unchanged.
+      * ``output_format`` is forwarded as-is (Vertex AI Claude accepts it).
+      * Non-dict values for ``output_config`` are dropped to avoid sending
+        malformed payloads downstream.
+    """
+    output_config = data.get("output_config")
+    if output_config is None:
+        return
+    if not isinstance(output_config, dict):
+        data.pop("output_config", None)
+        return
+    sanitized = {
+        k: v
+        for k, v in output_config.items()
+        if k not in VERTEX_UNSUPPORTED_OUTPUT_CONFIG_KEYS
+    }
+    if sanitized:
+        data["output_config"] = sanitized
+    else:
+        data.pop("output_config", None)

litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/transformation.py

@@ -10,6 +10,7 @@
 from litellm.types.utils import ModelResponse
 
 from ....anthropic.chat.transformation import AnthropicConfig
+from .output_params_utils import sanitize_vertex_anthropic_output_params
 
 
 class VertexAIError(Exception):
@@ -105,11 +106,12 @@ def transform_request(
 
         data.pop("model", None)  # vertex anthropic doesn't accept 'model' parameter
 
-        # VertexAI doesn't support output_format parameter, remove it if present
-        data.pop("output_format", None)
-
-        # VertexAI doesn't support output_config parameter, remove it if present
-        data.pop("output_config", None)
+        # Vertex AI Claude accepts ``output_config.format`` (structured outputs /
+        # JSON Schema) but NOT ``output_config.effort`` — sending ``effort`` to
+        # Vertex returns 400 "Extra inputs are not permitted". Sanitize in place:
+        # forward the structured-output bits, drop the unsupported keys.
+        # Same treatment for the legacy top-level ``output_format`` field.
+        sanitize_vertex_anthropic_output_params(data)
 
         tools = optional_params.get("tools")
         tool_search_used = self.is_tool_search_used(tools)