chore: initial snapshot for gitea/github upload

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/__init__.py

@@ -0,0 +1,15 @@
+from typing import Type, Union
+
+from .batches.transformation import AnthropicBatchesConfig
+from .chat.transformation import AnthropicConfig
+
+__all__ = ["AnthropicBatchesConfig", "AnthropicConfig"]
+
+
+def get_anthropic_config(
+    url_route: str,
+) -> Union[Type[AnthropicBatchesConfig], Type[AnthropicConfig]]:
+    if "messages/batches" in url_route and "results" in url_route:
+        return AnthropicBatchesConfig
+    else:
+        return AnthropicConfig

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/batches/__init__.py

@@ -0,0 +1,4 @@
+from .handler import AnthropicBatchesHandler
+from .transformation import AnthropicBatchesConfig
+
+__all__ = ["AnthropicBatchesHandler", "AnthropicBatchesConfig"]

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/batches/handler.py

@@ -0,0 +1,167 @@
+"""
+Anthropic Batches API Handler
+"""
+
+import asyncio
+from typing import TYPE_CHECKING, Any, Coroutine, Optional, Union
+
+import httpx
+
+from litellm.llms.custom_httpx.http_handler import (
+    get_async_httpx_client,
+)
+from litellm.types.utils import LiteLLMBatch, LlmProviders
+
+if TYPE_CHECKING:
+    from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
+else:
+    LiteLLMLoggingObj = Any
+
+from ..common_utils import AnthropicModelInfo
+from .transformation import AnthropicBatchesConfig
+
+
+class AnthropicBatchesHandler:
+    """
+    Handler for Anthropic Message Batches API.
+
+    Supports:
+    - retrieve_batch() - Retrieve batch status and information
+    """
+
+    def __init__(self):
+        self.anthropic_model_info = AnthropicModelInfo()
+        self.provider_config = AnthropicBatchesConfig()
+
+    async def aretrieve_batch(
+        self,
+        batch_id: str,
+        api_base: Optional[str],
+        api_key: Optional[str],
+        timeout: Union[float, httpx.Timeout],
+        max_retries: Optional[int],
+        logging_obj: Optional[LiteLLMLoggingObj] = None,
+    ) -> LiteLLMBatch:
+        """
+        Async: Retrieve a batch from Anthropic.
+
+        Args:
+            batch_id: The batch ID to retrieve
+            api_base: Anthropic API base URL
+            api_key: Anthropic API key
+            timeout: Request timeout
+            max_retries: Max retry attempts (unused for now)
+            logging_obj: Optional logging object
+
+        Returns:
+            LiteLLMBatch: Batch information in OpenAI format
+        """
+        # Resolve API credentials
+        api_base = api_base or self.anthropic_model_info.get_api_base(api_base)
+        api_key = api_key or self.anthropic_model_info.get_api_key()
+
+        if not api_key:
+            raise ValueError("Missing Anthropic API Key")
+
+        # Create a minimal logging object if not provided
+        if logging_obj is None:
+            from litellm.litellm_core_utils.litellm_logging import (
+                Logging as LiteLLMLoggingObjClass,
+            )
+
+            logging_obj = LiteLLMLoggingObjClass(
+                model="anthropic/unknown",
+                messages=[],
+                stream=False,
+                call_type="batch_retrieve",
+                start_time=None,
+                litellm_call_id=f"batch_retrieve_{batch_id}",
+                function_id="batch_retrieve",
+            )
+
+        # Get the complete URL for batch retrieval
+        retrieve_url = self.provider_config.get_retrieve_batch_url(
+            api_base=api_base,
+            batch_id=batch_id,
+            optional_params={},
+            litellm_params={},
+        )
+
+        # Validate environment and get headers
+        headers = self.provider_config.validate_environment(
+            headers={},
+            model="",
+            messages=[],
+            optional_params={},
+            litellm_params={},
+            api_key=api_key,
+            api_base=api_base,
+        )
+
+        logging_obj.pre_call(
+            input=batch_id,
+            api_key=api_key,
+            additional_args={
+                "api_base": retrieve_url,
+                "headers": headers,
+                "complete_input_dict": {},
+            },
+        )
+        # Make the request
+        async_client = get_async_httpx_client(llm_provider=LlmProviders.ANTHROPIC)
+        response = await async_client.get(url=retrieve_url, headers=headers)
+        response.raise_for_status()
+
+        # Transform response to LiteLLM format
+        return self.provider_config.transform_retrieve_batch_response(
+            model=None,
+            raw_response=response,
+            logging_obj=logging_obj,
+            litellm_params={},
+        )
+
+    def retrieve_batch(
+        self,
+        _is_async: bool,
+        batch_id: str,
+        api_base: Optional[str],
+        api_key: Optional[str],
+        timeout: Union[float, httpx.Timeout],
+        max_retries: Optional[int],
+        logging_obj: Optional[LiteLLMLoggingObj] = None,
+    ) -> Union[LiteLLMBatch, Coroutine[Any, Any, LiteLLMBatch]]:
+        """
+        Retrieve a batch from Anthropic.
+
+        Args:
+            _is_async: Whether to run asynchronously
+            batch_id: The batch ID to retrieve
+            api_base: Anthropic API base URL
+            api_key: Anthropic API key
+            timeout: Request timeout
+            max_retries: Max retry attempts (unused for now)
+            logging_obj: Optional logging object
+
+        Returns:
+            LiteLLMBatch or Coroutine: Batch information in OpenAI format
+        """
+        if _is_async:
+            return self.aretrieve_batch(
+                batch_id=batch_id,
+                api_base=api_base,
+                api_key=api_key,
+                timeout=timeout,
+                max_retries=max_retries,
+                logging_obj=logging_obj,
+            )
+        else:
+            return asyncio.run(
+                self.aretrieve_batch(
+                    batch_id=batch_id,
+                    api_base=api_base,
+                    api_key=api_key,
+                    timeout=timeout,
+                    max_retries=max_retries,
+                    logging_obj=logging_obj,
+                )
+            )

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/batches/transformation.py

@@ -0,0 +1,312 @@
+import json
+import time
+from typing import TYPE_CHECKING, Any, Dict, List, Literal, Optional, Union, cast
+
+import httpx
+from httpx import Headers, Response
+
+from litellm.llms.base_llm.batches.transformation import BaseBatchesConfig
+from litellm.llms.base_llm.chat.transformation import BaseLLMException
+from litellm.types.llms.openai import AllMessageValues, CreateBatchRequest
+from litellm.types.utils import LiteLLMBatch, LlmProviders, ModelResponse
+
+if TYPE_CHECKING:
+    from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
+
+    LoggingClass = LiteLLMLoggingObj
+else:
+    LoggingClass = Any
+
+
+class AnthropicBatchesConfig(BaseBatchesConfig):
+    def __init__(self):
+        from ..chat.transformation import AnthropicConfig
+        from ..common_utils import AnthropicModelInfo
+
+        self.anthropic_chat_config = AnthropicConfig()  # initialize once
+        self.anthropic_model_info = AnthropicModelInfo()
+
+    @property
+    def custom_llm_provider(self) -> LlmProviders:
+        """Return the LLM provider type for this configuration."""
+        return LlmProviders.ANTHROPIC
+
+    def validate_environment(
+        self,
+        headers: dict,
+        model: str,
+        messages: List[AllMessageValues],
+        optional_params: dict,
+        litellm_params: dict,
+        api_key: Optional[str] = None,
+        api_base: Optional[str] = None,
+    ) -> dict:
+        """Validate and prepare environment-specific headers and parameters."""
+        # Resolve api_key from environment if not provided
+        api_key = api_key or self.anthropic_model_info.get_api_key()
+        if api_key is None:
+            raise ValueError(
+                "Missing Anthropic API Key - A call is being made to anthropic but no key is set either in the environment variables or via params"
+            )
+        _headers = {
+            "accept": "application/json",
+            "anthropic-version": "2023-06-01",
+            "content-type": "application/json",
+            "x-api-key": api_key,
+        }
+        # Add beta header for message batches
+        if "anthropic-beta" not in headers:
+            headers["anthropic-beta"] = "message-batches-2024-09-24"
+        headers.update(_headers)
+        return headers
+
+    def get_complete_batch_url(
+        self,
+        api_base: Optional[str],
+        api_key: Optional[str],
+        model: str,
+        optional_params: Dict,
+        litellm_params: Dict,
+        data: CreateBatchRequest,
+    ) -> str:
+        """Get the complete URL for batch creation request."""
+        api_base = api_base or self.anthropic_model_info.get_api_base(api_base)
+        if not api_base.endswith("/v1/messages/batches"):
+            api_base = f"{api_base.rstrip('/')}/v1/messages/batches"
+        return api_base
+
+    def transform_create_batch_request(
+        self,
+        model: str,
+        create_batch_data: CreateBatchRequest,
+        optional_params: dict,
+        litellm_params: dict,
+    ) -> Union[bytes, str, Dict[str, Any]]:
+        """
+        Transform the batch creation request to Anthropic format.
+
+        Not currently implemented - placeholder to satisfy abstract base class.
+        """
+        raise NotImplementedError("Batch creation not yet implemented for Anthropic")
+
+    def transform_create_batch_response(
+        self,
+        model: Optional[str],
+        raw_response: httpx.Response,
+        logging_obj: LoggingClass,
+        litellm_params: dict,
+    ) -> LiteLLMBatch:
+        """
+        Transform Anthropic MessageBatch creation response to LiteLLM format.
+
+        Not currently implemented - placeholder to satisfy abstract base class.
+        """
+        raise NotImplementedError("Batch creation not yet implemented for Anthropic")
+
+    def get_retrieve_batch_url(
+        self,
+        api_base: Optional[str],
+        batch_id: str,
+        optional_params: Dict,
+        litellm_params: Dict,
+    ) -> str:
+        """
+        Get the complete URL for batch retrieval request.
+
+        Args:
+            api_base: Base API URL (optional, will use default if not provided)
+            batch_id: Batch ID to retrieve
+            optional_params: Optional parameters
+            litellm_params: LiteLLM parameters
+
+        Returns:
+            Complete URL for Anthropic batch retrieval: {api_base}/v1/messages/batches/{batch_id}
+        """
+        api_base = api_base or self.anthropic_model_info.get_api_base(api_base)
+        return f"{api_base.rstrip('/')}/v1/messages/batches/{batch_id}"
+
+    def transform_retrieve_batch_request(
+        self,
+        batch_id: str,
+        optional_params: dict,
+        litellm_params: dict,
+    ) -> Union[bytes, str, Dict[str, Any]]:
+        """
+        Transform batch retrieval request for Anthropic.
+
+        For Anthropic, the URL is constructed by get_retrieve_batch_url(),
+        so this method returns an empty dict (no additional request params needed).
+        """
+        # No additional request params needed - URL is handled by get_retrieve_batch_url
+        return {}
+
+    def transform_retrieve_batch_response(
+        self,
+        model: Optional[str],
+        raw_response: httpx.Response,
+        logging_obj: LoggingClass,
+        litellm_params: dict,
+    ) -> LiteLLMBatch:
+        """Transform Anthropic MessageBatch retrieval response to LiteLLM format."""
+        try:
+            response_data = raw_response.json()
+        except Exception as e:
+            raise ValueError(f"Failed to parse Anthropic batch response: {e}")
+
+        # Map Anthropic MessageBatch to OpenAI Batch format
+        batch_id = response_data.get("id", "")
+        processing_status = response_data.get("processing_status", "in_progress")
+
+        # Map Anthropic processing_status to OpenAI status
+        status_mapping: Dict[
+            str,
+            Literal[
+                "validating",
+                "failed",
+                "in_progress",
+                "finalizing",
+                "completed",
+                "expired",
+                "cancelling",
+                "cancelled",
+            ],
+        ] = {
+            "in_progress": "in_progress",
+            "canceling": "cancelling",
+            "ended": "completed",
+        }
+        openai_status = status_mapping.get(processing_status, "in_progress")
+
+        # Parse timestamps
+        def parse_timestamp(ts_str: Optional[str]) -> Optional[int]:
+            if not ts_str:
+                return None
+            try:
+                from datetime import datetime
+
+                dt = datetime.fromisoformat(ts_str.replace("Z", "+00:00"))
+                return int(dt.timestamp())
+            except Exception:
+                return None
+
+        created_at = parse_timestamp(response_data.get("created_at"))
+        ended_at = parse_timestamp(response_data.get("ended_at"))
+        expires_at = parse_timestamp(response_data.get("expires_at"))
+        cancel_initiated_at = parse_timestamp(response_data.get("cancel_initiated_at"))
+        archived_at = parse_timestamp(response_data.get("archived_at"))
+
+        # Extract request counts
+        request_counts_data = response_data.get("request_counts", {})
+        from openai.types.batch import BatchRequestCounts
+
+        request_counts = BatchRequestCounts(
+            total=sum(
+                [
+                    request_counts_data.get("processing", 0),
+                    request_counts_data.get("succeeded", 0),
+                    request_counts_data.get("errored", 0),
+                    request_counts_data.get("canceled", 0),
+                    request_counts_data.get("expired", 0),
+                ]
+            ),
+            completed=request_counts_data.get("succeeded", 0),
+            failed=request_counts_data.get("errored", 0),
+        )
+
+        return LiteLLMBatch(
+            id=batch_id,
+            object="batch",
+            endpoint="/v1/messages",
+            errors=None,
+            input_file_id="None",
+            completion_window="24h",
+            status=openai_status,
+            output_file_id=batch_id,
+            error_file_id=None,
+            created_at=created_at or int(time.time()),
+            in_progress_at=created_at if processing_status == "in_progress" else None,
+            expires_at=expires_at,
+            finalizing_at=None,
+            completed_at=ended_at if processing_status == "ended" else None,
+            failed_at=None,
+            expired_at=archived_at if archived_at else None,
+            cancelling_at=cancel_initiated_at
+            if processing_status == "canceling"
+            else None,
+            cancelled_at=ended_at
+            if processing_status == "canceling" and ended_at
+            else None,
+            request_counts=request_counts,
+            metadata={},
+        )
+
+    def get_error_class(
+        self, error_message: str, status_code: int, headers: Union[Dict, Headers]
+    ) -> "BaseLLMException":
+        """Get the appropriate error class for Anthropic."""
+        from ..common_utils import AnthropicError
+
+        # Convert Dict to Headers if needed
+        if isinstance(headers, dict):
+            headers_obj: Optional[Headers] = Headers(headers)
+        else:
+            headers_obj = headers if isinstance(headers, Headers) else None
+
+        return AnthropicError(
+            status_code=status_code, message=error_message, headers=headers_obj
+        )
+
+    def transform_response(
+        self,
+        model: str,
+        raw_response: Response,
+        model_response: ModelResponse,
+        logging_obj: LoggingClass,
+        request_data: Dict,
+        messages: List[AllMessageValues],
+        optional_params: Dict,
+        litellm_params: dict,
+        encoding: Any,
+        api_key: Optional[str] = None,
+        json_mode: Optional[bool] = None,
+    ) -> ModelResponse:
+        from litellm.cost_calculator import BaseTokenUsageProcessor
+        from litellm.types.utils import Usage
+
+        response_text = raw_response.text.strip()
+        all_usage: List[Usage] = []
+
+        try:
+            # Split by newlines and try to parse each line as JSON
+            lines = response_text.split("\n")
+            for line in lines:
+                line = line.strip()
+                if not line:
+                    continue
+                try:
+                    response_json = json.loads(line)
+                    # Update model_response with the parsed JSON
+                    completion_response = response_json["result"]["message"]
+                    transformed_response = (
+                        self.anthropic_chat_config.transform_parsed_response(
+                            completion_response=completion_response,
+                            raw_response=raw_response,
+                            model_response=model_response,
+                        )
+                    )
+
+                    transformed_response_usage = getattr(
+                        transformed_response, "usage", None
+                    )
+                    if transformed_response_usage:
+                        all_usage.append(cast(Usage, transformed_response_usage))
+                except json.JSONDecodeError:
+                    continue
+
+            ## SUM ALL USAGE
+            combined_usage = BaseTokenUsageProcessor.combine_usage_objects(all_usage)
+            setattr(model_response, "usage", combined_usage)
+
+            return model_response
+        except Exception as e:
+            raise e

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/chat/__init__.py

@@ -0,0 +1 @@
+from .handler import AnthropicChatCompletion, ModelResponseIterator

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/chat/guardrail_translation/__init__.py

@@ -0,0 +1,10 @@
+from litellm.llms.anthropic.chat.guardrail_translation.handler import (
+    AnthropicMessagesHandler,
+)
+from litellm.types.utils import CallTypes
+
+guardrail_translation_mappings = {
+    CallTypes.anthropic_messages: AnthropicMessagesHandler,
+}
+
+__all__ = ["guardrail_translation_mappings"]

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/chat/guardrail_translation/handler.py

@@ -0,0 +1,688 @@
+"""
+Anthropic Message Handler for Unified Guardrails
+
+This module provides a class-based handler for Anthropic-format messages.
+The class methods can be overridden for custom behavior.
+
+Pattern Overview:
+-----------------
+1. Extract text content from messages/responses (both string and list formats)
+2. Create async tasks to apply guardrails to each text segment
+3. Track mappings to know where each response belongs
+4. Apply guardrail responses back to the original structure
+"""
+
+import json
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, cast
+
+from litellm._logging import verbose_proxy_logger
+from litellm.llms.anthropic.chat.transformation import AnthropicConfig
+from litellm.llms.anthropic.experimental_pass_through.adapters.transformation import (
+    LiteLLMAnthropicMessagesAdapter,
+)
+from litellm.llms.base_llm.guardrail_translation.base_translation import BaseTranslation
+from litellm.proxy.pass_through_endpoints.llm_provider_handlers.anthropic_passthrough_logging_handler import (
+    AnthropicPassthroughLoggingHandler,
+)
+from litellm.types.llms.anthropic import (
+    AllAnthropicToolsValues,
+    AnthropicMessagesRequest,
+)
+from litellm.types.llms.openai import (
+    ChatCompletionToolCallChunk,
+    ChatCompletionToolParam,
+)
+from litellm.types.utils import (
+    ChatCompletionMessageToolCall,
+    Choices,
+    GenericGuardrailAPIInputs,
+    ModelResponse,
+)
+
+if TYPE_CHECKING:
+    from litellm.integrations.custom_guardrail import CustomGuardrail
+    from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
+    from litellm.types.llms.anthropic_messages.anthropic_response import (
+        AnthropicMessagesResponse,
+    )
+
+
+class AnthropicMessagesHandler(BaseTranslation):
+    """
+    Handler for processing Anthropic messages with guardrails.
+
+    This class provides methods to:
+    1. Process input messages (pre-call hook)
+    2. Process output responses (post-call hook)
+
+    Methods can be overridden to customize behavior for different message formats.
+    """
+
+    def __init__(self):
+        super().__init__()
+        self.adapter = LiteLLMAnthropicMessagesAdapter()
+
+    async def process_input_messages(
+        self,
+        data: dict,
+        guardrail_to_apply: "CustomGuardrail",
+        litellm_logging_obj: Optional[Any] = None,
+    ) -> Any:
+        """
+        Process input messages by applying guardrails to text content.
+        """
+        messages = data.get("messages")
+        if messages is None:
+            return data
+
+        (
+            chat_completion_compatible_request,
+            _tool_name_mapping,
+        ) = LiteLLMAnthropicMessagesAdapter().translate_anthropic_to_openai(
+            # Use a shallow copy to avoid mutating request data (pop on litellm_metadata).
+            anthropic_message_request=cast(AnthropicMessagesRequest, data.copy())
+        )
+
+        structured_messages = chat_completion_compatible_request.get("messages", [])
+
+        texts_to_check: List[str] = []
+        images_to_check: List[str] = []
+        tools_to_check: List[
+            ChatCompletionToolParam
+        ] = chat_completion_compatible_request.get("tools", [])
+        task_mappings: List[Tuple[int, Optional[int]]] = []
+        # Track (message_index, content_index) for each text
+        # content_index is None for string content, int for list content
+
+        # Step 1: Extract all text content and images
+        for msg_idx, message in enumerate(messages):
+            self._extract_input_text_and_images(
+                message=message,
+                msg_idx=msg_idx,
+                texts_to_check=texts_to_check,
+                images_to_check=images_to_check,
+                task_mappings=task_mappings,
+            )
+
+        # Step 2: Apply guardrail to all texts in batch
+        if texts_to_check:
+            inputs = GenericGuardrailAPIInputs(texts=texts_to_check)
+            if images_to_check:
+                inputs["images"] = images_to_check
+            if tools_to_check:
+                inputs["tools"] = tools_to_check
+            if structured_messages:
+                inputs["structured_messages"] = structured_messages
+            # Include model information if available
+            model = data.get("model")
+            if model:
+                inputs["model"] = model
+            guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
+                inputs=inputs,
+                request_data=data,
+                input_type="request",
+                logging_obj=litellm_logging_obj,
+            )
+
+            guardrailed_texts = guardrailed_inputs.get("texts", [])
+            guardrailed_tools = guardrailed_inputs.get("tools")
+            if guardrailed_tools is not None:
+                data["tools"] = guardrailed_tools
+
+            # Step 3: Map guardrail responses back to original message structure
+            await self._apply_guardrail_responses_to_input(
+                messages=messages,
+                responses=guardrailed_texts,
+                task_mappings=task_mappings,
+            )
+
+        verbose_proxy_logger.debug(
+            "Anthropic Messages: Processed input messages: %s", messages
+        )
+
+        return data
+
+    def extract_request_tool_names(self, data: dict) -> List[str]:
+        """Extract tool names from Anthropic messages request (tools[].name)."""
+        names: List[str] = []
+        for tool in data.get("tools") or []:
+            if isinstance(tool, dict) and tool.get("name"):
+                names.append(str(tool["name"]))
+        return names
+
+    def _extract_input_text_and_images(
+        self,
+        message: Dict[str, Any],
+        msg_idx: int,
+        texts_to_check: List[str],
+        images_to_check: List[str],
+        task_mappings: List[Tuple[int, Optional[int]]],
+    ) -> None:
+        """
+        Extract text content and images from a message.
+
+        Override this method to customize text/image extraction logic.
+        """
+        content = message.get("content", None)
+        tools = message.get("tools", None)
+        if content is None and tools is None:
+            return
+
+        ## CHECK FOR TEXT + IMAGES
+        if content is not None and isinstance(content, str):
+            # Simple string content
+            texts_to_check.append(content)
+            task_mappings.append((msg_idx, None))
+
+        elif content is not None and isinstance(content, list):
+            # List content (e.g., multimodal with text and images)
+            for content_idx, content_item in enumerate(content):
+                # Extract text
+                text_str = content_item.get("text", None)
+                if text_str is not None:
+                    texts_to_check.append(text_str)
+                    task_mappings.append((msg_idx, int(content_idx)))
+
+                # Extract images
+                if content_item.get("type") == "image":
+                    source = content_item.get("source", {})
+                    if isinstance(source, dict):
+                        # Could be base64 or url
+                        data = source.get("data")
+                        if data:
+                            images_to_check.append(data)
+
+    def _extract_input_tools(
+        self,
+        tools: List[Dict[str, Any]],
+        tools_to_check: List[ChatCompletionToolParam],
+    ) -> None:
+        """
+        Extract tools from a message.
+        """
+        ## CHECK FOR TOOLS
+        if tools is not None and isinstance(tools, list):
+            # TRANSFORM ANTHROPIC TOOLS TO OPENAI TOOLS
+            openai_tools = self.adapter.translate_anthropic_tools_to_openai(
+                tools=cast(List[AllAnthropicToolsValues], tools)
+            )
+            tools_to_check.extend(openai_tools)  # type: ignore
+
+    async def _apply_guardrail_responses_to_input(
+        self,
+        messages: List[Dict[str, Any]],
+        responses: List[str],
+        task_mappings: List[Tuple[int, Optional[int]]],
+    ) -> None:
+        """
+        Apply guardrail responses back to input messages.
+
+        Override this method to customize how responses are applied.
+        """
+        for task_idx, guardrail_response in enumerate(responses):
+            mapping = task_mappings[task_idx]
+            msg_idx = cast(int, mapping[0])
+            content_idx_optional = cast(Optional[int], mapping[1])
+
+            content = messages[msg_idx].get("content", None)
+            if content is None:
+                continue
+
+            if isinstance(content, str) and content_idx_optional is None:
+                # Replace string content with guardrail response
+                messages[msg_idx]["content"] = guardrail_response
+
+            elif isinstance(content, list) and content_idx_optional is not None:
+                # Replace specific text item in list content
+                messages[msg_idx]["content"][content_idx_optional][
+                    "text"
+                ] = guardrail_response
+
+    async def process_output_response(
+        self,
+        response: "AnthropicMessagesResponse",
+        guardrail_to_apply: "CustomGuardrail",
+        litellm_logging_obj: Optional[Any] = None,
+        user_api_key_dict: Optional[Any] = None,
+    ) -> Any:
+        """
+        Process output response by applying guardrails to text content and tool calls.
+
+        Args:
+            response: Anthropic MessagesResponse object
+            guardrail_to_apply: The guardrail instance to apply
+            litellm_logging_obj: Optional logging object
+            user_api_key_dict: User API key metadata to pass to guardrails
+
+        Returns:
+            Modified response with guardrail applied to content
+
+        Response Format Support:
+            - List content: response.content = [
+                {"type": "text", "text": "text here"},
+                {"type": "tool_use", "id": "...", "name": "...", "input": {...}},
+                ...
+            ]
+        """
+        texts_to_check: List[str] = []
+        images_to_check: List[str] = []
+        tool_calls_to_check: List[ChatCompletionToolCallChunk] = []
+        task_mappings: List[Tuple[int, Optional[int]]] = []
+        # Track (content_index, None) for each text
+
+        # Handle both dict and object responses
+        response_content: List[Any] = []
+        if isinstance(response, dict):
+            response_content = response.get("content", []) or []
+        elif hasattr(response, "content"):
+            content = getattr(response, "content", None)
+            response_content = content or []
+        else:
+            response_content = []
+
+        if not response_content:
+            return response
+
+        # Step 1: Extract all text content and tool calls from response
+        for content_idx, content_block in enumerate(response_content):
+            # Handle both dict and Pydantic object content blocks
+            block_dict: Dict[str, Any] = {}
+            if isinstance(content_block, dict):
+                block_type = content_block.get("type")
+                block_dict = cast(Dict[str, Any], content_block)
+            elif hasattr(content_block, "type"):
+                block_type = getattr(content_block, "type", None)
+                # Convert Pydantic object to dict for processing
+                if hasattr(content_block, "model_dump"):
+                    block_dict = content_block.model_dump()
+                else:
+                    block_dict = {
+                        "type": block_type,
+                        "text": getattr(content_block, "text", None),
+                    }
+            else:
+                continue
+
+            if block_type in ["text", "tool_use"]:
+                self._extract_output_text_and_images(
+                    content_block=block_dict,
+                    content_idx=content_idx,
+                    texts_to_check=texts_to_check,
+                    images_to_check=images_to_check,
+                    task_mappings=task_mappings,
+                    tool_calls_to_check=tool_calls_to_check,
+                )
+
+        # Step 2: Apply guardrail to all texts in batch
+        if texts_to_check or tool_calls_to_check:
+            # Create a request_data dict with response info and user API key metadata
+            request_data: dict = {"response": response}
+
+            # Add user API key metadata with prefixed keys
+            user_metadata = self.transform_user_api_key_dict_to_metadata(
+                user_api_key_dict
+            )
+            if user_metadata:
+                request_data["litellm_metadata"] = user_metadata
+
+            inputs = GenericGuardrailAPIInputs(texts=texts_to_check)
+            if images_to_check:
+                inputs["images"] = images_to_check
+            if tool_calls_to_check:
+                inputs["tool_calls"] = tool_calls_to_check
+            # Include model information from the response if available
+            response_model = None
+            if isinstance(response, dict):
+                response_model = response.get("model")
+            elif hasattr(response, "model"):
+                response_model = getattr(response, "model", None)
+            if response_model:
+                inputs["model"] = response_model
+
+            guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
+                inputs=inputs,
+                request_data=request_data,
+                input_type="response",
+                logging_obj=litellm_logging_obj,
+            )
+
+            guardrailed_texts = guardrailed_inputs.get("texts", [])
+
+            # Step 3: Map guardrail responses back to original response structure
+            await self._apply_guardrail_responses_to_output(
+                response=response,
+                responses=guardrailed_texts,
+                task_mappings=task_mappings,
+            )
+
+        verbose_proxy_logger.debug(
+            "Anthropic Messages: Processed output response: %s", response
+        )
+
+        return response
+
+    async def process_output_streaming_response(
+        self,
+        responses_so_far: List[Any],
+        guardrail_to_apply: "CustomGuardrail",
+        litellm_logging_obj: Optional[Any] = None,
+        user_api_key_dict: Optional[Any] = None,
+    ) -> List[Any]:
+        """
+        Process output streaming response by applying guardrails to text content.
+
+        Get the string so far, check the apply guardrail to the string so far, and return the list of responses so far.
+        """
+        has_ended = self._check_streaming_has_ended(responses_so_far)
+        if has_ended:
+            # build the model response from the responses_so_far
+            built_response = (
+                AnthropicPassthroughLoggingHandler._build_complete_streaming_response(
+                    all_chunks=responses_so_far,
+                    litellm_logging_obj=cast("LiteLLMLoggingObj", litellm_logging_obj),
+                    model="",
+                )
+            )
+
+            # Check if model_response is valid and has choices before accessing
+            if (
+                built_response is not None
+                and hasattr(built_response, "choices")
+                and built_response.choices
+            ):
+                model_response = cast(ModelResponse, built_response)
+                first_choice = cast(Choices, model_response.choices[0])
+                tool_calls_list = cast(
+                    Optional[List[ChatCompletionMessageToolCall]],
+                    first_choice.message.tool_calls,
+                )
+                string_so_far = first_choice.message.content
+                guardrail_inputs = GenericGuardrailAPIInputs()
+                if string_so_far:
+                    guardrail_inputs["texts"] = [string_so_far]
+                if tool_calls_list:
+                    guardrail_inputs["tool_calls"] = tool_calls_list
+
+                _guardrailed_inputs = await guardrail_to_apply.apply_guardrail(  # allow rejecting the response, if invalid
+                    inputs=guardrail_inputs,
+                    request_data={},
+                    input_type="response",
+                    logging_obj=litellm_logging_obj,
+                )
+            else:
+                verbose_proxy_logger.debug(
+                    "Skipping output guardrail - model response has no choices"
+                )
+            return responses_so_far
+
+        string_so_far = self.get_streaming_string_so_far(responses_so_far)
+        _guardrailed_inputs = await guardrail_to_apply.apply_guardrail(  # allow rejecting the response, if invalid
+            inputs={"texts": [string_so_far]},
+            request_data={},
+            input_type="response",
+            logging_obj=litellm_logging_obj,
+        )
+        return responses_so_far
+
+    def get_streaming_string_so_far(self, responses_so_far: List[Any]) -> str:
+        """
+        Parse streaming responses and extract accumulated text content.
+
+        Handles two formats:
+        1. Raw bytes in SSE (Server-Sent Events) format from Anthropic API
+        2. Parsed dict objects (for backwards compatibility)
+
+        SSE format example:
+            b'event: content_block_delta\\ndata: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" curious"}}\\n\\n'
+
+        Dict format example:
+            {
+                "type": "content_block_delta",
+                "index": 0,
+                "delta": {
+                    "type": "text_delta",
+                    "text": " curious"
+                }
+            }
+        """
+        text_so_far = ""
+        for response in responses_so_far:
+            # Handle raw bytes in SSE format
+            if isinstance(response, bytes):
+                text_so_far += self._extract_text_from_sse(response)
+            # Handle already-parsed dict format
+            elif isinstance(response, dict):
+                delta = response.get("delta") if response.get("delta") else None
+                if delta and delta.get("type") == "text_delta":
+                    text = delta.get("text", "")
+                    if text:
+                        text_so_far += text
+        return text_so_far
+
+    def _extract_text_from_sse(self, sse_bytes: bytes) -> str:
+        """
+        Extract text content from Server-Sent Events (SSE) format.
+
+        Args:
+            sse_bytes: Raw bytes in SSE format
+
+        Returns:
+            Accumulated text from all content_block_delta events
+        """
+        text = ""
+        try:
+            # Decode bytes to string
+            sse_string = sse_bytes.decode("utf-8")
+
+            # Split by double newline to get individual events
+            events = sse_string.split("\n\n")
+
+            for event in events:
+                if not event.strip():
+                    continue
+
+                # Parse event lines
+                lines = event.strip().split("\n")
+                event_type = None
+                data_line = None
+
+                for line in lines:
+                    if line.startswith("event:"):
+                        event_type = line[6:].strip()
+                    elif line.startswith("data:"):
+                        data_line = line[5:].strip()
+
+                # Only process content_block_delta events
+                if event_type == "content_block_delta" and data_line:
+                    try:
+                        data = json.loads(data_line)
+                        delta = data.get("delta", {})
+                        if delta.get("type") == "text_delta":
+                            text += delta.get("text", "")
+                    except json.JSONDecodeError:
+                        verbose_proxy_logger.warning(
+                            f"Failed to parse JSON from SSE data: {data_line}"
+                        )
+
+        except Exception as e:
+            verbose_proxy_logger.error(f"Error extracting text from SSE: {e}")
+
+        return text
+
+    def _check_streaming_has_ended(self, responses_so_far: List[Any]) -> bool:
+        """
+        Check if streaming response has ended by looking for non-null stop_reason.
+
+        Handles two formats:
+        1. Raw bytes in SSE (Server-Sent Events) format from Anthropic API
+        2. Parsed dict objects (for backwards compatibility)
+
+        SSE format example:
+            b'event: message_delta\\ndata: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},...}\\n\\n'
+
+        Dict format example:
+            {
+                "type": "message_delta",
+                "delta": {
+                    "stop_reason": "tool_use",
+                    "stop_sequence": null
+                }
+            }
+
+        Returns:
+            True if stop_reason is set to a non-null value, indicating stream has ended
+        """
+        for response in responses_so_far:
+            # Handle raw bytes in SSE format
+            if isinstance(response, bytes):
+                try:
+                    # Decode bytes to string
+                    sse_string = response.decode("utf-8")
+
+                    # Split by double newline to get individual events
+                    events = sse_string.split("\n\n")
+
+                    for event in events:
+                        if not event.strip():
+                            continue
+
+                        # Parse event lines
+                        lines = event.strip().split("\n")
+                        event_type = None
+                        data_line = None
+
+                        for line in lines:
+                            if line.startswith("event:"):
+                                event_type = line[6:].strip()
+                            elif line.startswith("data:"):
+                                data_line = line[5:].strip()
+
+                        # Check for message_delta event with stop_reason
+                        if event_type == "message_delta" and data_line:
+                            try:
+                                data = json.loads(data_line)
+                                delta = data.get("delta", {})
+                                stop_reason = delta.get("stop_reason")
+                                if stop_reason is not None:
+                                    return True
+                            except json.JSONDecodeError:
+                                verbose_proxy_logger.warning(
+                                    f"Failed to parse JSON from SSE data: {data_line}"
+                                )
+
+                except Exception as e:
+                    verbose_proxy_logger.error(
+                        f"Error checking streaming end in SSE: {e}"
+                    )
+
+            # Handle already-parsed dict format
+            elif isinstance(response, dict):
+                if response.get("type") == "message_delta":
+                    delta = response.get("delta", {})
+                    stop_reason = delta.get("stop_reason")
+                    if stop_reason is not None:
+                        return True
+
+        return False
+
+    def _has_text_content(self, response: "AnthropicMessagesResponse") -> bool:
+        """
+        Check if response has any text content to process.
+
+        Override this method to customize text content detection.
+        """
+        if isinstance(response, dict):
+            response_content = response.get("content", [])
+        else:
+            response_content = getattr(response, "content", None) or []
+
+        if not response_content:
+            return False
+        for content_block in response_content:
+            # Check if this is a text block by checking the 'type' field
+            if isinstance(content_block, dict) and content_block.get("type") == "text":
+                content_text = content_block.get("text")
+                if content_text and isinstance(content_text, str):
+                    return True
+        return False
+
+    def _extract_output_text_and_images(
+        self,
+        content_block: Dict[str, Any],
+        content_idx: int,
+        texts_to_check: List[str],
+        images_to_check: List[str],
+        task_mappings: List[Tuple[int, Optional[int]]],
+        tool_calls_to_check: Optional[List[ChatCompletionToolCallChunk]] = None,
+    ) -> None:
+        """
+        Extract text content, images, and tool calls from a response content block.
+
+        Override this method to customize text/image/tool extraction logic.
+        """
+        content_type = content_block.get("type")
+
+        # Extract text content
+        if content_type == "text":
+            content_text = content_block.get("text")
+            if content_text and isinstance(content_text, str):
+                # Simple string content
+                texts_to_check.append(content_text)
+                task_mappings.append((content_idx, None))
+
+        # Extract tool calls
+        elif content_type == "tool_use":
+            tool_call = AnthropicConfig.convert_tool_use_to_openai_format(
+                anthropic_tool_content=content_block,
+                index=content_idx,
+            )
+            if tool_calls_to_check is None:
+                tool_calls_to_check = []
+            tool_calls_to_check.append(tool_call)
+
+    async def _apply_guardrail_responses_to_output(
+        self,
+        response: "AnthropicMessagesResponse",
+        responses: List[str],
+        task_mappings: List[Tuple[int, Optional[int]]],
+    ) -> None:
+        """
+        Apply guardrail responses back to output response.
+
+        Override this method to customize how responses are applied.
+        """
+        for task_idx, guardrail_response in enumerate(responses):
+            mapping = task_mappings[task_idx]
+            content_idx = cast(int, mapping[0])
+
+            # Handle both dict and object responses
+            response_content: List[Any] = []
+            if isinstance(response, dict):
+                response_content = response.get("content", []) or []
+            elif hasattr(response, "content"):
+                content = getattr(response, "content", None)
+                response_content = content or []
+            else:
+                continue
+
+            if not response_content:
+                continue
+
+            # Get the content block at the index
+            if content_idx >= len(response_content):
+                continue
+
+            content_block = response_content[content_idx]
+
+            # Verify it's a text block and update the text field
+            # Handle both dict and Pydantic object content blocks
+            if isinstance(content_block, dict):
+                if content_block.get("type") == "text":
+                    cast(Dict[str, Any], content_block)["text"] = guardrail_response
+            elif (
+                hasattr(content_block, "type")
+                and getattr(content_block, "type", None) == "text"
+            ):
+                # Update Pydantic object's text attribute
+                if hasattr(content_block, "text"):
+                    content_block.text = guardrail_response

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/common_utils.py

@@ -0,0 +1,627 @@
+"""
+This file contains common utils for anthropic calls.
+"""
+
+from typing import Dict, List, Optional, Union
+
+import httpx
+
+import litellm
+from litellm.litellm_core_utils.prompt_templates.common_utils import (
+    get_file_ids_from_messages,
+)
+from litellm.llms.base_llm.base_utils import BaseLLMModelInfo, BaseTokenCounter
+from litellm.llms.base_llm.chat.transformation import BaseLLMException
+from litellm.types.llms.anthropic import (
+    ANTHROPIC_HOSTED_TOOLS,
+    ANTHROPIC_OAUTH_BETA_HEADER,
+    ANTHROPIC_OAUTH_TOKEN_PREFIX,
+    AllAnthropicToolsValues,
+    AnthropicMcpServerTool,
+)
+from litellm.types.llms.openai import AllMessageValues
+
+
+def is_anthropic_oauth_key(value: Optional[str]) -> bool:
+    """Check if a value contains an Anthropic OAuth token (sk-ant-oat*)."""
+    if value is None:
+        return False
+    # Handle both raw token and "Bearer <token>" format
+    if value.startswith("Bearer "):
+        value = value[7:]
+    return value.startswith(ANTHROPIC_OAUTH_TOKEN_PREFIX)
+
+
+def _merge_beta_headers(existing: Optional[str], new_beta: str) -> str:
+    """Merge a new beta value into an existing comma-separated anthropic-beta header."""
+    if not existing:
+        return new_beta
+    betas = {b.strip() for b in existing.split(",") if b.strip()}
+    betas.add(new_beta)
+    return ",".join(sorted(betas))
+
+
+def optionally_handle_anthropic_oauth(
+    headers: dict, api_key: Optional[str]
+) -> tuple[dict, Optional[str]]:
+    """
+    Handle Anthropic OAuth token detection and header setup.
+
+    If an OAuth token is detected in the Authorization header, extracts it
+    and sets the required OAuth headers.
+
+    Args:
+        headers: Request headers dict
+        api_key: Current API key (may be None)
+
+    Returns:
+        Tuple of (updated headers, api_key)
+    """
+    # Check Authorization header (passthrough / forwarded requests)
+    auth_header = headers.get("authorization", "")
+    if auth_header and auth_header.startswith(f"Bearer {ANTHROPIC_OAUTH_TOKEN_PREFIX}"):
+        api_key = auth_header.replace("Bearer ", "")
+        headers.pop("x-api-key", None)
+        headers["anthropic-beta"] = _merge_beta_headers(
+            headers.get("anthropic-beta"), ANTHROPIC_OAUTH_BETA_HEADER
+        )
+        headers["anthropic-dangerous-direct-browser-access"] = "true"
+        return headers, api_key
+    # Check api_key directly (standard chat/completion flow)
+    if api_key and api_key.startswith(ANTHROPIC_OAUTH_TOKEN_PREFIX):
+        headers.pop("x-api-key", None)
+        headers["authorization"] = f"Bearer {api_key}"
+        headers["anthropic-beta"] = _merge_beta_headers(
+            headers.get("anthropic-beta"), ANTHROPIC_OAUTH_BETA_HEADER
+        )
+        headers["anthropic-dangerous-direct-browser-access"] = "true"
+    return headers, api_key
+
+
+class AnthropicError(BaseLLMException):
+    def __init__(
+        self,
+        status_code: int,
+        message,
+        headers: Optional[httpx.Headers] = None,
+    ):
+        super().__init__(status_code=status_code, message=message, headers=headers)
+
+
+class AnthropicModelInfo(BaseLLMModelInfo):
+    def is_cache_control_set(self, messages: List[AllMessageValues]) -> bool:
+        """
+        Return if {"cache_control": ..} in message content block
+
+        Used to check if anthropic prompt caching headers need to be set.
+        """
+        for message in messages:
+            if message.get("cache_control", None) is not None:
+                return True
+            _message_content = message.get("content")
+            if _message_content is not None and isinstance(_message_content, list):
+                for content in _message_content:
+                    if "cache_control" in content:
+                        return True
+
+        return False
+
+    def is_file_id_used(self, messages: List[AllMessageValues]) -> bool:
+        """
+        Return if {"source": {"type": "file", "file_id": ..}} in message content block
+        """
+        file_ids = get_file_ids_from_messages(messages)
+        return len(file_ids) > 0
+
+    def is_mcp_server_used(
+        self, mcp_servers: Optional[List[AnthropicMcpServerTool]]
+    ) -> bool:
+        if mcp_servers is None:
+            return False
+        if mcp_servers:
+            return True
+        return False
+
+    def is_computer_tool_used(
+        self, tools: Optional[List[AllAnthropicToolsValues]]
+    ) -> Optional[str]:
+        """Returns the computer tool version if used, e.g. 'computer_20250124' or None"""
+        if tools is None:
+            return None
+        for tool in tools:
+            if "type" in tool and tool["type"].startswith("computer_"):
+                return tool["type"]
+        return None
+
+    def is_web_search_tool_used(
+        self, tools: Optional[List[AllAnthropicToolsValues]]
+    ) -> bool:
+        """Returns True if web_search tool is used"""
+        if tools is None:
+            return False
+        for tool in tools:
+            if "type" in tool and tool["type"].startswith(
+                ANTHROPIC_HOSTED_TOOLS.WEB_SEARCH.value
+            ):
+                return True
+        return False
+
+    def is_pdf_used(self, messages: List[AllMessageValues]) -> bool:
+        """
+        Set to true if media passed into messages.
+
+        """
+        for message in messages:
+            if (
+                "content" in message
+                and message["content"] is not None
+                and isinstance(message["content"], list)
+            ):
+                for content in message["content"]:
+                    if "type" in content and content["type"] != "text":
+                        return True
+        return False
+
+    def is_tool_search_used(self, tools: Optional[List]) -> bool:
+        """
+        Check if tool search tools are present in the tools list.
+        """
+        if not tools:
+            return False
+
+        for tool in tools:
+            tool_type = tool.get("type", "")
+            if tool_type in [
+                "tool_search_tool_regex_20251119",
+                "tool_search_tool_bm25_20251119",
+            ]:
+                return True
+        return False
+
+    def is_programmatic_tool_calling_used(self, tools: Optional[List]) -> bool:
+        """
+        Check if programmatic tool calling is being used (tools with allowed_callers field).
+
+        Returns True if any tool has allowed_callers containing 'code_execution_20250825'.
+        """
+        if not tools:
+            return False
+
+        for tool in tools:
+            # Check top-level allowed_callers
+            allowed_callers = tool.get("allowed_callers", None)
+            if allowed_callers and isinstance(allowed_callers, list):
+                if "code_execution_20250825" in allowed_callers:
+                    return True
+
+            # Check function.allowed_callers for OpenAI format tools
+            function = tool.get("function", {})
+            if isinstance(function, dict):
+                function_allowed_callers = function.get("allowed_callers", None)
+                if function_allowed_callers and isinstance(
+                    function_allowed_callers, list
+                ):
+                    if "code_execution_20250825" in function_allowed_callers:
+                        return True
+
+        return False
+
+    def is_input_examples_used(self, tools: Optional[List]) -> bool:
+        """
+        Check if input_examples is being used in any tools.
+
+        Returns True if any tool has input_examples field.
+        """
+        if not tools:
+            return False
+
+        for tool in tools:
+            # Check top-level input_examples
+            input_examples = tool.get("input_examples", None)
+            if (
+                input_examples
+                and isinstance(input_examples, list)
+                and len(input_examples) > 0
+            ):
+                return True
+
+            # Check function.input_examples for OpenAI format tools
+            function = tool.get("function", {})
+            if isinstance(function, dict):
+                function_input_examples = function.get("input_examples", None)
+                if (
+                    function_input_examples
+                    and isinstance(function_input_examples, list)
+                    and len(function_input_examples) > 0
+                ):
+                    return True
+
+        return False
+
+    @staticmethod
+    def _is_claude_4_6_model(model: str) -> bool:
+        """Check if the model is a Claude 4.6 model (Opus 4.6 or Sonnet 4.6)."""
+        model_lower = model.lower()
+        return any(
+            v in model_lower
+            for v in (
+                "opus-4-6",
+                "opus_4_6",
+                "opus-4.6",
+                "opus_4.6",
+                "sonnet-4-6",
+                "sonnet_4_6",
+                "sonnet-4.6",
+                "sonnet_4.6",
+            )
+        )
+
+    def is_effort_used(
+        self, optional_params: Optional[dict], model: Optional[str] = None
+    ) -> bool:
+        """
+        Check if effort parameter is being used and requires a beta header.
+
+        Returns True if effort-related parameters are present and
+        the model requires the effort beta header. Claude 4.6 models
+        use output_config as a stable API feature — no beta header needed.
+        """
+        if not optional_params:
+            return False
+
+        # Claude 4.6 models use output_config as a stable API feature — no beta header needed
+        if model and self._is_claude_4_6_model(model):
+            return False
+
+        # Check if reasoning_effort is provided for Claude Opus 4.5
+        if model and ("opus-4-5" in model.lower() or "opus_4_5" in model.lower()):
+            reasoning_effort = optional_params.get("reasoning_effort")
+            if reasoning_effort and isinstance(reasoning_effort, str):
+                return True
+
+        # Check if output_config is directly provided (for non-4.6 models)
+        output_config = optional_params.get("output_config")
+        if output_config and isinstance(output_config, dict):
+            effort = output_config.get("effort")
+            if effort and isinstance(effort, str):
+                return True
+
+        return False
+
+    def is_code_execution_tool_used(self, tools: Optional[List]) -> bool:
+        """
+        Check if code execution tool is being used.
+
+        Returns True if any tool has type "code_execution_20250825".
+        """
+        if not tools:
+            return False
+
+        for tool in tools:
+            tool_type = tool.get("type", "")
+            if tool_type == "code_execution_20250825":
+                return True
+        return False
+
+    def is_container_with_skills_used(self, optional_params: Optional[dict]) -> bool:
+        """
+        Check if container with skills is being used.
+
+        Returns True if optional_params contains container with skills.
+        """
+        if not optional_params:
+            return False
+
+        container = optional_params.get("container")
+        if container and isinstance(container, dict):
+            skills = container.get("skills")
+            if skills and isinstance(skills, list) and len(skills) > 0:
+                return True
+        return False
+
+    def _get_user_anthropic_beta_headers(
+        self, anthropic_beta_header: Optional[str]
+    ) -> Optional[List[str]]:
+        if anthropic_beta_header is None:
+            return None
+        return anthropic_beta_header.split(",")
+
+    def get_computer_tool_beta_header(self, computer_tool_version: str) -> str:
+        """
+        Get the appropriate beta header for a given computer tool version.
+
+        Args:
+            computer_tool_version: The computer tool version (e.g., 'computer_20250124', 'computer_20241022')
+
+        Returns:
+            The corresponding beta header string
+        """
+        computer_tool_beta_mapping = {
+            "computer_20250124": "computer-use-2025-01-24",
+            "computer_20241022": "computer-use-2024-10-22",
+        }
+        return computer_tool_beta_mapping.get(
+            computer_tool_version, "computer-use-2024-10-22"  # Default fallback
+        )
+
+    def get_anthropic_beta_list(
+        self,
+        model: str,
+        optional_params: Optional[dict] = None,
+        computer_tool_used: Optional[str] = None,
+        prompt_caching_set: bool = False,
+        file_id_used: bool = False,
+        mcp_server_used: bool = False,
+    ) -> List[str]:
+        """
+        Get list of common beta headers based on the features that are active.
+
+        Returns:
+            List of beta header strings
+        """
+        from litellm.types.llms.anthropic import (
+            ANTHROPIC_EFFORT_BETA_HEADER,
+        )
+
+        betas = []
+
+        # Detect features
+        effort_used = self.is_effort_used(optional_params, model)
+
+        if effort_used:
+            betas.append(ANTHROPIC_EFFORT_BETA_HEADER)  # effort-2025-11-24
+
+        if computer_tool_used:
+            beta_header = self.get_computer_tool_beta_header(computer_tool_used)
+            betas.append(beta_header)
+
+        # Anthropic no longer requires the prompt-caching beta header
+        # Prompt caching now works automatically when cache_control is used in messages
+        # Reference: https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
+
+        if file_id_used:
+            betas.append("files-api-2025-04-14")
+            betas.append("code-execution-2025-05-22")
+
+        if mcp_server_used:
+            betas.append("mcp-client-2025-04-04")
+
+        return list(set(betas))
+
+    def get_anthropic_headers(
+        self,
+        api_key: str,
+        anthropic_version: Optional[str] = None,
+        computer_tool_used: Optional[str] = None,
+        prompt_caching_set: bool = False,
+        pdf_used: bool = False,
+        file_id_used: bool = False,
+        mcp_server_used: bool = False,
+        web_search_tool_used: bool = False,
+        tool_search_used: bool = False,
+        programmatic_tool_calling_used: bool = False,
+        input_examples_used: bool = False,
+        effort_used: bool = False,
+        is_vertex_request: bool = False,
+        user_anthropic_beta_headers: Optional[List[str]] = None,
+        code_execution_tool_used: bool = False,
+        container_with_skills_used: bool = False,
+    ) -> dict:
+        betas = set()
+        # Anthropic no longer requires the prompt-caching beta header
+        # Prompt caching now works automatically when cache_control is used in messages
+        # Reference: https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
+        if computer_tool_used:
+            beta_header = self.get_computer_tool_beta_header(computer_tool_used)
+            betas.add(beta_header)
+        # if pdf_used:
+        #     betas.add("pdfs-2024-09-25")
+        if file_id_used:
+            betas.add("files-api-2025-04-14")
+            betas.add("code-execution-2025-05-22")
+        if mcp_server_used:
+            betas.add("mcp-client-2025-04-04")
+        # Tool search, programmatic tool calling, and input_examples all use the same beta header
+        if tool_search_used or programmatic_tool_calling_used or input_examples_used:
+            from litellm.types.llms.anthropic import ANTHROPIC_TOOL_SEARCH_BETA_HEADER
+
+            betas.add(ANTHROPIC_TOOL_SEARCH_BETA_HEADER)
+
+        # Effort parameter uses a separate beta header
+        if effort_used:
+            from litellm.types.llms.anthropic import ANTHROPIC_EFFORT_BETA_HEADER
+
+            betas.add(ANTHROPIC_EFFORT_BETA_HEADER)
+
+        # Code execution tool uses a separate beta header
+        if code_execution_tool_used:
+            betas.add("code-execution-2025-08-25")
+
+        # Container with skills uses a separate beta header
+        if container_with_skills_used:
+            betas.add("skills-2025-10-02")
+
+        _is_oauth = api_key and api_key.startswith(ANTHROPIC_OAUTH_TOKEN_PREFIX)
+        headers = {
+            "anthropic-version": anthropic_version or "2023-06-01",
+            "accept": "application/json",
+            "content-type": "application/json",
+        }
+        if _is_oauth:
+            headers["authorization"] = f"Bearer {api_key}"
+            headers["anthropic-dangerous-direct-browser-access"] = "true"
+            betas.add(ANTHROPIC_OAUTH_BETA_HEADER)
+        else:
+            headers["x-api-key"] = api_key
+
+        if user_anthropic_beta_headers is not None:
+            betas.update(user_anthropic_beta_headers)
+
+        # Don't send any beta headers to Vertex, except web search which is required
+        if is_vertex_request is True:
+            # Vertex AI requires web search beta header for web search to work
+            if web_search_tool_used:
+                from litellm.types.llms.anthropic import ANTHROPIC_BETA_HEADER_VALUES
+
+                headers[
+                    "anthropic-beta"
+                ] = ANTHROPIC_BETA_HEADER_VALUES.WEB_SEARCH_2025_03_05.value
+        elif len(betas) > 0:
+            headers["anthropic-beta"] = ",".join(betas)
+
+        return headers
+
+    def validate_environment(
+        self,
+        headers: dict,
+        model: str,
+        messages: List[AllMessageValues],
+        optional_params: dict,
+        litellm_params: dict,
+        api_key: Optional[str] = None,
+        api_base: Optional[str] = None,
+    ) -> Dict:
+        # Check for Anthropic OAuth token in headers
+        headers, api_key = optionally_handle_anthropic_oauth(
+            headers=headers, api_key=api_key
+        )
+        if api_key is None:
+            raise litellm.AuthenticationError(
+                message="Missing Anthropic API Key - A call is being made to anthropic but no key is set either in the environment variables or via params. Please set `ANTHROPIC_API_KEY` in your environment vars",
+                llm_provider="anthropic",
+                model=model,
+            )
+
+        tools = optional_params.get("tools")
+        prompt_caching_set = self.is_cache_control_set(messages=messages)
+        computer_tool_used = self.is_computer_tool_used(tools=tools)
+        mcp_server_used = self.is_mcp_server_used(
+            mcp_servers=optional_params.get("mcp_servers")
+        )
+        pdf_used = self.is_pdf_used(messages=messages)
+        file_id_used = self.is_file_id_used(messages=messages)
+        web_search_tool_used = self.is_web_search_tool_used(tools=tools)
+        tool_search_used = self.is_tool_search_used(tools=tools)
+        programmatic_tool_calling_used = self.is_programmatic_tool_calling_used(
+            tools=tools
+        )
+        input_examples_used = self.is_input_examples_used(tools=tools)
+        effort_used = self.is_effort_used(optional_params=optional_params, model=model)
+        code_execution_tool_used = self.is_code_execution_tool_used(tools=tools)
+        container_with_skills_used = self.is_container_with_skills_used(
+            optional_params=optional_params
+        )
+        user_anthropic_beta_headers = self._get_user_anthropic_beta_headers(
+            anthropic_beta_header=headers.get("anthropic-beta")
+        )
+        anthropic_headers = self.get_anthropic_headers(
+            computer_tool_used=computer_tool_used,
+            prompt_caching_set=prompt_caching_set,
+            pdf_used=pdf_used,
+            api_key=api_key,
+            file_id_used=file_id_used,
+            web_search_tool_used=web_search_tool_used,
+            is_vertex_request=optional_params.get("is_vertex_request", False),
+            user_anthropic_beta_headers=user_anthropic_beta_headers,
+            mcp_server_used=mcp_server_used,
+            tool_search_used=tool_search_used,
+            programmatic_tool_calling_used=programmatic_tool_calling_used,
+            input_examples_used=input_examples_used,
+            effort_used=effort_used,
+            code_execution_tool_used=code_execution_tool_used,
+            container_with_skills_used=container_with_skills_used,
+        )
+
+        headers = {**headers, **anthropic_headers}
+
+        return headers
+
+    @staticmethod
+    def get_api_base(api_base: Optional[str] = None) -> Optional[str]:
+        from litellm.secret_managers.main import get_secret_str
+
+        return (
+            api_base
+            or get_secret_str("ANTHROPIC_API_BASE")
+            or "https://api.anthropic.com"
+        )
+
+    @staticmethod
+    def get_api_key(api_key: Optional[str] = None) -> Optional[str]:
+        from litellm.secret_managers.main import get_secret_str
+
+        return api_key or get_secret_str("ANTHROPIC_API_KEY")
+
+    @staticmethod
+    def get_base_model(model: Optional[str] = None) -> Optional[str]:
+        return model.replace("anthropic/", "") if model else None
+
+    def get_models(
+        self, api_key: Optional[str] = None, api_base: Optional[str] = None
+    ) -> List[str]:
+        api_base = AnthropicModelInfo.get_api_base(api_base)
+        api_key = AnthropicModelInfo.get_api_key(api_key)
+        if api_base is None or api_key is None:
+            raise ValueError(
+                "ANTHROPIC_API_BASE or ANTHROPIC_API_KEY is not set. Please set the environment variable, to query Anthropic's `/models` endpoint."
+            )
+        response = litellm.module_level_client.get(
+            url=f"{api_base}/v1/models",
+            headers={"x-api-key": api_key, "anthropic-version": "2023-06-01"},
+        )
+
+        try:
+            response.raise_for_status()
+        except httpx.HTTPStatusError:
+            raise Exception(
+                f"Failed to fetch models from Anthropic. Status code: {response.status_code}, Response: {response.text}"
+            )
+
+        models = response.json()["data"]
+
+        litellm_model_names = []
+        for model in models:
+            stripped_model_name = model["id"]
+            litellm_model_name = "anthropic/" + stripped_model_name
+            litellm_model_names.append(litellm_model_name)
+        return litellm_model_names
+
+    def get_token_counter(self) -> Optional[BaseTokenCounter]:
+        """
+        Factory method to create an Anthropic token counter.
+
+        Returns:
+            AnthropicTokenCounter instance for this provider.
+        """
+        from litellm.llms.anthropic.count_tokens.token_counter import (
+            AnthropicTokenCounter,
+        )
+
+        return AnthropicTokenCounter()
+
+
+def process_anthropic_headers(headers: Union[httpx.Headers, dict]) -> dict:
+    openai_headers = {}
+    if "anthropic-ratelimit-requests-limit" in headers:
+        openai_headers["x-ratelimit-limit-requests"] = headers[
+            "anthropic-ratelimit-requests-limit"
+        ]
+    if "anthropic-ratelimit-requests-remaining" in headers:
+        openai_headers["x-ratelimit-remaining-requests"] = headers[
+            "anthropic-ratelimit-requests-remaining"
+        ]
+    if "anthropic-ratelimit-tokens-limit" in headers:
+        openai_headers["x-ratelimit-limit-tokens"] = headers[
+            "anthropic-ratelimit-tokens-limit"
+        ]
+    if "anthropic-ratelimit-tokens-remaining" in headers:
+        openai_headers["x-ratelimit-remaining-tokens"] = headers[
+            "anthropic-ratelimit-tokens-remaining"
+        ]
+
+    llm_response_headers = {
+        "{}-{}".format("llm_provider", k): v for k, v in headers.items()
+    }
+
+    additional_headers = {**llm_response_headers, **openai_headers}
+    return additional_headers

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/completion/handler.py

@@ -0,0 +1,5 @@
+"""
+Anthropic /complete API - uses `llm_http_handler.py` to make httpx requests
+
+Request/Response transformation is handled in `transformation.py`
+"""

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/completion/transformation.py

@@ -0,0 +1,310 @@
+"""
+Translation logic for anthropic's `/v1/complete` endpoint
+
+Litellm provider slug: `anthropic_text/<model_name>`
+"""
+
+import json
+import time
+from typing import AsyncIterator, Dict, Iterator, List, Optional, Union
+
+import httpx
+
+import litellm
+from litellm.constants import DEFAULT_MAX_TOKENS
+from litellm.litellm_core_utils.prompt_templates.factory import (
+    custom_prompt,
+    prompt_factory,
+)
+from litellm.llms.base_llm.base_model_iterator import BaseModelResponseIterator
+from litellm.llms.base_llm.chat.transformation import (
+    BaseConfig,
+    BaseLLMException,
+    LiteLLMLoggingObj,
+)
+from litellm.types.llms.openai import AllMessageValues
+from litellm.types.utils import (
+    ChatCompletionToolCallChunk,
+    ChatCompletionUsageBlock,
+    GenericStreamingChunk,
+    ModelResponse,
+    Usage,
+)
+
+
+class AnthropicTextError(BaseLLMException):
+    def __init__(self, status_code, message):
+        self.status_code = status_code
+        self.message = message
+        self.request = httpx.Request(
+            method="POST", url="https://api.anthropic.com/v1/complete"
+        )
+        self.response = httpx.Response(status_code=status_code, request=self.request)
+        super().__init__(
+            message=self.message,
+            status_code=self.status_code,
+            request=self.request,
+            response=self.response,
+        )  # Call the base class constructor with the parameters it needs
+
+
+class AnthropicTextConfig(BaseConfig):
+    """
+    Reference: https://docs.anthropic.com/claude/reference/complete_post
+
+    to pass metadata to anthropic, it's {"user_id": "any-relevant-information"}
+    """
+
+    max_tokens_to_sample: Optional[
+        int
+    ] = litellm.max_tokens  # anthropic requires a default
+    stop_sequences: Optional[list] = None
+    temperature: Optional[int] = None
+    top_p: Optional[int] = None
+    top_k: Optional[int] = None
+    metadata: Optional[dict] = None
+
+    def __init__(
+        self,
+        max_tokens_to_sample: Optional[
+            int
+        ] = DEFAULT_MAX_TOKENS,  # anthropic requires a default
+        stop_sequences: Optional[list] = None,
+        temperature: Optional[int] = None,
+        top_p: Optional[int] = None,
+        top_k: Optional[int] = None,
+        metadata: Optional[dict] = None,
+    ) -> None:
+        locals_ = locals().copy()
+        for key, value in locals_.items():
+            if key != "self" and value is not None:
+                setattr(self.__class__, key, value)
+
+    # makes headers for API call
+    def validate_environment(
+        self,
+        headers: dict,
+        model: str,
+        messages: List[AllMessageValues],
+        optional_params: dict,
+        litellm_params: dict,
+        api_key: Optional[str] = None,
+        api_base: Optional[str] = None,
+    ) -> dict:
+        if api_key is None:
+            raise ValueError(
+                "Missing Anthropic API Key - A call is being made to anthropic but no key is set either in the environment variables or via params"
+            )
+        _headers = {
+            "accept": "application/json",
+            "anthropic-version": "2023-06-01",
+            "content-type": "application/json",
+            "x-api-key": api_key,
+        }
+        headers.update(_headers)
+        return headers
+
+    def transform_request(
+        self,
+        model: str,
+        messages: List[AllMessageValues],
+        optional_params: dict,
+        litellm_params: dict,
+        headers: dict,
+    ) -> dict:
+        prompt = self._get_anthropic_text_prompt_from_messages(
+            messages=messages, model=model
+        )
+        ## Load Config
+        config = litellm.AnthropicTextConfig.get_config()
+        for k, v in config.items():
+            if (
+                k not in optional_params
+            ):  # completion(top_k=3) > anthropic_config(top_k=3) <- allows for dynamic variables to be passed in
+                optional_params[k] = v
+
+        data = {
+            "model": model,
+            "prompt": prompt,
+            **optional_params,
+        }
+
+        return data
+
+    def get_supported_openai_params(self, model: str):
+        """
+        Anthropic /complete API Ref: https://docs.anthropic.com/en/api/complete
+        """
+        return [
+            "stream",
+            "max_tokens",
+            "max_completion_tokens",
+            "stop",
+            "temperature",
+            "top_p",
+            "extra_headers",
+            "user",
+        ]
+
+    def map_openai_params(
+        self,
+        non_default_params: dict,
+        optional_params: dict,
+        model: str,
+        drop_params: bool,
+    ) -> dict:
+        """
+        Follows the same logic as the AnthropicConfig.map_openai_params method (which is the Anthropic /messages API)
+
+        Note: the only difference is in the get supported openai params method between the AnthropicConfig and AnthropicTextConfig
+        API Ref: https://docs.anthropic.com/en/api/complete
+        """
+        for param, value in non_default_params.items():
+            if param == "max_tokens":
+                optional_params["max_tokens_to_sample"] = value
+            if param == "max_completion_tokens":
+                optional_params["max_tokens_to_sample"] = value
+            if param == "stream" and value is True:
+                optional_params["stream"] = value
+            if param == "stop" and (isinstance(value, str) or isinstance(value, list)):
+                _value = litellm.AnthropicConfig()._map_stop_sequences(value)
+                if _value is not None:
+                    optional_params["stop_sequences"] = _value
+            if param == "temperature":
+                optional_params["temperature"] = value
+            if param == "top_p":
+                optional_params["top_p"] = value
+            if param == "user":
+                optional_params["metadata"] = {"user_id": value}
+
+        return optional_params
+
+    def transform_response(
+        self,
+        model: str,
+        raw_response: httpx.Response,
+        model_response: ModelResponse,
+        logging_obj: LiteLLMLoggingObj,
+        request_data: dict,
+        messages: List[AllMessageValues],
+        optional_params: dict,
+        litellm_params: dict,
+        encoding: str,
+        api_key: Optional[str] = None,
+        json_mode: Optional[bool] = None,
+    ) -> ModelResponse:
+        try:
+            completion_response = raw_response.json()
+        except Exception:
+            raise AnthropicTextError(
+                message=raw_response.text, status_code=raw_response.status_code
+            )
+        prompt = self._get_anthropic_text_prompt_from_messages(
+            messages=messages, model=model
+        )
+        if "error" in completion_response:
+            raise AnthropicTextError(
+                message=str(completion_response["error"]),
+                status_code=raw_response.status_code,
+            )
+        else:
+            if len(completion_response["completion"]) > 0:
+                model_response.choices[0].message.content = completion_response[  # type: ignore
+                    "completion"
+                ]
+            model_response.choices[0].finish_reason = completion_response["stop_reason"]
+
+        ## CALCULATING USAGE
+        prompt_tokens = len(
+            encoding.encode(prompt)
+        )  ##[TODO] use the anthropic tokenizer here
+        completion_tokens = len(
+            encoding.encode(model_response["choices"][0]["message"].get("content", ""))
+        )  ##[TODO] use the anthropic tokenizer here
+
+        model_response.created = int(time.time())
+        model_response.model = model
+        usage = Usage(
+            prompt_tokens=prompt_tokens,
+            completion_tokens=completion_tokens,
+            total_tokens=prompt_tokens + completion_tokens,
+        )
+
+        setattr(model_response, "usage", usage)
+        return model_response
+
+    def get_error_class(
+        self, error_message: str, status_code: int, headers: Union[Dict, httpx.Headers]
+    ) -> BaseLLMException:
+        return AnthropicTextError(
+            status_code=status_code,
+            message=error_message,
+        )
+
+    @staticmethod
+    def _is_anthropic_text_model(model: str) -> bool:
+        return model == "claude-2" or model == "claude-instant-1"
+
+    def _get_anthropic_text_prompt_from_messages(
+        self, messages: List[AllMessageValues], model: str
+    ) -> str:
+        custom_prompt_dict = litellm.custom_prompt_dict
+        if model in custom_prompt_dict:
+            # check if the model has a registered custom prompt
+            model_prompt_details = custom_prompt_dict[model]
+            prompt = custom_prompt(
+                role_dict=model_prompt_details["roles"],
+                initial_prompt_value=model_prompt_details["initial_prompt_value"],
+                final_prompt_value=model_prompt_details["final_prompt_value"],
+                messages=messages,
+            )
+        else:
+            prompt = prompt_factory(
+                model=model, messages=messages, custom_llm_provider="anthropic"
+            )
+
+        return str(prompt)
+
+    def get_model_response_iterator(
+        self,
+        streaming_response: Union[Iterator[str], AsyncIterator[str], ModelResponse],
+        sync_stream: bool,
+        json_mode: Optional[bool] = False,
+    ):
+        return AnthropicTextCompletionResponseIterator(
+            streaming_response=streaming_response,
+            sync_stream=sync_stream,
+            json_mode=json_mode,
+        )
+
+
+class AnthropicTextCompletionResponseIterator(BaseModelResponseIterator):
+    def chunk_parser(self, chunk: dict) -> GenericStreamingChunk:
+        try:
+            text = ""
+            tool_use: Optional[ChatCompletionToolCallChunk] = None
+            is_finished = False
+            finish_reason = ""
+            usage: Optional[ChatCompletionUsageBlock] = None
+            provider_specific_fields = None
+            index = int(chunk.get("index", 0))
+            _chunk_text = chunk.get("completion", None)
+            if _chunk_text is not None and isinstance(_chunk_text, str):
+                text = _chunk_text
+            finish_reason = chunk.get("stop_reason") or ""
+            if finish_reason is not None:
+                is_finished = True
+            returned_chunk = GenericStreamingChunk(
+                text=text,
+                tool_use=tool_use,
+                is_finished=is_finished,
+                finish_reason=finish_reason,
+                usage=usage,
+                index=index,
+                provider_specific_fields=provider_specific_fields,
+            )
+
+            return returned_chunk
+
+        except json.JSONDecodeError:
+            raise ValueError(f"Failed to decode JSON from chunk: {chunk}")

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/cost_calculation.py

@@ -0,0 +1,132 @@
+"""
+Helper util for handling anthropic-specific cost calculation
+- e.g.: prompt caching
+"""
+
+from typing import TYPE_CHECKING, Optional, Tuple
+
+from litellm.litellm_core_utils.llm_cost_calc.utils import (
+    _get_token_base_cost,
+    _parse_prompt_tokens_details,
+    calculate_cache_writing_cost,
+    generic_cost_per_token,
+)
+
+if TYPE_CHECKING:
+    from litellm.types.utils import ModelInfo, Usage
+import litellm
+
+
+def _compute_cache_only_cost(model_info: "ModelInfo", usage: "Usage") -> float:
+    """
+    Return only the cache-related portion of the prompt cost (cache read + cache write).
+
+    These costs must NOT be scaled by geo/speed multipliers because the old
+    explicit ``fast/`` model entries carried unchanged cache rates while
+    multiplying only the regular input/output token costs.
+    """
+    if usage.prompt_tokens_details is None:
+        return 0.0
+
+    prompt_tokens_details = _parse_prompt_tokens_details(usage)
+    (
+        _,
+        _,
+        cache_creation_cost,
+        cache_creation_cost_above_1hr,
+        cache_read_cost,
+    ) = _get_token_base_cost(model_info=model_info, usage=usage)
+
+    cache_cost = float(prompt_tokens_details["cache_hit_tokens"]) * cache_read_cost
+
+    if (
+        prompt_tokens_details["cache_creation_tokens"]
+        or prompt_tokens_details["cache_creation_token_details"] is not None
+    ):
+        cache_cost += calculate_cache_writing_cost(
+            cache_creation_tokens=prompt_tokens_details["cache_creation_tokens"],
+            cache_creation_token_details=prompt_tokens_details[
+                "cache_creation_token_details"
+            ],
+            cache_creation_cost_above_1hr=cache_creation_cost_above_1hr,
+            cache_creation_cost=cache_creation_cost,
+        )
+
+    return cache_cost
+
+
+def cost_per_token(model: str, usage: "Usage") -> Tuple[float, float]:
+    """
+    Calculates the cost per token for a given model, prompt tokens, and completion tokens.
+
+    Input:
+        - model: str, the model name without provider prefix
+        - usage: LiteLLM Usage block, containing anthropic caching information
+
+    Returns:
+        Tuple[float, float] - prompt_cost_in_usd, completion_cost_in_usd
+    """
+    prompt_cost, completion_cost = generic_cost_per_token(
+        model=model, usage=usage, custom_llm_provider="anthropic"
+    )
+
+    # Apply provider_specific_entry multipliers for geo/speed routing
+    try:
+        model_info = litellm.get_model_info(
+            model=model, custom_llm_provider="anthropic"
+        )
+        provider_specific_entry: dict = model_info.get("provider_specific_entry") or {}
+
+        multiplier = 1.0
+        if (
+            hasattr(usage, "inference_geo")
+            and usage.inference_geo
+            and usage.inference_geo.lower() not in ["global", "not_available"]
+        ):
+            multiplier *= provider_specific_entry.get(usage.inference_geo.lower(), 1.0)
+        if hasattr(usage, "speed") and usage.speed == "fast":
+            multiplier *= provider_specific_entry.get("fast", 1.0)
+
+        if multiplier != 1.0:
+            cache_cost = _compute_cache_only_cost(model_info=model_info, usage=usage)
+            prompt_cost = (prompt_cost - cache_cost) * multiplier + cache_cost
+            completion_cost *= multiplier
+    except Exception:
+        pass
+
+    return prompt_cost, completion_cost
+
+
+def get_cost_for_anthropic_web_search(
+    model_info: Optional["ModelInfo"] = None,
+    usage: Optional["Usage"] = None,
+) -> float:
+    """
+    Get the cost of using a web search tool for Anthropic.
+    """
+    from litellm.types.utils import SearchContextCostPerQuery
+
+    ## Check if web search requests are in the usage object
+    if model_info is None:
+        return 0.0
+
+    if (
+        usage is None
+        or usage.server_tool_use is None
+        or usage.server_tool_use.web_search_requests is None
+    ):
+        return 0.0
+
+    ## Get the cost per web search request
+    search_context_pricing: SearchContextCostPerQuery = (
+        model_info.get("search_context_cost_per_query") or SearchContextCostPerQuery()
+    )
+    cost_per_web_search_request = search_context_pricing.get(
+        "search_context_size_medium", 0.0
+    )
+    if cost_per_web_search_request is None or cost_per_web_search_request == 0.0:
+        return 0.0
+
+    ## Calculate the total cost
+    total_cost = cost_per_web_search_request * usage.server_tool_use.web_search_requests
+    return total_cost

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/count_tokens/__init__.py

@@ -0,0 +1,15 @@
+"""
+Anthropic CountTokens API implementation.
+"""
+
+from litellm.llms.anthropic.count_tokens.handler import AnthropicCountTokensHandler
+from litellm.llms.anthropic.count_tokens.token_counter import AnthropicTokenCounter
+from litellm.llms.anthropic.count_tokens.transformation import (
+    AnthropicCountTokensConfig,
+)
+
+__all__ = [
+    "AnthropicCountTokensHandler",
+    "AnthropicCountTokensConfig",
+    "AnthropicTokenCounter",
+]

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/count_tokens/handler.py

@@ -0,0 +1,128 @@
+"""
+Anthropic CountTokens API handler.
+
+Uses httpx for HTTP requests instead of the Anthropic SDK.
+"""
+
+from typing import Any, Dict, List, Optional, Union
+
+import httpx
+
+import litellm
+from litellm._logging import verbose_logger
+from litellm.llms.anthropic.common_utils import AnthropicError
+from litellm.llms.anthropic.count_tokens.transformation import (
+    AnthropicCountTokensConfig,
+)
+from litellm.llms.custom_httpx.http_handler import get_async_httpx_client
+
+
+class AnthropicCountTokensHandler(AnthropicCountTokensConfig):
+    """
+    Handler for Anthropic CountTokens API requests.
+
+    Uses httpx for HTTP requests, following the same pattern as BedrockCountTokensHandler.
+    """
+
+    async def handle_count_tokens_request(
+        self,
+        model: str,
+        messages: List[Dict[str, Any]],
+        api_key: str,
+        api_base: Optional[str] = None,
+        timeout: Optional[Union[float, httpx.Timeout]] = None,
+        tools: Optional[List[Dict[str, Any]]] = None,
+        system: Optional[Any] = None,
+    ) -> Dict[str, Any]:
+        """
+        Handle a CountTokens request using httpx.
+
+        Args:
+            model: The model identifier (e.g., "claude-3-5-sonnet-20241022")
+            messages: The messages to count tokens for
+            api_key: The Anthropic API key
+            api_base: Optional custom API base URL
+            timeout: Optional timeout for the request (defaults to litellm.request_timeout)
+
+        Returns:
+            Dictionary containing token count response
+
+        Raises:
+            AnthropicError: If the API request fails
+        """
+        try:
+            # Validate the request
+            self.validate_request(model, messages)
+
+            verbose_logger.debug(
+                f"Processing Anthropic CountTokens request for model: {model}"
+            )
+
+            # Transform request to Anthropic format
+            request_body = self.transform_request_to_count_tokens(
+                model=model,
+                messages=messages,
+                tools=tools,
+                system=system,
+            )
+
+            verbose_logger.debug(f"Transformed request: {request_body}")
+
+            # Get endpoint URL
+            endpoint_url = api_base or self.get_anthropic_count_tokens_endpoint()
+
+            verbose_logger.debug(f"Making request to: {endpoint_url}")
+
+            # Get required headers
+            headers = self.get_required_headers(api_key)
+
+            # Use LiteLLM's async httpx client
+            async_client = get_async_httpx_client(
+                llm_provider=litellm.LlmProviders.ANTHROPIC
+            )
+
+            # Use provided timeout or fall back to litellm.request_timeout
+            request_timeout = (
+                timeout if timeout is not None else litellm.request_timeout
+            )
+
+            response = await async_client.post(
+                endpoint_url,
+                headers=headers,
+                json=request_body,
+                timeout=request_timeout,
+            )
+
+            verbose_logger.debug(f"Response status: {response.status_code}")
+
+            if response.status_code != 200:
+                error_text = response.text
+                verbose_logger.error(f"Anthropic API error: {error_text}")
+                raise AnthropicError(
+                    status_code=response.status_code,
+                    message=error_text,
+                )
+
+            anthropic_response = response.json()
+
+            verbose_logger.debug(f"Anthropic response: {anthropic_response}")
+
+            # Return Anthropic response directly - no transformation needed
+            return anthropic_response
+
+        except AnthropicError:
+            # Re-raise Anthropic exceptions as-is
+            raise
+        except httpx.HTTPStatusError as e:
+            # HTTP errors - preserve the actual status code
+            verbose_logger.error(f"HTTP error in CountTokens handler: {str(e)}")
+            raise AnthropicError(
+                status_code=e.response.status_code,
+                message=e.response.text,
+            )
+        except Exception as e:
+            verbose_logger.error(f"Error in CountTokens handler: {str(e)}")
+            raise AnthropicError(
+                status_code=500,
+                message=f"CountTokens processing error: {str(e)}",
+            )

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/count_tokens/token_counter.py

@@ -0,0 +1,108 @@
+"""
+Anthropic Token Counter implementation using the CountTokens API.
+"""
+
+import os
+from typing import Any, Dict, List, Optional
+
+from litellm._logging import verbose_logger
+from litellm.llms.anthropic.count_tokens.handler import AnthropicCountTokensHandler
+from litellm.llms.base_llm.base_utils import BaseTokenCounter
+from litellm.types.utils import LlmProviders, TokenCountResponse
+
+# Global handler instance - reuse across all token counting requests
+anthropic_count_tokens_handler = AnthropicCountTokensHandler()
+
+
+class AnthropicTokenCounter(BaseTokenCounter):
+    """Token counter implementation for Anthropic provider using the CountTokens API."""
+
+    def should_use_token_counting_api(
+        self,
+        custom_llm_provider: Optional[str] = None,
+    ) -> bool:
+        return custom_llm_provider == LlmProviders.ANTHROPIC.value
+
+    async def count_tokens(
+        self,
+        model_to_use: str,
+        messages: Optional[List[Dict[str, Any]]],
+        contents: Optional[List[Dict[str, Any]]],
+        deployment: Optional[Dict[str, Any]] = None,
+        request_model: str = "",
+        tools: Optional[List[Dict[str, Any]]] = None,
+        system: Optional[Any] = None,
+    ) -> Optional[TokenCountResponse]:
+        """
+        Count tokens using Anthropic's CountTokens API.
+
+        Args:
+            model_to_use: The model identifier
+            messages: The messages to count tokens for
+            contents: Alternative content format (not used for Anthropic)
+            deployment: Deployment configuration containing litellm_params
+            request_model: The original request model name
+
+        Returns:
+            TokenCountResponse with token count, or None if counting fails
+        """
+        from litellm.llms.anthropic.common_utils import AnthropicError
+
+        if not messages:
+            return None
+
+        deployment = deployment or {}
+        litellm_params = deployment.get("litellm_params", {})
+
+        # Get Anthropic API key from deployment config or environment
+        api_key = litellm_params.get("api_key")
+        if not api_key:
+            api_key = os.getenv("ANTHROPIC_API_KEY")
+
+        if not api_key:
+            verbose_logger.warning("No Anthropic API key found for token counting")
+            return None
+
+        try:
+            result = await anthropic_count_tokens_handler.handle_count_tokens_request(
+                model=model_to_use,
+                messages=messages,
+                api_key=api_key,
+                tools=tools,
+                system=system,
+            )
+
+            if result is not None:
+                return TokenCountResponse(
+                    total_tokens=result.get("input_tokens", 0),
+                    request_model=request_model,
+                    model_used=model_to_use,
+                    tokenizer_type="anthropic_api",
+                    original_response=result,
+                )
+        except AnthropicError as e:
+            verbose_logger.warning(
+                f"Anthropic CountTokens API error: status={e.status_code}, message={e.message}"
+            )
+            return TokenCountResponse(
+                total_tokens=0,
+                request_model=request_model,
+                model_used=model_to_use,
+                tokenizer_type="anthropic_api",
+                error=True,
+                error_message=e.message,
+                status_code=e.status_code,
+            )
+        except Exception as e:
+            verbose_logger.warning(f"Error calling Anthropic CountTokens API: {e}")
+            return TokenCountResponse(
+                total_tokens=0,
+                request_model=request_model,
+                model_used=model_to_use,
+                tokenizer_type="anthropic_api",
+                error=True,
+                error_message=str(e),
+                status_code=500,
+            )
+
+        return None

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/count_tokens/transformation.py

@@ -0,0 +1,107 @@
+"""
+Anthropic CountTokens API transformation logic.
+
+This module handles the transformation of requests to Anthropic's CountTokens API format.
+"""
+
+from typing import Any, Dict, List, Optional
+
+from litellm.constants import ANTHROPIC_TOKEN_COUNTING_BETA_VERSION
+
+
+class AnthropicCountTokensConfig:
+    """
+    Configuration and transformation logic for Anthropic CountTokens API.
+
+    Anthropic CountTokens API Specification:
+    - Endpoint: POST https://api.anthropic.com/v1/messages/count_tokens
+    - Beta header required: anthropic-beta: token-counting-2024-11-01
+    - Response: {"input_tokens": <number>}
+    """
+
+    def get_anthropic_count_tokens_endpoint(self) -> str:
+        """
+        Get the Anthropic CountTokens API endpoint.
+
+        Returns:
+            The endpoint URL for the CountTokens API
+        """
+        return "https://api.anthropic.com/v1/messages/count_tokens"
+
+    def transform_request_to_count_tokens(
+        self,
+        model: str,
+        messages: List[Dict[str, Any]],
+        tools: Optional[List[Dict[str, Any]]] = None,
+        system: Optional[Any] = None,
+    ) -> Dict[str, Any]:
+        """
+        Transform request to Anthropic CountTokens format.
+
+        Includes optional system and tools fields for accurate token counting.
+        """
+        request: Dict[str, Any] = {
+            "model": model,
+            "messages": messages,
+        }
+
+        if system is not None:
+            request["system"] = system
+
+        if tools is not None:
+            request["tools"] = tools
+
+        return request
+
+    def get_required_headers(self, api_key: str) -> Dict[str, str]:
+        """
+        Get the required headers for the CountTokens API.
+
+        Args:
+            api_key: The Anthropic API key
+
+        Returns:
+            Dictionary of required headers
+        """
+        from litellm.llms.anthropic.common_utils import (
+            optionally_handle_anthropic_oauth,
+        )
+
+        headers: Dict[str, str] = {
+            "Content-Type": "application/json",
+            "x-api-key": api_key,
+            "anthropic-version": "2023-06-01",
+            "anthropic-beta": ANTHROPIC_TOKEN_COUNTING_BETA_VERSION,
+        }
+        headers, _ = optionally_handle_anthropic_oauth(headers=headers, api_key=api_key)
+        return headers
+
+    def validate_request(self, model: str, messages: List[Dict[str, Any]]) -> None:
+        """
+        Validate the incoming count tokens request.
+
+        Args:
+            model: The model name
+            messages: The messages to count tokens for
+
+        Raises:
+            ValueError: If the request is invalid
+        """
+        if not model:
+            raise ValueError("model parameter is required")
+
+        if not messages:
+            raise ValueError("messages parameter is required")
+
+        if not isinstance(messages, list):
+            raise ValueError("messages must be a list")
+
+        for i, message in enumerate(messages):
+            if not isinstance(message, dict):
+                raise ValueError(f"Message {i} must be a dictionary")
+
+            if "role" not in message:
+                raise ValueError(f"Message {i} must have a 'role' field")
+
+            if "content" not in message:
+                raise ValueError(f"Message {i} must have a 'content' field")

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/experimental_pass_through/adapters/__init__.py

@@ -0,0 +1,3 @@
+from .transformation import LiteLLMAnthropicMessagesAdapter
+
+__all__ = ["LiteLLMAnthropicMessagesAdapter"]

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/experimental_pass_through/adapters/handler.py

@@ -0,0 +1,345 @@
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    AsyncIterator,
+    Coroutine,
+    Dict,
+    List,
+    Optional,
+    Tuple,
+    Union,
+    cast,
+)
+
+import litellm
+from litellm.llms.anthropic.experimental_pass_through.adapters.transformation import (
+    AnthropicAdapter,
+)
+from litellm.types.llms.anthropic_messages.anthropic_response import (
+    AnthropicMessagesResponse,
+)
+from litellm.types.utils import ModelResponse
+from litellm.utils import get_model_info
+
+if TYPE_CHECKING:
+    pass
+
+########################################################
+# init adapter
+ANTHROPIC_ADAPTER = AnthropicAdapter()
+########################################################
+
+
+class LiteLLMMessagesToCompletionTransformationHandler:
+    @staticmethod
+    def _route_openai_thinking_to_responses_api_if_needed(
+        completion_kwargs: Dict[str, Any],
+        *,
+        thinking: Optional[Dict[str, Any]],
+    ) -> None:
+        """
+        When users call `litellm.anthropic.messages.*` with a non-Anthropic model and
+        `thinking={"type": "enabled", ...}`, LiteLLM converts this into OpenAI
+        `reasoning_effort`.
+
+        For OpenAI models, Chat Completions typically does not return reasoning text
+        (only token accounting). To return a thinking-like content block in the
+        Anthropic response format, we route the request through OpenAI's Responses API
+        and request a reasoning summary.
+        """
+        custom_llm_provider = completion_kwargs.get("custom_llm_provider")
+        if custom_llm_provider is None:
+            try:
+                _, inferred_provider, _, _ = litellm.utils.get_llm_provider(
+                    model=cast(str, completion_kwargs.get("model"))
+                )
+                custom_llm_provider = inferred_provider
+            except Exception:
+                custom_llm_provider = None
+
+        if custom_llm_provider != "openai":
+            return
+
+        if not isinstance(thinking, dict) or thinking.get("type") != "enabled":
+            return
+
+        model = completion_kwargs.get("model")
+        try:
+            model_info = get_model_info(
+                model=cast(str, model), custom_llm_provider=custom_llm_provider
+            )
+            if model_info and model_info.get("supports_reasoning") is False:
+                # Model doesn't support reasoning/responses API, don't route
+                return
+        except Exception:
+            pass
+
+        if isinstance(model, str) and model and not model.startswith("responses/"):
+            # Prefix model with "responses/" to route to OpenAI Responses API
+            completion_kwargs["model"] = f"responses/{model}"
+
+        reasoning_effort = completion_kwargs.get("reasoning_effort")
+        if isinstance(reasoning_effort, str) and reasoning_effort:
+            completion_kwargs["reasoning_effort"] = {
+                "effort": reasoning_effort,
+                "summary": "detailed",
+            }
+        elif isinstance(reasoning_effort, dict):
+            if (
+                "summary" not in reasoning_effort
+                and "generate_summary" not in reasoning_effort
+            ):
+                updated_reasoning_effort = dict(reasoning_effort)
+                updated_reasoning_effort["summary"] = "detailed"
+                completion_kwargs["reasoning_effort"] = updated_reasoning_effort
+
+    @staticmethod
+    def _prepare_completion_kwargs(
+        *,
+        max_tokens: int,
+        messages: List[Dict],
+        model: str,
+        metadata: Optional[Dict] = None,
+        stop_sequences: Optional[List[str]] = None,
+        stream: Optional[bool] = False,
+        system: Optional[str] = None,
+        temperature: Optional[float] = None,
+        thinking: Optional[Dict] = None,
+        tool_choice: Optional[Dict] = None,
+        tools: Optional[List[Dict]] = None,
+        top_k: Optional[int] = None,
+        top_p: Optional[float] = None,
+        output_format: Optional[Dict] = None,
+        extra_kwargs: Optional[Dict[str, Any]] = None,
+    ) -> Tuple[Dict[str, Any], Dict[str, str]]:
+        """Prepare kwargs for litellm.completion/acompletion.
+
+        Returns:
+            Tuple of (completion_kwargs, tool_name_mapping)
+            - tool_name_mapping maps truncated tool names back to original names
+              for tools that exceeded OpenAI's 64-char limit
+        """
+        from litellm.litellm_core_utils.litellm_logging import (
+            Logging as LiteLLMLoggingObject,
+        )
+
+        request_data = {
+            "model": model,
+            "messages": messages,
+            "max_tokens": max_tokens,
+        }
+
+        if metadata:
+            request_data["metadata"] = metadata
+        if stop_sequences:
+            request_data["stop_sequences"] = stop_sequences
+        if system:
+            request_data["system"] = system
+        if temperature is not None:
+            request_data["temperature"] = temperature
+        if thinking:
+            request_data["thinking"] = thinking
+        if tool_choice:
+            request_data["tool_choice"] = tool_choice
+        if tools:
+            request_data["tools"] = tools
+        if top_k is not None:
+            request_data["top_k"] = top_k
+        if top_p is not None:
+            request_data["top_p"] = top_p
+        if output_format:
+            request_data["output_format"] = output_format
+
+        (
+            openai_request,
+            tool_name_mapping,
+        ) = ANTHROPIC_ADAPTER.translate_completion_input_params_with_tool_mapping(
+            request_data
+        )
+
+        if openai_request is None:
+            raise ValueError("Failed to translate request to OpenAI format")
+
+        completion_kwargs: Dict[str, Any] = dict(openai_request)
+
+        if stream:
+            completion_kwargs["stream"] = stream
+            completion_kwargs["stream_options"] = {
+                "include_usage": True,
+            }
+
+        excluded_keys = {"anthropic_messages"}
+        extra_kwargs = extra_kwargs or {}
+        for key, value in extra_kwargs.items():
+            if (
+                key == "litellm_logging_obj"
+                and value is not None
+                and isinstance(value, LiteLLMLoggingObject)
+            ):
+                from litellm.types.utils import CallTypes
+
+                setattr(value, "call_type", CallTypes.completion.value)
+                setattr(
+                    value, "stream_options", completion_kwargs.get("stream_options")
+                )
+            if (
+                key not in excluded_keys
+                and key not in completion_kwargs
+                and value is not None
+            ):
+                completion_kwargs[key] = value
+
+        LiteLLMMessagesToCompletionTransformationHandler._route_openai_thinking_to_responses_api_if_needed(
+            completion_kwargs,
+            thinking=thinking,
+        )
+
+        return completion_kwargs, tool_name_mapping
+
+    @staticmethod
+    async def async_anthropic_messages_handler(
+        max_tokens: int,
+        messages: List[Dict],
+        model: str,
+        metadata: Optional[Dict] = None,
+        stop_sequences: Optional[List[str]] = None,
+        stream: Optional[bool] = False,
+        system: Optional[str] = None,
+        temperature: Optional[float] = None,
+        thinking: Optional[Dict] = None,
+        tool_choice: Optional[Dict] = None,
+        tools: Optional[List[Dict]] = None,
+        top_k: Optional[int] = None,
+        top_p: Optional[float] = None,
+        output_format: Optional[Dict] = None,
+        **kwargs,
+    ) -> Union[AnthropicMessagesResponse, AsyncIterator]:
+        """Handle non-Anthropic models asynchronously using the adapter"""
+        (
+            completion_kwargs,
+            tool_name_mapping,
+        ) = LiteLLMMessagesToCompletionTransformationHandler._prepare_completion_kwargs(
+            max_tokens=max_tokens,
+            messages=messages,
+            model=model,
+            metadata=metadata,
+            stop_sequences=stop_sequences,
+            stream=stream,
+            system=system,
+            temperature=temperature,
+            thinking=thinking,
+            tool_choice=tool_choice,
+            tools=tools,
+            top_k=top_k,
+            top_p=top_p,
+            output_format=output_format,
+            extra_kwargs=kwargs,
+        )
+
+        completion_response = await litellm.acompletion(**completion_kwargs)
+
+        if stream:
+            transformed_stream = (
+                ANTHROPIC_ADAPTER.translate_completion_output_params_streaming(
+                    completion_response,
+                    model=model,
+                    tool_name_mapping=tool_name_mapping,
+                )
+            )
+            if transformed_stream is not None:
+                return transformed_stream
+            raise ValueError("Failed to transform streaming response")
+        else:
+            anthropic_response = ANTHROPIC_ADAPTER.translate_completion_output_params(
+                cast(ModelResponse, completion_response),
+                tool_name_mapping=tool_name_mapping,
+            )
+            if anthropic_response is not None:
+                return anthropic_response
+            raise ValueError("Failed to transform response to Anthropic format")
+
+    @staticmethod
+    def anthropic_messages_handler(
+        max_tokens: int,
+        messages: List[Dict],
+        model: str,
+        metadata: Optional[Dict] = None,
+        stop_sequences: Optional[List[str]] = None,
+        stream: Optional[bool] = False,
+        system: Optional[str] = None,
+        temperature: Optional[float] = None,
+        thinking: Optional[Dict] = None,
+        tool_choice: Optional[Dict] = None,
+        tools: Optional[List[Dict]] = None,
+        top_k: Optional[int] = None,
+        top_p: Optional[float] = None,
+        output_format: Optional[Dict] = None,
+        _is_async: bool = False,
+        **kwargs,
+    ) -> Union[
+        AnthropicMessagesResponse,
+        AsyncIterator[Any],
+        Coroutine[Any, Any, Union[AnthropicMessagesResponse, AsyncIterator[Any]]],
+    ]:
+        """Handle non-Anthropic models using the adapter."""
+        if _is_async is True:
+            return LiteLLMMessagesToCompletionTransformationHandler.async_anthropic_messages_handler(
+                max_tokens=max_tokens,
+                messages=messages,
+                model=model,
+                metadata=metadata,
+                stop_sequences=stop_sequences,
+                stream=stream,
+                system=system,
+                temperature=temperature,
+                thinking=thinking,
+                tool_choice=tool_choice,
+                tools=tools,
+                top_k=top_k,
+                top_p=top_p,
+                output_format=output_format,
+                **kwargs,
+            )
+
+        (
+            completion_kwargs,
+            tool_name_mapping,
+        ) = LiteLLMMessagesToCompletionTransformationHandler._prepare_completion_kwargs(
+            max_tokens=max_tokens,
+            messages=messages,
+            model=model,
+            metadata=metadata,
+            stop_sequences=stop_sequences,
+            stream=stream,
+            system=system,
+            temperature=temperature,
+            thinking=thinking,
+            tool_choice=tool_choice,
+            tools=tools,
+            top_k=top_k,
+            top_p=top_p,
+            output_format=output_format,
+            extra_kwargs=kwargs,
+        )
+
+        completion_response = litellm.completion(**completion_kwargs)
+
+        if stream:
+            transformed_stream = (
+                ANTHROPIC_ADAPTER.translate_completion_output_params_streaming(
+                    completion_response,
+                    model=model,
+                    tool_name_mapping=tool_name_mapping,
+                )
+            )
+            if transformed_stream is not None:
+                return transformed_stream
+            raise ValueError("Failed to transform streaming response")
+        else:
+            anthropic_response = ANTHROPIC_ADAPTER.translate_completion_output_params(
+                cast(ModelResponse, completion_response),
+                tool_name_mapping=tool_name_mapping,
+            )
+            if anthropic_response is not None:
+                return anthropic_response
+            raise ValueError("Failed to transform response to Anthropic format")

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/experimental_pass_through/adapters/streaming_iterator.py

@@ -0,0 +1,488 @@
+# What is this?
+## Translates OpenAI call to Anthropic `/v1/messages` format
+import json
+import traceback
+from collections import deque
+from typing import TYPE_CHECKING, Any, AsyncIterator, Dict, Iterator, Literal, Optional
+
+from litellm import verbose_logger
+from litellm._uuid import uuid
+from litellm.types.llms.anthropic import UsageDelta
+from litellm.types.utils import AdapterCompletionStreamWrapper
+
+if TYPE_CHECKING:
+    from litellm.types.utils import ModelResponseStream
+
+
+class AnthropicStreamWrapper(AdapterCompletionStreamWrapper):
+    """
+    - first chunk return 'message_start'
+    - content block must be started and stopped
+    - finish_reason must map exactly to anthropic reason, else anthropic client won't be able to parse it.
+    """
+
+    from litellm.types.llms.anthropic import (
+        ContentBlockContentBlockDict,
+        ContentBlockStart,
+        ContentBlockStartText,
+        TextBlock,
+    )
+
+    sent_first_chunk: bool = False
+    sent_content_block_start: bool = False
+    sent_content_block_finish: bool = False
+    current_content_block_type: Literal["text", "tool_use", "thinking"] = "text"
+    sent_last_message: bool = False
+    holding_chunk: Optional[Any] = None
+    holding_stop_reason_chunk: Optional[Any] = None
+    queued_usage_chunk: bool = False
+    current_content_block_index: int = 0
+    current_content_block_start: ContentBlockContentBlockDict = TextBlock(
+        type="text",
+        text="",
+    )
+    chunk_queue: deque = deque()  # Queue for buffering multiple chunks
+
+    def __init__(
+        self,
+        completion_stream: Any,
+        model: str,
+        tool_name_mapping: Optional[Dict[str, str]] = None,
+    ):
+        super().__init__(completion_stream)
+        self.model = model
+        # Mapping of truncated tool names to original names (for OpenAI's 64-char limit)
+        self.tool_name_mapping = tool_name_mapping or {}
+
+    def _create_initial_usage_delta(self) -> UsageDelta:
+        """
+        Create the initial UsageDelta for the message_start event.
+
+        Initializes cache token fields (cache_creation_input_tokens, cache_read_input_tokens)
+        to 0 to indicate to clients (like Claude Code) that prompt caching is supported.
+
+        The actual cache token values will be provided in the message_delta event at the
+        end of the stream, since Bedrock Converse API only returns usage data in the final
+        response chunk.
+
+        Returns:
+            UsageDelta with all token counts initialized to 0.
+        """
+        return UsageDelta(
+            input_tokens=0,
+            output_tokens=0,
+            cache_creation_input_tokens=0,
+            cache_read_input_tokens=0,
+        )
+
+    def __next__(self):
+        from .transformation import LiteLLMAnthropicMessagesAdapter
+
+        try:
+            # Always return queued chunks first
+            if self.chunk_queue:
+                return self.chunk_queue.popleft()
+
+            # Queue initial chunks if not sent yet
+            if self.sent_first_chunk is False:
+                self.sent_first_chunk = True
+                self.chunk_queue.append(
+                    {
+                        "type": "message_start",
+                        "message": {
+                            "id": "msg_{}".format(uuid.uuid4()),
+                            "type": "message",
+                            "role": "assistant",
+                            "content": [],
+                            "model": self.model,
+                            "stop_reason": None,
+                            "stop_sequence": None,
+                            "usage": self._create_initial_usage_delta(),
+                        },
+                    }
+                )
+                return self.chunk_queue.popleft()
+
+            if self.sent_content_block_start is False:
+                self.sent_content_block_start = True
+                self.chunk_queue.append(
+                    {
+                        "type": "content_block_start",
+                        "index": self.current_content_block_index,
+                        "content_block": {"type": "text", "text": ""},
+                    }
+                )
+                return self.chunk_queue.popleft()
+
+            for chunk in self.completion_stream:
+                if chunk == "None" or chunk is None:
+                    raise Exception
+
+                should_start_new_block = self._should_start_new_content_block(chunk)
+                if should_start_new_block:
+                    self._increment_content_block_index()
+
+                processed_chunk = LiteLLMAnthropicMessagesAdapter().translate_streaming_openai_response_to_anthropic(
+                    response=chunk,
+                    current_content_block_index=self.current_content_block_index,
+                )
+
+                if should_start_new_block and not self.sent_content_block_finish:
+                    # Queue the sequence: content_block_stop -> content_block_start
+                    # The trigger chunk itself is not emitted as a delta since the
+                    # content_block_start already carries the relevant information.
+                    self.chunk_queue.append(
+                        {
+                            "type": "content_block_stop",
+                            "index": max(self.current_content_block_index - 1, 0),
+                        }
+                    )
+                    self.chunk_queue.append(
+                        {
+                            "type": "content_block_start",
+                            "index": self.current_content_block_index,
+                            "content_block": self.current_content_block_start,
+                        }
+                    )
+                    self.sent_content_block_finish = False
+                    return self.chunk_queue.popleft()
+
+                if (
+                    processed_chunk["type"] == "message_delta"
+                    and self.sent_content_block_finish is False
+                ):
+                    # Queue both the content_block_stop and the message_delta
+                    self.chunk_queue.append(
+                        {
+                            "type": "content_block_stop",
+                            "index": self.current_content_block_index,
+                        }
+                    )
+                    self.sent_content_block_finish = True
+                    self.chunk_queue.append(processed_chunk)
+                    return self.chunk_queue.popleft()
+                elif self.holding_chunk is not None:
+                    self.chunk_queue.append(self.holding_chunk)
+                    self.chunk_queue.append(processed_chunk)
+                    self.holding_chunk = None
+                    return self.chunk_queue.popleft()
+                else:
+                    self.chunk_queue.append(processed_chunk)
+                    return self.chunk_queue.popleft()
+
+            # Handle any remaining held chunks after stream ends
+            if self.holding_chunk is not None:
+                self.chunk_queue.append(self.holding_chunk)
+                self.holding_chunk = None
+
+            if not self.sent_last_message:
+                self.sent_last_message = True
+                self.chunk_queue.append({"type": "message_stop"})
+
+            if self.chunk_queue:
+                return self.chunk_queue.popleft()
+
+            raise StopIteration
+        except StopIteration:
+            if self.chunk_queue:
+                return self.chunk_queue.popleft()
+            if self.sent_last_message is False:
+                self.sent_last_message = True
+                return {"type": "message_stop"}
+            raise StopIteration
+        except Exception as e:
+            verbose_logger.error(
+                "Anthropic Adapter - {}\n{}".format(e, traceback.format_exc())
+            )
+            raise StopAsyncIteration
+
+    async def __anext__(self):  # noqa: PLR0915
+        from .transformation import LiteLLMAnthropicMessagesAdapter
+
+        try:
+            # Always return queued chunks first
+            if self.chunk_queue:
+                return self.chunk_queue.popleft()
+
+            # Queue initial chunks if not sent yet
+            if self.sent_first_chunk is False:
+                self.sent_first_chunk = True
+                self.chunk_queue.append(
+                    {
+                        "type": "message_start",
+                        "message": {
+                            "id": "msg_{}".format(uuid.uuid4()),
+                            "type": "message",
+                            "role": "assistant",
+                            "content": [],
+                            "model": self.model,
+                            "stop_reason": None,
+                            "stop_sequence": None,
+                            "usage": self._create_initial_usage_delta(),
+                        },
+                    }
+                )
+                return self.chunk_queue.popleft()
+
+            if self.sent_content_block_start is False:
+                self.sent_content_block_start = True
+                self.chunk_queue.append(
+                    {
+                        "type": "content_block_start",
+                        "index": self.current_content_block_index,
+                        "content_block": {"type": "text", "text": ""},
+                    }
+                )
+                return self.chunk_queue.popleft()
+
+            async for chunk in self.completion_stream:
+                if chunk == "None" or chunk is None:
+                    raise Exception
+
+                # Check if we need to start a new content block
+                should_start_new_block = self._should_start_new_content_block(chunk)
+                if should_start_new_block:
+                    self._increment_content_block_index()
+
+                processed_chunk = LiteLLMAnthropicMessagesAdapter().translate_streaming_openai_response_to_anthropic(
+                    response=chunk,
+                    current_content_block_index=self.current_content_block_index,
+                )
+
+                # Check if this is a usage chunk and we have a held stop_reason chunk
+                if (
+                    self.holding_stop_reason_chunk is not None
+                    and getattr(chunk, "usage", None) is not None
+                ):
+                    # Merge usage into the held stop_reason chunk
+                    merged_chunk = self.holding_stop_reason_chunk.copy()
+                    if "delta" not in merged_chunk:
+                        merged_chunk["delta"] = {}
+
+                    # Add usage to the held chunk
+                    uncached_input_tokens = chunk.usage.prompt_tokens or 0
+                    if (
+                        hasattr(chunk.usage, "prompt_tokens_details")
+                        and chunk.usage.prompt_tokens_details
+                    ):
+                        cached_tokens = (
+                            getattr(
+                                chunk.usage.prompt_tokens_details, "cached_tokens", 0
+                            )
+                            or 0
+                        )
+                        uncached_input_tokens -= cached_tokens
+
+                    usage_dict: UsageDelta = {
+                        "input_tokens": uncached_input_tokens,
+                        "output_tokens": chunk.usage.completion_tokens or 0,
+                    }
+                    # Add cache tokens if available (for prompt caching support)
+                    if (
+                        hasattr(chunk.usage, "_cache_creation_input_tokens")
+                        and chunk.usage._cache_creation_input_tokens > 0
+                    ):
+                        usage_dict[
+                            "cache_creation_input_tokens"
+                        ] = chunk.usage._cache_creation_input_tokens
+                    if (
+                        hasattr(chunk.usage, "_cache_read_input_tokens")
+                        and chunk.usage._cache_read_input_tokens > 0
+                    ):
+                        usage_dict[
+                            "cache_read_input_tokens"
+                        ] = chunk.usage._cache_read_input_tokens
+                    merged_chunk["usage"] = usage_dict
+
+                    # Queue the merged chunk and reset
+                    self.chunk_queue.append(merged_chunk)
+                    self.queued_usage_chunk = True
+                    self.holding_stop_reason_chunk = None
+                    return self.chunk_queue.popleft()
+
+                # Check if this processed chunk has a stop_reason - hold it for next chunk
+
+                if not self.queued_usage_chunk:
+                    if should_start_new_block and not self.sent_content_block_finish:
+                        # Queue the sequence: content_block_stop -> content_block_start
+                        # The trigger chunk itself is not emitted as a delta since the
+                        # content_block_start already carries the relevant information.
+
+                        # 1. Stop current content block
+                        self.chunk_queue.append(
+                            {
+                                "type": "content_block_stop",
+                                "index": max(self.current_content_block_index - 1, 0),
+                            }
+                        )
+
+                        # 2. Start new content block
+                        self.chunk_queue.append(
+                            {
+                                "type": "content_block_start",
+                                "index": self.current_content_block_index,
+                                "content_block": self.current_content_block_start,
+                            }
+                        )
+
+                        # Reset state for new block
+                        self.sent_content_block_finish = False
+
+                        # Return the first queued item
+                        return self.chunk_queue.popleft()
+
+                    if (
+                        processed_chunk["type"] == "message_delta"
+                        and self.sent_content_block_finish is False
+                    ):
+                        # Queue both the content_block_stop and the holding chunk
+                        self.chunk_queue.append(
+                            {
+                                "type": "content_block_stop",
+                                "index": self.current_content_block_index,
+                            }
+                        )
+                        self.sent_content_block_finish = True
+                        if (
+                            processed_chunk.get("delta", {}).get("stop_reason")
+                            is not None
+                        ):
+                            self.holding_stop_reason_chunk = processed_chunk
+                        else:
+                            self.chunk_queue.append(processed_chunk)
+                        return self.chunk_queue.popleft()
+                    elif self.holding_chunk is not None:
+                        # Queue both chunks
+                        self.chunk_queue.append(self.holding_chunk)
+                        self.chunk_queue.append(processed_chunk)
+                        self.holding_chunk = None
+                        return self.chunk_queue.popleft()
+                    else:
+                        # Queue the current chunk
+                        self.chunk_queue.append(processed_chunk)
+                        return self.chunk_queue.popleft()
+
+            # Handle any remaining held chunks after stream ends
+            if not self.queued_usage_chunk:
+                if self.holding_stop_reason_chunk is not None:
+                    self.chunk_queue.append(self.holding_stop_reason_chunk)
+                    self.holding_stop_reason_chunk = None
+
+                if self.holding_chunk is not None:
+                    self.chunk_queue.append(self.holding_chunk)
+                    self.holding_chunk = None
+
+            if not self.sent_last_message:
+                self.sent_last_message = True
+                self.chunk_queue.append({"type": "message_stop"})
+
+            # Return queued items if any
+            if self.chunk_queue:
+                return self.chunk_queue.popleft()
+
+            raise StopIteration
+
+        except StopIteration:
+            # Handle any remaining queued chunks before stopping
+            if self.chunk_queue:
+                return self.chunk_queue.popleft()
+            # Handle any held stop_reason chunk
+            if self.holding_stop_reason_chunk is not None:
+                return self.holding_stop_reason_chunk
+            if not self.sent_last_message:
+                self.sent_last_message = True
+                return {"type": "message_stop"}
+            raise StopAsyncIteration
+
+    def anthropic_sse_wrapper(self) -> Iterator[bytes]:
+        """
+        Convert AnthropicStreamWrapper dict chunks to Server-Sent Events format.
+        Similar to the Bedrock bedrock_sse_wrapper implementation.
+
+        This wrapper ensures dict chunks are SSE formatted with both event and data lines.
+        """
+        for chunk in self:
+            if isinstance(chunk, dict):
+                event_type: str = str(chunk.get("type", "message"))
+                payload = f"event: {event_type}\ndata: {json.dumps(chunk)}\n\n"
+                yield payload.encode()
+            else:
+                # For non-dict chunks, forward the original value unchanged
+                yield chunk
+
+    async def async_anthropic_sse_wrapper(self) -> AsyncIterator[bytes]:
+        """
+        Async version of anthropic_sse_wrapper.
+        Convert AnthropicStreamWrapper dict chunks to Server-Sent Events format.
+        """
+        async for chunk in self:
+            if isinstance(chunk, dict):
+                event_type: str = str(chunk.get("type", "message"))
+                payload = f"event: {event_type}\ndata: {json.dumps(chunk)}\n\n"
+                yield payload.encode()
+            else:
+                # For non-dict chunks, forward the original value unchanged
+                yield chunk
+
+    def _increment_content_block_index(self):
+        self.current_content_block_index += 1
+
+    def _should_start_new_content_block(self, chunk: "ModelResponseStream") -> bool:
+        """
+        Determine if we should start a new content block based on the processed chunk.
+        Override this method with your specific logic for detecting new content blocks.
+
+        Examples of when you might want to start a new content block:
+        - Switching from text to tool calls
+        - Different content types in the response
+        - Specific markers in the content
+        """
+        from .transformation import LiteLLMAnthropicMessagesAdapter
+
+        # Example logic - customize based on your needs:
+        # If chunk indicates a tool call
+        if chunk.choices[0].finish_reason is not None:
+            return False
+
+        (
+            block_type,
+            content_block_start,
+        ) = LiteLLMAnthropicMessagesAdapter()._translate_streaming_openai_chunk_to_anthropic_content_block(
+            choices=chunk.choices  # type: ignore
+        )
+
+        # Restore original tool name if it was truncated for OpenAI's 64-char limit
+        if block_type == "tool_use":
+            # Type narrowing: content_block_start is ToolUseBlock when block_type is "tool_use"
+            from typing import cast
+
+            from litellm.types.llms.anthropic import ToolUseBlock
+
+            tool_block = cast(ToolUseBlock, content_block_start)
+
+            if tool_block.get("name"):
+                truncated_name = tool_block["name"]
+                original_name = self.tool_name_mapping.get(
+                    truncated_name, truncated_name
+                )
+                tool_block["name"] = original_name
+
+        if block_type != self.current_content_block_type:
+            self.current_content_block_type = block_type
+            self.current_content_block_start = content_block_start
+            return True
+
+        # For parallel tool calls, we'll necessarily have a new content block
+        # if we get a function name since it signals a new tool call
+        if block_type == "tool_use":
+            from typing import cast
+
+            from litellm.types.llms.anthropic import ToolUseBlock
+
+            tool_block = cast(ToolUseBlock, content_block_start)
+            if tool_block.get("name"):
+                self.current_content_block_type = block_type
+                self.current_content_block_start = content_block_start
+                return True
+
+        return False

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/experimental_pass_through/architecture.md

@@ -0,0 +1,51 @@
+# Anthropic Messages Pass-Through Architecture
+
+## Request Flow
+
+```mermaid
+flowchart TD
+    A[litellm.anthropic.messages.acreate] --> B{Provider?}
+    
+    B -->|anthropic| C[AnthropicMessagesConfig]
+    B -->|azure_ai| D[AzureAnthropicMessagesConfig]
+    B -->|bedrock invoke| E[BedrockAnthropicMessagesConfig]
+    B -->|vertex_ai| F[VertexAnthropicMessagesConfig]
+    B -->|Other providers| G[LiteLLMAnthropicMessagesAdapter]
+    
+    C --> H[Direct Anthropic API]
+    D --> I[Azure AI Foundry API]
+    E --> J[Bedrock Invoke API]
+    F --> K[Vertex AI API]
+    
+    G --> L[translate_anthropic_to_openai]
+    L --> M[litellm.completion]
+    M --> N[Provider API]
+    N --> O[translate_openai_response_to_anthropic]
+    O --> P[Anthropic Response Format]
+    
+    H --> P
+    I --> P
+    J --> P
+    K --> P
+```
+
+## Adapter Flow (Non-Native Providers)
+
+```mermaid
+sequenceDiagram
+    participant User
+    participant Handler as anthropic_messages_handler
+    participant Adapter as LiteLLMAnthropicMessagesAdapter
+    participant LiteLLM as litellm.completion
+    participant Provider as Provider API
+
+    User->>Handler: Anthropic Messages Request
+    Handler->>Adapter: translate_anthropic_to_openai()
+    Note over Adapter: messages, tools, thinking,<br/>output_format → response_format
+    Adapter->>LiteLLM: OpenAI Format Request
+    LiteLLM->>Provider: Provider-specific Request
+    Provider->>LiteLLM: Provider Response
+    LiteLLM->>Adapter: OpenAI Format Response
+    Adapter->>Handler: translate_openai_response_to_anthropic()
+    Handler->>User: Anthropic Messages Response
+```

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/experimental_pass_through/messages/fake_stream_iterator.py

@@ -0,0 +1,251 @@
+"""
+Fake Streaming Iterator for Anthropic Messages
+
+This module provides a fake streaming iterator that converts non-streaming
+Anthropic Messages responses into proper streaming format.
+
+Used when WebSearch interception converts stream=True to stream=False but
+the LLM doesn't make a tool call, and we need to return a stream to the user.
+"""
+
+import json
+from typing import Any, Dict, List, cast
+
+from litellm.types.llms.anthropic_messages.anthropic_response import (
+    AnthropicMessagesResponse,
+)
+
+
+class FakeAnthropicMessagesStreamIterator:
+    """
+    Fake streaming iterator for Anthropic Messages responses.
+
+    Used when we need to convert a non-streaming response to a streaming format,
+    such as when WebSearch interception converts stream=True to stream=False but
+    the LLM doesn't make a tool call.
+
+    This creates a proper Anthropic-style streaming response with multiple events:
+    - message_start
+    - content_block_start (for each content block)
+    - content_block_delta (for text content, chunked)
+    - content_block_stop
+    - message_delta (for usage)
+    - message_stop
+    """
+
+    def __init__(self, response: AnthropicMessagesResponse):
+        self.response = response
+        self.chunks = self._create_streaming_chunks()
+        self.current_index = 0
+
+    def _create_streaming_chunks(self) -> List[bytes]:
+        """Convert the non-streaming response to streaming chunks"""
+        chunks = []
+
+        # Cast response to dict for easier access
+        response_dict = cast(Dict[str, Any], self.response)
+
+        # 1. message_start event
+        usage = response_dict.get("usage", {})
+        message_start = {
+            "type": "message_start",
+            "message": {
+                "id": response_dict.get("id"),
+                "type": "message",
+                "role": response_dict.get("role", "assistant"),
+                "model": response_dict.get("model"),
+                "content": [],
+                "stop_reason": None,
+                "stop_sequence": None,
+                "usage": {
+                    "input_tokens": usage.get("input_tokens", 0) if usage else 0,
+                    "output_tokens": 0,
+                },
+            },
+        }
+        chunks.append(
+            f"event: message_start\ndata: {json.dumps(message_start)}\n\n".encode()
+        )
+
+        # 2-4. For each content block, send start/delta/stop events
+        content_blocks = response_dict.get("content", [])
+        if content_blocks:
+            for index, block in enumerate(content_blocks):
+                # Cast block to dict for easier access
+                block_dict = cast(Dict[str, Any], block)
+                block_type = block_dict.get("type")
+
+                if block_type == "text":
+                    # content_block_start
+                    content_block_start = {
+                        "type": "content_block_start",
+                        "index": index,
+                        "content_block": {"type": "text", "text": ""},
+                    }
+                    chunks.append(
+                        f"event: content_block_start\ndata: {json.dumps(content_block_start)}\n\n".encode()
+                    )
+
+                    # content_block_delta (send full text as one delta for simplicity)
+                    text = block_dict.get("text", "")
+                    content_block_delta = {
+                        "type": "content_block_delta",
+                        "index": index,
+                        "delta": {"type": "text_delta", "text": text},
+                    }
+                    chunks.append(
+                        f"event: content_block_delta\ndata: {json.dumps(content_block_delta)}\n\n".encode()
+                    )
+
+                    # content_block_stop
+                    content_block_stop = {"type": "content_block_stop", "index": index}
+                    chunks.append(
+                        f"event: content_block_stop\ndata: {json.dumps(content_block_stop)}\n\n".encode()
+                    )
+
+                elif block_type == "thinking":
+                    # content_block_start for thinking
+                    content_block_start = {
+                        "type": "content_block_start",
+                        "index": index,
+                        "content_block": {
+                            "type": "thinking",
+                            "thinking": "",
+                            "signature": "",
+                        },
+                    }
+                    chunks.append(
+                        f"event: content_block_start\ndata: {json.dumps(content_block_start)}\n\n".encode()
+                    )
+
+                    # content_block_delta for thinking text
+                    thinking_text = block_dict.get("thinking", "")
+                    if thinking_text:
+                        content_block_delta = {
+                            "type": "content_block_delta",
+                            "index": index,
+                            "delta": {
+                                "type": "thinking_delta",
+                                "thinking": thinking_text,
+                            },
+                        }
+                        chunks.append(
+                            f"event: content_block_delta\ndata: {json.dumps(content_block_delta)}\n\n".encode()
+                        )
+
+                    # content_block_delta for signature (if present)
+                    signature = block_dict.get("signature", "")
+                    if signature:
+                        signature_delta = {
+                            "type": "content_block_delta",
+                            "index": index,
+                            "delta": {
+                                "type": "signature_delta",
+                                "signature": signature,
+                            },
+                        }
+                        chunks.append(
+                            f"event: content_block_delta\ndata: {json.dumps(signature_delta)}\n\n".encode()
+                        )
+
+                    # content_block_stop
+                    content_block_stop = {"type": "content_block_stop", "index": index}
+                    chunks.append(
+                        f"event: content_block_stop\ndata: {json.dumps(content_block_stop)}\n\n".encode()
+                    )
+
+                elif block_type == "redacted_thinking":
+                    # content_block_start for redacted_thinking
+                    content_block_start = {
+                        "type": "content_block_start",
+                        "index": index,
+                        "content_block": {"type": "redacted_thinking"},
+                    }
+                    chunks.append(
+                        f"event: content_block_start\ndata: {json.dumps(content_block_start)}\n\n".encode()
+                    )
+
+                    # content_block_stop (no delta for redacted thinking)
+                    content_block_stop = {"type": "content_block_stop", "index": index}
+                    chunks.append(
+                        f"event: content_block_stop\ndata: {json.dumps(content_block_stop)}\n\n".encode()
+                    )
+
+                elif block_type == "tool_use":
+                    # content_block_start
+                    content_block_start = {
+                        "type": "content_block_start",
+                        "index": index,
+                        "content_block": {
+                            "type": "tool_use",
+                            "id": block_dict.get("id"),
+                            "name": block_dict.get("name"),
+                            "input": {},
+                        },
+                    }
+                    chunks.append(
+                        f"event: content_block_start\ndata: {json.dumps(content_block_start)}\n\n".encode()
+                    )
+
+                    # content_block_delta (send input as JSON delta)
+                    input_data = block_dict.get("input", {})
+                    content_block_delta = {
+                        "type": "content_block_delta",
+                        "index": index,
+                        "delta": {
+                            "type": "input_json_delta",
+                            "partial_json": json.dumps(input_data),
+                        },
+                    }
+                    chunks.append(
+                        f"event: content_block_delta\ndata: {json.dumps(content_block_delta)}\n\n".encode()
+                    )
+
+                    # content_block_stop
+                    content_block_stop = {"type": "content_block_stop", "index": index}
+                    chunks.append(
+                        f"event: content_block_stop\ndata: {json.dumps(content_block_stop)}\n\n".encode()
+                    )
+
+        # 5. message_delta event (with final usage and stop_reason)
+        message_delta = {
+            "type": "message_delta",
+            "delta": {
+                "stop_reason": response_dict.get("stop_reason"),
+                "stop_sequence": response_dict.get("stop_sequence"),
+            },
+            "usage": {"output_tokens": usage.get("output_tokens", 0) if usage else 0},
+        }
+        chunks.append(
+            f"event: message_delta\ndata: {json.dumps(message_delta)}\n\n".encode()
+        )
+
+        # 6. message_stop event
+        message_stop = {"type": "message_stop", "usage": usage if usage else {}}
+        chunks.append(
+            f"event: message_stop\ndata: {json.dumps(message_stop)}\n\n".encode()
+        )
+
+        return chunks
+
+    def __aiter__(self):
+        return self
+
+    async def __anext__(self):
+        if self.current_index >= len(self.chunks):
+            raise StopAsyncIteration
+
+        chunk = self.chunks[self.current_index]
+        self.current_index += 1
+        return chunk
+
+    def __iter__(self):
+        return self
+
+    def __next__(self):
+        if self.current_index >= len(self.chunks):
+            raise StopIteration
+
+        chunk = self.chunks[self.current_index]
+        self.current_index += 1
+        return chunk

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/experimental_pass_through/messages/handler.py

@@ -0,0 +1,362 @@
+"""
+- call /messages on Anthropic API
+- Make streaming + non-streaming request - just pass it through direct to Anthropic. No need to do anything special here
+- Ensure requests are logged in the DB - stream + non-stream
+
+"""
+
+import asyncio
+import contextvars
+from functools import partial
+from typing import Any, AsyncIterator, Coroutine, Dict, List, Optional, Union
+
+import litellm
+from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
+from litellm.llms.base_llm.anthropic_messages.transformation import (
+    BaseAnthropicMessagesConfig,
+)
+from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler
+from litellm.llms.custom_httpx.llm_http_handler import BaseLLMHTTPHandler
+from litellm.types.llms.anthropic_messages.anthropic_request import AnthropicMetadata
+from litellm.types.llms.anthropic_messages.anthropic_response import (
+    AnthropicMessagesResponse,
+)
+from litellm.types.router import GenericLiteLLMParams
+from litellm.utils import ProviderConfigManager, client
+
+from ..adapters.handler import LiteLLMMessagesToCompletionTransformationHandler
+from ..responses_adapters.handler import LiteLLMMessagesToResponsesAPIHandler
+from .utils import AnthropicMessagesRequestUtils, mock_response
+
+# Providers that are routed directly to the OpenAI Responses API instead of
+# going through chat/completions.
+_RESPONSES_API_PROVIDERS = frozenset({"openai"})
+
+
+def _should_route_to_responses_api(custom_llm_provider: Optional[str]) -> bool:
+    """Return True when the provider should use the Responses API path.
+
+    Set ``litellm.use_chat_completions_url_for_anthropic_messages = True`` to
+    opt out and route OpenAI/Azure requests through chat/completions instead.
+    """
+    if litellm.use_chat_completions_url_for_anthropic_messages:
+        return False
+    return custom_llm_provider in _RESPONSES_API_PROVIDERS
+
+
+####### ENVIRONMENT VARIABLES ###################
+# Initialize any necessary instances or variables here
+base_llm_http_handler = BaseLLMHTTPHandler()
+#################################################
+
+
+async def _execute_pre_request_hooks(
+    model: str,
+    messages: List[Dict],
+    tools: Optional[List[Dict]],
+    stream: Optional[bool],
+    custom_llm_provider: Optional[str],
+    **kwargs,
+) -> Dict:
+    """
+    Execute pre-request hooks from CustomLogger callbacks.
+
+    Allows CustomLoggers to modify request parameters before the API call.
+    Used for WebSearch tool conversion, stream modification, etc.
+
+    Args:
+        model: Model name
+        messages: List of messages
+        tools: Optional tools list
+        stream: Optional stream flag
+        custom_llm_provider: Provider name (if not set, will be extracted from model)
+        **kwargs: Additional request parameters
+
+    Returns:
+        Dict containing all (potentially modified) request parameters including tools, stream
+    """
+    # If custom_llm_provider not provided, extract from model
+    if not custom_llm_provider:
+        try:
+            _, custom_llm_provider, _, _ = litellm.get_llm_provider(model=model)
+        except Exception:
+            # If extraction fails, continue without provider
+            pass
+
+    # Build complete request kwargs dict
+    request_kwargs = {
+        "tools": tools,
+        "stream": stream,
+        "litellm_params": {
+            "custom_llm_provider": custom_llm_provider,
+        },
+        **kwargs,
+    }
+
+    if not litellm.callbacks:
+        return request_kwargs
+
+    from litellm.integrations.custom_logger import CustomLogger as _CustomLogger
+
+    for callback in litellm.callbacks:
+        if not isinstance(callback, _CustomLogger):
+            continue
+
+        # Call the pre-request hook
+        modified_kwargs = await callback.async_pre_request_hook(
+            model, messages, request_kwargs
+        )
+
+        # If hook returned modified kwargs, use them
+        if modified_kwargs is not None:
+            request_kwargs = modified_kwargs
+
+    return request_kwargs
+
+
+@client
+async def anthropic_messages(
+    max_tokens: int,
+    messages: List[Dict],
+    model: str,
+    metadata: Optional[Dict] = None,
+    stop_sequences: Optional[List[str]] = None,
+    stream: Optional[bool] = False,
+    system: Optional[str] = None,
+    temperature: Optional[float] = None,
+    thinking: Optional[Dict] = None,
+    tool_choice: Optional[Dict] = None,
+    tools: Optional[List[Dict]] = None,
+    top_k: Optional[int] = None,
+    top_p: Optional[float] = None,
+    api_key: Optional[str] = None,
+    api_base: Optional[str] = None,
+    client: Optional[AsyncHTTPHandler] = None,
+    custom_llm_provider: Optional[str] = None,
+    **kwargs,
+) -> Union[AnthropicMessagesResponse, AsyncIterator]:
+    """
+    Async: Make llm api request in Anthropic /messages API spec
+    """
+    # Execute pre-request hooks to allow CustomLoggers to modify request
+    request_kwargs = await _execute_pre_request_hooks(
+        model=model,
+        messages=messages,
+        tools=tools,
+        stream=stream,
+        custom_llm_provider=custom_llm_provider,
+        **kwargs,
+    )
+
+    # Extract modified parameters
+    tools = request_kwargs.pop("tools", tools)
+    stream = request_kwargs.pop("stream", stream)
+    # Remove litellm_params from kwargs (only needed for hooks)
+    request_kwargs.pop("litellm_params", None)
+    # Merge back any other modifications
+    kwargs.update(request_kwargs)
+
+    loop = asyncio.get_event_loop()
+    kwargs["is_async"] = True
+
+    func = partial(
+        anthropic_messages_handler,
+        max_tokens=max_tokens,
+        messages=messages,
+        model=model,
+        metadata=metadata,
+        stop_sequences=stop_sequences,
+        stream=stream,
+        system=system,
+        temperature=temperature,
+        thinking=thinking,
+        tool_choice=tool_choice,
+        tools=tools,
+        top_k=top_k,
+        top_p=top_p,
+        api_key=api_key,
+        api_base=api_base,
+        client=client,
+        custom_llm_provider=custom_llm_provider,
+        **kwargs,
+    )
+    ctx = contextvars.copy_context()
+    func_with_context = partial(ctx.run, func)
+    init_response = await loop.run_in_executor(None, func_with_context)
+
+    if asyncio.iscoroutine(init_response):
+        response = await init_response
+    else:
+        response = init_response
+    return response
+
+
+def validate_anthropic_api_metadata(metadata: Optional[Dict] = None) -> Optional[Dict]:
+    """
+    Validate Anthropic API metadata - This is done to ensure only allowed `metadata` fields are passed to Anthropic API
+
+    If there are any litellm specific metadata fields, use `litellm_metadata` key to pass them.
+    """
+    if metadata is None:
+        return None
+    anthropic_metadata_obj = AnthropicMetadata(**metadata)
+    return anthropic_metadata_obj.model_dump(exclude_none=True)
+
+
+def anthropic_messages_handler(
+    max_tokens: int,
+    messages: List[Dict],
+    model: str,
+    metadata: Optional[Dict] = None,
+    stop_sequences: Optional[List[str]] = None,
+    stream: Optional[bool] = False,
+    system: Optional[str] = None,
+    temperature: Optional[float] = None,
+    thinking: Optional[Dict] = None,
+    tool_choice: Optional[Dict] = None,
+    tools: Optional[List[Dict]] = None,
+    top_k: Optional[int] = None,
+    top_p: Optional[float] = None,
+    container: Optional[Dict] = None,
+    api_key: Optional[str] = None,
+    api_base: Optional[str] = None,
+    client: Optional[AsyncHTTPHandler] = None,
+    custom_llm_provider: Optional[str] = None,
+    **kwargs,
+) -> Union[
+    AnthropicMessagesResponse,
+    AsyncIterator[Any],
+    Coroutine[Any, Any, Union[AnthropicMessagesResponse, AsyncIterator[Any]]],
+]:
+    """
+    Makes Anthropic `/v1/messages` API calls In the Anthropic API Spec
+
+    Args:
+        container: Container config with skills for code execution
+    """
+    from litellm.types.utils import LlmProviders
+
+    metadata = validate_anthropic_api_metadata(metadata)
+
+    local_vars = locals()
+    is_async = kwargs.pop("is_async", False)
+    # Use provided client or create a new one
+    litellm_logging_obj: LiteLLMLoggingObj = kwargs.get("litellm_logging_obj")  # type: ignore
+
+    # Store original model name before get_llm_provider strips the provider prefix
+    # This is needed by agentic hooks (e.g., websearch_interception) to make follow-up requests
+    original_model = model
+
+    litellm_params = GenericLiteLLMParams(
+        **kwargs,
+        api_key=api_key,
+        api_base=api_base,
+        custom_llm_provider=custom_llm_provider,
+    )
+    (
+        model,
+        custom_llm_provider,
+        dynamic_api_key,
+        dynamic_api_base,
+    ) = litellm.get_llm_provider(
+        model=model,
+        custom_llm_provider=custom_llm_provider,
+        api_base=litellm_params.api_base,
+        api_key=litellm_params.api_key,
+    )
+
+    # Store agentic loop params in logging object for agentic hooks
+    # This provides original request context needed for follow-up calls
+    if litellm_logging_obj is not None:
+        litellm_logging_obj.model_call_details["agentic_loop_params"] = {
+            "model": original_model,
+            "custom_llm_provider": custom_llm_provider,
+        }
+
+        # Check if stream was converted for WebSearch interception
+        # This is set in the async wrapper above when stream=True is converted to stream=False
+        if kwargs.get("_websearch_interception_converted_stream", False):
+            litellm_logging_obj.model_call_details[
+                "websearch_interception_converted_stream"
+            ] = True
+
+    if litellm_params.mock_response and isinstance(litellm_params.mock_response, str):
+        return mock_response(
+            model=model,
+            messages=messages,
+            max_tokens=max_tokens,
+            mock_response=litellm_params.mock_response,
+        )
+
+    anthropic_messages_provider_config: Optional[BaseAnthropicMessagesConfig] = None
+
+    if custom_llm_provider is not None and custom_llm_provider in [
+        provider.value for provider in LlmProviders
+    ]:
+        anthropic_messages_provider_config = (
+            ProviderConfigManager.get_provider_anthropic_messages_config(
+                model=model,
+                provider=litellm.LlmProviders(custom_llm_provider),
+            )
+        )
+    if anthropic_messages_provider_config is None:
+        # Route to Responses API for OpenAI / Azure, chat/completions for everything else.
+        _shared_kwargs = dict(
+            max_tokens=max_tokens,
+            messages=messages,
+            model=model,
+            metadata=metadata,
+            stop_sequences=stop_sequences,
+            stream=stream,
+            system=system,
+            temperature=temperature,
+            thinking=thinking,
+            tool_choice=tool_choice,
+            tools=tools,
+            top_k=top_k,
+            top_p=top_p,
+            _is_async=is_async,
+            api_key=api_key,
+            api_base=api_base,
+            client=client,
+            custom_llm_provider=custom_llm_provider,
+            **kwargs,
+        )
+        if _should_route_to_responses_api(custom_llm_provider):
+            return LiteLLMMessagesToResponsesAPIHandler.anthropic_messages_handler(
+                **_shared_kwargs
+            )
+        return (
+            LiteLLMMessagesToCompletionTransformationHandler.anthropic_messages_handler(
+                **_shared_kwargs
+            )
+        )
+
+    if custom_llm_provider is None:
+        raise ValueError(
+            f"custom_llm_provider is required for Anthropic messages, passed in model={model}, custom_llm_provider={custom_llm_provider}"
+        )
+
+    local_vars.update(kwargs)
+    anthropic_messages_optional_request_params = (
+        AnthropicMessagesRequestUtils.get_requested_anthropic_messages_optional_param(
+            params=local_vars
+        )
+    )
+    return base_llm_http_handler.anthropic_messages_handler(
+        model=model,
+        messages=messages,
+        anthropic_messages_provider_config=anthropic_messages_provider_config,
+        anthropic_messages_optional_request_params=dict(
+            anthropic_messages_optional_request_params
+        ),
+        _is_async=is_async,
+        client=client,
+        custom_llm_provider=custom_llm_provider,
+        litellm_params=litellm_params,
+        logging_obj=litellm_logging_obj,
+        api_key=api_key,
+        api_base=api_base,
+        stream=stream,
+        kwargs=kwargs,
+    )

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/experimental_pass_through/messages/streaming_iterator.py

@@ -0,0 +1,108 @@
+import asyncio
+import json
+from datetime import datetime
+from typing import Any, AsyncIterator, List, Union
+
+from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
+from litellm.proxy.pass_through_endpoints.success_handler import (
+    PassThroughEndpointLogging,
+)
+from litellm.types.passthrough_endpoints.pass_through_endpoints import EndpointType
+from litellm.types.utils import GenericStreamingChunk, ModelResponseStream
+
+GLOBAL_PASS_THROUGH_SUCCESS_HANDLER_OBJ = PassThroughEndpointLogging()
+
+
+class BaseAnthropicMessagesStreamingIterator:
+    """
+    Base class for Anthropic Messages streaming iterators that provides common logic
+    for streaming response handling and logging.
+    """
+
+    def __init__(
+        self,
+        litellm_logging_obj: LiteLLMLoggingObj,
+        request_body: dict,
+    ):
+        self.litellm_logging_obj = litellm_logging_obj
+        self.request_body = request_body
+        self.start_time = datetime.now()
+
+    async def _handle_streaming_logging(self, collected_chunks: List[bytes]):
+        """Handle the logging after all chunks have been collected."""
+        from litellm.proxy.pass_through_endpoints.streaming_handler import (
+            PassThroughStreamingHandler,
+        )
+
+        end_time = datetime.now()
+        asyncio.create_task(
+            PassThroughStreamingHandler._route_streaming_logging_to_handler(
+                litellm_logging_obj=self.litellm_logging_obj,
+                passthrough_success_handler_obj=GLOBAL_PASS_THROUGH_SUCCESS_HANDLER_OBJ,
+                url_route="/v1/messages",
+                request_body=self.request_body or {},
+                endpoint_type=EndpointType.ANTHROPIC,
+                start_time=self.start_time,
+                raw_bytes=collected_chunks,
+                end_time=end_time,
+            )
+        )
+
+    def get_async_streaming_response_iterator(
+        self,
+        httpx_response,
+        request_body: dict,
+        litellm_logging_obj: LiteLLMLoggingObj,
+    ) -> AsyncIterator:
+        """Helper function to handle Anthropic streaming responses using the existing logging handlers"""
+        from litellm.proxy.pass_through_endpoints.streaming_handler import (
+            PassThroughStreamingHandler,
+        )
+
+        # Use the existing streaming handler for Anthropic
+        return PassThroughStreamingHandler.chunk_processor(
+            response=httpx_response,
+            request_body=request_body,
+            litellm_logging_obj=litellm_logging_obj,
+            endpoint_type=EndpointType.ANTHROPIC,
+            start_time=self.start_time,
+            passthrough_success_handler_obj=GLOBAL_PASS_THROUGH_SUCCESS_HANDLER_OBJ,
+            url_route="/v1/messages",
+        )
+
+    def _convert_chunk_to_sse_format(self, chunk: Union[dict, Any]) -> bytes:
+        """
+        Convert a chunk to Server-Sent Events format.
+
+        This method should be overridden by subclasses if they need custom
+        chunk formatting logic.
+        """
+        if isinstance(chunk, dict):
+            event_type: str = str(chunk.get("type", "message"))
+            payload = f"event: {event_type}\n" f"data: {json.dumps(chunk)}\n\n"
+            return payload.encode()
+        else:
+            # For non-dict chunks, return as is
+            return chunk
+
+    async def async_sse_wrapper(
+        self,
+        completion_stream: AsyncIterator[
+            Union[bytes, GenericStreamingChunk, ModelResponseStream, dict]
+        ],
+    ) -> AsyncIterator[bytes]:
+        """
+        Generic async SSE wrapper that converts streaming chunks to SSE format
+        and handles logging.
+
+        This method provides the common logic for both Anthropic and Bedrock implementations.
+        """
+        collected_chunks = []
+
+        async for chunk in completion_stream:
+            encoded_chunk = self._convert_chunk_to_sse_format(chunk)
+            collected_chunks.append(encoded_chunk)
+            yield encoded_chunk
+
+        # Handle logging after all chunks are processed
+        await self._handle_streaming_logging(collected_chunks)

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/experimental_pass_through/messages/transformation.py

@@ -0,0 +1,308 @@
+from typing import Any, AsyncIterator, Dict, List, Optional, Tuple
+
+import httpx
+
+from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
+from litellm.litellm_core_utils.litellm_logging import verbose_logger
+from litellm.llms.base_llm.anthropic_messages.transformation import (
+    BaseAnthropicMessagesConfig,
+)
+from litellm.types.llms.anthropic import (
+    ANTHROPIC_BETA_HEADER_VALUES,
+    AnthropicMessagesRequest,
+)
+from litellm.types.llms.anthropic_messages.anthropic_response import (
+    AnthropicMessagesResponse,
+)
+from litellm.types.llms.anthropic_tool_search import get_tool_search_beta_header
+from litellm.types.router import GenericLiteLLMParams
+
+from ...common_utils import (
+    AnthropicError,
+    AnthropicModelInfo,
+    optionally_handle_anthropic_oauth,
+)
+
+DEFAULT_ANTHROPIC_API_BASE = "https://api.anthropic.com"
+DEFAULT_ANTHROPIC_API_VERSION = "2023-06-01"
+
+
+class AnthropicMessagesConfig(BaseAnthropicMessagesConfig):
+    def get_supported_anthropic_messages_params(self, model: str) -> list:
+        return [
+            "messages",
+            "model",
+            "system",
+            "max_tokens",
+            "stop_sequences",
+            "temperature",
+            "top_p",
+            "top_k",
+            "tools",
+            "tool_choice",
+            "thinking",
+            "context_management",
+            "output_format",
+            "inference_geo",
+            "speed",
+            "output_config",
+            # TODO: Add Anthropic `metadata` support
+            # "metadata",
+        ]
+
+    @staticmethod
+    def _filter_billing_headers_from_system(system_param):
+        """
+        Filter out x-anthropic-billing-header metadata from system parameter.
+
+        Args:
+            system_param: Can be a string or a list of system message content blocks
+
+        Returns:
+            Filtered system parameter (string or list), or None if all content was filtered
+        """
+        if isinstance(system_param, str):
+            # If it's a string and starts with billing header, filter it out
+            if system_param.startswith("x-anthropic-billing-header:"):
+                return None
+            return system_param
+        elif isinstance(system_param, list):
+            # Filter list of system content blocks
+            filtered_list = []
+            for content_block in system_param:
+                if isinstance(content_block, dict):
+                    text = content_block.get("text", "")
+                    content_type = content_block.get("type", "")
+                    # Skip text blocks that start with billing header
+                    if content_type == "text" and text.startswith(
+                        "x-anthropic-billing-header:"
+                    ):
+                        continue
+                    filtered_list.append(content_block)
+                else:
+                    # Keep non-dict items as-is
+                    filtered_list.append(content_block)
+            return filtered_list if len(filtered_list) > 0 else None
+        else:
+            return system_param
+
+    def get_complete_url(
+        self,
+        api_base: Optional[str],
+        api_key: Optional[str],
+        model: str,
+        optional_params: dict,
+        litellm_params: dict,
+        stream: Optional[bool] = None,
+    ) -> str:
+        api_base = api_base or DEFAULT_ANTHROPIC_API_BASE
+        if not api_base.endswith("/v1/messages"):
+            api_base = f"{api_base}/v1/messages"
+        return api_base
+
+    def validate_anthropic_messages_environment(
+        self,
+        headers: dict,
+        model: str,
+        messages: List[Any],
+        optional_params: dict,
+        litellm_params: dict,
+        api_key: Optional[str] = None,
+        api_base: Optional[str] = None,
+    ) -> Tuple[dict, Optional[str]]:
+        import os
+
+        # Check for Anthropic OAuth token in Authorization header
+        headers, api_key = optionally_handle_anthropic_oauth(
+            headers=headers, api_key=api_key
+        )
+        if api_key is None:
+            api_key = os.getenv("ANTHROPIC_API_KEY")
+
+        if "x-api-key" not in headers and "authorization" not in headers and api_key:
+            headers["x-api-key"] = api_key
+        if "anthropic-version" not in headers:
+            headers["anthropic-version"] = DEFAULT_ANTHROPIC_API_VERSION
+        if "content-type" not in headers:
+            headers["content-type"] = "application/json"
+
+        headers = self._update_headers_with_anthropic_beta(
+            headers=headers,
+            optional_params=optional_params,
+        )
+
+        return headers, api_base
+
+    def transform_anthropic_messages_request(
+        self,
+        model: str,
+        messages: List[Dict],
+        anthropic_messages_optional_request_params: Dict,
+        litellm_params: GenericLiteLLMParams,
+        headers: dict,
+    ) -> Dict:
+        """
+        No transformation is needed for Anthropic messages
+
+
+        This takes in a request in the Anthropic /v1/messages API spec -> transforms it to /v1/messages API spec (i.e) no transformation is needed
+        """
+        max_tokens = anthropic_messages_optional_request_params.pop("max_tokens", None)
+        if max_tokens is None:
+            raise AnthropicError(
+                message="max_tokens is required for Anthropic /v1/messages API",
+                status_code=400,
+            )
+
+        # Filter out x-anthropic-billing-header from system messages
+        system_param = anthropic_messages_optional_request_params.get("system")
+        if system_param is not None:
+            filtered_system = self._filter_billing_headers_from_system(system_param)
+            if filtered_system is not None and len(filtered_system) > 0:
+                anthropic_messages_optional_request_params["system"] = filtered_system
+            else:
+                # Remove system parameter if all content was filtered out
+                anthropic_messages_optional_request_params.pop("system", None)
+
+        # Transform context_management from OpenAI format to Anthropic format if needed
+        context_management_param = anthropic_messages_optional_request_params.get(
+            "context_management"
+        )
+        if context_management_param is not None:
+            from litellm.llms.anthropic.chat.transformation import AnthropicConfig
+
+            transformed_context_management = (
+                AnthropicConfig.map_openai_context_management_to_anthropic(
+                    context_management_param
+                )
+            )
+            if transformed_context_management is not None:
+                anthropic_messages_optional_request_params[
+                    "context_management"
+                ] = transformed_context_management
+
+        ####### get required params for all anthropic messages requests ######
+        verbose_logger.debug(f"TRANSFORMATION DEBUG - Messages: {messages}")
+        anthropic_messages_request: AnthropicMessagesRequest = AnthropicMessagesRequest(
+            messages=messages,
+            max_tokens=max_tokens,
+            model=model,
+            **anthropic_messages_optional_request_params,
+        )
+        return dict(anthropic_messages_request)
+
+    def transform_anthropic_messages_response(
+        self,
+        model: str,
+        raw_response: httpx.Response,
+        logging_obj: LiteLLMLoggingObj,
+    ) -> AnthropicMessagesResponse:
+        """
+        No transformation is needed for Anthropic messages, since we want the response in the Anthropic /v1/messages API spec
+        """
+        try:
+            raw_response_json = raw_response.json()
+        except Exception:
+            raise AnthropicError(
+                message=raw_response.text, status_code=raw_response.status_code
+            )
+        return AnthropicMessagesResponse(**raw_response_json)
+
+    def get_async_streaming_response_iterator(
+        self,
+        model: str,
+        httpx_response: httpx.Response,
+        request_body: dict,
+        litellm_logging_obj: LiteLLMLoggingObj,
+    ) -> AsyncIterator:
+        """Helper function to handle Anthropic streaming responses using the existing logging handlers"""
+        from litellm.llms.anthropic.experimental_pass_through.messages.streaming_iterator import (
+            BaseAnthropicMessagesStreamingIterator,
+        )
+
+        # Use the shared streaming handler for Anthropic
+        handler = BaseAnthropicMessagesStreamingIterator(
+            litellm_logging_obj=litellm_logging_obj,
+            request_body=request_body,
+        )
+        return handler.get_async_streaming_response_iterator(
+            httpx_response=httpx_response,
+            request_body=request_body,
+            litellm_logging_obj=litellm_logging_obj,
+        )
+
+    @staticmethod
+    def _update_headers_with_anthropic_beta(
+        headers: dict,
+        optional_params: dict,
+        custom_llm_provider: str = "anthropic",
+    ) -> dict:
+        """
+        Auto-inject anthropic-beta headers based on features used.
+
+        Handles:
+        - context_management: adds 'context-management-2025-06-27'
+        - tool_search: adds provider-specific tool search header
+        - output_format: adds 'structured-outputs-2025-11-13'
+        - speed: adds 'fast-mode-2026-02-01'
+
+        Args:
+            headers: Request headers dict
+            optional_params: Optional parameters including tools, context_management, output_format, speed
+            custom_llm_provider: Provider name for looking up correct tool search header
+        """
+        beta_values: set = set()
+
+        # Get existing beta headers if any
+        existing_beta = headers.get("anthropic-beta")
+        if existing_beta:
+            beta_values.update(b.strip() for b in existing_beta.split(","))
+
+        # Check for context management
+        context_management_param = optional_params.get("context_management")
+        if context_management_param is not None:
+            # Check edits array for compact_20260112 type
+            edits = context_management_param.get("edits", [])
+            has_compact = False
+            has_other = False
+
+            for edit in edits:
+                edit_type = edit.get("type", "")
+                if edit_type == "compact_20260112":
+                    has_compact = True
+                else:
+                    has_other = True
+
+            # Add compact header if any compact edits exist
+            if has_compact:
+                beta_values.add(ANTHROPIC_BETA_HEADER_VALUES.COMPACT_2026_01_12.value)
+
+            # Add context management header if any other edits exist
+            if has_other:
+                beta_values.add(
+                    ANTHROPIC_BETA_HEADER_VALUES.CONTEXT_MANAGEMENT_2025_06_27.value
+                )
+
+        # Check for structured outputs
+        if optional_params.get("output_format") is not None:
+            beta_values.add(
+                ANTHROPIC_BETA_HEADER_VALUES.STRUCTURED_OUTPUT_2025_09_25.value
+            )
+
+        # Check for fast mode
+        if optional_params.get("speed") == "fast":
+            beta_values.add(ANTHROPIC_BETA_HEADER_VALUES.FAST_MODE_2026_02_01.value)
+
+        # Check for tool search tools
+        tools = optional_params.get("tools")
+        if tools:
+            anthropic_model_info = AnthropicModelInfo()
+            if anthropic_model_info.is_tool_search_used(tools):
+                # Use provider-specific tool search header
+                tool_search_header = get_tool_search_beta_header(custom_llm_provider)
+                beta_values.add(tool_search_header)
+
+        if beta_values:
+            headers["anthropic-beta"] = ",".join(sorted(beta_values))
+
+        return headers

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/experimental_pass_through/messages/utils.py

@@ -0,0 +1,75 @@
+from typing import Any, Dict, List, cast, get_type_hints
+
+from litellm.types.llms.anthropic import AnthropicMessagesRequestOptionalParams
+from litellm.types.llms.anthropic_messages.anthropic_response import (
+    AnthropicMessagesResponse,
+)
+
+
+class AnthropicMessagesRequestUtils:
+    @staticmethod
+    def get_requested_anthropic_messages_optional_param(
+        params: Dict[str, Any],
+    ) -> AnthropicMessagesRequestOptionalParams:
+        """
+        Filter parameters to only include those defined in AnthropicMessagesRequestOptionalParams.
+
+        Args:
+            params: Dictionary of parameters to filter
+
+        Returns:
+            AnthropicMessagesRequestOptionalParams instance with only the valid parameters
+        """
+        valid_keys = get_type_hints(AnthropicMessagesRequestOptionalParams).keys()
+        filtered_params = {
+            k: v for k, v in params.items() if k in valid_keys and v is not None
+        }
+        return cast(AnthropicMessagesRequestOptionalParams, filtered_params)
+
+
+def mock_response(
+    model: str,
+    messages: List[Dict],
+    max_tokens: int,
+    mock_response: str = "Hi! My name is Claude.",
+    **kwargs,
+) -> AnthropicMessagesResponse:
+    """
+    Mock response for Anthropic messages
+    """
+    from litellm.exceptions import (
+        ContextWindowExceededError,
+        InternalServerError,
+        RateLimitError,
+    )
+
+    if mock_response == "litellm.InternalServerError":
+        raise InternalServerError(
+            message="this is a mock internal server error",
+            llm_provider="anthropic",
+            model=model,
+        )
+    elif mock_response == "litellm.ContextWindowExceededError":
+        raise ContextWindowExceededError(
+            message="this is a mock context window exceeded error",
+            llm_provider="anthropic",
+            model=model,
+        )
+    elif mock_response == "litellm.RateLimitError":
+        raise RateLimitError(
+            message="this is a mock rate limit error",
+            llm_provider="anthropic",
+            model=model,
+        )
+    return AnthropicMessagesResponse(
+        **{
+            "content": [{"text": mock_response, "type": "text"}],
+            "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF",
+            "model": "claude-sonnet-4-20250514",
+            "role": "assistant",
+            "stop_reason": "end_turn",
+            "stop_sequence": None,
+            "type": "message",
+            "usage": {"input_tokens": 2095, "output_tokens": 503},
+        }
+    )

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/experimental_pass_through/responses_adapters/__init__.py

@@ -0,0 +1,3 @@
+from .transformation import LiteLLMAnthropicToResponsesAPIAdapter
+
+__all__ = ["LiteLLMAnthropicToResponsesAPIAdapter"]

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/experimental_pass_through/responses_adapters/handler.py

@@ -0,0 +1,239 @@
+"""
+Handler for the Anthropic v1/messages -> OpenAI Responses API path.
+
+Used when the target model is an OpenAI or Azure model.
+"""
+
+from typing import Any, AsyncIterator, Coroutine, Dict, List, Optional, Union
+
+import litellm
+from litellm.types.llms.anthropic import AnthropicMessagesRequest
+from litellm.types.llms.anthropic_messages.anthropic_response import (
+    AnthropicMessagesResponse,
+)
+from litellm.types.llms.openai import ResponsesAPIResponse
+
+from .streaming_iterator import AnthropicResponsesStreamWrapper
+from .transformation import LiteLLMAnthropicToResponsesAPIAdapter
+
+_ADAPTER = LiteLLMAnthropicToResponsesAPIAdapter()
+
+
+def _build_responses_kwargs(
+    *,
+    max_tokens: int,
+    messages: List[Dict],
+    model: str,
+    context_management: Optional[Dict] = None,
+    metadata: Optional[Dict] = None,
+    output_config: Optional[Dict] = None,
+    stop_sequences: Optional[List[str]] = None,
+    stream: Optional[bool] = False,
+    system: Optional[str] = None,
+    temperature: Optional[float] = None,
+    thinking: Optional[Dict] = None,
+    tool_choice: Optional[Dict] = None,
+    tools: Optional[List[Dict]] = None,
+    top_k: Optional[int] = None,
+    top_p: Optional[float] = None,
+    output_format: Optional[Dict] = None,
+    extra_kwargs: Optional[Dict[str, Any]] = None,
+) -> Dict[str, Any]:
+    """
+    Build the kwargs dict to pass directly to litellm.responses() / litellm.aresponses().
+    """
+    # Build a typed AnthropicMessagesRequest for the adapter
+    request_data: Dict[str, Any] = {
+        "model": model,
+        "messages": messages,
+        "max_tokens": max_tokens,
+    }
+    if context_management:
+        request_data["context_management"] = context_management
+    if output_config:
+        request_data["output_config"] = output_config
+    if metadata:
+        request_data["metadata"] = metadata
+    if system:
+        request_data["system"] = system
+    if temperature is not None:
+        request_data["temperature"] = temperature
+    if thinking:
+        request_data["thinking"] = thinking
+    if tool_choice:
+        request_data["tool_choice"] = tool_choice
+    if tools:
+        request_data["tools"] = tools
+    if top_p is not None:
+        request_data["top_p"] = top_p
+    if output_format:
+        request_data["output_format"] = output_format
+
+    anthropic_request = AnthropicMessagesRequest(**request_data)  # type: ignore[typeddict-item]
+    responses_kwargs = _ADAPTER.translate_request(anthropic_request)
+
+    if stream:
+        responses_kwargs["stream"] = True
+
+    # Forward litellm-specific kwargs (api_key, api_base, logging obj, etc.)
+    excluded = {"anthropic_messages"}
+    for key, value in (extra_kwargs or {}).items():
+        if key == "litellm_logging_obj" and value is not None:
+            from litellm.litellm_core_utils.litellm_logging import (
+                Logging as LiteLLMLoggingObject,
+            )
+            from litellm.types.utils import CallTypes
+
+            if isinstance(value, LiteLLMLoggingObject):
+                # Reclassify as acompletion so the success handler doesn't try to
+                # validate the Responses API event as an AnthropicResponse.
+                # (Mirrors the pattern used in LiteLLMMessagesToCompletionTransformationHandler.)
+                setattr(value, "call_type", CallTypes.acompletion.value)
+            responses_kwargs[key] = value
+        elif key not in excluded and key not in responses_kwargs and value is not None:
+            responses_kwargs[key] = value
+
+    return responses_kwargs
+
+
+class LiteLLMMessagesToResponsesAPIHandler:
+    """
+    Handles Anthropic /v1/messages requests for OpenAI / Azure models by
+    calling litellm.responses() / litellm.aresponses() directly and translating
+    the response back to Anthropic format.
+    """
+
+    @staticmethod
+    async def async_anthropic_messages_handler(
+        max_tokens: int,
+        messages: List[Dict],
+        model: str,
+        context_management: Optional[Dict] = None,
+        metadata: Optional[Dict] = None,
+        output_config: Optional[Dict] = None,
+        stop_sequences: Optional[List[str]] = None,
+        stream: Optional[bool] = False,
+        system: Optional[str] = None,
+        temperature: Optional[float] = None,
+        thinking: Optional[Dict] = None,
+        tool_choice: Optional[Dict] = None,
+        tools: Optional[List[Dict]] = None,
+        top_k: Optional[int] = None,
+        top_p: Optional[float] = None,
+        output_format: Optional[Dict] = None,
+        **kwargs,
+    ) -> Union[AnthropicMessagesResponse, AsyncIterator]:
+        responses_kwargs = _build_responses_kwargs(
+            max_tokens=max_tokens,
+            messages=messages,
+            model=model,
+            context_management=context_management,
+            metadata=metadata,
+            output_config=output_config,
+            stop_sequences=stop_sequences,
+            stream=stream,
+            system=system,
+            temperature=temperature,
+            thinking=thinking,
+            tool_choice=tool_choice,
+            tools=tools,
+            top_k=top_k,
+            top_p=top_p,
+            output_format=output_format,
+            extra_kwargs=kwargs,
+        )
+
+        result = await litellm.aresponses(**responses_kwargs)
+
+        if stream:
+            wrapper = AnthropicResponsesStreamWrapper(
+                responses_stream=result, model=model
+            )
+            return wrapper.async_anthropic_sse_wrapper()
+
+        if not isinstance(result, ResponsesAPIResponse):
+            raise ValueError(f"Expected ResponsesAPIResponse, got {type(result)}")
+
+        return _ADAPTER.translate_response(result)
+
+    @staticmethod
+    def anthropic_messages_handler(
+        max_tokens: int,
+        messages: List[Dict],
+        model: str,
+        context_management: Optional[Dict] = None,
+        metadata: Optional[Dict] = None,
+        output_config: Optional[Dict] = None,
+        stop_sequences: Optional[List[str]] = None,
+        stream: Optional[bool] = False,
+        system: Optional[str] = None,
+        temperature: Optional[float] = None,
+        thinking: Optional[Dict] = None,
+        tool_choice: Optional[Dict] = None,
+        tools: Optional[List[Dict]] = None,
+        top_k: Optional[int] = None,
+        top_p: Optional[float] = None,
+        output_format: Optional[Dict] = None,
+        _is_async: bool = False,
+        **kwargs,
+    ) -> Union[
+        AnthropicMessagesResponse,
+        AsyncIterator[Any],
+        Coroutine[Any, Any, Union[AnthropicMessagesResponse, AsyncIterator[Any]]],
+    ]:
+        if _is_async:
+            return (
+                LiteLLMMessagesToResponsesAPIHandler.async_anthropic_messages_handler(
+                    max_tokens=max_tokens,
+                    messages=messages,
+                    model=model,
+                    context_management=context_management,
+                    metadata=metadata,
+                    output_config=output_config,
+                    stop_sequences=stop_sequences,
+                    stream=stream,
+                    system=system,
+                    temperature=temperature,
+                    thinking=thinking,
+                    tool_choice=tool_choice,
+                    tools=tools,
+                    top_k=top_k,
+                    top_p=top_p,
+                    output_format=output_format,
+                    **kwargs,
+                )
+            )
+
+        # Sync path
+        responses_kwargs = _build_responses_kwargs(
+            max_tokens=max_tokens,
+            messages=messages,
+            model=model,
+            context_management=context_management,
+            metadata=metadata,
+            output_config=output_config,
+            stop_sequences=stop_sequences,
+            stream=stream,
+            system=system,
+            temperature=temperature,
+            thinking=thinking,
+            tool_choice=tool_choice,
+            tools=tools,
+            top_k=top_k,
+            top_p=top_p,
+            output_format=output_format,
+            extra_kwargs=kwargs,
+        )
+
+        result = litellm.responses(**responses_kwargs)
+
+        if stream:
+            wrapper = AnthropicResponsesStreamWrapper(
+                responses_stream=result, model=model
+            )
+            return wrapper.async_anthropic_sse_wrapper()
+
+        if not isinstance(result, ResponsesAPIResponse):
+            raise ValueError(f"Expected ResponsesAPIResponse, got {type(result)}")
+
+        return _ADAPTER.translate_response(result)

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/experimental_pass_through/responses_adapters/streaming_iterator.py

@@ -0,0 +1,344 @@
+# What is this?
+## Translates OpenAI call to Anthropic `/v1/messages` format
+import json
+import traceback
+from collections import deque
+from typing import Any, AsyncIterator, Dict
+
+from litellm import verbose_logger
+from litellm._uuid import uuid
+
+
+class AnthropicResponsesStreamWrapper:
+    """
+    Wraps a Responses API streaming iterator and re-emits events in Anthropic SSE format.
+
+    Responses API event flow (relevant subset):
+      response.created                   -> message_start
+      response.output_item.added         -> content_block_start (if message/function_call)
+      response.output_text.delta         -> content_block_delta (text_delta)
+      response.reasoning_summary_text.delta -> content_block_delta (thinking_delta)
+      response.function_call_arguments.delta -> content_block_delta (input_json_delta)
+      response.output_item.done          -> content_block_stop
+      response.completed                 -> message_delta + message_stop
+    """
+
+    def __init__(
+        self,
+        responses_stream: Any,
+        model: str,
+    ) -> None:
+        self.responses_stream = responses_stream
+        self.model = model
+        self._message_id: str = f"msg_{uuid.uuid4()}"
+        self._current_block_index: int = -1
+        # Map item_id -> content_block_index so we can stop the right block later
+        self._item_id_to_block_index: Dict[str, int] = {}
+        # Track open function_call items by item_id so we can emit tool_use start
+        self._pending_tool_ids: Dict[
+            str, str
+        ] = {}  # item_id -> call_id / name accumulator
+        self._sent_message_start = False
+        self._sent_message_stop = False
+        self._chunk_queue: deque = deque()
+
+    def _make_message_start(self) -> Dict[str, Any]:
+        return {
+            "type": "message_start",
+            "message": {
+                "id": self._message_id,
+                "type": "message",
+                "role": "assistant",
+                "content": [],
+                "model": self.model,
+                "stop_reason": None,
+                "stop_sequence": None,
+                "usage": {
+                    "input_tokens": 0,
+                    "output_tokens": 0,
+                    "cache_creation_input_tokens": 0,
+                    "cache_read_input_tokens": 0,
+                },
+            },
+        }
+
+    def _next_block_index(self) -> int:
+        self._current_block_index += 1
+        return self._current_block_index
+
+    def _process_event(self, event: Any) -> None:  # noqa: PLR0915
+        """Convert one Responses API event into zero or more Anthropic chunks queued for emission."""
+        event_type = getattr(event, "type", None)
+        if event_type is None and isinstance(event, dict):
+            event_type = event.get("type")
+
+        if event_type is None:
+            return
+
+        # ---- message_start ----
+        if event_type == "response.created":
+            self._sent_message_start = True
+            self._chunk_queue.append(self._make_message_start())
+            return
+
+        # ---- content_block_start for a new output message item ----
+        if event_type == "response.output_item.added":
+            item = getattr(event, "item", None) or (
+                event.get("item") if isinstance(event, dict) else None
+            )
+            if item is None:
+                return
+            item_type = getattr(item, "type", None) or (
+                item.get("type") if isinstance(item, dict) else None
+            )
+            item_id = getattr(item, "id", None) or (
+                item.get("id") if isinstance(item, dict) else None
+            )
+
+            if item_type == "message":
+                block_idx = self._next_block_index()
+                if item_id:
+                    self._item_id_to_block_index[item_id] = block_idx
+                self._chunk_queue.append(
+                    {
+                        "type": "content_block_start",
+                        "index": block_idx,
+                        "content_block": {"type": "text", "text": ""},
+                    }
+                )
+            elif item_type == "function_call":
+                call_id = (
+                    getattr(item, "call_id", None)
+                    or (item.get("call_id") if isinstance(item, dict) else None)
+                    or ""
+                )
+                name = (
+                    getattr(item, "name", None)
+                    or (item.get("name") if isinstance(item, dict) else None)
+                    or ""
+                )
+                block_idx = self._next_block_index()
+                if item_id:
+                    self._item_id_to_block_index[item_id] = block_idx
+                    self._pending_tool_ids[item_id] = call_id
+                self._chunk_queue.append(
+                    {
+                        "type": "content_block_start",
+                        "index": block_idx,
+                        "content_block": {
+                            "type": "tool_use",
+                            "id": call_id,
+                            "name": name,
+                            "input": {},
+                        },
+                    }
+                )
+            elif item_type == "reasoning":
+                block_idx = self._next_block_index()
+                if item_id:
+                    self._item_id_to_block_index[item_id] = block_idx
+                self._chunk_queue.append(
+                    {
+                        "type": "content_block_start",
+                        "index": block_idx,
+                        "content_block": {"type": "thinking", "thinking": ""},
+                    }
+                )
+            return
+
+        # ---- text delta ----
+        if event_type == "response.output_text.delta":
+            item_id = getattr(event, "item_id", None) or (
+                event.get("item_id") if isinstance(event, dict) else None
+            )
+            delta = getattr(event, "delta", "") or (
+                event.get("delta", "") if isinstance(event, dict) else ""
+            )
+            block_idx = (
+                self._item_id_to_block_index.get(item_id, self._current_block_index)
+                if item_id
+                else self._current_block_index
+            )
+            self._chunk_queue.append(
+                {
+                    "type": "content_block_delta",
+                    "index": block_idx,
+                    "delta": {"type": "text_delta", "text": delta},
+                }
+            )
+            return
+
+        # ---- reasoning summary text delta ----
+        if event_type == "response.reasoning_summary_text.delta":
+            item_id = getattr(event, "item_id", None) or (
+                event.get("item_id") if isinstance(event, dict) else None
+            )
+            delta = getattr(event, "delta", "") or (
+                event.get("delta", "") if isinstance(event, dict) else ""
+            )
+            block_idx = (
+                self._item_id_to_block_index.get(item_id, self._current_block_index)
+                if item_id
+                else self._current_block_index
+            )
+            self._chunk_queue.append(
+                {
+                    "type": "content_block_delta",
+                    "index": block_idx,
+                    "delta": {"type": "thinking_delta", "thinking": delta},
+                }
+            )
+            return
+
+        # ---- function call arguments delta ----
+        if event_type == "response.function_call_arguments.delta":
+            item_id = getattr(event, "item_id", None) or (
+                event.get("item_id") if isinstance(event, dict) else None
+            )
+            delta = getattr(event, "delta", "") or (
+                event.get("delta", "") if isinstance(event, dict) else ""
+            )
+            block_idx = (
+                self._item_id_to_block_index.get(item_id, self._current_block_index)
+                if item_id
+                else self._current_block_index
+            )
+            self._chunk_queue.append(
+                {
+                    "type": "content_block_delta",
+                    "index": block_idx,
+                    "delta": {"type": "input_json_delta", "partial_json": delta},
+                }
+            )
+            return
+
+        # ---- output item done -> content_block_stop ----
+        if event_type == "response.output_item.done":
+            item = getattr(event, "item", None) or (
+                event.get("item") if isinstance(event, dict) else None
+            )
+            item_id = (
+                getattr(item, "id", None)
+                or (item.get("id") if isinstance(item, dict) else None)
+                if item
+                else None
+            )
+            block_idx = (
+                self._item_id_to_block_index.get(item_id, self._current_block_index)
+                if item_id
+                else self._current_block_index
+            )
+            self._chunk_queue.append(
+                {
+                    "type": "content_block_stop",
+                    "index": block_idx,
+                }
+            )
+            return
+
+        # ---- response completed -> message_delta + message_stop ----
+        if event_type in (
+            "response.completed",
+            "response.failed",
+            "response.incomplete",
+        ):
+            response_obj = getattr(event, "response", None) or (
+                event.get("response") if isinstance(event, dict) else None
+            )
+            stop_reason = "end_turn"
+            input_tokens = 0
+            output_tokens = 0
+            cache_creation_tokens = 0
+            cache_read_tokens = 0
+
+            if response_obj is not None:
+                status = getattr(response_obj, "status", None)
+                if status == "incomplete":
+                    stop_reason = "max_tokens"
+                usage = getattr(response_obj, "usage", None)
+                if usage is not None:
+                    input_tokens = getattr(usage, "input_tokens", 0) or 0
+                    output_tokens = getattr(usage, "output_tokens", 0) or 0
+                    cache_creation_tokens = getattr(usage, "input_tokens_details", None)  # type: ignore[assignment]
+                    cache_read_tokens = getattr(usage, "output_tokens_details", None)  # type: ignore[assignment]
+                    # Prefer direct cache fields if present
+                    cache_creation_tokens = int(
+                        getattr(usage, "cache_creation_input_tokens", 0) or 0
+                    )
+                    cache_read_tokens = int(
+                        getattr(usage, "cache_read_input_tokens", 0) or 0
+                    )
+
+            # Check if tool_use was in the output to override stop_reason
+            if response_obj is not None:
+                output = getattr(response_obj, "output", []) or []
+                for out_item in output:
+                    out_type = getattr(out_item, "type", None) or (
+                        out_item.get("type") if isinstance(out_item, dict) else None
+                    )
+                    if out_type == "function_call":
+                        stop_reason = "tool_use"
+                        break
+
+            usage_delta: Dict[str, Any] = {
+                "input_tokens": input_tokens,
+                "output_tokens": output_tokens,
+            }
+            if cache_creation_tokens:
+                usage_delta["cache_creation_input_tokens"] = cache_creation_tokens
+            if cache_read_tokens:
+                usage_delta["cache_read_input_tokens"] = cache_read_tokens
+
+            self._chunk_queue.append(
+                {
+                    "type": "message_delta",
+                    "delta": {"stop_reason": stop_reason, "stop_sequence": None},
+                    "usage": usage_delta,
+                }
+            )
+            self._chunk_queue.append({"type": "message_stop"})
+            self._sent_message_stop = True
+            return
+
+    def __aiter__(self) -> "AnthropicResponsesStreamWrapper":
+        return self
+
+    async def __anext__(self) -> Dict[str, Any]:
+        # Return any queued chunks first
+        if self._chunk_queue:
+            return self._chunk_queue.popleft()
+
+        # Emit message_start if not yet done (fallback if response.created wasn't fired)
+        if not self._sent_message_start:
+            self._sent_message_start = True
+            self._chunk_queue.append(self._make_message_start())
+            return self._chunk_queue.popleft()
+
+        # Consume the upstream stream
+        try:
+            async for event in self.responses_stream:
+                self._process_event(event)
+                if self._chunk_queue:
+                    return self._chunk_queue.popleft()
+        except StopAsyncIteration:
+            pass
+        except Exception as e:
+            verbose_logger.error(
+                f"AnthropicResponsesStreamWrapper error: {e}\n{traceback.format_exc()}"
+            )
+
+        # Drain any remaining queued chunks
+        if self._chunk_queue:
+            return self._chunk_queue.popleft()
+
+        raise StopAsyncIteration
+
+    async def async_anthropic_sse_wrapper(self) -> AsyncIterator[bytes]:
+        """Yield SSE-encoded bytes for each Anthropic event chunk."""
+        async for chunk in self:
+            if isinstance(chunk, dict):
+                event_type: str = str(chunk.get("type", "message"))
+                payload = f"event: {event_type}\ndata: {json.dumps(chunk)}\n\n"
+                yield payload.encode()
+            else:
+                yield chunk

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/experimental_pass_through/responses_adapters/transformation.py

@@ -0,0 +1,488 @@
+"""
+Transformation layer: Anthropic /v1/messages <-> OpenAI Responses API.
+
+This module owns all format conversions for the direct v1/messages -> Responses API
+path used for OpenAI and Azure models.
+"""
+
+import json
+from typing import Any, Dict, List, Optional, Union, cast
+
+from litellm.types.llms.anthropic import (
+    AllAnthropicToolsValues,
+    AnthopicMessagesAssistantMessageParam,
+    AnthropicFinishReason,
+    AnthropicMessagesRequest,
+    AnthropicMessagesToolChoice,
+    AnthropicMessagesUserMessageParam,
+    AnthropicResponseContentBlockText,
+    AnthropicResponseContentBlockThinking,
+    AnthropicResponseContentBlockToolUse,
+)
+from litellm.types.llms.anthropic_messages.anthropic_response import (
+    AnthropicMessagesResponse,
+    AnthropicUsage,
+)
+from litellm.types.llms.openai import ResponsesAPIResponse
+
+
+class LiteLLMAnthropicToResponsesAPIAdapter:
+    """
+    Converts Anthropic /v1/messages requests to OpenAI Responses API format and
+    converts Responses API responses back to Anthropic format.
+    """
+
+    # ------------------------------------------------------------------ #
+    # Request translation: Anthropic -> Responses API                     #
+    # ------------------------------------------------------------------ #
+
+    @staticmethod
+    def _translate_anthropic_image_source_to_url(source: dict) -> Optional[str]:
+        """Convert Anthropic image source to a URL string."""
+        source_type = source.get("type")
+        if source_type == "base64":
+            media_type = source.get("media_type", "image/jpeg")
+            data = source.get("data", "")
+            return f"data:{media_type};base64,{data}" if data else None
+        elif source_type == "url":
+            return source.get("url")
+        return None
+
+    def translate_messages_to_responses_input(  # noqa: PLR0915
+        self,
+        messages: List[
+            Union[
+                AnthropicMessagesUserMessageParam,
+                AnthopicMessagesAssistantMessageParam,
+            ]
+        ],
+    ) -> List[Dict[str, Any]]:
+        """
+        Convert Anthropic messages list to Responses API `input` items.
+
+        Mapping:
+          user text          -> message(role=user, input_text)
+          user image         -> message(role=user, input_image)
+          user tool_result   -> function_call_output
+          assistant text     -> message(role=assistant, output_text)
+          assistant tool_use -> function_call
+        """
+        input_items: List[Dict[str, Any]] = []
+
+        for m in messages:
+            role = m["role"]
+            content = m.get("content")
+
+            if role == "user":
+                if isinstance(content, str):
+                    input_items.append(
+                        {
+                            "type": "message",
+                            "role": "user",
+                            "content": [{"type": "input_text", "text": content}],
+                        }
+                    )
+                elif isinstance(content, list):
+                    user_parts: List[Dict[str, Any]] = []
+                    for block in content:
+                        if not isinstance(block, dict):
+                            continue
+                        btype = block.get("type")
+                        if btype == "text":
+                            user_parts.append(
+                                {"type": "input_text", "text": block.get("text", "")}
+                            )
+                        elif btype == "image":
+                            url = self._translate_anthropic_image_source_to_url(
+                                block.get("source", {})
+                            )
+                            if url:
+                                user_parts.append(
+                                    {"type": "input_image", "image_url": url}
+                                )
+                        elif btype == "tool_result":
+                            tool_use_id = block.get("tool_use_id", "")
+                            inner = block.get("content")
+                            if inner is None:
+                                output_text = ""
+                            elif isinstance(inner, str):
+                                output_text = inner
+                            elif isinstance(inner, list):
+                                parts = [
+                                    c.get("text", "")
+                                    for c in inner
+                                    if isinstance(c, dict) and c.get("type") == "text"
+                                ]
+                                output_text = "\n".join(parts)
+                            else:
+                                output_text = str(inner)
+                            # tool_result is a top-level item, not inside the message
+                            input_items.append(
+                                {
+                                    "type": "function_call_output",
+                                    "call_id": tool_use_id,
+                                    "output": output_text,
+                                }
+                            )
+                    if user_parts:
+                        input_items.append(
+                            {
+                                "type": "message",
+                                "role": "user",
+                                "content": user_parts,
+                            }
+                        )
+
+            elif role == "assistant":
+                if isinstance(content, str):
+                    input_items.append(
+                        {
+                            "type": "message",
+                            "role": "assistant",
+                            "content": [{"type": "output_text", "text": content}],
+                        }
+                    )
+                elif isinstance(content, list):
+                    asst_parts: List[Dict[str, Any]] = []
+                    for block in content:
+                        if not isinstance(block, dict):
+                            continue
+                        btype = block.get("type")
+                        if btype == "text":
+                            asst_parts.append(
+                                {"type": "output_text", "text": block.get("text", "")}
+                            )
+                        elif btype == "tool_use":
+                            # tool_use becomes a top-level function_call item
+                            input_items.append(
+                                {
+                                    "type": "function_call",
+                                    "call_id": block.get("id", ""),
+                                    "name": block.get("name", ""),
+                                    "arguments": json.dumps(block.get("input", {})),
+                                }
+                            )
+                        elif btype == "thinking":
+                            thinking_text = block.get("thinking", "")
+                            if thinking_text:
+                                asst_parts.append(
+                                    {"type": "output_text", "text": thinking_text}
+                                )
+                    if asst_parts:
+                        input_items.append(
+                            {
+                                "type": "message",
+                                "role": "assistant",
+                                "content": asst_parts,
+                            }
+                        )
+
+        return input_items
+
+    def translate_tools_to_responses_api(
+        self,
+        tools: List[AllAnthropicToolsValues],
+    ) -> List[Dict[str, Any]]:
+        """Convert Anthropic tool definitions to Responses API function tools."""
+        result: List[Dict[str, Any]] = []
+        for tool in tools:
+            tool_dict = cast(Dict[str, Any], tool)
+            tool_type = tool_dict.get("type", "")
+            tool_name = tool_dict.get("name", "")
+            # web_search tool
+            if (
+                isinstance(tool_type, str) and tool_type.startswith("web_search")
+            ) or tool_name == "web_search":
+                result.append({"type": "web_search_preview"})
+                continue
+            func_tool: Dict[str, Any] = {"type": "function", "name": tool_name}
+            if "description" in tool_dict:
+                func_tool["description"] = tool_dict["description"]
+            if "input_schema" in tool_dict:
+                func_tool["parameters"] = tool_dict["input_schema"]
+            result.append(func_tool)
+        return result
+
+    @staticmethod
+    def translate_tool_choice_to_responses_api(
+        tool_choice: AnthropicMessagesToolChoice,
+    ) -> Dict[str, Any]:
+        """Convert Anthropic tool_choice to Responses API tool_choice."""
+        tc_type = tool_choice.get("type")
+        if tc_type == "any":
+            return {"type": "required"}
+        elif tc_type == "tool":
+            return {"type": "function", "name": tool_choice.get("name", "")}
+        return {"type": "auto"}
+
+    @staticmethod
+    def translate_context_management_to_responses_api(
+        context_management: Dict[str, Any],
+    ) -> Optional[List[Dict[str, Any]]]:
+        """
+        Convert Anthropic context_management dict to OpenAI Responses API array format.
+
+        Anthropic format: {"edits": [{"type": "compact_20260112", "trigger": {"type": "input_tokens", "value": 150000}}]}
+        OpenAI format:    [{"type": "compaction", "compact_threshold": 150000}]
+        """
+        if not isinstance(context_management, dict):
+            return None
+
+        edits = context_management.get("edits", [])
+        if not isinstance(edits, list):
+            return None
+
+        result: List[Dict[str, Any]] = []
+        for edit in edits:
+            if not isinstance(edit, dict):
+                continue
+            edit_type = edit.get("type", "")
+            if edit_type == "compact_20260112":
+                entry: Dict[str, Any] = {"type": "compaction"}
+                trigger = edit.get("trigger")
+                if isinstance(trigger, dict) and trigger.get("value") is not None:
+                    entry["compact_threshold"] = int(trigger["value"])
+                result.append(entry)
+
+        return result if result else None
+
+    @staticmethod
+    def translate_thinking_to_reasoning(
+        thinking: Dict[str, Any]
+    ) -> Optional[Dict[str, Any]]:
+        """
+        Convert Anthropic thinking param to Responses API reasoning param.
+
+        thinking.budget_tokens maps to reasoning effort:
+          >= 10000 -> high, >= 5000 -> medium, >= 2000 -> low, < 2000 -> minimal
+        """
+        if not isinstance(thinking, dict) or thinking.get("type") != "enabled":
+            return None
+        budget = thinking.get("budget_tokens", 0)
+        if budget >= 10000:
+            effort = "high"
+        elif budget >= 5000:
+            effort = "medium"
+        elif budget >= 2000:
+            effort = "low"
+        else:
+            effort = "minimal"
+        return {"effort": effort, "summary": "detailed"}
+
+    def translate_request(
+        self,
+        anthropic_request: AnthropicMessagesRequest,
+    ) -> Dict[str, Any]:
+        """
+        Translate a full Anthropic /v1/messages request dict to
+        litellm.responses() / litellm.aresponses() kwargs.
+        """
+        model: str = anthropic_request["model"]
+        messages_list = cast(
+            List[
+                Union[
+                    AnthropicMessagesUserMessageParam,
+                    AnthopicMessagesAssistantMessageParam,
+                ]
+            ],
+            anthropic_request["messages"],
+        )
+
+        responses_kwargs: Dict[str, Any] = {
+            "model": model,
+            "input": self.translate_messages_to_responses_input(messages_list),
+        }
+
+        # system -> instructions
+        system = anthropic_request.get("system")
+        if system:
+            if isinstance(system, str):
+                responses_kwargs["instructions"] = system
+            elif isinstance(system, list):
+                text_parts = [
+                    b.get("text", "")
+                    for b in system
+                    if isinstance(b, dict) and b.get("type") == "text"
+                ]
+                responses_kwargs["instructions"] = "\n".join(filter(None, text_parts))
+
+        # max_tokens -> max_output_tokens
+        max_tokens = anthropic_request.get("max_tokens")
+        if max_tokens:
+            responses_kwargs["max_output_tokens"] = max_tokens
+
+        # temperature / top_p passed through
+        if "temperature" in anthropic_request:
+            responses_kwargs["temperature"] = anthropic_request["temperature"]
+        if "top_p" in anthropic_request:
+            responses_kwargs["top_p"] = anthropic_request["top_p"]
+
+        # tools
+        tools = anthropic_request.get("tools")
+        if tools:
+            responses_kwargs["tools"] = self.translate_tools_to_responses_api(
+                cast(List[AllAnthropicToolsValues], tools)
+            )
+
+        # tool_choice
+        tool_choice = anthropic_request.get("tool_choice")
+        if tool_choice:
+            responses_kwargs[
+                "tool_choice"
+            ] = self.translate_tool_choice_to_responses_api(
+                cast(AnthropicMessagesToolChoice, tool_choice)
+            )
+
+        # thinking -> reasoning
+        thinking = anthropic_request.get("thinking")
+        if isinstance(thinking, dict):
+            reasoning = self.translate_thinking_to_reasoning(thinking)
+            if reasoning:
+                responses_kwargs["reasoning"] = reasoning
+
+        # output_format / output_config.format -> text format
+        # output_format: {"type": "json_schema", "schema": {...}}
+        # output_config: {"format": {"type": "json_schema", "schema": {...}}}
+        output_format: Any = anthropic_request.get("output_format")
+        output_config = anthropic_request.get("output_config")
+        if not isinstance(output_format, dict) and isinstance(output_config, dict):
+            output_format = output_config.get("format")  # type: ignore[assignment]
+        if (
+            isinstance(output_format, dict)
+            and output_format.get("type") == "json_schema"
+        ):
+            schema = output_format.get("schema")
+            if schema:
+                responses_kwargs["text"] = {
+                    "format": {
+                        "type": "json_schema",
+                        "name": "structured_output",
+                        "schema": schema,
+                        "strict": True,
+                    }
+                }
+
+        # context_management: Anthropic dict -> OpenAI array
+        context_management = anthropic_request.get("context_management")
+        if isinstance(context_management, dict):
+            openai_cm = self.translate_context_management_to_responses_api(
+                context_management
+            )
+            if openai_cm is not None:
+                responses_kwargs["context_management"] = openai_cm
+
+        # metadata user_id -> user
+        metadata = anthropic_request.get("metadata")
+        if isinstance(metadata, dict) and "user_id" in metadata:
+            responses_kwargs["user"] = str(metadata["user_id"])[:64]
+
+        return responses_kwargs
+
+    # ------------------------------------------------------------------ #
+    # Response translation: Responses API -> Anthropic                    #
+    # ------------------------------------------------------------------ #
+
+    def translate_response(
+        self,
+        response: ResponsesAPIResponse,
+    ) -> AnthropicMessagesResponse:
+        """
+        Translate an OpenAI ResponsesAPIResponse to AnthropicMessagesResponse.
+        """
+        from openai.types.responses import (
+            ResponseFunctionToolCall,
+            ResponseOutputMessage,
+            ResponseReasoningItem,
+        )
+
+        from litellm.types.llms.openai import ResponseAPIUsage
+
+        content: List[Dict[str, Any]] = []
+        stop_reason: AnthropicFinishReason = "end_turn"
+
+        for item in response.output:
+            if isinstance(item, ResponseReasoningItem):
+                for summary in item.summary:
+                    text = getattr(summary, "text", "")
+                    if text:
+                        content.append(
+                            AnthropicResponseContentBlockThinking(
+                                type="thinking",
+                                thinking=text,
+                                signature=None,
+                            ).model_dump()
+                        )
+
+            elif isinstance(item, ResponseOutputMessage):
+                for part in item.content:
+                    if getattr(part, "type", None) == "output_text":
+                        content.append(
+                            AnthropicResponseContentBlockText(
+                                type="text", text=getattr(part, "text", "")
+                            ).model_dump()
+                        )
+
+            elif isinstance(item, ResponseFunctionToolCall):
+                try:
+                    input_data = json.loads(item.arguments) if item.arguments else {}
+                except (json.JSONDecodeError, TypeError):
+                    input_data = {}
+                content.append(
+                    AnthropicResponseContentBlockToolUse(
+                        type="tool_use",
+                        id=item.call_id or item.id or "",
+                        name=item.name,
+                        input=input_data,
+                    ).model_dump()
+                )
+                stop_reason = "tool_use"
+
+            elif isinstance(item, dict):
+                item_type = item.get("type")
+                if item_type == "message":
+                    for part in item.get("content", []):
+                        if isinstance(part, dict) and part.get("type") == "output_text":
+                            content.append(
+                                AnthropicResponseContentBlockText(
+                                    type="text", text=part.get("text", "")
+                                ).model_dump()
+                            )
+                elif item_type == "function_call":
+                    try:
+                        input_data = json.loads(item.get("arguments", "{}"))
+                    except (json.JSONDecodeError, TypeError):
+                        input_data = {}
+                    content.append(
+                        AnthropicResponseContentBlockToolUse(
+                            type="tool_use",
+                            id=item.get("call_id") or item.get("id", ""),
+                            name=item.get("name", ""),
+                            input=input_data,
+                        ).model_dump()
+                    )
+                    stop_reason = "tool_use"
+
+        # status -> stop_reason override
+        if response.status == "incomplete":
+            stop_reason = "max_tokens"
+
+        # usage
+        raw_usage: Optional[ResponseAPIUsage] = response.usage
+        input_tokens = int(getattr(raw_usage, "input_tokens", 0) or 0)
+        output_tokens = int(getattr(raw_usage, "output_tokens", 0) or 0)
+
+        anthropic_usage = AnthropicUsage(
+            input_tokens=input_tokens,
+            output_tokens=output_tokens,
+        )
+
+        return AnthropicMessagesResponse(
+            id=response.id,
+            type="message",
+            role="assistant",
+            model=response.model or "unknown-model",
+            stop_sequence=None,
+            usage=anthropic_usage,  # type: ignore
+            content=content,  # type: ignore
+            stop_reason=stop_reason,
+        )

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/files/__init__.py

@@ -0,0 +1,4 @@
+from .handler import AnthropicFilesHandler
+from .transformation import AnthropicFilesConfig
+
+__all__ = ["AnthropicFilesHandler", "AnthropicFilesConfig"]

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/files/handler.py

@@ -0,0 +1,366 @@
+import asyncio
+import json
+import time
+from typing import Any, Coroutine, Optional, Union
+
+import httpx
+
+import litellm
+from litellm._logging import verbose_logger
+from litellm._uuid import uuid
+from litellm.llms.custom_httpx.http_handler import (
+    get_async_httpx_client,
+)
+from litellm.litellm_core_utils.litellm_logging import Logging
+from litellm.types.llms.openai import (
+    FileContentRequest,
+    HttpxBinaryResponseContent,
+    OpenAIBatchResult,
+    OpenAIChatCompletionResponse,
+    OpenAIErrorBody,
+)
+from litellm.types.utils import CallTypes, LlmProviders, ModelResponse
+
+from ..chat.transformation import AnthropicConfig
+from ..common_utils import AnthropicModelInfo
+
+# Map Anthropic error types to HTTP status codes
+ANTHROPIC_ERROR_STATUS_CODE_MAP = {
+    "invalid_request_error": 400,
+    "authentication_error": 401,
+    "permission_error": 403,
+    "not_found_error": 404,
+    "rate_limit_error": 429,
+    "api_error": 500,
+    "overloaded_error": 503,
+    "timeout_error": 504,
+}
+
+
+class AnthropicFilesHandler:
+    """
+    Handles Anthropic Files API operations.
+
+    Currently supports:
+    - file_content() for retrieving Anthropic Message Batch results
+    """
+
+    def __init__(self):
+        self.anthropic_model_info = AnthropicModelInfo()
+
+    async def afile_content(
+        self,
+        file_content_request: FileContentRequest,
+        api_base: Optional[str] = None,
+        api_key: Optional[str] = None,
+        timeout: Union[float, httpx.Timeout] = 600.0,
+        max_retries: Optional[int] = None,
+    ) -> HttpxBinaryResponseContent:
+        """
+        Async: Retrieve file content from Anthropic.
+
+        For batch results, the file_id should be the batch_id.
+        This will call Anthropic's /v1/messages/batches/{batch_id}/results endpoint.
+
+        Args:
+            file_content_request: Contains file_id (batch_id for batch results)
+            api_base: Anthropic API base URL
+            api_key: Anthropic API key
+            timeout: Request timeout
+            max_retries: Max retry attempts (unused for now)
+
+        Returns:
+            HttpxBinaryResponseContent: Binary content wrapped in compatible response format
+        """
+        file_id = file_content_request.get("file_id")
+        if not file_id:
+            raise ValueError("file_id is required in file_content_request")
+
+        # Extract batch_id from file_id
+        # Handle both formats: "anthropic_batch_results:{batch_id}" or just "{batch_id}"
+        if file_id.startswith("anthropic_batch_results:"):
+            batch_id = file_id.replace("anthropic_batch_results:", "", 1)
+        else:
+            batch_id = file_id
+
+        # Get Anthropic API credentials
+        api_base = self.anthropic_model_info.get_api_base(api_base)
+        api_key = api_key or self.anthropic_model_info.get_api_key()
+
+        if not api_key:
+            raise ValueError("Missing Anthropic API Key")
+
+        # Construct the Anthropic batch results URL
+        results_url = f"{api_base.rstrip('/')}/v1/messages/batches/{batch_id}/results"
+
+        # Prepare headers
+        headers = {
+            "accept": "application/json",
+            "anthropic-version": "2023-06-01",
+            "x-api-key": api_key,
+        }
+
+        # Make the request to Anthropic
+        async_client = get_async_httpx_client(llm_provider=LlmProviders.ANTHROPIC)
+        anthropic_response = await async_client.get(url=results_url, headers=headers)
+        anthropic_response.raise_for_status()
+
+        # Transform Anthropic batch results to OpenAI format
+        transformed_content = self._transform_anthropic_batch_results_to_openai_format(
+            anthropic_response.content
+        )
+
+        # Create a new response with transformed content
+        transformed_response = httpx.Response(
+            status_code=anthropic_response.status_code,
+            headers=anthropic_response.headers,
+            content=transformed_content,
+            request=anthropic_response.request,
+        )
+
+        # Return the transformed response content
+        return HttpxBinaryResponseContent(response=transformed_response)
+
+    def file_content(
+        self,
+        _is_async: bool,
+        file_content_request: FileContentRequest,
+        api_base: Optional[str] = None,
+        api_key: Optional[str] = None,
+        timeout: Union[float, httpx.Timeout] = 600.0,
+        max_retries: Optional[int] = None,
+    ) -> Union[
+        HttpxBinaryResponseContent, Coroutine[Any, Any, HttpxBinaryResponseContent]
+    ]:
+        """
+        Retrieve file content from Anthropic.
+
+        For batch results, the file_id should be the batch_id.
+        This will call Anthropic's /v1/messages/batches/{batch_id}/results endpoint.
+
+        Args:
+            _is_async: Whether to run asynchronously
+            file_content_request: Contains file_id (batch_id for batch results)
+            api_base: Anthropic API base URL
+            api_key: Anthropic API key
+            timeout: Request timeout
+            max_retries: Max retry attempts (unused for now)
+
+        Returns:
+            HttpxBinaryResponseContent or Coroutine: Binary content wrapped in compatible response format
+        """
+        if _is_async:
+            return self.afile_content(
+                file_content_request=file_content_request,
+                api_base=api_base,
+                api_key=api_key,
+                max_retries=max_retries,
+            )
+        else:
+            return asyncio.run(
+                self.afile_content(
+                    file_content_request=file_content_request,
+                    api_base=api_base,
+                    api_key=api_key,
+                    timeout=timeout,
+                    max_retries=max_retries,
+                )
+            )
+
+    def _transform_anthropic_batch_results_to_openai_format(
+        self, anthropic_content: bytes
+    ) -> bytes:
+        """
+        Transform Anthropic batch results JSONL to OpenAI batch results JSONL format.
+
+        Anthropic format:
+        {
+          "custom_id": "...",
+          "result": {
+            "type": "succeeded",
+            "message": { ... }  // Anthropic message format
+          }
+        }
+
+        OpenAI format:
+        {
+          "custom_id": "...",
+          "response": {
+            "status_code": 200,
+            "request_id": "...",
+            "body": { ... }  // OpenAI chat completion format
+          }
+        }
+        """
+        try:
+            anthropic_config = AnthropicConfig()
+            transformed_lines = []
+
+            # Parse JSONL content
+            content_str = anthropic_content.decode("utf-8")
+            for line in content_str.strip().split("\n"):
+                if not line.strip():
+                    continue
+
+                anthropic_result = json.loads(line)
+                custom_id = anthropic_result.get("custom_id", "")
+                result = anthropic_result.get("result", {})
+                result_type = result.get("type", "")
+
+                # Transform based on result type
+                if result_type == "succeeded":
+                    # Transform Anthropic message to OpenAI format
+                    anthropic_message = result.get("message", {})
+                    if anthropic_message:
+                        openai_response_body = (
+                            self._transform_anthropic_message_to_openai_format(
+                                anthropic_message=anthropic_message,
+                                anthropic_config=anthropic_config,
+                            )
+                        )
+
+                        # Create OpenAI batch result format
+                        openai_result: OpenAIBatchResult = {
+                            "custom_id": custom_id,
+                            "response": {
+                                "status_code": 200,
+                                "request_id": anthropic_message.get("id", ""),
+                                "body": openai_response_body,
+                            },
+                        }
+                        transformed_lines.append(json.dumps(openai_result))
+                elif result_type == "errored":
+                    # Handle error case
+                    error = result.get("error", {})
+                    error_obj = error.get("error", {})
+                    error_message = error_obj.get("message", "Unknown error")
+                    error_type = error_obj.get("type", "api_error")
+
+                    status_code = ANTHROPIC_ERROR_STATUS_CODE_MAP.get(error_type, 500)
+
+                    error_body_errored: OpenAIErrorBody = {
+                        "error": {
+                            "message": error_message,
+                            "type": error_type,
+                        }
+                    }
+                    openai_result_errored: OpenAIBatchResult = {
+                        "custom_id": custom_id,
+                        "response": {
+                            "status_code": status_code,
+                            "request_id": error.get("request_id", ""),
+                            "body": error_body_errored,
+                        },
+                    }
+                    transformed_lines.append(json.dumps(openai_result_errored))
+                elif result_type in ["canceled", "expired"]:
+                    # Handle canceled/expired cases
+                    error_body_canceled: OpenAIErrorBody = {
+                        "error": {
+                            "message": f"Batch request was {result_type}",
+                            "type": "invalid_request_error",
+                        }
+                    }
+                    openai_result_canceled: OpenAIBatchResult = {
+                        "custom_id": custom_id,
+                        "response": {
+                            "status_code": 400,
+                            "request_id": "",
+                            "body": error_body_canceled,
+                        },
+                    }
+                    transformed_lines.append(json.dumps(openai_result_canceled))
+
+            # Join lines and encode back to bytes
+            transformed_content = "\n".join(transformed_lines)
+            if transformed_lines:
+                transformed_content += "\n"  # Add trailing newline for JSONL format
+            return transformed_content.encode("utf-8")
+        except Exception as e:
+            verbose_logger.error(
+                f"Error transforming Anthropic batch results to OpenAI format: {e}"
+            )
+            # Return original content if transformation fails
+            return anthropic_content
+
+    def _transform_anthropic_message_to_openai_format(
+        self, anthropic_message: dict, anthropic_config: AnthropicConfig
+    ) -> OpenAIChatCompletionResponse:
+        """
+        Transform a single Anthropic message to OpenAI chat completion format.
+        """
+        try:
+            # Create a mock httpx.Response for transformation
+            mock_response = httpx.Response(
+                status_code=200,
+                content=json.dumps(anthropic_message).encode("utf-8"),
+            )
+
+            # Create a ModelResponse object
+            model_response = ModelResponse()
+            # Initialize with required fields - will be populated by transform_parsed_response
+            model_response.choices = [
+                litellm.Choices(
+                    finish_reason="stop",
+                    index=0,
+                    message=litellm.Message(content="", role="assistant"),
+                )
+            ]  # type: ignore
+
+            # Create a logging object for transformation
+            logging_obj = Logging(
+                model=anthropic_message.get("model", "claude-3-5-sonnet-20241022"),
+                messages=[{"role": "user", "content": "batch_request"}],
+                stream=False,
+                call_type=CallTypes.aretrieve_batch,
+                start_time=time.time(),
+                litellm_call_id="batch_" + str(uuid.uuid4()),
+                function_id="batch_processing",
+                litellm_trace_id=str(uuid.uuid4()),
+                kwargs={"optional_params": {}},
+            )
+            logging_obj.optional_params = {}
+
+            # Transform using AnthropicConfig
+            transformed_response = anthropic_config.transform_parsed_response(
+                completion_response=anthropic_message,
+                raw_response=mock_response,
+                model_response=model_response,
+                json_mode=False,
+                prefix_prompt=None,
+            )
+
+            # Convert ModelResponse to OpenAI format dict - it's already in OpenAI format
+            openai_body: OpenAIChatCompletionResponse = transformed_response.model_dump(
+                exclude_none=True
+            )
+
+            # Ensure id comes from anthropic_message if not set
+            if not openai_body.get("id"):
+                openai_body["id"] = anthropic_message.get("id", "")
+
+            return openai_body
+        except Exception as e:
+            verbose_logger.error(
+                f"Error transforming Anthropic message to OpenAI format: {e}"
+            )
+            # Return a basic error response if transformation fails
+            error_response: OpenAIChatCompletionResponse = {
+                "id": anthropic_message.get("id", ""),
+                "object": "chat.completion",
+                "created": int(time.time()),
+                "model": anthropic_message.get("model", ""),
+                "choices": [
+                    {
+                        "index": 0,
+                        "message": {"role": "assistant", "content": ""},
+                        "finish_reason": "error",
+                    }
+                ],
+                "usage": {
+                    "prompt_tokens": 0,
+                    "completion_tokens": 0,
+                    "total_tokens": 0,
+                },
+            }
+            return error_response

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/files/transformation.py

@@ -0,0 +1,307 @@
+"""
+Anthropic Files API transformation config.
+
+Implements BaseFilesConfig for Anthropic's Files API (beta).
+Reference: https://docs.anthropic.com/en/docs/build-with-claude/files
+
+Anthropic Files API endpoints:
+- POST   /v1/files              - Upload a file
+- GET    /v1/files              - List files
+- GET    /v1/files/{file_id}    - Retrieve file metadata
+- DELETE /v1/files/{file_id}    - Delete a file
+- GET    /v1/files/{file_id}/content - Download file content
+"""
+
+import calendar
+import time
+from typing import Any, Dict, List, Optional, Union, cast
+
+import httpx
+from openai.types.file_deleted import FileDeleted
+
+from litellm.litellm_core_utils.prompt_templates.common_utils import extract_file_data
+from litellm.llms.base_llm.chat.transformation import BaseLLMException
+from litellm.llms.base_llm.files.transformation import (
+    BaseFilesConfig,
+    LiteLLMLoggingObj,
+)
+from litellm.types.llms.openai import (
+    CreateFileRequest,
+    FileContentRequest,
+    HttpxBinaryResponseContent,
+    OpenAICreateFileRequestOptionalParams,
+    OpenAIFileObject,
+)
+from litellm.types.utils import LlmProviders
+
+from ..common_utils import AnthropicError, AnthropicModelInfo
+
+ANTHROPIC_FILES_API_BASE = "https://api.anthropic.com"
+ANTHROPIC_FILES_BETA_HEADER = "files-api-2025-04-14"
+
+
+class AnthropicFilesConfig(BaseFilesConfig):
+    """
+    Transformation config for Anthropic Files API.
+
+    Anthropic uses:
+    - x-api-key header for authentication
+    - anthropic-beta: files-api-2025-04-14 header
+    - multipart/form-data for file uploads
+    - purpose="messages" (Anthropic-specific, not for batches/fine-tuning)
+    """
+
+    def __init__(self):
+        pass
+
+    @property
+    def custom_llm_provider(self) -> LlmProviders:
+        return LlmProviders.ANTHROPIC
+
+    def get_complete_url(
+        self,
+        api_base: Optional[str],
+        api_key: Optional[str],
+        model: str,
+        optional_params: dict,
+        litellm_params: dict,
+        stream: Optional[bool] = None,
+    ) -> str:
+        api_base = AnthropicModelInfo.get_api_base(api_base) or ANTHROPIC_FILES_API_BASE
+        return f"{api_base.rstrip('/')}/v1/files"
+
+    def get_error_class(
+        self,
+        error_message: str,
+        status_code: int,
+        headers: Union[dict, httpx.Headers],
+    ) -> BaseLLMException:
+        return AnthropicError(
+            status_code=status_code,
+            message=error_message,
+            headers=cast(httpx.Headers, headers) if isinstance(headers, dict) else headers,
+        )
+
+    def validate_environment(
+        self,
+        headers: dict,
+        model: str,
+        messages: list,
+        optional_params: dict,
+        litellm_params: dict,
+        api_key: Optional[str] = None,
+        api_base: Optional[str] = None,
+    ) -> dict:
+        api_key = AnthropicModelInfo.get_api_key(api_key)
+        if not api_key:
+            raise ValueError(
+                "Anthropic API key is required. Set ANTHROPIC_API_KEY environment variable or pass api_key parameter."
+            )
+        headers.update(
+            {
+                "x-api-key": api_key,
+                "anthropic-version": "2023-06-01",
+                "anthropic-beta": ANTHROPIC_FILES_BETA_HEADER,
+            }
+        )
+        return headers
+
+    def get_supported_openai_params(
+        self, model: str
+    ) -> List[OpenAICreateFileRequestOptionalParams]:
+        return ["purpose"]
+
+    def map_openai_params(
+        self,
+        non_default_params: dict,
+        optional_params: dict,
+        model: str,
+        drop_params: bool,
+    ) -> dict:
+        return optional_params
+
+    def transform_create_file_request(
+        self,
+        model: str,
+        create_file_data: CreateFileRequest,
+        optional_params: dict,
+        litellm_params: dict,
+    ) -> dict:
+        """
+        Transform to multipart form data for Anthropic file upload.
+
+        Anthropic expects: POST /v1/files with multipart form-data
+        - file: the file content
+        - purpose: "messages" (defaults to "messages" if not provided)
+        """
+        file_data = create_file_data.get("file")
+        if file_data is None:
+            raise ValueError("File data is required")
+
+        extracted = extract_file_data(file_data)
+        filename = extracted["filename"] or f"file_{int(time.time())}"
+        content = extracted["content"]
+        content_type = extracted.get("content_type", "application/octet-stream")
+
+        purpose = create_file_data.get("purpose", "messages")
+
+        return {
+            "file": (filename, content, content_type),
+            "purpose": (None, purpose),
+        }
+
+    def transform_create_file_response(
+        self,
+        model: Optional[str],
+        raw_response: httpx.Response,
+        logging_obj: LiteLLMLoggingObj,
+        litellm_params: dict,
+    ) -> OpenAIFileObject:
+        """
+        Transform Anthropic file response to OpenAI format.
+
+        Anthropic response:
+        {
+            "id": "file-xxx",
+            "type": "file",
+            "filename": "document.pdf",
+            "mime_type": "application/pdf",
+            "size_bytes": 12345,
+            "created_at": "2025-01-01T00:00:00Z"
+        }
+        """
+        response_json = raw_response.json()
+        return self._parse_anthropic_file(response_json)
+
+    def transform_retrieve_file_request(
+        self,
+        file_id: str,
+        optional_params: dict,
+        litellm_params: dict,
+    ) -> tuple[str, dict]:
+        api_base = (
+            AnthropicModelInfo.get_api_base(litellm_params.get("api_base"))
+            or ANTHROPIC_FILES_API_BASE
+        )
+        return f"{api_base.rstrip('/')}/v1/files/{file_id}", {}
+
+    def transform_retrieve_file_response(
+        self,
+        raw_response: httpx.Response,
+        logging_obj: LiteLLMLoggingObj,
+        litellm_params: dict,
+    ) -> OpenAIFileObject:
+        response_json = raw_response.json()
+        return self._parse_anthropic_file(response_json)
+
+    def transform_delete_file_request(
+        self,
+        file_id: str,
+        optional_params: dict,
+        litellm_params: dict,
+    ) -> tuple[str, dict]:
+        api_base = (
+            AnthropicModelInfo.get_api_base(litellm_params.get("api_base"))
+            or ANTHROPIC_FILES_API_BASE
+        )
+        return f"{api_base.rstrip('/')}/v1/files/{file_id}", {}
+
+    def transform_delete_file_response(
+        self,
+        raw_response: httpx.Response,
+        logging_obj: LiteLLMLoggingObj,
+        litellm_params: dict,
+    ) -> FileDeleted:
+        response_json = raw_response.json()
+        file_id = response_json.get("id", "")
+        return FileDeleted(
+            id=file_id,
+            deleted=True,
+            object="file",
+        )
+
+    def transform_list_files_request(
+        self,
+        purpose: Optional[str],
+        optional_params: dict,
+        litellm_params: dict,
+    ) -> tuple[str, dict]:
+        api_base = (
+            AnthropicModelInfo.get_api_base(litellm_params.get("api_base"))
+            or ANTHROPIC_FILES_API_BASE
+        )
+        url = f"{api_base.rstrip('/')}/v1/files"
+        params: Dict[str, Any] = {}
+        if purpose:
+            params["purpose"] = purpose
+        return url, params
+
+    def transform_list_files_response(
+        self,
+        raw_response: httpx.Response,
+        logging_obj: LiteLLMLoggingObj,
+        litellm_params: dict,
+    ) -> List[OpenAIFileObject]:
+        """
+        Anthropic list response:
+        {
+            "data": [...],
+            "has_more": false,
+            "first_id": "...",
+            "last_id": "..."
+        }
+        """
+        response_json = raw_response.json()
+        files_data = response_json.get("data", [])
+        return [self._parse_anthropic_file(f) for f in files_data]
+
+    def transform_file_content_request(
+        self,
+        file_content_request: FileContentRequest,
+        optional_params: dict,
+        litellm_params: dict,
+    ) -> tuple[str, dict]:
+        file_id = file_content_request.get("file_id")
+        api_base = (
+            AnthropicModelInfo.get_api_base(litellm_params.get("api_base"))
+            or ANTHROPIC_FILES_API_BASE
+        )
+        return f"{api_base.rstrip('/')}/v1/files/{file_id}/content", {}
+
+    def transform_file_content_response(
+        self,
+        raw_response: httpx.Response,
+        logging_obj: LiteLLMLoggingObj,
+        litellm_params: dict,
+    ) -> HttpxBinaryResponseContent:
+        return HttpxBinaryResponseContent(response=raw_response)
+
+    @staticmethod
+    def _parse_anthropic_file(file_data: dict) -> OpenAIFileObject:
+        """Parse Anthropic file object into OpenAI format."""
+        created_at_str = file_data.get("created_at", "")
+        if created_at_str:
+            try:
+                created_at = int(
+                    calendar.timegm(
+                        time.strptime(
+                            created_at_str.replace("Z", "+00:00")[:19],
+                            "%Y-%m-%dT%H:%M:%S",
+                        )
+                    )
+                )
+            except (ValueError, TypeError):
+                created_at = int(time.time())
+        else:
+            created_at = int(time.time())
+
+        return OpenAIFileObject(
+            id=file_data.get("id", ""),
+            bytes=file_data.get("size_bytes", file_data.get("bytes", 0)),
+            created_at=created_at,
+            filename=file_data.get("filename", ""),
+            object="file",
+            purpose=file_data.get("purpose", "messages"),
+            status="uploaded",
+            status_details=None,
+        )

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/skills/__init__.py

@@ -0,0 +1,5 @@
+"""Anthropic Skills API integration"""
+
+from .transformation import AnthropicSkillsConfig
+
+__all__ = ["AnthropicSkillsConfig"]

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/skills/readme.md

@@ -0,0 +1,279 @@
+# Anthropic Skills API Integration
+
+This module provides comprehensive support for the Anthropic Skills API through LiteLLM.
+
+## Features
+
+The Skills API allows you to:
+- **Create skills**: Define reusable AI capabilities
+- **List skills**: Browse all available skills
+- **Get skills**: Retrieve detailed information about a specific skill
+- **Delete skills**: Remove skills that are no longer needed
+
+## Quick Start
+
+### Prerequisites
+
+Set your Anthropic API key:
+```python
+import os
+os.environ["ANTHROPIC_API_KEY"] = "your-api-key-here"
+```
+
+### Basic Usage
+
+#### Create a Skill
+
+```python
+import litellm
+
+# Create a skill with files
+# Note: All files must be in the same top-level directory
+# and must include a SKILL.md file at the root
+skill = litellm.create_skill(
+    files=[
+        # List of file objects to upload
+        # Must include SKILL.md
+    ],
+    display_title="Python Code Generator",
+    custom_llm_provider="anthropic"
+)
+print(f"Created skill: {skill.id}")
+
+# Asynchronous version
+skill = await litellm.acreate_skill(
+    files=[...],  # Your files here
+    display_title="Python Code Generator",
+    custom_llm_provider="anthropic"
+)
+```
+
+#### List Skills
+
+```python
+# List all skills
+skills = litellm.list_skills(
+    custom_llm_provider="anthropic"
+)
+
+for skill in skills.data:
+    print(f"{skill.display_title}: {skill.id}")
+
+# With pagination and filtering
+skills = litellm.list_skills(
+    limit=20,
+    source="custom",  # Filter by 'custom' or 'anthropic'
+    custom_llm_provider="anthropic"
+)
+
+# Get next page if available
+if skills.has_more:
+    next_page = litellm.list_skills(
+        page=skills.next_page,
+        custom_llm_provider="anthropic"
+    )
+```
+
+#### Get a Skill
+
+```python
+skill = litellm.get_skill(
+    skill_id="skill_abc123",
+    custom_llm_provider="anthropic"
+)
+
+print(f"Skill: {skill.display_title}")
+print(f"Created: {skill.created_at}")
+print(f"Latest version: {skill.latest_version}")
+print(f"Source: {skill.source}")
+```
+
+#### Delete a Skill
+
+```python
+result = litellm.delete_skill(
+    skill_id="skill_abc123",
+    custom_llm_provider="anthropic"
+)
+
+print(f"Deleted skill {result.id}, type: {result.type}")
+```
+
+## API Reference
+
+### `create_skill()`
+
+Create a new skill.
+
+**Parameters:**
+- `files` (List[Any], optional): Files to upload for the skill. All files must be in the same top-level directory and must include a SKILL.md file at the root.
+- `display_title` (str, optional): Display title for the skill
+- `custom_llm_provider` (str, optional): Provider name (default: "anthropic")
+- `extra_headers` (dict, optional): Additional HTTP headers
+- `timeout` (float, optional): Request timeout
+
+**Returns:**
+- `Skill`: The created skill object
+
+**Async version:** `acreate_skill()`
+
+### `list_skills()`
+
+List all skills.
+
+**Parameters:**
+- `limit` (int, optional): Number of results to return per page (max 100, default 20)
+- `page` (str, optional): Pagination token for fetching a specific page of results
+- `source` (str, optional): Filter skills by source ('custom' or 'anthropic')
+- `custom_llm_provider` (str, optional): Provider name (default: "anthropic")
+- `extra_headers` (dict, optional): Additional HTTP headers
+- `timeout` (float, optional): Request timeout
+
+**Returns:**
+- `ListSkillsResponse`: Object containing a list of skills and pagination info
+
+**Async version:** `alist_skills()`
+
+### `get_skill()`
+
+Get a specific skill by ID.
+
+**Parameters:**
+- `skill_id` (str, required): The skill ID
+- `custom_llm_provider` (str, optional): Provider name (default: "anthropic")
+- `extra_headers` (dict, optional): Additional HTTP headers
+- `timeout` (float, optional): Request timeout
+
+**Returns:**
+- `Skill`: The requested skill object
+
+**Async version:** `aget_skill()`
+
+### `delete_skill()`
+
+Delete a skill.
+
+**Parameters:**
+- `skill_id` (str, required): The skill ID to delete
+- `custom_llm_provider` (str, optional): Provider name (default: "anthropic")
+- `extra_headers` (dict, optional): Additional HTTP headers
+- `timeout` (float, optional): Request timeout
+
+**Returns:**
+- `DeleteSkillResponse`: Object with `id` and `type` fields
+
+**Async version:** `adelete_skill()`
+
+## Response Types
+
+### `Skill`
+
+Represents a skill from the Anthropic Skills API.
+
+**Fields:**
+- `id` (str): Unique identifier
+- `created_at` (str): ISO 8601 timestamp
+- `display_title` (str, optional): Display title
+- `latest_version` (str, optional): Latest version identifier
+- `source` (str): Source ("custom" or "anthropic")
+- `type` (str): Object type (always "skill")
+- `updated_at` (str): ISO 8601 timestamp
+
+### `ListSkillsResponse`
+
+Response from listing skills.
+
+**Fields:**
+- `data` (List[Skill]): List of skills
+- `next_page` (str, optional): Pagination token for the next page
+- `has_more` (bool): Whether more skills are available
+
+### `DeleteSkillResponse`
+
+Response from deleting a skill.
+
+**Fields:**
+- `id` (str): The deleted skill ID
+- `type` (str): Deleted object type (always "skill_deleted")
+
+## Architecture
+
+The Skills API implementation follows LiteLLM's standard patterns:
+
+1. **Type Definitions** (`litellm/types/llms/anthropic_skills.py`)
+   - Pydantic models for request/response types
+   - TypedDict definitions for request parameters
+
+2. **Base Configuration** (`litellm/llms/base_llm/skills/transformation.py`)
+   - Abstract base class `BaseSkillsAPIConfig`
+   - Defines transformation interface for provider-specific implementations
+
+3. **Provider Implementation** (`litellm/llms/anthropic/skills/transformation.py`)
+   - `AnthropicSkillsConfig` - Anthropic-specific transformations
+   - Handles API authentication, URL construction, and response mapping
+
+4. **Main Handler** (`litellm/skills/main.py`)
+   - Public API functions (sync and async)
+   - Request validation and routing
+   - Error handling
+
+5. **HTTP Handlers** (`litellm/llms/custom_httpx/llm_http_handler.py`)
+   - Low-level HTTP request/response handling
+   - Connection pooling and retry logic
+
+## Beta API Support
+
+The Skills API is in beta. The beta header (`skills-2025-10-02`) is automatically added by the Anthropic provider configuration. You can customize it if needed:
+
+```python
+skill = litellm.create_skill(
+    display_title="My Skill",
+    extra_headers={
+        "anthropic-beta": "skills-2025-10-02"  # Or any other beta version
+    },
+    custom_llm_provider="anthropic"
+)
+```
+
+The default beta version is configured in `litellm.constants.ANTHROPIC_SKILLS_API_BETA_VERSION`.
+
+## Error Handling
+
+All Skills API functions follow LiteLLM's standard error handling:
+
+```python
+import litellm
+
+try:
+    skill = litellm.create_skill(
+        display_title="My Skill",
+        custom_llm_provider="anthropic"
+    )
+except litellm.exceptions.AuthenticationError as e:
+    print(f"Authentication failed: {e}")
+except litellm.exceptions.RateLimitError as e:
+    print(f"Rate limit exceeded: {e}")
+except litellm.exceptions.APIError as e:
+    print(f"API error: {e}")
+```
+
+## Contributing
+
+To add support for Skills API to a new provider:
+
+1. Create provider-specific configuration class inheriting from `BaseSkillsAPIConfig`
+2. Implement all abstract methods for request/response transformations
+3. Register the config in `ProviderConfigManager.get_provider_skills_api_config()`
+4. Add appropriate tests
+
+## Related Documentation
+
+- [Anthropic Skills API Documentation](https://platform.claude.com/docs/en/api/beta/skills/create)
+- [LiteLLM Responses API](../../../responses/)
+- [Provider Configuration System](../../base_llm/)
+
+## Support
+
+For issues or questions:
+- GitHub Issues: https://github.com/BerriAI/litellm/issues
+- Discord: https://discord.gg/wuPM9dRgDw

llm-gateway-competitors/litellm-wheel-src/litellm/llms/anthropic/skills/transformation.py

@@ -0,0 +1,204 @@
+"""
+Anthropic Skills API configuration and transformations
+"""
+
+from typing import Any, Dict, Optional, Tuple
+
+import httpx
+
+from litellm._logging import verbose_logger
+from litellm.llms.base_llm.skills.transformation import (
+    BaseSkillsAPIConfig,
+    LiteLLMLoggingObj,
+)
+from litellm.types.llms.anthropic_skills import (
+    CreateSkillRequest,
+    DeleteSkillResponse,
+    ListSkillsParams,
+    ListSkillsResponse,
+    Skill,
+)
+from litellm.types.router import GenericLiteLLMParams
+from litellm.types.utils import LlmProviders
+
+
+class AnthropicSkillsConfig(BaseSkillsAPIConfig):
+    """Anthropic-specific Skills API configuration"""
+
+    @property
+    def custom_llm_provider(self) -> LlmProviders:
+        return LlmProviders.ANTHROPIC
+
+    def validate_environment(
+        self, headers: dict, litellm_params: Optional[GenericLiteLLMParams]
+    ) -> dict:
+        """Add Anthropic-specific headers"""
+        from litellm.llms.anthropic.common_utils import AnthropicModelInfo
+
+        # Get API key
+        api_key = None
+        if litellm_params:
+            api_key = litellm_params.api_key
+        api_key = AnthropicModelInfo.get_api_key(api_key)
+
+        if not api_key:
+            raise ValueError("ANTHROPIC_API_KEY is required for Skills API")
+
+        # Add required headers
+        headers["x-api-key"] = api_key
+        headers["anthropic-version"] = "2023-06-01"
+
+        # Add beta header for skills API
+        from litellm.constants import ANTHROPIC_SKILLS_API_BETA_VERSION
+
+        if "anthropic-beta" not in headers:
+            headers["anthropic-beta"] = ANTHROPIC_SKILLS_API_BETA_VERSION
+        elif isinstance(headers["anthropic-beta"], list):
+            if ANTHROPIC_SKILLS_API_BETA_VERSION not in headers["anthropic-beta"]:
+                headers["anthropic-beta"].append(ANTHROPIC_SKILLS_API_BETA_VERSION)
+        elif isinstance(headers["anthropic-beta"], str):
+            if ANTHROPIC_SKILLS_API_BETA_VERSION not in headers["anthropic-beta"]:
+                headers["anthropic-beta"] = [
+                    headers["anthropic-beta"],
+                    ANTHROPIC_SKILLS_API_BETA_VERSION,
+                ]
+
+        headers["content-type"] = "application/json"
+
+        return headers
+
+    def get_complete_url(
+        self,
+        api_base: Optional[str],
+        endpoint: str,
+        skill_id: Optional[str] = None,
+    ) -> str:
+        """Get complete URL for Anthropic Skills API"""
+        from litellm.llms.anthropic.common_utils import AnthropicModelInfo
+
+        if api_base is None:
+            api_base = AnthropicModelInfo.get_api_base()
+
+        if skill_id:
+            return f"{api_base}/v1/skills/{skill_id}"
+        return f"{api_base}/v1/{endpoint}"
+
+    def transform_create_skill_request(
+        self,
+        create_request: CreateSkillRequest,
+        litellm_params: GenericLiteLLMParams,
+        headers: dict,
+    ) -> Dict:
+        """Transform create skill request for Anthropic"""
+        verbose_logger.debug("Transforming create skill request: %s", create_request)
+
+        # Anthropic expects the request body directly
+        request_body = {k: v for k, v in create_request.items() if v is not None}
+
+        return request_body
+
+    def transform_create_skill_response(
+        self,
+        raw_response: httpx.Response,
+        logging_obj: LiteLLMLoggingObj,
+    ) -> Skill:
+        """Transform Anthropic response to Skill object"""
+        response_json = raw_response.json()
+        verbose_logger.debug("Transforming create skill response: %s", response_json)
+
+        return Skill(**response_json)
+
+    def transform_list_skills_request(
+        self,
+        list_params: ListSkillsParams,
+        litellm_params: GenericLiteLLMParams,
+        headers: dict,
+    ) -> Tuple[str, Dict]:
+        """Transform list skills request for Anthropic"""
+        from litellm.llms.anthropic.common_utils import AnthropicModelInfo
+
+        api_base = AnthropicModelInfo.get_api_base(
+            litellm_params.api_base if litellm_params else None
+        )
+        url = self.get_complete_url(api_base=api_base, endpoint="skills")
+
+        # Build query parameters
+        query_params: Dict[str, Any] = {}
+        if "limit" in list_params and list_params["limit"]:
+            query_params["limit"] = list_params["limit"]
+        if "page" in list_params and list_params["page"]:
+            query_params["page"] = list_params["page"]
+        if "source" in list_params and list_params["source"]:
+            query_params["source"] = list_params["source"]
+
+        verbose_logger.debug(
+            "List skills request made to Anthropic Skills endpoint with params: %s",
+            query_params,
+        )
+
+        return url, query_params
+
+    def transform_list_skills_response(
+        self,
+        raw_response: httpx.Response,
+        logging_obj: LiteLLMLoggingObj,
+    ) -> ListSkillsResponse:
+        """Transform Anthropic response to ListSkillsResponse"""
+        response_json = raw_response.json()
+        verbose_logger.debug("Transforming list skills response: %s", response_json)
+
+        return ListSkillsResponse(**response_json)
+
+    def transform_get_skill_request(
+        self,
+        skill_id: str,
+        api_base: str,
+        litellm_params: GenericLiteLLMParams,
+        headers: dict,
+    ) -> Tuple[str, Dict]:
+        """Transform get skill request for Anthropic"""
+        url = self.get_complete_url(
+            api_base=api_base, endpoint="skills", skill_id=skill_id
+        )
+
+        verbose_logger.debug("Get skill request - URL: %s", url)
+
+        return url, headers
+
+    def transform_get_skill_response(
+        self,
+        raw_response: httpx.Response,
+        logging_obj: LiteLLMLoggingObj,
+    ) -> Skill:
+        """Transform Anthropic response to Skill object"""
+        response_json = raw_response.json()
+        verbose_logger.debug("Transforming get skill response: %s", response_json)
+
+        return Skill(**response_json)
+
+    def transform_delete_skill_request(
+        self,
+        skill_id: str,
+        api_base: str,
+        litellm_params: GenericLiteLLMParams,
+        headers: dict,
+    ) -> Tuple[str, Dict]:
+        """Transform delete skill request for Anthropic"""
+        url = self.get_complete_url(
+            api_base=api_base, endpoint="skills", skill_id=skill_id
+        )
+
+        verbose_logger.debug("Delete skill request - URL: %s", url)
+
+        return url, headers
+
+    def transform_delete_skill_response(
+        self,
+        raw_response: httpx.Response,
+        logging_obj: LiteLLMLoggingObj,
+    ) -> DeleteSkillResponse:
+        """Transform Anthropic response to DeleteSkillResponse"""
+        response_json = raw_response.json()
+        verbose_logger.debug("Transforming delete skill response: %s", response_json)
+
+        return DeleteSkillResponse(**response_json)