From 0622ce3f2c44c7602bbafba707cee4aee4df328b Mon Sep 17 00:00:00 2001
From: jquinter <jquinter@gmail.com>
Date: Fri, 23 Jan 2026 00:34:29 -0300
Subject: [PATCH 01/11] Fix/nova grounding (#19598)

* added support for nova grounding for amazon nova model

* added citations support

* added integration tests

* removing test file

* refactor: Use web_search_options for Nova grounding instead of system_tool

---------

Co-authored-by: Juhie <juhiechandra@gmail.com>
Co-authored-by: Juhie <75068056+juhiechandra@users.noreply.github.com>
---
 .../prompt_templates/factory.py               |   3 +-
 .../bedrock/chat/converse_transformation.py   |  71 ++-
 litellm/llms/bedrock/chat/invoke_handler.py   |   5 +
 litellm/types/llms/bedrock.py                 |  85 +++
 poetry.lock                                   | 592 ++++++++++++++++--
 .../test_bedrock_completion.py                | 285 +++++++++
 ...llm_core_utils_prompt_templates_factory.py |  83 ++-
 7 files changed, 1057 insertions(+), 67 deletions(-)

diff --git a/litellm/litellm_core_utils/prompt_templates/factory.py b/litellm/litellm_core_utils/prompt_templates/factory.py
index 30263543fc..1d1e38c09d 100644
--- a/litellm/litellm_core_utils/prompt_templates/factory.py
+++ b/litellm/litellm_core_utils/prompt_templates/factory.py
@@ -4408,7 +4408,7 @@ def _bedrock_tools_pt(tools: List) -> List[BedrockToolBlock]:
     ]
     """
     """
-    Bedrock toolConfig looks like: 
+    Bedrock toolConfig looks like:
     "tools": [
         {
             "toolSpec": {
@@ -4436,6 +4436,7 @@ def _bedrock_tools_pt(tools: List) -> List[BedrockToolBlock]:
 
     tool_block_list: List[BedrockToolBlock] = []
     for tool in tools:
+        # Handle regular function tools
         parameters = tool.get("function", {}).get(
             "parameters", {"type": "object", "properties": {}}
         )
diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py
index cb26a22edf..2ec27a7af0 100644
--- a/litellm/llms/bedrock/chat/converse_transformation.py
+++ b/litellm/llms/bedrock/chat/converse_transformation.py
@@ -298,6 +298,39 @@ class AmazonConverseConfig(BaseConfig):
         # Check if the model is specifically Nova Lite 2
         return "nova-2-lite" in model_without_region
 
+    def _map_web_search_options(
+        self,
+        web_search_options: dict,
+        model: str
+    ) -> Optional[BedrockToolBlock]:
+        """
+        Map web_search_options to Nova grounding systemTool.
+
+        Nova grounding (web search) is only supported on Amazon Nova models.
+        Returns None for non-Nova models.
+
+        Args:
+            web_search_options: The web_search_options dict from the request
+            model: The model identifier string
+
+        Returns:
+            BedrockToolBlock with systemTool for Nova models, None otherwise
+
+        Reference: https://docs.aws.amazon.com/nova/latest/userguide/grounding.html
+        """
+        # Only Nova models support nova_grounding
+        # Model strings can be like: "amazon.nova-pro-v1:0", "us.amazon.nova-pro-v1:0", etc.
+        if "nova" not in model.lower():
+            verbose_logger.debug(
+                f"web_search_options passed but model {model} is not a Nova model. "
+                "Nova grounding is only supported on Amazon Nova models."
+            )
+            return None
+
+        # Nova doesn't support search_context_size or user_location params
+        # (unlike Anthropic), so we just enable grounding with no options
+        return BedrockToolBlock(systemTool={"name": "nova_grounding"})
+
     def _transform_reasoning_effort_to_reasoning_config(
         self, reasoning_effort: str
     ) -> dict:
@@ -438,6 +471,10 @@ class AmazonConverseConfig(BaseConfig):
         ):
             supported_params.append("tools")
 
+        # Nova models support web_search_options (mapped to nova_grounding systemTool)
+        if base_model.startswith("amazon.nova"):
+            supported_params.append("web_search_options")
+
         if litellm.utils.supports_tool_choice(
             model=model, custom_llm_provider=self.custom_llm_provider
         ) or litellm.utils.supports_tool_choice(
@@ -730,6 +767,13 @@ class AmazonConverseConfig(BaseConfig):
                 if bedrock_tier in ("default", "flex", "priority"):
                     optional_params["serviceTier"] = {"type": bedrock_tier}
 
+            if param == "web_search_options" and value and isinstance(value, dict):                                                                                 
+                grounding_tool = self._map_web_search_options(value, model)                                                                                         
+                if grounding_tool is not None:                                                                                                                      
+                    optional_params = self._add_tools_to_optional_params(                                                                                           
+                        optional_params=optional_params, tools=[grounding_tool]                                                                                     
+                    )  
+
         # Only update thinking tokens for non-GPT-OSS models and non-Nova-Lite-2 models
         # Nova Lite 2 handles token budgeting differently through reasoningConfig
         if "gpt-oss" not in model and not self._is_nova_lite_2_model(model):
@@ -1388,20 +1432,23 @@ class AmazonConverseConfig(BaseConfig):
         str,
         List[ChatCompletionToolCallChunk],
         Optional[List[BedrockConverseReasoningContentBlock]],
+        Optional[List[CitationsContentBlock]],
     ]:
         """
-        Translate the message content to a string and a list of tool calls and reasoning content blocks
+        Translate the message content to a string and a list of tool calls, reasoning content blocks, and citations.
 
         Returns:
             content_str: str
             tools: List[ChatCompletionToolCallChunk]
             reasoningContentBlocks: Optional[List[BedrockConverseReasoningContentBlock]]
+            citationsContentBlocks: Optional[List[CitationsContentBlock]] - Citations from Nova grounding
         """
         content_str = ""
         tools: List[ChatCompletionToolCallChunk] = []
         reasoningContentBlocks: Optional[List[BedrockConverseReasoningContentBlock]] = (
             None
         )
+        citationsContentBlocks: Optional[List[CitationsContentBlock]] = None
         for idx, content in enumerate(content_blocks):
             """
             - Content is either a tool response or text
@@ -1446,8 +1493,13 @@ class AmazonConverseConfig(BaseConfig):
                 if reasoningContentBlocks is None:
                     reasoningContentBlocks = []
                 reasoningContentBlocks.append(content["reasoningContent"])
+            # Handle Nova grounding citations content
+            if "citationsContent" in content:
+                if citationsContentBlocks is None:
+                    citationsContentBlocks = []
+                citationsContentBlocks.append(content["citationsContent"])
 
-        return content_str, tools, reasoningContentBlocks
+        return content_str, tools, reasoningContentBlocks, citationsContentBlocks
 
     def _transform_response(
         self,
@@ -1525,18 +1577,27 @@ class AmazonConverseConfig(BaseConfig):
         reasoningContentBlocks: Optional[List[BedrockConverseReasoningContentBlock]] = (
             None
         )
+        citationsContentBlocks: Optional[List[CitationsContentBlock]] = None
 
         if message is not None:
             (
                 content_str,
                 tools,
                 reasoningContentBlocks,
+                citationsContentBlocks,
             ) = self._translate_message_content(message["content"])
 
+        # Initialize provider_specific_fields if we have any special content blocks
+        provider_specific_fields: dict = {}
+        if reasoningContentBlocks is not None:
+            provider_specific_fields["reasoningContentBlocks"] = reasoningContentBlocks
+        if citationsContentBlocks is not None:
+            provider_specific_fields["citationsContent"] = citationsContentBlocks
+
+        if provider_specific_fields:
+            chat_completion_message["provider_specific_fields"] = provider_specific_fields
+
         if reasoningContentBlocks is not None:
-            chat_completion_message["provider_specific_fields"] = {
-                "reasoningContentBlocks": reasoningContentBlocks,
-            }
             chat_completion_message["reasoning_content"] = (
                 self._transform_reasoning_content(reasoningContentBlocks)
             )
diff --git a/litellm/llms/bedrock/chat/invoke_handler.py b/litellm/llms/bedrock/chat/invoke_handler.py
index dfa1f02a15..77d2a3c0c2 100644
--- a/litellm/llms/bedrock/chat/invoke_handler.py
+++ b/litellm/llms/bedrock/chat/invoke_handler.py
@@ -1476,6 +1476,11 @@ class AWSEventStreamDecoder:
                 reasoning_content = (
                     ""  # set to non-empty string to ensure consistency with Anthropic
                 )
+        elif "citationsContent" in delta_obj:
+            # Handle Nova grounding citations in streaming responses
+            provider_specific_fields = {
+                "citationsContent": delta_obj["citationsContent"],
+            }
         return (
             text,
             tool_use,
diff --git a/litellm/types/llms/bedrock.py b/litellm/types/llms/bedrock.py
index ef2f1ba4d5..a85aaafe23 100644
--- a/litellm/types/llms/bedrock.py
+++ b/litellm/types/llms/bedrock.py
@@ -93,6 +93,67 @@ class GuardrailConverseContentBlock(TypedDict, total=False):
     text: GuardrailConverseTextBlock
 
 
+class CitationWebLocationBlock(TypedDict, total=False):
+    """
+    Web location block for Nova grounding citations.
+    Contains the URL and domain from web search results.
+
+    Reference: https://docs.aws.amazon.com/nova/latest/userguide/grounding.html
+    """
+
+    url: str
+    domain: str
+
+
+class CitationLocationBlock(TypedDict, total=False):
+    """
+    Location block containing the web location for a citation.
+    """
+
+    web: CitationWebLocationBlock
+
+
+class CitationReferenceBlock(TypedDict, total=False):
+    """
+    Citation reference block containing a single citation with its location.
+
+    Each citation contains:
+    - location.web.url: The URL of the source
+    - location.web.domain: The domain of the source
+    """
+
+    location: CitationLocationBlock
+
+
+class CitationsContentBlock(TypedDict, total=False):
+    """
+    Citations content block returned by Nova grounding (web search) tool.
+
+    When Nova grounding is enabled via systemTool, the model may return
+    citationsContent blocks containing web search citation references.
+
+    Reference: https://docs.aws.amazon.com/nova/latest/userguide/grounding.html
+
+    Example response structure:
+        {
+            "citationsContent": {
+                "citations": [
+                    {
+                        "location": {
+                            "web": {
+                                "url": "https://example.com/article",
+                                "domain": "example.com"
+                            }
+                        }
+                    }
+                ]
+            }
+        }
+    """
+
+    citations: List[CitationReferenceBlock]
+
+
 class ContentBlock(TypedDict, total=False):
     text: str
     image: ImageBlock
@@ -103,6 +164,7 @@ class ContentBlock(TypedDict, total=False):
     cachePoint: CachePointBlock
     reasoningContent: BedrockConverseReasoningContentBlock
     guardContent: GuardrailConverseContentBlock
+    citationsContent: CitationsContentBlock
 
 
 class MessageBlock(TypedDict):
@@ -159,8 +221,24 @@ class ToolSpecBlock(TypedDict, total=False):
     description: str
 
 
+class SystemToolBlock(TypedDict, total=False):
+    """
+    System tool block for Nova grounding and other built-in tools.
+
+    Example:
+        {
+            "systemTool": {
+                "name": "nova_grounding"
+            }
+        }
+    """
+
+    name: Required[str]
+
+
 class ToolBlock(TypedDict, total=False):
     toolSpec: Optional[ToolSpecBlock]
+    systemTool: Optional[SystemToolBlock]
     cachePoint: Optional[CachePointBlock]
 
 
@@ -210,11 +288,13 @@ class ContentBlockStartEvent(TypedDict, total=False):
 class ContentBlockDeltaEvent(TypedDict, total=False):
     """
     Either 'text' or 'toolUse' will be specified for Converse API streaming response.
+    May also include 'citationsContent' when Nova grounding is enabled.
     """
 
     text: str
     toolUse: ToolBlockDeltaEvent
     reasoningContent: BedrockConverseReasoningContentBlockDelta
+    citationsContent: CitationsContentBlock
 
 
 class PerformanceConfigBlock(TypedDict):
@@ -879,3 +959,8 @@ class BedrockGetBatchResponse(TypedDict, total=False):
     outputDataConfig: BedrockOutputDataConfig
     timeoutDurationInHours: Optional[int]
     clientRequestToken: Optional[str]
+
+class BedrockToolBlock(TypedDict, total=False):
+    toolSpec: Optional[ToolSpecBlock]
+    systemTool: Optional[SystemToolBlock]  # For Nova grounding
+    cachePoint: Optional[CachePointBlock]
diff --git a/poetry.lock b/poetry.lock
index c5f5a87894..e5ef1750da 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -275,7 +275,7 @@ files = [
     {file = "annotated_doc-0.0.4-py3-none-any.whl", hash = "sha256:571ac1dc6991c450b25a9c2d84a3705e2ae7a53467b5d111c24fa8baabbed320"},
     {file = "annotated_doc-0.0.4.tar.gz", hash = "sha256:fbcda96e87e9c92ad167c2e53839e57503ecfda18804ea28102353485033faa4"},
 ]
-markers = {main = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"proxy\") or extra == \"proxy\""}
+markers = {main = "(extra == \"mlflow\" or extra == \"proxy\") and python_version >= \"3.10\" or extra == \"proxy\""}
 
 [[package]]
 name = "annotated-types"
@@ -343,7 +343,7 @@ zookeeper = ["kazoo"]
 name = "async-timeout"
 version = "5.0.1"
 description = "Timeout context manager for asyncio programs"
-optional = true
+optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 markers = "python_full_version < \"3.11.3\" and (extra == \"extra-proxy\" or extra == \"proxy\" or python_version < \"3.11\")"
@@ -557,48 +557,48 @@ files = [
 
 [[package]]
 name = "boto3"
-version = "1.36.0"
+version = "1.40.76"
 description = "The AWS SDK for Python"
 optional = true
-python-versions = ">=3.8"
+python-versions = ">=3.9"
 groups = ["main"]
 markers = "extra == \"proxy\""
 files = [
-    {file = "boto3-1.36.0-py3-none-any.whl", hash = "sha256:d0ca7a58ce25701a52232cc8df9d87854824f1f2964b929305722ebc7959d5a9"},
-    {file = "boto3-1.36.0.tar.gz", hash = "sha256:159898f51c2997a12541c0e02d6e5a8fe2993ddb307b9478fd9a339f98b57e00"},
+    {file = "boto3-1.40.76-py3-none-any.whl", hash = "sha256:8df6df755727be40ad9e309cfda07f9a12c147e17b639430c55d4e4feee8a167"},
+    {file = "boto3-1.40.76.tar.gz", hash = "sha256:16f4cf97f8dd8e0aae015f4dc66219bd7716a91a40d1e2daa0dafa241a4761c5"},
 ]
 
 [package.dependencies]
-botocore = ">=1.36.0,<1.37.0"
+botocore = ">=1.40.76,<1.41.0"
 jmespath = ">=0.7.1,<2.0.0"
-s3transfer = ">=0.11.0,<0.12.0"
+s3transfer = ">=0.14.0,<0.15.0"
 
 [package.extras]
 crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]
 
 [[package]]
 name = "botocore"
-version = "1.36.26"
+version = "1.40.76"
 description = "Low-level, data-driven core of boto 3."
 optional = true
-python-versions = ">=3.8"
+python-versions = ">=3.9"
 groups = ["main"]
 markers = "extra == \"proxy\""
 files = [
-    {file = "botocore-1.36.26-py3-none-any.whl", hash = "sha256:4e3f19913887a58502e71ef8d696fe7eaa54de7813ff73390cd5883f837dfa6e"},
-    {file = "botocore-1.36.26.tar.gz", hash = "sha256:4a63bcef7ecf6146fd3a61dc4f9b33b7473b49bdaf1770e9aaca6eee0c9eab62"},
+    {file = "botocore-1.40.76-py3-none-any.whl", hash = "sha256:fe425d386e48ac64c81cbb4a7181688d813df2e2b4c78b95ebe833c9e868c6f4"},
+    {file = "botocore-1.40.76.tar.gz", hash = "sha256:2b16024d68b29b973005adfb5039adfe9099ebe772d40a90ca89f2e165c495dc"},
 ]
 
 [package.dependencies]
 jmespath = ">=0.7.1,<2.0.0"
 python-dateutil = ">=2.1,<3.0.0"
 urllib3 = [
-    {version = ">=1.25.4,<2.2.0 || >2.2.0,<3", markers = "python_version >= \"3.10\""},
     {version = ">=1.25.4,<1.27", markers = "python_version < \"3.10\""},
+    {version = ">=1.25.4,<2.2.0 || >2.2.0,<3", markers = "python_version >= \"3.10\""},
 ]
 
 [package.extras]
-crt = ["awscrt (==0.23.8)"]
+crt = ["awscrt (==0.28.4)"]
 
 [[package]]
 name = "cachetools"
@@ -607,7 +607,7 @@ description = "Extensible memoizing collections and decorators"
 optional = true
 python-versions = ">=3.9"
 groups = ["main"]
-markers = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"extra-proxy\") or extra == \"extra-proxy\""
+markers = "(extra == \"extra-proxy\" or extra == \"google\" or extra == \"mlflow\") and python_version >= \"3.10\" or extra == \"google\" or extra == \"extra-proxy\""
 files = [
     {file = "cachetools-6.2.2-py3-none-any.whl", hash = "sha256:6c09c98183bf58560c97b2abfcedcbaf6a896a490f534b031b661d3723b45ace"},
     {file = "cachetools-6.2.2.tar.gz", hash = "sha256:8e6d266b25e539df852251cfd6f990b4bc3a141db73b939058d809ebd2590fc6"},
@@ -1393,6 +1393,24 @@ docs = ["myst-parser (==0.18.0)", "sphinx (==5.1.1)"]
 ssh = ["paramiko (>=2.4.3)"]
 websockets = ["websocket-client (>=1.3.0)"]
 
+[[package]]
+name = "docstring-parser"
+version = "0.17.0"
+description = "Parse Python docstrings in reST, Google and Numpydoc format"
+optional = true
+python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"google\""
+files = [
+    {file = "docstring_parser-0.17.0-py3-none-any.whl", hash = "sha256:cf2569abd23dce8099b300f9b4fa8191e9582dda731fd533daf54c4551658708"},
+    {file = "docstring_parser-0.17.0.tar.gz", hash = "sha256:583de4a309722b3315439bb31d64ba3eebada841f2e2cee23b99df001434c912"},
+]
+
+[package.extras]
+dev = ["pre-commit (>=2.16.0) ; python_version >= \"3.9\"", "pydoctor (>=25.4.0)", "pytest"]
+docs = ["pydoctor (>=25.4.0)"]
+test = ["pytest"]
+
 [[package]]
 name = "docutils"
 version = "0.21.2"
@@ -1453,7 +1471,7 @@ files = [
     {file = "fastapi-0.121.3-py3-none-any.whl", hash = "sha256:0c78fc87587fcd910ca1bbf5bc8ba37b80e119b388a7206b39f0ecc95ebf53e9"},
     {file = "fastapi-0.121.3.tar.gz", hash = "sha256:0055bc24fe53e56a40e9e0ad1ae2baa81622c406e548e501e717634e2dfbc40b"},
 ]
-markers = {main = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"proxy\") or extra == \"proxy\""}
+markers = {main = "(extra == \"mlflow\" or extra == \"proxy\") and python_version >= \"3.10\" or extra == \"proxy\""}
 
 [package.dependencies]
 annotated-doc = ">=0.0.2"
@@ -1982,7 +2000,7 @@ description = "Google API client core library"
 optional = true
 python-versions = ">=3.7"
 groups = ["main"]
-markers = "python_version >= \"3.14\" and extra == \"extra-proxy\""
+markers = "python_version >= \"3.14\" and (extra == \"extra-proxy\" or extra == \"google\")"
 files = [
     {file = "google_api_core-2.25.2-py3-none-any.whl", hash = "sha256:e9a8f62d363dc8424a8497f4c2a47d6bcda6c16514c935629c257ab5d10210e7"},
     {file = "google_api_core-2.25.2.tar.gz", hash = "sha256:1c63aa6af0d0d5e37966f157a77f9396d820fba59f9e43e9415bc3dc5baff300"},
@@ -2010,7 +2028,7 @@ description = "Google API client core library"
 optional = true
 python-versions = ">=3.7"
 groups = ["main"]
-markers = "extra == \"extra-proxy\" and python_version < \"3.14\""
+markers = "python_version == \"3.9\" and (extra == \"google\" or extra == \"extra-proxy\") or python_version < \"3.14\" and (extra == \"extra-proxy\" or extra == \"google\")"
 files = [
     {file = "google_api_core-2.28.1-py3-none-any.whl", hash = "sha256:4021b0f8ceb77a6fb4de6fde4502cecab45062e66ff4f2895169e0b35bc9466c"},
     {file = "google_api_core-2.28.1.tar.gz", hash = "sha256:2b405df02d68e68ce0fbc138559e6036559e685159d148ae5861013dc201baf8"},
@@ -2020,12 +2038,12 @@ files = [
 google-auth = ">=2.14.1,<3.0.0"
 googleapis-common-protos = ">=1.56.2,<2.0.0"
 grpcio = [
+    {version = ">=1.33.2,<2.0.0", optional = true, markers = "extra == \"grpc\""},
     {version = ">=1.49.1,<2.0.0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
-    {version = ">=1.33.2,<2.0.0", optional = true, markers = "python_version < \"3.11\" and extra == \"grpc\""},
 ]
 grpcio-status = [
-    {version = ">=1.49.1,<2.0.0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
     {version = ">=1.33.2,<2.0.0", optional = true, markers = "extra == \"grpc\""},
+    {version = ">=1.49.1,<2.0.0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
 ]
 proto-plus = [
     {version = ">=1.22.3,<2.0.0"},
@@ -2047,7 +2065,7 @@ description = "Google Authentication Library"
 optional = true
 python-versions = ">=3.7"
 groups = ["main"]
-markers = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"extra-proxy\") or extra == \"extra-proxy\""
+markers = "(extra == \"extra-proxy\" or extra == \"google\" or extra == \"mlflow\") and python_version >= \"3.10\" or extra == \"google\" or extra == \"extra-proxy\""
 files = [
     {file = "google_auth-2.43.0-py2.py3-none-any.whl", hash = "sha256:af628ba6fa493f75c7e9dbe9373d148ca9f4399b5ea29976519e0a3848eddd16"},
     {file = "google_auth-2.43.0.tar.gz", hash = "sha256:88228eee5fc21b62a1b5fe773ca15e67778cb07dc8363adcb4a8827b52d81483"},
@@ -2056,6 +2074,7 @@ files = [
 [package.dependencies]
 cachetools = ">=2.0.0,<7.0"
 pyasn1-modules = ">=0.2.1"
+requests = {version = ">=2.20.0,<3.0.0", optional = true, markers = "extra == \"requests\""}
 rsa = ">=3.1.4,<5"
 
 [package.extras]
@@ -2068,6 +2087,120 @@ requests = ["requests (>=2.20.0,<3.0.0)"]
 testing = ["aiohttp (<3.10.0)", "aiohttp (>=3.6.2,<4.0.0)", "aioresponses", "cryptography (<39.0.0) ; python_version < \"3.8\"", "cryptography (<39.0.0) ; python_version < \"3.8\"", "cryptography (>=38.0.3)", "cryptography (>=38.0.3)", "flask", "freezegun", "grpcio", "mock", "oauth2client", "packaging", "pyjwt (>=2.0)", "pyopenssl (<24.3.0)", "pyopenssl (>=20.0.0)", "pytest", "pytest-asyncio", "pytest-cov", "pytest-localserver", "pyu2f (>=0.1.5)", "requests (>=2.20.0,<3.0.0)", "responses", "urllib3"]
 urllib3 = ["packaging", "urllib3"]
 
+[[package]]
+name = "google-cloud-aiplatform"
+version = "1.130.0"
+description = "Vertex AI API client library"
+optional = true
+python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"google\""
+files = [
+    {file = "google_cloud_aiplatform-1.130.0-py2.py3-none-any.whl", hash = "sha256:f578ccee55655dd9e2300cfcafb178e47c3dfdcf746ad465234b875d3e955929"},
+    {file = "google_cloud_aiplatform-1.130.0.tar.gz", hash = "sha256:f66aeb23f0a6848fc2d5bbdf1b5777c3cf8e06056f73ef815317abf89d5a0262"},
+]
+
+[package.dependencies]
+docstring_parser = "<1"
+google-api-core = {version = ">=1.34.1,<2.0.dev0 || >=2.8.dev0,<3.0.0", extras = ["grpc"]}
+google-auth = ">=2.14.1,<3.0.0"
+google-cloud-bigquery = ">=1.15.0,<3.20.0 || >3.20.0,<4.0.0"
+google-cloud-resource-manager = ">=1.3.3,<3.0.0"
+google-cloud-storage = [
+    {version = ">=1.32.0,<4.0.0", markers = "python_version < \"3.13\""},
+    {version = ">=2.10.0,<4.0.0", markers = "python_version >= \"3.13\""},
+]
+google-genai = ">=1.37.0,<2.0.0"
+packaging = ">=14.3"
+proto-plus = ">=1.22.3,<2.0.0"
+protobuf = ">=3.20.2,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<7.0.0"
+pydantic = "<3"
+shapely = "<3.0.0"
+typing_extensions = "*"
+
+[package.extras]
+adk = ["google-adk (>=1.0.0,<2.0.0)", "opentelemetry-instrumentation-google-genai (>=0.3b0,<1.0.0)"]
+ag2 = ["ag2[gemini]", "openinference-instrumentation-autogen (>=0.1.6,<0.2)"]
+ag2-testing = ["absl-py", "ag2[gemini]", "cloudpickle (>=3.0,<4.0)", "google-cloud-trace (<2)", "openinference-instrumentation-autogen (>=0.1.6,<0.2)", "opentelemetry-exporter-gcp-logging (>=1.11.0a0,<2.0.0)", "opentelemetry-exporter-gcp-trace (<2)", "opentelemetry-exporter-otlp-proto-http (<2)", "opentelemetry-sdk (<2)", "pydantic (>=2.11.1,<3)", "pytest-xdist", "typing_extensions"]
+agent-engines = ["cloudpickle (>=3.0,<4.0)", "google-cloud-logging (<4)", "google-cloud-trace (<2)", "opentelemetry-exporter-gcp-logging (>=1.11.0a0,<2.0.0)", "opentelemetry-exporter-gcp-trace (<2)", "opentelemetry-exporter-otlp-proto-http (<2)", "opentelemetry-sdk (<2)", "packaging (>=24.0)", "pydantic (>=2.11.1,<3)", "typing_extensions"]
+autologging = ["mlflow (>=1.27.0) ; python_version >= \"3.13\"", "mlflow (>=1.27.0,<=2.16.0) ; python_version < \"3.13\""]
+cloud-profiler = ["tensorboard-plugin-profile (>=2.4.0,<2.18.0)", "werkzeug (>=2.0.0,<4.0.0)"]
+datasets = ["pyarrow (>=10.0.1) ; python_version == \"3.11\"", "pyarrow (>=14.0.0) ; python_version >= \"3.12\"", "pyarrow (>=3.0.0,<8.0.0) ; python_version < \"3.11\""]
+endpoint = ["requests (>=2.28.1)", "requests-toolbelt (<=1.0.0)"]
+evaluation = ["jsonschema", "litellm (>=1.72.4,!=1.77.2,!=1.77.3,!=1.77.4)", "pandas (>=1.0.0)", "pyyaml", "ruamel.yaml", "scikit-learn (<1.6.0) ; python_version <= \"3.10\"", "scikit-learn ; python_version > \"3.10\"", "tqdm (>=4.23.0)"]
+full = ["docker (>=5.0.3)", "explainable-ai-sdk (>=1.0.0) ; python_version < \"3.13\"", "fastapi (>=0.71.0,<=0.114.0)", "google-cloud-bigquery", "google-cloud-bigquery-storage", "google-vizier (>=0.1.6)", "httpx (>=0.23.0,<=0.28.1)", "immutabledict", "jsonschema", "lit-nlp (==0.4.0) ; python_version < \"3.14\"", "litellm (>=1.72.4,!=1.77.2,!=1.77.3,!=1.77.4)", "mlflow (>=1.27.0) ; python_version >= \"3.13\"", "mlflow (>=1.27.0,<=2.16.0) ; python_version < \"3.13\"", "numpy (>=1.15.0)", "pandas (>=1.0.0)", "pyarrow (>=10.0.1) ; python_version == \"3.11\"", "pyarrow (>=14.0.0) ; python_version >= \"3.12\"", "pyarrow (>=3.0.0,<8.0.0) ; python_version < \"3.11\"", "pyarrow (>=6.0.1)", "pyyaml", "pyyaml (>=5.3.1,<7)", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<2.10.dev0 || ==2.33.* || >=2.42.dev0,<=2.42.0) ; python_version < \"3.11\"", "ray[default] (>=2.5,<=2.47.1) ; python_version == \"3.11\"", "requests (>=2.28.1)", "requests-toolbelt (<=1.0.0)", "ruamel.yaml", "scikit-learn (<1.6.0) ; python_version <= \"3.10\"", "scikit-learn ; python_version > \"3.10\"", "starlette (>=0.17.1)", "tensorboard-plugin-profile (>=2.4.0,<2.18.0)", "tensorflow (>=2.3.0,<3.0.0) ; python_version < \"3.13\"", "tensorflow (>=2.3.0,<3.0.0) ; python_version < \"3.13\"", "tqdm (>=4.23.0)", "urllib3 (>=1.21.1,<1.27)", "uvicorn[standard] (>=0.16.0)", "werkzeug (>=2.0.0,<4.0.0)"]
+langchain = ["langchain (>=0.3,<0.4)", "langchain-core (>=0.3,<0.4)", "langchain-google-vertexai (>=2.0.22,<3)", "langgraph (>=0.2.45,<0.4)", "openinference-instrumentation-langchain (>=0.1.19,<0.2)"]
+langchain-testing = ["absl-py", "cloudpickle (>=3.0,<4.0)", "google-cloud-trace (<2)", "langchain (>=0.3,<0.4)", "langchain-core (>=0.3,<0.4)", "langchain-google-vertexai (>=2.0.22,<3)", "langgraph (>=0.2.45,<0.4)", "openinference-instrumentation-langchain (>=0.1.19,<0.2)", "opentelemetry-exporter-gcp-logging (>=1.11.0a0,<2.0.0)", "opentelemetry-exporter-gcp-trace (<2)", "opentelemetry-exporter-otlp-proto-http (<2)", "opentelemetry-sdk (<2)", "pydantic (>=2.11.1,<3)", "pytest-xdist", "typing_extensions"]
+lit = ["explainable-ai-sdk (>=1.0.0) ; python_version < \"3.13\"", "lit-nlp (==0.4.0) ; python_version < \"3.14\"", "pandas (>=1.0.0)", "tensorflow (>=2.3.0,<3.0.0) ; python_version < \"3.13\""]
+llama-index = ["llama-index", "llama-index-llms-google-genai", "openinference-instrumentation-llama-index (>=3.0,<4.0)"]
+llama-index-testing = ["absl-py", "cloudpickle (>=3.0,<4.0)", "google-cloud-trace (<2)", "llama-index", "llama-index-llms-google-genai", "openinference-instrumentation-llama-index (>=3.0,<4.0)", "opentelemetry-exporter-gcp-logging (>=1.11.0a0,<2.0.0)", "opentelemetry-exporter-gcp-trace (<2)", "opentelemetry-exporter-otlp-proto-http (<2)", "opentelemetry-sdk (<2)", "pydantic (>=2.11.1,<3)", "pytest-xdist", "typing_extensions"]
+metadata = ["numpy (>=1.15.0)", "pandas (>=1.0.0)"]
+pipelines = ["pyyaml (>=5.3.1,<7)"]
+prediction = ["docker (>=5.0.3)", "fastapi (>=0.71.0,<=0.114.0)", "httpx (>=0.23.0,<=0.28.1)", "starlette (>=0.17.1)", "uvicorn[standard] (>=0.16.0)"]
+private-endpoints = ["requests (>=2.28.1)", "urllib3 (>=1.21.1,<1.27)"]
+ray = ["google-cloud-bigquery", "google-cloud-bigquery-storage", "immutabledict", "pandas (>=1.0.0)", "pyarrow (>=6.0.1)", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<2.10.dev0 || ==2.33.* || >=2.42.dev0,<=2.42.0) ; python_version < \"3.11\"", "ray[default] (>=2.5,<=2.47.1) ; python_version == \"3.11\""]
+ray-testing = ["google-cloud-bigquery", "google-cloud-bigquery-storage", "immutabledict", "pandas (>=1.0.0)", "pyarrow (>=6.0.1)", "pytest-xdist", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<2.10.dev0 || ==2.33.* || >=2.42.dev0,<=2.42.0) ; python_version < \"3.11\"", "ray[default] (>=2.5,<=2.47.1) ; python_version == \"3.11\"", "ray[train]", "scikit-learn (<1.6.0)", "tensorflow ; python_version < \"3.13\"", "torch (>=2.0.0,<2.1.0)", "xgboost", "xgboost_ray"]
+reasoningengine = ["cloudpickle (>=3.0,<4.0)", "google-cloud-trace (<2)", "opentelemetry-exporter-gcp-logging (>=1.11.0a0,<2.0.0)", "opentelemetry-exporter-gcp-trace (<2)", "opentelemetry-exporter-otlp-proto-http (<2)", "opentelemetry-sdk (<2)", "pydantic (>=2.11.1,<3)", "typing_extensions"]
+tensorboard = ["tensorboard-plugin-profile (>=2.4.0,<2.18.0)", "werkzeug (>=2.0.0,<4.0.0)"]
+testing = ["Pillow", "aiohttp", "bigframes ; python_version >= \"3.10\" and python_version < \"3.14\"", "docker (>=5.0.3)", "explainable-ai-sdk (>=1.0.0) ; python_version < \"3.13\"", "fastapi (>=0.71.0,<=0.114.0)", "google-api-core (>=2.11,<3.0.0)", "google-cloud-bigquery", "google-cloud-bigquery-storage", "google-vizier (>=0.1.6)", "google-vizier (>=0.1.6)", "grpcio-testing", "grpcio-tools (>=1.63.0) ; python_version >= \"3.13\"", "httpx (>=0.23.0,<=0.28.1)", "immutabledict", "immutabledict", "ipython", "jsonschema", "kfp (>=2.6.0,<3.0.0) ; python_version < \"3.13\"", "lit-nlp (==0.4.0) ; python_version < \"3.14\"", "litellm (>=1.72.4,!=1.77.2,!=1.77.3,!=1.77.4)", "mlflow (>=1.27.0) ; python_version >= \"3.13\"", "mlflow (>=1.27.0,<=2.16.0) ; python_version < \"3.13\"", "mock", "nltk", "numpy (>=1.15.0)", "pandas (>=1.0.0)", "protobuf (<=5.29.4)", "pyarrow (>=10.0.1) ; python_version == \"3.11\"", "pyarrow (>=14.0.0) ; python_version >= \"3.12\"", "pyarrow (>=3.0.0,<8.0.0) ; python_version < \"3.11\"", "pyarrow (>=6.0.1)", "pytest-asyncio", "pytest-cov", "pytest-xdist", "pyyaml", "pyyaml (>=5.3.1,<7)", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<2.10.dev0 || ==2.33.* || >=2.42.dev0,<=2.42.0) ; python_version < \"3.11\"", "ray[default] (>=2.5,<=2.47.1) ; python_version == \"3.11\"", "requests (>=2.28.1)", "requests-toolbelt (<=1.0.0)", "requests-toolbelt (<=1.0.0)", "ruamel.yaml", "scikit-learn (<1.6.0) ; python_version <= \"3.10\"", "scikit-learn (<1.6.0) ; python_version <= \"3.10\"", "scikit-learn ; python_version > \"3.10\"", "scikit-learn ; python_version > \"3.10\"", "sentencepiece (>=0.2.0)", "starlette (>=0.17.1)", "tensorboard-plugin-profile (>=2.4.0,<2.18.0)", "tensorboard-plugin-profile (>=2.4.0,<2.18.0)", "tensorflow (==2.14.1) ; python_version <= \"3.11\"", "tensorflow (==2.19.0) ; python_version > \"3.11\" and python_version < \"3.13\"", "tensorflow (>=2.3.0,<3.0.0) ; python_version < \"3.13\"", "tensorflow (>=2.3.0,<3.0.0) ; python_version < \"3.13\"", "torch (>=2.0.0,<2.1.0) ; python_version <= \"3.11\"", "torch (>=2.2.0) ; python_version > \"3.11\" and python_version < \"3.13\"", "tqdm (>=4.23.0)", "urllib3 (>=1.21.1,<1.27)", "uvicorn[standard] (>=0.16.0)", "werkzeug (>=2.0.0,<4.0.0)", "werkzeug (>=2.0.0,<4.0.0)", "xgboost"]
+tokenization = ["sentencepiece (>=0.2.0)"]
+vizier = ["google-vizier (>=0.1.6)"]
+xai = ["tensorflow (>=2.3.0,<3.0.0) ; python_version < \"3.13\""]
+
+[[package]]
+name = "google-cloud-bigquery"
+version = "3.40.0"
+description = "Google BigQuery API client library"
+optional = true
+python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"google\""
+files = [
+    {file = "google_cloud_bigquery-3.40.0-py3-none-any.whl", hash = "sha256:0469bcf9e3dad3cab65b67cce98180c8c0aacf3253d47f0f8e976f299b49b5ab"},
+    {file = "google_cloud_bigquery-3.40.0.tar.gz", hash = "sha256:b3ccb11caf0029f15b29569518f667553fe08f6f1459b959020c83fbbd8f2e68"},
+]
+
+[package.dependencies]
+google-api-core = {version = ">=2.11.1,<3.0.0", extras = ["grpc"]}
+google-auth = ">=2.14.1,<3.0.0"
+google-cloud-core = ">=2.4.1,<3.0.0"
+google-resumable-media = ">=2.0.0,<3.0.0"
+packaging = ">=24.2.0"
+python-dateutil = ">=2.8.2,<3.0.0"
+requests = ">=2.21.0,<3.0.0"
+
+[package.extras]
+all = ["google-cloud-bigquery[bigquery-v2,bqstorage,geopandas,ipython,ipywidgets,matplotlib,opentelemetry,pandas,tqdm]"]
+bigquery-v2 = ["proto-plus (>=1.22.3,<2.0.0)", "protobuf (>=3.20.2,!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<7.0.0)"]
+bqstorage = ["google-cloud-bigquery-storage (>=2.18.0,<3.0.0)", "grpcio (>=1.47.0,<2.0.0)", "grpcio (>=1.49.1,<2.0.0) ; python_version >= \"3.11\"", "grpcio (>=1.75.1,<2.0.0) ; python_version >= \"3.14\"", "pyarrow (>=4.0.0)"]
+geopandas = ["Shapely (>=1.8.4,<3.0.0)", "geopandas (>=0.9.0,<2.0.0)"]
+ipython = ["bigquery-magics (>=0.6.0)", "ipython (>=7.23.1)"]
+ipywidgets = ["ipykernel (>=6.2.0)", "ipywidgets (>=7.7.1)"]
+matplotlib = ["matplotlib (>=3.10.3) ; python_version >= \"3.10\"", "matplotlib (>=3.7.1,<=3.9.2) ; python_version == \"3.9\""]
+opentelemetry = ["opentelemetry-api (>=1.1.0)", "opentelemetry-instrumentation (>=0.20b0)", "opentelemetry-sdk (>=1.1.0)"]
+pandas = ["db-dtypes (>=1.0.4,<2.0.0)", "grpcio (>=1.47.0,<2.0.0)", "grpcio (>=1.49.1,<2.0.0) ; python_version >= \"3.11\"", "grpcio (>=1.75.1,<2.0.0) ; python_version >= \"3.14\"", "pandas (>=1.3.0)", "pandas-gbq (>=0.26.1)", "pyarrow (>=3.0.0)"]
+tqdm = ["tqdm (>=4.23.4,<5.0.0)"]
+
+[[package]]
+name = "google-cloud-core"
+version = "2.5.0"
+description = "Google Cloud API client core library"
+optional = true
+python-versions = ">=3.7"
+groups = ["main"]
+markers = "extra == \"google\""
+files = [
+    {file = "google_cloud_core-2.5.0-py3-none-any.whl", hash = "sha256:67d977b41ae6c7211ee830c7912e41003ea8194bff15ae7d72fd6f51e57acabc"},
+    {file = "google_cloud_core-2.5.0.tar.gz", hash = "sha256:7c1b7ef5c92311717bd05301aa1a91ffbc565673d3b0b4163a52d8413a186963"},
+]
+
+[package.dependencies]
+google-api-core = ">=1.31.6,<2.0.dev0 || >2.3.0,<3.0.0"
+google-auth = ">=1.25.0,<3.0.0"
+
+[package.extras]
+grpc = ["grpcio (>=1.38.0,<2.0.0) ; python_version < \"3.14\"", "grpcio (>=1.75.1,<2.0.0) ; python_version >= \"3.14\"", "grpcio-status (>=1.38.0,<2.0.0)"]
+
 [[package]]
 name = "google-cloud-iam"
 version = "2.20.0"
@@ -2115,6 +2248,204 @@ grpc-google-iam-v1 = ">=0.12.4,<1.0.0dev"
 proto-plus = ">=1.22.3,<2.0.0dev"
 protobuf = ">=3.20.2,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<6.0.0dev"
 
+[[package]]
+name = "google-cloud-resource-manager"
+version = "1.16.0"
+description = "Google Cloud Resource Manager API client library"
+optional = true
+python-versions = ">=3.7"
+groups = ["main"]
+markers = "extra == \"google\""
+files = [
+    {file = "google_cloud_resource_manager-1.16.0-py3-none-any.whl", hash = "sha256:fb9a2ad2b5053c508e1c407ac31abfd1a22e91c32876c1892830724195819a28"},
+    {file = "google_cloud_resource_manager-1.16.0.tar.gz", hash = "sha256:cc938f87cc36c2672f062b1e541650629e0d954c405a4dac35ceedee70c267c3"},
+]
+
+[package.dependencies]
+google-api-core = {version = ">=1.34.1,<2.0.dev0 || >=2.11.dev0,<3.0.0", extras = ["grpc"]}
+google-auth = ">=2.14.1,<2.24.0 || >2.24.0,<2.25.0 || >2.25.0,<3.0.0"
+grpc-google-iam-v1 = ">=0.14.0,<1.0.0"
+grpcio = [
+    {version = ">=1.33.2,<2.0.0"},
+    {version = ">=1.75.1,<2.0.0", markers = "python_version >= \"3.14\""},
+]
+proto-plus = [
+    {version = ">=1.22.3,<2.0.0"},
+    {version = ">=1.25.0,<2.0.0", markers = "python_version >= \"3.13\""},
+]
+protobuf = ">=3.20.2,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<7.0.0"
+
+[[package]]
+name = "google-cloud-storage"
+version = "3.4.1"
+description = "Google Cloud Storage API client library"
+optional = true
+python-versions = ">=3.7"
+groups = ["main"]
+markers = "extra == \"google\" and python_version >= \"3.14\""
+files = [
+    {file = "google_cloud_storage-3.4.1-py3-none-any.whl", hash = "sha256:972764cc0392aa097be8f49a5354e22eb47c3f62370067fb1571ffff4a1c1189"},
+    {file = "google_cloud_storage-3.4.1.tar.gz", hash = "sha256:6f041a297e23a4b485fad8c305a7a6e6831855c208bcbe74d00332a909f82268"},
+]
+
+[package.dependencies]
+google-api-core = ">=2.15.0,<3.0.0"
+google-auth = ">=2.26.1,<3.0.0"
+google-cloud-core = ">=2.4.2,<3.0.0"
+google-crc32c = ">=1.1.3,<2.0.0"
+google-resumable-media = ">=2.7.2,<3.0.0"
+requests = ">=2.22.0,<3.0.0"
+
+[package.extras]
+protobuf = ["protobuf (>=3.20.2,<7.0.0)"]
+tracing = ["opentelemetry-api (>=1.1.0,<2.0.0)"]
+
+[[package]]
+name = "google-cloud-storage"
+version = "3.8.0"
+description = "Google Cloud Storage API client library"
+optional = true
+python-versions = ">=3.7"
+groups = ["main"]
+markers = "extra == \"google\" and python_version < \"3.14\""
+files = [
+    {file = "google_cloud_storage-3.8.0-py3-none-any.whl", hash = "sha256:78cfeae7cac2ca9441d0d0271c2eb4ebfa21aa4c6944dd0ccac0389e81d955a7"},
+    {file = "google_cloud_storage-3.8.0.tar.gz", hash = "sha256:cc67952dce84ebc9d44970e24647a58260630b7b64d72360cedaf422d6727f28"},
+]
+
+[package.dependencies]
+google-api-core = ">=2.27.0,<3.0.0"
+google-auth = ">=2.26.1,<3.0.0"
+google-cloud-core = ">=2.4.2,<3.0.0"
+google-crc32c = ">=1.1.3,<2.0.0"
+google-resumable-media = ">=2.7.2,<3.0.0"
+requests = ">=2.22.0,<3.0.0"
+
+[package.extras]
+grpc = ["google-api-core[grpc] (>=2.27.0,<3.0.0)", "grpc-google-iam-v1 (>=0.14.0,<1.0.0)", "grpcio (>=1.33.2,<2.0.0) ; python_version < \"3.14\"", "grpcio (>=1.75.1,<2.0.0) ; python_version >= \"3.14\"", "grpcio-status (>=1.76.0,<2.0.0)", "proto-plus (>=1.22.3,<2.0.0) ; python_version < \"3.13\"", "proto-plus (>=1.25.0,<2.0.0) ; python_version >= \"3.13\"", "protobuf (>=3.20.2,!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<7.0.0)"]
+protobuf = ["protobuf (>=3.20.2,<7.0.0)"]
+tracing = ["opentelemetry-api (>=1.1.0,<2.0.0)"]
+
+[[package]]
+name = "google-crc32c"
+version = "1.8.0"
+description = "A python wrapper of the C library 'Google CRC32C'"
+optional = true
+python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"google\""
+files = [
+    {file = "google_crc32c-1.8.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:0470b8c3d73b5f4e3300165498e4cf25221c7eb37f1159e221d1825b6df8a7ff"},
+    {file = "google_crc32c-1.8.0-cp310-cp310-macosx_12_0_x86_64.whl", hash = "sha256:119fcd90c57c89f30040b47c211acee231b25a45d225e3225294386f5d258288"},
+    {file = "google_crc32c-1.8.0-cp310-cp310-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:6f35aaffc8ccd81ba3162443fabb920e65b1f20ab1952a31b13173a67811467d"},
+    {file = "google_crc32c-1.8.0-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:864abafe7d6e2c4c66395c1eb0fe12dc891879769b52a3d56499612ca93b6092"},
+    {file = "google_crc32c-1.8.0-cp310-cp310-win_amd64.whl", hash = "sha256:db3fe8eaf0612fc8b20fa21a5f25bd785bc3cd5be69f8f3412b0ac2ffd49e733"},
+    {file = "google_crc32c-1.8.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:014a7e68d623e9a4222d663931febc3033c5c7c9730785727de2a81f87d5bab8"},
+    {file = "google_crc32c-1.8.0-cp311-cp311-macosx_12_0_x86_64.whl", hash = "sha256:86cfc00fe45a0ac7359e5214a1704e51a99e757d0272554874f419f79838c5f7"},
+    {file = "google_crc32c-1.8.0-cp311-cp311-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:19b40d637a54cb71e0829179f6cb41835f0fbd9e8eb60552152a8b52c36cbe15"},
+    {file = "google_crc32c-1.8.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:17446feb05abddc187e5441a45971b8394ea4c1b6efd88ab0af393fd9e0a156a"},
+    {file = "google_crc32c-1.8.0-cp311-cp311-win_amd64.whl", hash = "sha256:71734788a88f551fbd6a97be9668a0020698e07b2bf5b3aa26a36c10cdfb27b2"},
+    {file = "google_crc32c-1.8.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:4b8286b659c1335172e39563ab0a768b8015e88e08329fa5321f774275fc3113"},
+    {file = "google_crc32c-1.8.0-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:2a3dc3318507de089c5384cc74d54318401410f82aa65b2d9cdde9d297aca7cb"},
+    {file = "google_crc32c-1.8.0-cp312-cp312-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:14f87e04d613dfa218d6135e81b78272c3b904e2a7053b841481b38a7d901411"},
+    {file = "google_crc32c-1.8.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cb5c869c2923d56cb0c8e6bcdd73c009c36ae39b652dbe46a05eb4ef0ad01454"},
+    {file = "google_crc32c-1.8.0-cp312-cp312-win_amd64.whl", hash = "sha256:3cc0c8912038065eafa603b238abf252e204accab2a704c63b9e14837a854962"},
+    {file = "google_crc32c-1.8.0-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:3ebb04528e83b2634857f43f9bb8ef5b2bbe7f10f140daeb01b58f972d04736b"},
+    {file = "google_crc32c-1.8.0-cp313-cp313-macosx_12_0_x86_64.whl", hash = "sha256:450dc98429d3e33ed2926fc99ee81001928d63460f8538f21a5d6060912a8e27"},
+    {file = "google_crc32c-1.8.0-cp313-cp313-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:3b9776774b24ba76831609ffbabce8cdf6fa2bd5e9df37b594221c7e333a81fa"},
+    {file = "google_crc32c-1.8.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:89c17d53d75562edfff86679244830599ee0a48efc216200691de8b02ab6b2b8"},
+    {file = "google_crc32c-1.8.0-cp313-cp313-win_amd64.whl", hash = "sha256:57a50a9035b75643996fbf224d6661e386c7162d1dfdab9bc4ca790947d1007f"},
+    {file = "google_crc32c-1.8.0-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:e6584b12cb06796d285d09e33f63309a09368b9d806a551d8036a4207ea43697"},
+    {file = "google_crc32c-1.8.0-cp314-cp314-macosx_12_0_x86_64.whl", hash = "sha256:f4b51844ef67d6cf2e9425983274da75f18b1597bb2c998e1c0a0e8d46f8f651"},
+    {file = "google_crc32c-1.8.0-cp314-cp314-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:b0d1a7afc6e8e4635564ba8aa5c0548e3173e41b6384d7711a9123165f582de2"},
+    {file = "google_crc32c-1.8.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8b3f68782f3cbd1bce027e48768293072813469af6a61a86f6bb4977a4380f21"},
+    {file = "google_crc32c-1.8.0-cp314-cp314-win_amd64.whl", hash = "sha256:d511b3153e7011a27ab6ee6bb3a5404a55b994dc1a7322c0b87b29606d9790e2"},
+    {file = "google_crc32c-1.8.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:ba6aba18daf4d36ad4412feede6221414692f44d17e5428bdd81ad3fc1eee5dc"},
+    {file = "google_crc32c-1.8.0-cp39-cp39-macosx_12_0_x86_64.whl", hash = "sha256:87b0072c4ecc9505cfa16ee734b00cd7721d20a0f595be4d40d3d21b41f65ae2"},
+    {file = "google_crc32c-1.8.0-cp39-cp39-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:3d488e98b18809f5e322978d4506373599c0c13e6c5ad13e53bb44758e18d215"},
+    {file = "google_crc32c-1.8.0-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:01f126a5cfddc378290de52095e2c7052be2ba7656a9f0caf4bcd1bfb1833f8a"},
+    {file = "google_crc32c-1.8.0-cp39-cp39-win_amd64.whl", hash = "sha256:61f58b28e0b21fcb249a8247ad0db2e64114e201e2e9b4200af020f3b6242c9f"},
+    {file = "google_crc32c-1.8.0-pp311-pypy311_pp73-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:87fa445064e7db928226b2e6f0d5304ab4cd0339e664a4e9a25029f384d9bb93"},
+    {file = "google_crc32c-1.8.0-pp311-pypy311_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:f639065ea2042d5c034bf258a9f085eaa7af0cd250667c0635a3118e8f92c69c"},
+    {file = "google_crc32c-1.8.0.tar.gz", hash = "sha256:a428e25fb7691024de47fecfbff7ff957214da51eddded0da0ae0e0f03a2cf79"},
+]
+
+[[package]]
+name = "google-genai"
+version = "1.47.0"
+description = "GenAI Python SDK"
+optional = true
+python-versions = ">=3.9"
+groups = ["main"]
+markers = "python_version == \"3.9\" and extra == \"google\""
+files = [
+    {file = "google_genai-1.47.0-py3-none-any.whl", hash = "sha256:e3851237556cbdec96007d8028b4b1f2425cdc5c099a8dc36b72a57e42821b60"},
+    {file = "google_genai-1.47.0.tar.gz", hash = "sha256:ecece00d0a04e6739ea76cc8dad82ec9593d9380aaabef078990e60574e5bf59"},
+]
+
+[package.dependencies]
+anyio = ">=4.8.0,<5.0.0"
+google-auth = ">=2.14.1,<3.0.0"
+httpx = ">=0.28.1,<1.0.0"
+pydantic = ">=2.9.0,<3.0.0"
+requests = ">=2.28.1,<3.0.0"
+tenacity = ">=8.2.3,<9.2.0"
+typing-extensions = ">=4.11.0,<5.0.0"
+websockets = ">=13.0.0,<15.1.0"
+
+[package.extras]
+aiohttp = ["aiohttp (<4.0.0)"]
+local-tokenizer = ["protobuf", "sentencepiece (>=0.2.0)"]
+
+[[package]]
+name = "google-genai"
+version = "1.55.0"
+description = "GenAI Python SDK"
+optional = true
+python-versions = ">=3.10"
+groups = ["main"]
+markers = "python_version >= \"3.10\" and extra == \"google\""
+files = [
+    {file = "google_genai-1.55.0-py3-none-any.whl", hash = "sha256:98c422762b5ff6e16b8d9a1e4938e8e0ad910392a5422e47f5301498d7f373a1"},
+    {file = "google_genai-1.55.0.tar.gz", hash = "sha256:ae9f1318fedb05c7c1b671a4148724751201e8908a87568364a309804064d986"},
+]
+
+[package.dependencies]
+anyio = ">=4.8.0,<5.0.0"
+distro = ">=1.7.0,<2"
+google-auth = {version = ">=2.14.1,<3.0.0", extras = ["requests"]}
+httpx = ">=0.28.1,<1.0.0"
+pydantic = ">=2.9.0,<3.0.0"
+requests = ">=2.28.1,<3.0.0"
+sniffio = "*"
+tenacity = ">=8.2.3,<9.2.0"
+typing-extensions = ">=4.11.0,<5.0.0"
+websockets = ">=13.0.0,<15.1.0"
+
+[package.extras]
+aiohttp = ["aiohttp (<3.13.3)"]
+local-tokenizer = ["protobuf", "sentencepiece (>=0.2.0)"]
+
+[[package]]
+name = "google-resumable-media"
+version = "2.8.0"
+description = "Utilities for Google Media Downloads and Resumable Uploads"
+optional = true
+python-versions = ">=3.7"
+groups = ["main"]
+markers = "extra == \"google\""
+files = [
+    {file = "google_resumable_media-2.8.0-py3-none-any.whl", hash = "sha256:dd14a116af303845a8d932ddae161a26e86cc229645bc98b39f026f9b1717582"},
+    {file = "google_resumable_media-2.8.0.tar.gz", hash = "sha256:f1157ed8b46994d60a1bc432544db62352043113684d4e030ee02e77ebe9a1ae"},
+]
+
+[package.dependencies]
+google-crc32c = ">=1.0.0,<2.0.0"
+
+[package.extras]
+aiohttp = ["aiohttp (>=3.6.2,<4.0.0)", "google-auth (>=1.22.0,<2.0.0)"]
+requests = ["requests (>=2.18.0,<3.0.0)"]
+
 [[package]]
 name = "googleapis-common-protos"
 version = "1.72.0"
@@ -2126,7 +2457,7 @@ files = [
     {file = "googleapis_common_protos-1.72.0-py3-none-any.whl", hash = "sha256:4299c5a82d5ae1a9702ada957347726b167f9f8d1fc352477702a1e851ff4038"},
     {file = "googleapis_common_protos-1.72.0.tar.gz", hash = "sha256:e55a601c1b32b52d7a3e65f43563e2aa61bcd737998ee672ac9b951cd49319f5"},
 ]
-markers = {main = "extra == \"extra-proxy\""}
+markers = {main = "extra == \"extra-proxy\" or extra == \"google\" or python_version == \"3.9\" and (extra == \"google\" or extra == \"extra-proxy\")"}
 
 [package.dependencies]
 grpcio = {version = ">=1.44.0,<2.0.0", optional = true, markers = "extra == \"grpc\""}
@@ -2275,7 +2606,7 @@ description = "IAM API client library"
 optional = true
 python-versions = ">=3.7"
 groups = ["main"]
-markers = "extra == \"extra-proxy\""
+markers = "extra == \"extra-proxy\" or extra == \"google\""
 files = [
     {file = "grpc_google_iam_v1-0.14.3-py3-none-any.whl", hash = "sha256:7a7f697e017a067206a3dfef44e4c634a34d3dee135fe7d7a4613fe3e59217e6"},
     {file = "grpc_google_iam_v1-0.14.3.tar.gz", hash = "sha256:879ac4ef33136c5491a6300e27575a9ec760f6cdf9a2518798c1b8977a5dc389"},
@@ -2371,7 +2702,7 @@ description = "Status proto mapping for gRPC"
 optional = true
 python-versions = ">=3.6"
 groups = ["main"]
-markers = "extra == \"extra-proxy\""
+markers = "extra == \"extra-proxy\" or extra == \"google\""
 files = [
     {file = "grpcio-status-1.62.3.tar.gz", hash = "sha256:289bdd7b2459794a12cf95dc0cb727bd4a1742c37bd823f760236c937e53a485"},
     {file = "grpcio_status-1.62.3-py3-none-any.whl", hash = "sha256:f9049b762ba8de6b1086789d8315846e094edac2c50beaf462338b301a8fd4b8"},
@@ -2389,7 +2720,7 @@ description = "WSGI HTTP Server for UNIX"
 optional = true
 python-versions = ">=3.7"
 groups = ["main"]
-markers = "extra == \"proxy\" or (extra == \"proxy\" or extra == \"mlflow\") and platform_system != \"Windows\" and python_version >= \"3.10\""
+markers = "(python_version < \"3.14\" or extra == \"mlflow\" or extra == \"proxy\") and (platform_system != \"Windows\" or extra == \"proxy\") and (python_version >= \"3.10\" or extra == \"proxy\") and (extra == \"proxy\" or extra == \"mlflow\")"
 files = [
     {file = "gunicorn-23.0.0-py3-none-any.whl", hash = "sha256:ec400d38950de4dfd418cff8328b2c8faed0edb0d517d3394e457c317908ca4d"},
     {file = "gunicorn-23.0.0.tar.gz", hash = "sha256:f014447a0101dc57e294f6c18ca6b40227a4c90e9bdb586042628030cba004ec"},
@@ -3095,15 +3426,15 @@ files = [
 
 [[package]]
 name = "litellm-proxy-extras"
-version = "0.4.23"
+version = "0.4.25"
 description = "Additional files for the LiteLLM Proxy. Reduces the size of the main litellm package."
 optional = true
 python-versions = "!=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,>=3.8"
 groups = ["main"]
 markers = "extra == \"proxy\""
 files = [
-    {file = "litellm_proxy_extras-0.4.23-py3-none-any.whl", hash = "sha256:dfda21203dde9fd97cf364396a9b5be0cfdf00fa9846439ee33ce11b7a52f9ce"},
-    {file = "litellm_proxy_extras-0.4.23.tar.gz", hash = "sha256:8e3f95576dc2a296e7f73d8c87e73628bd899b4644c45863960fe3c3762d8f64"},
+    {file = "litellm_proxy_extras-0.4.25-py3-none-any.whl", hash = "sha256:da79e1a7a999020a82ec33c45d8fd35eb390ff3d0bc3d7686542b3529aff2cda"},
+    {file = "litellm_proxy_extras-0.4.25.tar.gz", hash = "sha256:a03790e574ec6b8098c74d49836313651c0a0e72354a716c76c50ed16b087815"},
 ]
 
 [[package]]
@@ -3446,8 +3777,8 @@ files = [
 
 [package.dependencies]
 numpy = [
-    {version = ">=1.23.3", markers = "python_version >= \"3.11\""},
     {version = ">1.20"},
+    {version = ">=1.23.3", markers = "python_version >= \"3.11\""},
     {version = ">=1.21.2", markers = "python_version >= \"3.10\""},
     {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
 ]
@@ -3860,7 +4191,7 @@ description = "Fundamental package for array computing in Python"
 optional = true
 python-versions = ">=3.9"
 groups = ["main"]
-markers = "(python_version >= \"3.10\" or extra == \"extra-proxy\" or extra == \"semantic-router\") and python_version < \"3.12\" and (extra == \"extra-proxy\" or extra == \"semantic-router\" or extra == \"mlflow\")"
+markers = "python_version < \"3.12\" and (extra == \"extra-proxy\" or extra == \"semantic-router\" or extra == \"google\" or python_version >= \"3.10\") and (extra == \"extra-proxy\" or extra == \"semantic-router\" or extra == \"google\" or extra == \"mlflow\")"
 files = [
     {file = "numpy-1.26.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9ff0f4f29c51e2803569d7a51c2304de5554655a60c5d776e35b4a41413830d0"},
     {file = "numpy-1.26.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2e4ee3380d6de9c9ec04745830fd9e2eccb3e6cf790d39d7b98ffd19b0dd754a"},
@@ -3907,7 +4238,7 @@ description = "Fundamental package for array computing in Python"
 optional = true
 python-versions = ">=3.11"
 groups = ["main"]
-markers = "python_version >= \"3.12\" and (extra == \"extra-proxy\" or extra == \"semantic-router\" or extra == \"mlflow\") and (python_version < \"3.14\" or extra == \"mlflow\")"
+markers = "python_version >= \"3.12\" and (extra == \"extra-proxy\" or extra == \"google\" or extra == \"semantic-router\" or extra == \"mlflow\") and (python_version < \"3.14\" or extra == \"mlflow\" or extra == \"google\")"
 files = [
     {file = "numpy-2.3.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:de5672f4a7b200c15a4127042170a694d4df43c992948f5e1af57f0174beed10"},
     {file = "numpy-2.3.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:acfd89508504a19ed06ef963ad544ec6664518c863436306153e13e94605c218"},
@@ -4838,7 +5169,7 @@ description = "Beautiful, Pythonic protocol buffers"
 optional = true
 python-versions = ">=3.7"
 groups = ["main"]
-markers = "extra == \"extra-proxy\""
+markers = "extra == \"google\" or extra == \"extra-proxy\""
 files = [
     {file = "proto_plus-1.26.1-py3-none-any.whl", hash = "sha256:13285478c2dcf2abb829db158e1047e2f1e8d63a077d94263c2b88b043c75a66"},
     {file = "proto_plus-1.26.1.tar.gz", hash = "sha256:21a515a4c4c0088a773899e23c7bbade3d18f9c66c73edd4c7ee3816bc96a012"},
@@ -4870,7 +5201,7 @@ files = [
     {file = "protobuf-5.29.5-py3-none-any.whl", hash = "sha256:6cf42630262c59b2d8de33954443d94b746c952b01434fc58a417fdbd2e84bd5"},
     {file = "protobuf-5.29.5.tar.gz", hash = "sha256:bc1463bafd4b0929216c35f437a8e28731a2b7fe3d98bb77a600efced5a15c84"},
 ]
-markers = {main = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"extra-proxy\") or extra == \"extra-proxy\""}
+markers = {main = "(extra == \"extra-proxy\" or extra == \"google\" or extra == \"mlflow\") and python_version >= \"3.10\" or extra == \"google\" or extra == \"extra-proxy\""}
 
 [[package]]
 name = "pyarrow"
@@ -4940,7 +5271,7 @@ description = "Pure-Python implementation of ASN.1 types and DER/BER/CER codecs
 optional = true
 python-versions = ">=3.8"
 groups = ["main"]
-markers = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"extra-proxy\") or extra == \"extra-proxy\""
+markers = "(extra == \"extra-proxy\" or extra == \"google\" or extra == \"mlflow\") and python_version >= \"3.10\" or extra == \"google\" or extra == \"extra-proxy\""
 files = [
     {file = "pyasn1-0.6.1-py3-none-any.whl", hash = "sha256:0d632f46f2ba09143da3a8afe9e33fb6f92fa2320ab7e886e2d0f7672af84629"},
     {file = "pyasn1-0.6.1.tar.gz", hash = "sha256:6f580d2bdd84365380830acf45550f2511469f673cb4a5ae3857a3170128b034"},
@@ -4953,7 +5284,7 @@ description = "A collection of ASN.1-based protocols modules"
 optional = true
 python-versions = ">=3.8"
 groups = ["main"]
-markers = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"extra-proxy\") or extra == \"extra-proxy\""
+markers = "(extra == \"extra-proxy\" or extra == \"google\" or extra == \"mlflow\") and python_version >= \"3.10\" or extra == \"google\" or extra == \"extra-proxy\""
 files = [
     {file = "pyasn1_modules-0.4.2-py3-none-any.whl", hash = "sha256:29253a9207ce32b64c3ac6600edc75368f98473906e8fd1043bd6b5b1de2c14a"},
     {file = "pyasn1_modules-0.4.2.tar.gz", hash = "sha256:677091de870a80aae844b1ca6134f54652fa2c8c5a52aa396440ac3106e941e6"},
@@ -4985,7 +5316,7 @@ files = [
     {file = "pycparser-2.23-py3-none-any.whl", hash = "sha256:e5c6e8d3fbad53479cab09ac03729e0a9faf2bee3db8208a550daf5af81a5934"},
     {file = "pycparser-2.23.tar.gz", hash = "sha256:78816d4f24add8f10a06d6f05b4d424ad9e96cfebf68a4ddc99c65c0720d00c2"},
 ]
-markers = {main = "(platform_python_implementation != \"PyPy\" or extra == \"proxy\") and implementation_name != \"PyPy\"", dev = "platform_python_implementation != \"PyPy\" and implementation_name != \"PyPy\"", proxy-dev = "platform_python_implementation != \"PyPy\" and implementation_name != \"PyPy\""}
+markers = {main = "implementation_name != \"PyPy\" and (platform_python_implementation != \"PyPy\" or extra == \"proxy\")", dev = "platform_python_implementation != \"PyPy\" and implementation_name != \"PyPy\"", proxy-dev = "platform_python_implementation != \"PyPy\" and implementation_name != \"PyPy\""}
 
 [[package]]
 name = "pydantic"
@@ -5362,7 +5693,7 @@ description = "Extensions to the standard Python datetime module"
 optional = true
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
 groups = ["main"]
-markers = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"proxy\") or extra == \"proxy\""
+markers = "(extra == \"mlflow\" or extra == \"proxy\" or extra == \"google\") and python_version >= \"3.10\" or extra == \"proxy\" or extra == \"google\""
 files = [
     {file = "python-dateutil-2.9.0.post0.tar.gz", hash = "sha256:37dd54208da7e1cd875388217d5e00ebd4179249f90fb72437e91a35459a0ad3"},
     {file = "python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427"},
@@ -5422,7 +5753,7 @@ description = "World timezone definitions, modern and historical"
 optional = true
 python-versions = "*"
 groups = ["main"]
-markers = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"proxy\") or extra == \"proxy\""
+markers = "(extra == \"mlflow\" or extra == \"proxy\") and python_version >= \"3.10\" or extra == \"proxy\""
 files = [
     {file = "pytz-2025.2-py2.py3-none-any.whl", hash = "sha256:5ddf76296dd8c44c26eb8f4b6f35488f3ccbf6fbbd7adee0b7262d43f0ec2f00"},
     {file = "pytz-2025.2.tar.gz", hash = "sha256:360b9e3dbb49a209c21ad61809c7fb453643e048b38924c765813546746e81c3"},
@@ -6241,7 +6572,7 @@ description = "Pure-Python RSA implementation"
 optional = true
 python-versions = "<4,>=3.6"
 groups = ["main"]
-markers = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"extra-proxy\") or extra == \"extra-proxy\""
+markers = "(extra == \"extra-proxy\" or extra == \"google\" or extra == \"mlflow\") and python_version >= \"3.10\" or extra == \"google\" or extra == \"extra-proxy\""
 files = [
     {file = "rsa-4.9.1-py3-none-any.whl", hash = "sha256:68635866661c6836b8d39430f97a996acbd61bfa49406748ea243539fe239762"},
     {file = "rsa-4.9.1.tar.gz", hash = "sha256:e7bdbfdb5497da4c07dfd35530e1a902659db6ff241e39d9953cad06ebd0ae75"},
@@ -6279,22 +6610,22 @@ files = [
 
 [[package]]
 name = "s3transfer"
-version = "0.11.3"
+version = "0.14.0"
 description = "An Amazon S3 Transfer Manager"
 optional = true
-python-versions = ">=3.8"
+python-versions = ">=3.9"
 groups = ["main"]
 markers = "extra == \"proxy\""
 files = [
-    {file = "s3transfer-0.11.3-py3-none-any.whl", hash = "sha256:ca855bdeb885174b5ffa95b9913622459d4ad8e331fc98eb01e6d5eb6a30655d"},
-    {file = "s3transfer-0.11.3.tar.gz", hash = "sha256:edae4977e3a122445660c7c114bba949f9d191bae3b34a096f18a1c8c354527a"},
+    {file = "s3transfer-0.14.0-py3-none-any.whl", hash = "sha256:ea3b790c7077558ed1f02a3072fb3cb992bbbd253392f4b6e9e8976941c7d456"},
+    {file = "s3transfer-0.14.0.tar.gz", hash = "sha256:eff12264e7c8b4985074ccce27a3b38a485bb7f7422cc8046fee9be4983e4125"},
 ]
 
 [package.dependencies]
-botocore = ">=1.36.0,<2.0a.0"
+botocore = ">=1.37.4,<2.0a.0"
 
 [package.extras]
-crt = ["botocore[crt] (>=1.36.0,<2.0a.0)"]
+crt = ["botocore[crt] (>=1.37.4,<2.0a.0)"]
 
 [[package]]
 name = "scikit-learn"
@@ -6542,6 +6873,141 @@ postgres = ["psycopg[binary] (>=3.1.0,<4)"]
 qdrant = ["qdrant-client (>=1.11.1,<2)"]
 vision = ["pillow (>=10.2.0,<11.0.0) ; python_version < \"3.13\"", "torch (>=2.6.0) ; python_version < \"3.13\"", "torchvision (>=0.17.0) ; python_version < \"3.13\"", "transformers (>=4.36.2) ; python_version < \"3.13\""]
 
+[[package]]
+name = "shapely"
+version = "2.0.7"
+description = "Manipulation and analysis of geometric objects"
+optional = true
+python-versions = ">=3.7"
+groups = ["main"]
+markers = "python_version == \"3.9\" and extra == \"google\""
+files = [
+    {file = "shapely-2.0.7-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:33fb10e50b16113714ae40adccf7670379e9ccf5b7a41d0002046ba2b8f0f691"},
+    {file = "shapely-2.0.7-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f44eda8bd7a4bccb0f281264b34bf3518d8c4c9a8ffe69a1a05dabf6e8461147"},
+    {file = "shapely-2.0.7-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cf6c50cd879831955ac47af9c907ce0310245f9d162e298703f82e1785e38c98"},
+    {file = "shapely-2.0.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:04a65d882456e13c8b417562c36324c0cd1e5915f3c18ad516bb32ee3f5fc895"},
+    {file = "shapely-2.0.7-cp310-cp310-win32.whl", hash = "sha256:7e97104d28e60b69f9b6a957c4d3a2a893b27525bc1fc96b47b3ccef46726bf2"},
+    {file = "shapely-2.0.7-cp310-cp310-win_amd64.whl", hash = "sha256:35524cc8d40ee4752520819f9894b9f28ba339a42d4922e92c99b148bed3be39"},
+    {file = "shapely-2.0.7-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5cf23400cb25deccf48c56a7cdda8197ae66c0e9097fcdd122ac2007e320bc34"},
+    {file = "shapely-2.0.7-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d8f1da01c04527f7da59ee3755d8ee112cd8967c15fab9e43bba936b81e2a013"},
+    {file = "shapely-2.0.7-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8f623b64bb219d62014781120f47499a7adc30cf7787e24b659e56651ceebcb0"},
+    {file = "shapely-2.0.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e6d95703efaa64aaabf278ced641b888fc23d9c6dd71f8215091afd8a26a66e3"},
+    {file = "shapely-2.0.7-cp311-cp311-win32.whl", hash = "sha256:2f6e4759cf680a0f00a54234902415f2fa5fe02f6b05546c662654001f0793a2"},
+    {file = "shapely-2.0.7-cp311-cp311-win_amd64.whl", hash = "sha256:b52f3ab845d32dfd20afba86675c91919a622f4627182daec64974db9b0b4608"},
+    {file = "shapely-2.0.7-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:4c2b9859424facbafa54f4a19b625a752ff958ab49e01bc695f254f7db1835fa"},
+    {file = "shapely-2.0.7-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:5aed1c6764f51011d69a679fdf6b57e691371ae49ebe28c3edb5486537ffbd51"},
+    {file = "shapely-2.0.7-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:73c9ae8cf443187d784d57202199bf9fd2d4bb7d5521fe8926ba40db1bc33e8e"},
+    {file = "shapely-2.0.7-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a9469f49ff873ef566864cb3516091881f217b5d231c8164f7883990eec88b73"},
+    {file = "shapely-2.0.7-cp312-cp312-win32.whl", hash = "sha256:6bca5095e86be9d4ef3cb52d56bdd66df63ff111d580855cb8546f06c3c907cd"},
+    {file = "shapely-2.0.7-cp312-cp312-win_amd64.whl", hash = "sha256:f86e2c0259fe598c4532acfcf638c1f520fa77c1275912bbc958faecbf00b108"},
+    {file = "shapely-2.0.7-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:a0c09e3e02f948631c7763b4fd3dd175bc45303a0ae04b000856dedebefe13cb"},
+    {file = "shapely-2.0.7-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:06ff6020949b44baa8fc2e5e57e0f3d09486cd5c33b47d669f847c54136e7027"},
+    {file = "shapely-2.0.7-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5d6dbf096f961ca6bec5640e22e65ccdec11e676344e8157fe7d636e7904fd36"},
+    {file = "shapely-2.0.7-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:adeddfb1e22c20548e840403e5e0b3d9dc3daf66f05fa59f1fcf5b5f664f0e98"},
+    {file = "shapely-2.0.7-cp313-cp313-win32.whl", hash = "sha256:a7f04691ce1c7ed974c2f8b34a1fe4c3c5dfe33128eae886aa32d730f1ec1913"},
+    {file = "shapely-2.0.7-cp313-cp313-win_amd64.whl", hash = "sha256:aaaf5f7e6cc234c1793f2a2760da464b604584fb58c6b6d7d94144fd2692d67e"},
+    {file = "shapely-2.0.7-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:19cbc8808efe87a71150e785b71d8a0e614751464e21fb679d97e274eca7bd43"},
+    {file = "shapely-2.0.7-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fc19b78cc966db195024d8011649b4e22812f805dd49264323980715ab80accc"},
+    {file = "shapely-2.0.7-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd37d65519b3f8ed8976fa4302a2827cbb96e0a461a2e504db583b08a22f0b98"},
+    {file = "shapely-2.0.7-cp37-cp37m-win32.whl", hash = "sha256:25085a30a2462cee4e850a6e3fb37431cbbe4ad51cbcc163af0cea1eaa9eb96d"},
+    {file = "shapely-2.0.7-cp37-cp37m-win_amd64.whl", hash = "sha256:1a2e03277128e62f9a49a58eb7eb813fa9b343925fca5e7d631d50f4c0e8e0b8"},
+    {file = "shapely-2.0.7-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:e1c4f1071fe9c09af077a69b6c75f17feb473caeea0c3579b3e94834efcbdc36"},
+    {file = "shapely-2.0.7-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:3697bd078b4459f5a1781015854ef5ea5d824dbf95282d0b60bfad6ff83ec8dc"},
+    {file = "shapely-2.0.7-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1e9fed9a7d6451979d914cb6ebbb218b4b4e77c0d50da23e23d8327948662611"},
+    {file = "shapely-2.0.7-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2934834c7f417aeb7cba3b0d9b4441a76ebcecf9ea6e80b455c33c7c62d96a24"},
+    {file = "shapely-2.0.7-cp38-cp38-win32.whl", hash = "sha256:2e4a1749ad64bc6e7668c8f2f9479029f079991f4ae3cb9e6b25440e35a4b532"},
+    {file = "shapely-2.0.7-cp38-cp38-win_amd64.whl", hash = "sha256:8ae5cb6b645ac3fba34ad84b32fbdccb2ab321facb461954925bde807a0d3b74"},
+    {file = "shapely-2.0.7-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:4abeb44b3b946236e4e1a1b3d2a0987fb4d8a63bfb3fdefb8a19d142b72001e5"},
+    {file = "shapely-2.0.7-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:cd0e75d9124b73e06a42bf1615ad3d7d805f66871aa94538c3a9b7871d620013"},
+    {file = "shapely-2.0.7-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7977d8a39c4cf0e06247cd2dca695ad4e020b81981d4c82152c996346cf1094b"},
+    {file = "shapely-2.0.7-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0145387565fcf8f7c028b073c802956431308da933ef41d08b1693de49990d27"},
+    {file = "shapely-2.0.7-cp39-cp39-win32.whl", hash = "sha256:98697c842d5c221408ba8aa573d4f49caef4831e9bc6b6e785ce38aca42d1999"},
+    {file = "shapely-2.0.7-cp39-cp39-win_amd64.whl", hash = "sha256:a3fb7fbae257e1b042f440289ee7235d03f433ea880e73e687f108d044b24db5"},
+    {file = "shapely-2.0.7.tar.gz", hash = "sha256:28fe2997aab9a9dc026dc6a355d04e85841546b2a5d232ed953e3321ab958ee5"},
+]
+
+[package.dependencies]
+numpy = ">=1.14,<3"
+
+[package.extras]
+docs = ["matplotlib", "numpydoc (==1.1.*)", "sphinx", "sphinx-book-theme", "sphinx-remove-toctrees"]
+test = ["pytest", "pytest-cov"]
+
+[[package]]
+name = "shapely"
+version = "2.1.2"
+description = "Manipulation and analysis of geometric objects"
+optional = true
+python-versions = ">=3.10"
+groups = ["main"]
+markers = "python_version >= \"3.10\" and extra == \"google\""
+files = [
+    {file = "shapely-2.1.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:7ae48c236c0324b4e139bea88a306a04ca630f49be66741b340729d380d8f52f"},
+    {file = "shapely-2.1.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:eba6710407f1daa8e7602c347dfc94adc02205ec27ed956346190d66579eb9ea"},
+    {file = "shapely-2.1.2-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ef4a456cc8b7b3d50ccec29642aa4aeda959e9da2fe9540a92754770d5f0cf1f"},
+    {file = "shapely-2.1.2-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e38a190442aacc67ff9f75ce60aec04893041f16f97d242209106d502486a142"},
+    {file = "shapely-2.1.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:40d784101f5d06a1fd30b55fc11ea58a61be23f930d934d86f19a180909908a4"},
+    {file = "shapely-2.1.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:f6f6cd5819c50d9bcf921882784586aab34a4bd53e7553e175dece6db513a6f0"},
+    {file = "shapely-2.1.2-cp310-cp310-win32.whl", hash = "sha256:fe9627c39c59e553c90f5bc3128252cb85dc3b3be8189710666d2f8bc3a5503e"},
+    {file = "shapely-2.1.2-cp310-cp310-win_amd64.whl", hash = "sha256:1d0bfb4b8f661b3b4ec3565fa36c340bfb1cda82087199711f86a88647d26b2f"},
+    {file = "shapely-2.1.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:91121757b0a36c9aac3427a651a7e6567110a4a67c97edf04f8d55d4765f6618"},
+    {file = "shapely-2.1.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:16a9c722ba774cf50b5d4541242b4cce05aafd44a015290c82ba8a16931ff63d"},
+    {file = "shapely-2.1.2-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cc4f7397459b12c0b196c9efe1f9d7e92463cbba142632b4cc6d8bbbbd3e2b09"},
+    {file = "shapely-2.1.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:136ab87b17e733e22f0961504d05e77e7be8c9b5a8184f685b4a91a84efe3c26"},
+    {file = "shapely-2.1.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:16c5d0fc45d3aa0a69074979f4f1928ca2734fb2e0dde8af9611e134e46774e7"},
+    {file = "shapely-2.1.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:6ddc759f72b5b2b0f54a7e7cde44acef680a55019eb52ac63a7af2cf17cb9cd2"},
+    {file = "shapely-2.1.2-cp311-cp311-win32.whl", hash = "sha256:2fa78b49485391224755a856ed3b3bd91c8455f6121fee0db0e71cefb07d0ef6"},
+    {file = "shapely-2.1.2-cp311-cp311-win_amd64.whl", hash = "sha256:c64d5c97b2f47e3cd9b712eaced3b061f2b71234b3fc263e0fcf7d889c6559dc"},
+    {file = "shapely-2.1.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:fe2533caae6a91a543dec62e8360fe86ffcdc42a7c55f9dfd0128a977a896b94"},
+    {file = "shapely-2.1.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ba4d1333cc0bc94381d6d4308d2e4e008e0bd128bdcff5573199742ee3634359"},
+    {file = "shapely-2.1.2-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:0bd308103340030feef6c111d3eb98d50dc13feea33affc8a6f9fa549e9458a3"},
+    {file = "shapely-2.1.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:1e7d4d7ad262a48bb44277ca12c7c78cb1b0f56b32c10734ec9a1d30c0b0c54b"},
+    {file = "shapely-2.1.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e9eddfe513096a71896441a7c37db72da0687b34752c4e193577a145c71736fc"},
+    {file = "shapely-2.1.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:980c777c612514c0cf99bc8a9de6d286f5e186dcaf9091252fcd444e5638193d"},
+    {file = "shapely-2.1.2-cp312-cp312-win32.whl", hash = "sha256:9111274b88e4d7b54a95218e243282709b330ef52b7b86bc6aaf4f805306f454"},
+    {file = "shapely-2.1.2-cp312-cp312-win_amd64.whl", hash = "sha256:743044b4cfb34f9a67205cee9279feaf60ba7d02e69febc2afc609047cb49179"},
+    {file = "shapely-2.1.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:b510dda1a3672d6879beb319bc7c5fd302c6c354584690973c838f46ec3e0fa8"},
+    {file = "shapely-2.1.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:8cff473e81017594d20ec55d86b54bc635544897e13a7cfc12e36909c5309a2a"},
+    {file = "shapely-2.1.2-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:fe7b77dc63d707c09726b7908f575fc04ff1d1ad0f3fb92aec212396bc6cfe5e"},
+    {file = "shapely-2.1.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:7ed1a5bbfb386ee8332713bf7508bc24e32d24b74fc9a7b9f8529a55db9f4ee6"},
+    {file = "shapely-2.1.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:a84e0582858d841d54355246ddfcbd1fce3179f185da7470f41ce39d001ee1af"},
+    {file = "shapely-2.1.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:dc3487447a43d42adcdf52d7ac73804f2312cbfa5d433a7d2c506dcab0033dfd"},
+    {file = "shapely-2.1.2-cp313-cp313-win32.whl", hash = "sha256:9c3a3c648aedc9f99c09263b39f2d8252f199cb3ac154fadc173283d7d111350"},
+    {file = "shapely-2.1.2-cp313-cp313-win_amd64.whl", hash = "sha256:ca2591bff6645c216695bdf1614fca9c82ea1144d4a7591a466fef64f28f0715"},
+    {file = "shapely-2.1.2-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:2d93d23bdd2ed9dc157b46bc2f19b7da143ca8714464249bef6771c679d5ff40"},
+    {file = "shapely-2.1.2-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:01d0d304b25634d60bd7cf291828119ab55a3bab87dc4af1e44b07fb225f188b"},
+    {file = "shapely-2.1.2-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8d8382dd120d64b03698b7298b89611a6ea6f55ada9d39942838b79c9bc89801"},
+    {file = "shapely-2.1.2-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:19efa3611eef966e776183e338b2d7ea43569ae99ab34f8d17c2c054d3205cc0"},
+    {file = "shapely-2.1.2-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:346ec0c1a0fcd32f57f00e4134d1200e14bf3f5ae12af87ba83ca275c502498c"},
+    {file = "shapely-2.1.2-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:6305993a35989391bd3476ee538a5c9a845861462327efe00dd11a5c8c709a99"},
+    {file = "shapely-2.1.2-cp313-cp313t-win32.whl", hash = "sha256:c8876673449f3401f278c86eb33224c5764582f72b653a415d0e6672fde887bf"},
+    {file = "shapely-2.1.2-cp313-cp313t-win_amd64.whl", hash = "sha256:4a44bc62a10d84c11a7a3d7c1c4fe857f7477c3506e24c9062da0db0ae0c449c"},
+    {file = "shapely-2.1.2-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:9a522f460d28e2bf4e12396240a5fc1518788b2fcd73535166d748399ef0c223"},
+    {file = "shapely-2.1.2-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:1ff629e00818033b8d71139565527ced7d776c269a49bd78c9df84e8f852190c"},
+    {file = "shapely-2.1.2-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:f67b34271dedc3c653eba4e3d7111aa421d5be9b4c4c7d38d30907f796cb30df"},
+    {file = "shapely-2.1.2-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:21952dc00df38a2c28375659b07a3979d22641aeb104751e769c3ee825aadecf"},
+    {file = "shapely-2.1.2-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:1f2f33f486777456586948e333a56ae21f35ae273be99255a191f5c1fa302eb4"},
+    {file = "shapely-2.1.2-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:cf831a13e0d5a7eb519e96f58ec26e049b1fad411fc6fc23b162a7ce04d9cffc"},
+    {file = "shapely-2.1.2-cp314-cp314-win32.whl", hash = "sha256:61edcd8d0d17dd99075d320a1dd39c0cb9616f7572f10ef91b4b5b00c4aeb566"},
+    {file = "shapely-2.1.2-cp314-cp314-win_amd64.whl", hash = "sha256:a444e7afccdb0999e203b976adb37ea633725333e5b119ad40b1ca291ecf311c"},
+    {file = "shapely-2.1.2-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:5ebe3f84c6112ad3d4632b1fd2290665aa75d4cef5f6c5d77c4c95b324527c6a"},
+    {file = "shapely-2.1.2-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:5860eb9f00a1d49ebb14e881f5caf6c2cf472c7fd38bd7f253bbd34f934eb076"},
+    {file = "shapely-2.1.2-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:b705c99c76695702656327b819c9660768ec33f5ce01fa32b2af62b56ba400a1"},
+    {file = "shapely-2.1.2-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:a1fd0ea855b2cf7c9cddaf25543e914dd75af9de08785f20ca3085f2c9ca60b0"},
+    {file = "shapely-2.1.2-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:df90e2db118c3671a0754f38e36802db75fe0920d211a27481daf50a711fdf26"},
+    {file = "shapely-2.1.2-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:361b6d45030b4ac64ddd0a26046906c8202eb60d0f9f53085f5179f1d23021a0"},
+    {file = "shapely-2.1.2-cp314-cp314t-win32.whl", hash = "sha256:b54df60f1fbdecc8ebc2c5b11870461a6417b3d617f555e5033f1505d36e5735"},
+    {file = "shapely-2.1.2-cp314-cp314t-win_amd64.whl", hash = "sha256:0036ac886e0923417932c2e6369b6c52e38e0ff5d9120b90eef5cd9a5fc5cae9"},
+    {file = "shapely-2.1.2.tar.gz", hash = "sha256:2ed4ecb28320a433db18a5bf029986aa8afcfd740745e78847e330d5d94922a9"},
+]
+
+[package.dependencies]
+numpy = ">=1.21"
+
+[package.extras]
+docs = ["matplotlib", "numpydoc (==1.1.*)", "sphinx", "sphinx-book-theme", "sphinx-remove-toctrees"]
+test = ["pytest", "pytest-cov", "scipy-doctest"]
+
 [[package]]
 name = "shellingham"
 version = "1.5.4"
@@ -6561,7 +7027,7 @@ description = "Python 2 and 3 compatibility utilities"
 optional = true
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
 groups = ["main"]
-markers = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"proxy\") or extra == \"proxy\""
+markers = "(extra == \"mlflow\" or extra == \"proxy\" or extra == \"google\") and python_version >= \"3.10\" or extra == \"proxy\" or extra == \"google\""
 files = [
     {file = "six-1.17.0-py2.py3-none-any.whl", hash = "sha256:4721f391ed90541fddacab5acf947aa0d3dc7d27b2e1e8eda2be8970586c3274"},
     {file = "six-1.17.0.tar.gz", hash = "sha256:ff70335d468e7eb6ec65b95b99d3a2836546063f63acc5171de367e834932a81"},
@@ -6984,6 +7450,26 @@ examples = ["aiosqlite (>=0.21.0)", "fastapi (>=0.115.12)", "sqlalchemy[asyncio]
 granian = ["granian (>=2.3.1)"]
 uvicorn = ["uvicorn (>=0.34.0)"]
 
+[[package]]
+name = "starlette"
+version = "0.49.3"
+description = "The little ASGI library that shines."
+optional = false
+python-versions = ">=3.9"
+groups = ["main", "dev"]
+files = [
+    {file = "starlette-0.49.3-py3-none-any.whl", hash = "sha256:b579b99715fdc2980cf88c8ec96d3bf1ce16f5a8051a7c2b84ef9b1cdecaea2f"},
+    {file = "starlette-0.49.3.tar.gz", hash = "sha256:1c14546f299b5901a1ea0e34410575bc33bbd741377a10484a54445588d00284"},
+]
+markers = {main = "python_version == \"3.9\" and extra == \"proxy\"", dev = "python_version == \"3.9\""}
+
+[package.dependencies]
+anyio = ">=3.6.2,<5"
+typing-extensions = {version = ">=4.10.0", markers = "python_version < \"3.13\""}
+
+[package.extras]
+full = ["httpx (>=0.27.0,<0.29.0)", "itsdangerous", "jinja2", "python-multipart (>=0.0.18)", "pyyaml"]
+
 [[package]]
 name = "starlette"
 version = "0.50.0"
@@ -6995,7 +7481,7 @@ files = [
     {file = "starlette-0.50.0-py3-none-any.whl", hash = "sha256:9e5391843ec9b6e472eed1365a78c8098cfceb7a74bfd4d6b1c0c0095efb3bca"},
     {file = "starlette-0.50.0.tar.gz", hash = "sha256:a2a17b22203254bcbc2e1f926d2d55f3f9497f769416b3190768befe598fa3ca"},
 ]
-markers = {main = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"proxy\") or extra == \"proxy\""}
+markers = {main = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"proxy\")", dev = "python_version >= \"3.10\""}
 
 [package.dependencies]
 anyio = ">=3.6.2,<5"
@@ -7044,7 +7530,7 @@ description = "Retry code until it succeeds"
 optional = true
 python-versions = ">=3.9"
 groups = ["main"]
-markers = "extra == \"extra-proxy\" and python_version < \"3.14\""
+markers = "(extra == \"extra-proxy\" or extra == \"google\") and (python_version < \"3.14\" or extra == \"google\")"
 files = [
     {file = "tenacity-9.1.2-py3-none-any.whl", hash = "sha256:f77bf36710d8b73a50b2dd155c97b870017ad21afe6ab300326b0371b3b05138"},
     {file = "tenacity-9.1.2.tar.gz", hash = "sha256:1169d376c297e7de388d18b4481760d478b0e99a777cad3a9c86e556f4b697cb"},
@@ -7522,7 +8008,7 @@ description = "The lightning-fast ASGI server."
 optional = true
 python-versions = ">=3.8"
 groups = ["main"]
-markers = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"proxy\") or extra == \"proxy\""
+markers = "(extra == \"mlflow\" or extra == \"proxy\") and python_version >= \"3.10\" or extra == \"proxy\""
 files = [
     {file = "uvicorn-0.31.1-py3-none-any.whl", hash = "sha256:adc42d9cac80cf3e51af97c1851648066841e7cfb6993a4ca8de29ac1548ed41"},
     {file = "uvicorn-0.31.1.tar.gz", hash = "sha256:f5167919867b161b7bcaf32646c6a94cdbd4c3aa2eb5c17d36bb9aa5cfd8c493"},
@@ -7543,7 +8029,7 @@ description = "Fast implementation of asyncio event loop on top of libuv"
 optional = true
 python-versions = ">=3.8.0"
 groups = ["main"]
-markers = "sys_platform != \"win32\" and extra == \"proxy\""
+markers = "extra == \"proxy\" and sys_platform != \"win32\""
 files = [
     {file = "uvloop-0.21.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:ec7e6b09a6fdded42403182ab6b832b71f4edaf7f37a9a0e371a01db5f0cb45f"},
     {file = "uvloop-0.21.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:196274f2adb9689a289ad7d65700d37df0c0930fd8e4e743fa4834e850d7719d"},
@@ -7613,7 +8099,7 @@ description = "An implementation of the WebSocket Protocol (RFC 6455 & 7692)"
 optional = true
 python-versions = ">=3.9"
 groups = ["main"]
-markers = "extra == \"proxy\""
+markers = "extra == \"google\" or extra == \"proxy\""
 files = [
     {file = "websockets-15.0.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:d63efaa0cd96cf0c5fe4d581521d9fa87744540d4bc999ae6e08595a1014b45b"},
     {file = "websockets-15.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ac60e3b188ec7574cb761b08d50fcedf9d77f1530352db4eef1707fe9dee7205"},
@@ -7996,7 +8482,7 @@ type = ["pytest-mypy"]
 [extras]
 caching = ["diskcache"]
 extra-proxy = ["a2a-sdk", "azure-identity", "azure-keyvault-secrets", "google-cloud-iam", "google-cloud-kms", "prisma", "redisvl", "resend"]
-grpc = ["grpcio", "grpcio"]
+google = ["google-cloud-aiplatform"]
 mlflow = ["mlflow"]
 proxy = ["PyJWT", "apscheduler", "azure-identity", "azure-storage-blob", "backoff", "boto3", "cryptography", "fastapi", "fastapi-sso", "gunicorn", "litellm-enterprise", "litellm-proxy-extras", "mcp", "orjson", "polars", "pynacl", "python-multipart", "pyyaml", "rich", "rq", "soundfile", "uvicorn", "uvloop", "websockets"]
 semantic-router = ["semantic-router"]
@@ -8005,4 +8491,4 @@ utils = ["numpydoc"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<4.0"
-content-hash = "f6a98e687d478db6e30274a4cf70391960775cbf648da0783558444da3a662ea"
+content-hash = "76f5b5fb10667c2dcf428976292672e7a1f3f2eb5f5bf78998e2192899f5037e"
diff --git a/tests/llm_translation/test_bedrock_completion.py b/tests/llm_translation/test_bedrock_completion.py
index 7c0db41d13..d48dd1bfd9 100644
--- a/tests/llm_translation/test_bedrock_completion.py
+++ b/tests/llm_translation/test_bedrock_completion.py
@@ -3954,3 +3954,288 @@ def test_bedrock_openai_error_handling():
 
     assert exc_info.value.status_code == 422
     print("✓ Error handling works correctly")
+
+# ============================================================================
+# Nova Grounding (web_search_options) Unit Tests (Mocked)
+# ============================================================================
+
+def test_bedrock_nova_grounding_web_search_options_non_streaming():
+    """
+    Unit test for Nova grounding using web_search_options parameter (non-streaming).
+
+    This test mocks the HTTP call to verify:
+    1. web_search_options is correctly mapped to systemTool for Nova models
+    2. The request structure is correct
+
+    Related: https://docs.aws.amazon.com/nova/latest/userguide/grounding.html
+    """
+    from unittest.mock import patch, MagicMock
+    from litellm.llms.custom_httpx.http_handler import HTTPHandler
+
+    client = HTTPHandler()
+
+    messages = [
+        {
+            "role": "user",
+            "content": "What is the current population of Tokyo, Japan?",
+        }
+    ]
+
+    with patch.object(client, "post") as mock_post:
+        try:
+            completion(
+                model="us.amazon.nova-pro-v1:0",  # No bedrock/ prefix when using api_base
+                messages=messages,
+                web_search_options={},  # Enables Nova grounding
+                max_tokens=500,
+                client=client,
+                api_base="https://bedrock-runtime.us-east-1.amazonaws.com",
+            )
+        except Exception:
+            pass  # Expected - we're just checking the request structure
+
+        # Verify the request was made correctly
+        if mock_post.called:
+            request_body = json.loads(mock_post.call_args.kwargs.get("data", "{}"))
+            print(f"Request body: {json.dumps(request_body, indent=2)}")
+
+            # Verify toolConfig is present with systemTool
+            assert "toolConfig" in request_body, "toolConfig should be in request"
+            tool_config = request_body["toolConfig"]
+            assert "tools" in tool_config, "tools should be in toolConfig"
+
+            # Find the systemTool for nova_grounding
+            system_tool_found = False
+            for tool in tool_config["tools"]:
+                if "systemTool" in tool:
+                    assert tool["systemTool"]["name"] == "nova_grounding"
+                    system_tool_found = True
+                    break
+
+            assert system_tool_found, "systemTool with nova_grounding should be present"
+            print(f"✓ web_search_options correctly transformed to systemTool (non-streaming)")
+
+
+def test_bedrock_nova_grounding_with_function_tools():
+    """
+    Unit test for Nova grounding combined with regular function tools.
+
+    This tests the scenario where users want both web grounding AND
+    custom function calling capabilities.
+    """
+    from unittest.mock import patch
+    from litellm.llms.custom_httpx.http_handler import HTTPHandler
+
+    client = HTTPHandler()
+
+    # Regular function tool
+    tools = [
+        {
+            "type": "function",
+            "function": {
+                "name": "get_stock_price",
+                "description": "Get the current stock price for a given ticker symbol",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "ticker": {
+                            "type": "string",
+                            "description": "The stock ticker symbol, e.g. AAPL, GOOGL",
+                        }
+                    },
+                    "required": ["ticker"],
+                },
+            },
+        }
+    ]
+
+    messages = [
+        {
+            "role": "user",
+            "content": "What is the current market cap of Apple Inc?",
+        }
+    ]
+
+    with patch.object(client, "post") as mock_post:
+        try:
+            completion(
+                model="us.amazon.nova-pro-v1:0",  # No bedrock/ prefix when using api_base
+                messages=messages,
+                tools=tools,
+                web_search_options={},  # Also enable web grounding
+                max_tokens=500,
+                client=client,
+                api_base="https://bedrock-runtime.us-east-1.amazonaws.com",
+            )
+        except Exception:
+            pass  # Expected - we're just checking the request structure
+
+        # Verify the request was made correctly
+        if mock_post.called:
+            request_body = json.loads(mock_post.call_args.kwargs.get("data", "{}"))
+            print(f"Request body: {json.dumps(request_body, indent=2)}")
+
+            # Verify toolConfig has both function tool and systemTool
+            assert "toolConfig" in request_body, "toolConfig should be in request"
+            tool_config = request_body["toolConfig"]
+            assert "tools" in tool_config, "tools should be in toolConfig"
+
+            tools_in_request = tool_config["tools"]
+
+            # Should have both the function tool and the systemTool
+            function_tool_found = False
+            system_tool_found = False
+
+            for tool in tools_in_request:
+                if "toolSpec" in tool:
+                    assert tool["toolSpec"]["name"] == "get_stock_price"
+                    function_tool_found = True
+                if "systemTool" in tool:
+                    assert tool["systemTool"]["name"] == "nova_grounding"
+                    system_tool_found = True
+
+            assert function_tool_found, "Function tool (get_stock_price) should be present"
+            assert system_tool_found, "systemTool (nova_grounding) should be present"
+            print(f"✓ Both function tools and web_search_options correctly combined")
+
+
+@pytest.mark.asyncio
+async def test_bedrock_nova_grounding_async():
+    """
+    Async unit test for Nova grounding via web_search_options.
+
+    This test verifies the request transformation for async calls.
+    """
+    from unittest.mock import patch, AsyncMock
+    from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler
+
+    client = AsyncHTTPHandler()
+
+    messages = [
+        {
+            "role": "user",
+            "content": "What is the weather forecast for New York City today?",
+        }
+    ]
+
+    with patch.object(client, "post", new=AsyncMock()) as mock_post:
+        try:
+            await litellm.acompletion(
+                model="us.amazon.nova-pro-v1:0",  # No bedrock/ prefix when using api_base
+                messages=messages,
+                web_search_options={},
+                max_tokens=500,
+                client=client,
+                api_base="https://bedrock-runtime.us-east-1.amazonaws.com",
+            )
+        except Exception:
+            pass  # Expected - we're just checking the request structure
+
+        # Verify the request was made correctly
+        if mock_post.called:
+            request_body = json.loads(mock_post.call_args.kwargs.get("data", "{}"))
+            print(f"Request body: {json.dumps(request_body, indent=2)}")
+
+            # Verify toolConfig is present with systemTool
+            assert "toolConfig" in request_body, "toolConfig should be in request"
+            tool_config = request_body["toolConfig"]
+            assert "tools" in tool_config, "tools should be in toolConfig"
+
+            # Find the systemTool for nova_grounding
+            system_tool_found = False
+            for tool in tool_config["tools"]:
+                if "systemTool" in tool:
+                    assert tool["systemTool"]["name"] == "nova_grounding"
+                    system_tool_found = True
+                    break
+
+            assert system_tool_found, "systemTool with nova_grounding should be present"
+            print(f"✓ Async web_search_options correctly transformed to systemTool")
+
+
+def test_bedrock_nova_web_search_options_ignored_for_non_nova():
+    """
+    Test that web_search_options is ignored for non-Nova Bedrock models.
+
+    Nova grounding is only supported on Nova models. For other models,
+    the parameter should be silently ignored.
+    """
+    from litellm.llms.bedrock.chat.converse_transformation import AmazonConverseConfig
+
+    config = AmazonConverseConfig()
+
+    # Should return None for non-Nova models
+    result = config._map_web_search_options({}, "anthropic.claude-3-sonnet-v1")
+    assert result is None
+
+    result = config._map_web_search_options({}, "amazon.titan-text-express-v1")
+    assert result is None
+
+    # Should return systemTool for Nova models
+    result = config._map_web_search_options({}, "amazon.nova-pro-v1:0")
+    assert result is not None
+    system_tool = result.get("systemTool")
+    assert system_tool is not None
+    assert system_tool["name"] == "nova_grounding"
+
+    result2 = config._map_web_search_options({}, "us.amazon.nova-premier-v1:0")
+    assert result2 is not None
+    system_tool2 = result2.get("systemTool")
+    assert system_tool2 is not None
+    assert system_tool2["name"] == "nova_grounding"
+
+
+def test_bedrock_nova_grounding_request_transformation():
+    """
+    Unit test to verify that web_search_options transforms to systemTool in the request.
+    """
+    from unittest.mock import patch, MagicMock
+    from litellm.llms.custom_httpx.http_handler import HTTPHandler
+
+    client = HTTPHandler()
+
+    messages = [{"role": "user", "content": "What is the population of Tokyo?"}]
+
+    with patch.object(client, "post") as mock_post:
+        mock_post.return_value = MagicMock(
+            status_code=200,
+            json=lambda: {
+                "output": {"message": {"role": "assistant", "content": [{"text": "Test"}]}},
+                "stopReason": "end_turn",
+                "usage": {"inputTokens": 10, "outputTokens": 5}
+            }
+        )
+
+        try:
+            response = completion(
+                model="bedrock/us.amazon.nova-pro-v1:0",
+                messages=messages,
+                web_search_options={},
+                max_tokens=100,
+                client=client,
+            )
+        except Exception:
+            pass  # Expected - we're just checking the request
+
+        if mock_post.called:
+            request_body = json.loads(mock_post.call_args.kwargs.get("data", "{}"))
+            print(f"Request body: {json.dumps(request_body, indent=2)}")
+
+            # Verify toolConfig is present with systemTool
+            assert "toolConfig" in request_body, "toolConfig should be in request"
+
+            tool_config = request_body["toolConfig"]
+            assert "tools" in tool_config, "tools should be in toolConfig"
+
+            tools_in_request = tool_config["tools"]
+
+            # Find the systemTool
+            system_tool_found = False
+            for tool in tools_in_request:
+                if "systemTool" in tool:
+                    assert tool["systemTool"]["name"] == "nova_grounding"
+                    system_tool_found = True
+                    break
+
+            assert system_tool_found, "systemTool with nova_grounding should be present"
+            print("✓ web_search_options correctly transformed to systemTool")
diff --git a/tests/test_litellm/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py b/tests/test_litellm/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py
index a22fe13798..e87233a52a 100644
--- a/tests/test_litellm/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py
+++ b/tests/test_litellm/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py
@@ -1138,6 +1138,73 @@ def test_bedrock_create_bedrock_block_different_document_formats():
         assert block["document"]["name"].endswith(f"_{format_type}")
         assert block["document"]["format"] == format_type
 
+def test_bedrock_nova_web_search_options_mapping():
+    """
+    Test that web_search_options is correctly mapped to Nova grounding.
+
+    This follows the LiteLLM pattern for web search where:
+    - Vertex AI maps web_search_options to {"googleSearch": {}}
+    - Anthropic maps web_search_options to {"type": "web_search_20250305", ...}
+    - Nova should map web_search_options to {"systemTool": {"name": "nova_grounding"}}
+    """
+    from litellm.llms.bedrock.chat.converse_transformation import AmazonConverseConfig
+
+    config = AmazonConverseConfig()
+
+    # Test basic mapping for Nova model
+    result = config._map_web_search_options({}, "amazon.nova-pro-v1:0")
+
+    assert result is not None
+    system_tool = result.get("systemTool")
+    assert system_tool is not None
+    assert system_tool["name"] == "nova_grounding"
+
+    # Test with search_context_size (should be ignored for Nova)
+    result2 = config._map_web_search_options(
+        {"search_context_size": "high"},
+        "us.amazon.nova-premier-v1:0"
+    )
+
+    assert result2 is not None
+    system_tool2 = result2.get("systemTool")
+    assert system_tool2 is not None
+    assert system_tool2["name"] == "nova_grounding"
+    # Nova doesn't support search_context_size, so it's just ignored
+
+def test_bedrock_tools_pt_does_not_handle_system_tool():
+    """
+    Verify that _bedrock_tools_pt does NOT handle system_tool format.
+
+    System tools (nova_grounding) should be added via web_search_options,
+    not via the tools parameter directly.
+    """
+    
+    from litellm.litellm_core_utils.prompt_templates.factory import _bedrock_tools_pt
+
+    # Regular function tools should still work
+    tools = [
+        {
+            "type": "function",
+            "function": {
+                "name": "get_weather",
+                "description": "Get the current weather",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "location": {"type": "string"}
+                    },
+                    "required": ["location"]
+                }
+            }
+        }
+    ]
+
+    result = _bedrock_tools_pt(tools=tools)
+
+    assert len(result) == 1
+    tool_spec = result[0].get("toolSpec")
+    assert tool_spec is not None
+    assert tool_spec["name"] == "get_weather"
 
 def test_convert_to_anthropic_tool_result_image_with_cache_control():
     """
@@ -1305,12 +1372,12 @@ def test_convert_to_anthropic_tool_result_image_url_as_http():
     assert result["content"][0]["cache_control"]["type"] == "ephemeral"
 def test_anthropic_messages_pt_server_tool_use_passthrough():
     """
-    Test that anthropic_messages_pt passes through server_tool_use and 
+    Test that anthropic_messages_pt passes through server_tool_use and
     tool_search_tool_result blocks in assistant message content.
-    
+
     These are Anthropic-native content types used for tool search functionality
     that need to be preserved when reconstructing multi-turn conversations.
-    
+
     Fixes: https://github.com/BerriAI/litellm/issues/XXXXX
     """
     from litellm.litellm_core_utils.prompt_templates.factory import anthropic_messages_pt
@@ -1359,15 +1426,15 @@ def test_anthropic_messages_pt_server_tool_use_passthrough():
 
     # Verify we have 3 messages (user, assistant, user)
     assert len(result) == 3
-    
+
     # Verify the assistant message content
     assistant_msg = result[1]
     assert assistant_msg["role"] == "assistant"
     assert isinstance(assistant_msg["content"], list)
-    
+
     # Find the different content block types
     content_types = [block.get("type") for block in assistant_msg["content"]]
-    
+
     # Verify server_tool_use block is preserved
     assert "server_tool_use" in content_types
     server_tool_use_block = next(
@@ -1376,7 +1443,7 @@ def test_anthropic_messages_pt_server_tool_use_passthrough():
     assert server_tool_use_block["id"] == "srvtoolu_01ABC123"
     assert server_tool_use_block["name"] == "tool_search_tool_regex"
     assert server_tool_use_block["input"] == {"query": ".*time.*"}
-    
+
     # Verify tool_search_tool_result block is preserved
     assert "tool_search_tool_result" in content_types
     tool_result_block = next(
@@ -1385,7 +1452,7 @@ def test_anthropic_messages_pt_server_tool_use_passthrough():
     assert tool_result_block["tool_use_id"] == "srvtoolu_01ABC123"
     assert tool_result_block["content"]["type"] == "tool_search_tool_search_result"
     assert tool_result_block["content"]["tool_references"][0]["tool_name"] == "get_time"
-    
+
     # Verify text block is also preserved
     assert "text" in content_types
     text_block = next(

From 324f1f4682c82cc0572398ecb774b862a8804231 Mon Sep 17 00:00:00 2001
From: ruanjiefeng <runjf@qq.com>
Date: Fri, 23 Jan 2026 11:38:14 +0800
Subject: [PATCH 02/11] add Vertex_AI  llm credentials sensitive keywords
 "vertex_credentials" (#19551)

* add Vertex_AI  llm credentials sensitive keywords "vertex_credentials"

* Update test_litellm_logging.py add test case
---
 litellm/litellm_core_utils/litellm_logging.py                 | 1 +
 tests/test_litellm/litellm_core_utils/test_litellm_logging.py | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py
index d3bcfe8200..d512893465 100644
--- a/litellm/litellm_core_utils/litellm_logging.py
+++ b/litellm/litellm_core_utils/litellm_logging.py
@@ -3296,6 +3296,7 @@ def _get_masked_values(
         "token",
         "key",
         "secret",
+        "vertex_credentials",
     ]
     return {
         k: (
diff --git a/tests/test_litellm/litellm_core_utils/test_litellm_logging.py b/tests/test_litellm/litellm_core_utils/test_litellm_logging.py
index e035e193fe..1f3f558a49 100644
--- a/tests/test_litellm/litellm_core_utils/test_litellm_logging.py
+++ b/tests/test_litellm/litellm_core_utils/test_litellm_logging.py
@@ -787,11 +787,13 @@ def test_get_masked_values():
         "presidio_ad_hoc_recognizers": None,
         "aws_bedrock_runtime_endpoint": None,
         "presidio_anonymizer_api_base": None,
+        "vertex_credentials": "{sensitive_api_key}",
     }
     masked_values = _get_masked_values(
         sensitive_object, unmasked_length=4, number_of_asterisks=4
     )
     assert masked_values["presidio_anonymizer_api_base"] is None
+    assert masked_values["vertex_credentials"] == "{s****y}"
 
 
 @pytest.mark.asyncio

From 65e943dc2b99b68e5d2b0a23653c8670c282fa48 Mon Sep 17 00:00:00 2001
From: moh-dev-stack <mohsin.c.zafar@gmail.com>
Date: Fri, 23 Jan 2026 03:39:58 +0000
Subject: [PATCH 03/11] Bugfix/19481 num retries env var type (#19507)

* Enhance error handling for num_retries in Router class to support string values. Add test case to verify conversion from string to int for deployment num_retries.

* Refactor Router class for improved readability by formatting long lines and enhancing exception handling tests for num_retries. Ensure consistent style in test cases for better maintainability.

* Update exception handling for num_retries in Router class to suppress mypy warnings. Add type ignore comment for clarity in type conversion from string to int.
---
 litellm/router.py                             | 19 +++++--
 .../test_router_per_deployment_num_retries.py | 57 +++++++++++++++----
 2 files changed, 59 insertions(+), 17 deletions(-)

diff --git a/litellm/router.py b/litellm/router.py
index 62070d2375..3234366cfb 100644
--- a/litellm/router.py
+++ b/litellm/router.py
@@ -1696,8 +1696,11 @@ class Router:
 
         litellm_params = deployment.get("litellm_params", {})
         dep_num_retries = litellm_params.get("num_retries")
-        if dep_num_retries is not None and isinstance(dep_num_retries, int):
-            exception.num_retries = dep_num_retries  # type: ignore
+        if dep_num_retries is not None:
+            try:
+                exception.num_retries = int(dep_num_retries)  # type: ignore  # Handle both int and str
+            except (ValueError, TypeError):
+                pass  # Skip if value can't be converted to int
 
     def _update_kwargs_with_default_litellm_params(
         self, kwargs: dict, metadata_variable_name: Optional[str] = "metadata"
@@ -4692,9 +4695,12 @@ class Router:
                 # get num_retries from retry policy
                 # Use the model_group captured at the start of the function, or get it from metadata
                 # kwargs.get("model") at this point is the deployment model, not the model_group
-                _model_group_for_retry_policy = model_group or _metadata.get("model_group") or kwargs.get("model")
+                _model_group_for_retry_policy = (
+                    model_group or _metadata.get("model_group") or kwargs.get("model")
+                )
                 _retry_policy_retries = self.get_num_retries_from_retry_policy(
-                    exception=original_exception, model_group=_model_group_for_retry_policy
+                    exception=original_exception,
+                    model_group=_model_group_for_retry_policy,
                 )
                 if _retry_policy_retries is not None:
                     num_retries = _retry_policy_retries
@@ -5879,7 +5885,10 @@ class Router:
             )
             # done reading model["litellm_params"]
             # Check if provider is supported: either in enum or JSON-configured
-            if custom_llm_provider not in litellm.provider_list and not JSONProviderRegistry.exists(custom_llm_provider):
+            if (
+                custom_llm_provider not in litellm.provider_list
+                and not JSONProviderRegistry.exists(custom_llm_provider)
+            ):
                 raise Exception(f"Unsupported provider - {custom_llm_provider}")
 
         #### DEPLOYMENT NAMES INIT ########
diff --git a/tests/test_litellm/test_router_per_deployment_num_retries.py b/tests/test_litellm/test_router_per_deployment_num_retries.py
index 4021ca2807..154ba579e4 100644
--- a/tests/test_litellm/test_router_per_deployment_num_retries.py
+++ b/tests/test_litellm/test_router_per_deployment_num_retries.py
@@ -32,17 +32,17 @@ class TestPerDeploymentNumRetries:
         )
 
         deployment = router.model_list[0]
-        
+
         # Create a mock exception without num_retries
         class MockException(Exception):
             pass
-        
+
         exc = MockException("test error")
         assert not hasattr(exc, "num_retries") or exc.num_retries is None
-        
+
         # Call the helper
         router._set_deployment_num_retries_on_exception(exc, deployment)
-        
+
         # Verify num_retries was set from deployment
         assert exc.num_retries == 5
 
@@ -66,16 +66,16 @@ class TestPerDeploymentNumRetries:
         )
 
         deployment = router.model_list[0]
-        
+
         # Create an exception that already has num_retries
         class MockException(Exception):
             num_retries = 10  # Already set
-        
+
         exc = MockException("test error")
-        
+
         # Call the helper
         router._set_deployment_num_retries_on_exception(exc, deployment)
-        
+
         # Verify num_retries was NOT overridden
         assert exc.num_retries == 10
 
@@ -99,15 +99,15 @@ class TestPerDeploymentNumRetries:
         )
 
         deployment = router.model_list[0]
-        
+
         class MockException(Exception):
             pass
-        
+
         exc = MockException("test error")
-        
+
         # Call the helper
         router._set_deployment_num_retries_on_exception(exc, deployment)
-        
+
         # Verify num_retries was not set (deployment has no num_retries)
         assert not hasattr(exc, "num_retries") or exc.num_retries is None
 
@@ -155,3 +155,36 @@ class TestPerDeploymentNumRetries:
         kwargs = {}
         router._update_kwargs_before_fallbacks(model="test-model", kwargs=kwargs)
         assert kwargs["num_retries"] == 7  # Uses global
+
+    def test_set_deployment_num_retries_with_string_value(self):
+        """
+        Test that _set_deployment_num_retries_on_exception handles string values
+        from environment variables correctly.
+        GitHub Issue: #19481
+        """
+        router = Router(
+            model_list=[
+                {
+                    "model_name": "test-model",
+                    "litellm_params": {
+                        "model": "openai/gpt-4",
+                        "api_key": "test-key",
+                        "num_retries": "6",  # String value (as from env var)
+                    },
+                },
+            ],
+            num_retries=0,  # Global setting
+        )
+
+        deployment = router.model_list[0]
+
+        class MockException(Exception):
+            pass
+
+        exc = MockException("test error")
+
+        # Call the helper
+        router._set_deployment_num_retries_on_exception(exc, deployment)
+
+        # Verify num_retries was converted from string to int
+        assert exc.num_retries == 6

From 6cf7bd7c0fc7962bd63b9d6b87439b82cdee1d0a Mon Sep 17 00:00:00 2001
From: Cesar Garcia <128240629+Chesars@users.noreply.github.com>
Date: Fri, 23 Jan 2026 00:42:15 -0300
Subject: [PATCH 04/11] Fix gpt-image-1.5 cost calculation not including output
 image tokens (#19515)

Fixes #19508

The cost calculation for gpt-image-1.5 was not including image tokens
from output_tokens_details, causing costs to be underreported
(e.g., $0.046 instead of $0.14).

Root cause: The OpenAI image generation API uses Responses API naming
(input_tokens, output_tokens, output_tokens_details) but the cost
calculator expected Chat Completions API naming (prompt_tokens,
completion_tokens, completion_tokens_details).

Changes:
- convert_dict_to_response.py: Map Responses API fields to Chat
  Completions API fields and convert dicts to wrapper objects
- cost_calculator.py: Use usage directly if already transformed,
  avoiding double transformation that lost the wrapper objects
- Added test for gpt-image-1.5 output image token cost calculation
---
 .../convert_dict_to_response.py               | 18 +++++
 .../image_generation/cost_calculator.py       | 20 ++++--
 .../test_gpt_image_cost_calculator.py         | 68 +++++++++++++++++++
 3 files changed, 99 insertions(+), 7 deletions(-)

diff --git a/litellm/litellm_core_utils/llm_response_utils/convert_dict_to_response.py b/litellm/litellm_core_utils/llm_response_utils/convert_dict_to_response.py
index bbe28e3ec2..25ad0a570c 100644
--- a/litellm/litellm_core_utils/llm_response_utils/convert_dict_to_response.py
+++ b/litellm/litellm_core_utils/llm_response_utils/convert_dict_to_response.py
@@ -21,11 +21,13 @@ from litellm.types.utils import (
     ChatCompletionMessageToolCall,
     ChatCompletionRedactedThinkingBlock,
     Choices,
+    CompletionTokensDetailsWrapper,
     Delta,
     EmbeddingResponse,
     Function,
     HiddenParams,
     ImageResponse,
+    PromptTokensDetailsWrapper,
 )
 from litellm.types.utils import Logprobs as TextCompletionLogprobs
 from litellm.types.utils import (
@@ -304,6 +306,22 @@ class LiteLLMResponseObjectHandler:
                     "text_tokens": 0,
                 }
 
+            # Map Responses API naming to Chat Completions API naming for cost calculator
+            if usage.get("prompt_tokens") is None:
+                usage["prompt_tokens"] = usage.get("input_tokens", 0)
+            if usage.get("completion_tokens") is None:
+                usage["completion_tokens"] = usage.get("output_tokens", 0)
+
+            # Convert dicts to wrapper objects so getattr() works in cost calculation
+            if isinstance(usage.get("input_tokens_details"), dict):
+                usage["prompt_tokens_details"] = PromptTokensDetailsWrapper(
+                    **usage["input_tokens_details"]
+                )
+            if isinstance(usage.get("output_tokens_details"), dict):
+                usage["completion_tokens_details"] = CompletionTokensDetailsWrapper(
+                    **usage["output_tokens_details"]
+                )
+
         if model_response_object is None:
             model_response_object = ImageResponse(**response_object)
             return model_response_object
diff --git a/litellm/llms/openai/image_generation/cost_calculator.py b/litellm/llms/openai/image_generation/cost_calculator.py
index 35caaf6e9b..988d562613 100644
--- a/litellm/llms/openai/image_generation/cost_calculator.py
+++ b/litellm/llms/openai/image_generation/cost_calculator.py
@@ -8,8 +8,7 @@ from typing import Optional
 
 from litellm import verbose_logger
 from litellm.litellm_core_utils.llm_cost_calc.utils import generic_cost_per_token
-from litellm.responses.utils import ResponseAPILoggingUtils
-from litellm.types.utils import ImageResponse
+from litellm.types.utils import ImageResponse, Usage
 
 
 def cost_calculator(
@@ -39,11 +38,18 @@ def cost_calculator(
         )
         return 0.0
 
-    # Transform ImageUsage to Usage using the existing helper
-    # ImageUsage has the same format as ResponseAPIUsage
-    chat_usage = ResponseAPILoggingUtils._transform_response_api_usage_to_chat_usage(
-        usage
-    )
+    # If usage is already a Usage object with completion_tokens_details set,
+    # use it directly (it was already transformed in convert_to_image_response)
+    if isinstance(usage, Usage) and usage.completion_tokens_details is not None:
+        chat_usage = usage
+    else:
+        # Transform ImageUsage to Usage using the existing helper
+        # ImageUsage has the same format as ResponseAPIUsage
+        from litellm.responses.utils import ResponseAPILoggingUtils
+
+        chat_usage = ResponseAPILoggingUtils._transform_response_api_usage_to_chat_usage(
+            usage
+        )
 
     # Use generic_cost_per_token for cost calculation
     prompt_cost, completion_cost = generic_cost_per_token(
diff --git a/tests/test_litellm/test_gpt_image_cost_calculator.py b/tests/test_litellm/test_gpt_image_cost_calculator.py
index 0a2a62b6c9..620c073498 100644
--- a/tests/test_litellm/test_gpt_image_cost_calculator.py
+++ b/tests/test_litellm/test_gpt_image_cost_calculator.py
@@ -19,10 +19,13 @@ import pytest
 
 import litellm
 from litellm.types.utils import (
+    CompletionTokensDetailsWrapper,
     ImageResponse,
     ImageObject,
     ImageUsage,
     ImageUsageInputTokensDetails,
+    PromptTokensDetailsWrapper,
+    Usage,
 )
 
 
@@ -202,6 +205,71 @@ class TestGPTImageCostRouting:
         assert cost >= 0
 
 
+class TestGPTImage15OutputImageTokens:
+    """
+    Test for GitHub issue #19508:
+    Image usage calculation does not include image tokens in gpt-image-1.5
+
+    gpt-image-1.5 returns output_tokens_details with separate image_tokens and text_tokens,
+    and these must be correctly included in cost calculation.
+    """
+
+    def test_gpt_image_15_output_image_tokens_cost(self):
+        """
+        Test that output image tokens are correctly included in cost calculation.
+
+        This tests the fix for issue #19508 where output_tokens_details.image_tokens
+        were not being included in the cost calculation, causing costs to be
+        underreported (e.g., $0.046 instead of $0.14).
+        """
+        # Simulate gpt-image-1.5 response with output_tokens_details
+        # This is what the API returns and what convert_to_image_response transforms
+        usage = Usage(
+            prompt_tokens=169,
+            completion_tokens=4599,
+            total_tokens=4768,
+            prompt_tokens_details=PromptTokensDetailsWrapper(
+                text_tokens=169,
+                image_tokens=0,
+            ),
+            completion_tokens_details=CompletionTokensDetailsWrapper(
+                text_tokens=439,
+                image_tokens=4160,
+            ),
+        )
+
+        image_response = ImageResponse(
+            created=1234567890,
+            data=[ImageObject(b64_json="test")],
+        )
+        image_response.usage = usage
+        image_response._hidden_params = {"custom_llm_provider": "openai"}
+
+        cost = litellm.completion_cost(
+            completion_response=image_response,
+            model="gpt-image-1.5",
+            call_type="image_generation",
+            custom_llm_provider="openai",
+        )
+
+        # gpt-image-1.5 pricing:
+        # - input_cost_per_token: 5e-06 ($5/1M for text input)
+        # - output_cost_per_token: 1e-05 ($10/1M for text output)
+        # - output_cost_per_image_token: 3.2e-05 ($32/1M for image output)
+        #
+        # Expected cost:
+        # Input text: 169 * $5/1M = $0.000845
+        # Output text: 439 * $10/1M = $0.00439
+        # Output image: 4160 * $32/1M = $0.13312
+        # Total: $0.138355
+        expected_cost = 169 * 5e-06 + 439 * 1e-05 + 4160 * 3.2e-05
+
+        assert abs(cost - expected_cost) < 1e-6, (
+            f"Expected {expected_cost}, got {cost}. "
+            f"Image tokens may not be included in cost calculation."
+        )
+
+
 class TestCompletionCostIntegration:
     """Test the full completion_cost integration for gpt-image-1"""
 

From 3372430d40cc94223ec4d7f12101f38e4e606455 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=8B=90=E7=88=B7=26=26=E8=80=81=E6=8B=90=E7=98=A6?=
 <geyunfei@gmail.com>
Date: Fri, 23 Jan 2026 11:47:21 +0800
Subject: [PATCH 05/11] Add pricing for volcengine models (deepseek-v3-2,
 glm-4-7, kimi-k2-thinking) (#19335)

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
---
 model_prices_and_context_window.json | 42 ++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 6d87e0b599..3d67bc25b5 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -10219,6 +10219,48 @@
         "mode": "completion",
         "output_cost_per_token": 5e-07
     },
+    "deepseek-v3-2-251201": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "volcengine",
+        "max_input_tokens": 98304,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 0.0,
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "glm-4-7-251222": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "volcengine",
+        "max_input_tokens": 204800,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 0.0,
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "kimi-k2-thinking-251104": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "volcengine",
+        "max_input_tokens": 229376,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 0.0,
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
     "doubao-embedding": {
         "input_cost_per_token": 0.0,
         "litellm_provider": "volcengine",

From 1d04414f305497a14d3005be23717d514619b5aa Mon Sep 17 00:00:00 2001
From: Harshit Jain <48647625+Harshit28j@users.noreply.github.com>
Date: Fri, 23 Jan 2026 09:19:22 +0530
Subject: [PATCH 06/11] feat(datadog): add agent support for LLM Observability
 (#19574)

---
 docs/my-website/docs/observability/datadog.md |  7 +-
 litellm/integrations/datadog/datadog.py       | 17 ++---
 .../integrations/datadog/datadog_handler.py   |  8 +++
 .../integrations/datadog/datadog_llm_obs.py   | 64 ++++++++++++++-----
 .../datadog/test_datadog_llm_obs_agent.py     | 62 ++++++++++++++++++
 5 files changed, 127 insertions(+), 31 deletions(-)
 create mode 100644 tests/test_litellm/integrations/datadog/test_datadog_llm_obs_agent.py

diff --git a/docs/my-website/docs/observability/datadog.md b/docs/my-website/docs/observability/datadog.md
index 7cf91ced34..0f50cbd5c9 100644
--- a/docs/my-website/docs/observability/datadog.md
+++ b/docs/my-website/docs/observability/datadog.md
@@ -73,7 +73,7 @@ Send logs through a local DataDog agent (useful for containerized environments):
 ```shell
 LITELLM_DD_AGENT_HOST="localhost"         # hostname or IP of DataDog agent
 LITELLM_DD_AGENT_PORT="10518"             # [OPTIONAL] port of DataDog agent (default: 10518)
-DD_API_KEY="5f2d0f310***********"         # [OPTIONAL] your datadog API Key (agent handles auth)
+DD_API_KEY="5f2d0f310***********"         # [OPTIONAL] your datadog API Key (Agent handles auth for Logs. REQUIRED for LLM Observability)
 DD_SOURCE="litellm_dev"                   # [OPTIONAL] your datadog source
 ```
 
@@ -84,6 +84,9 @@ When `LITELLM_DD_AGENT_HOST` is set, logs are sent to the agent instead of direc
 
 **Note:** We use `LITELLM_DD_AGENT_HOST` instead of `DD_AGENT_HOST` to avoid conflicts with `ddtrace` which automatically sets `DD_AGENT_HOST` for APM tracing.
 
+> [!IMPORTANT]
+> **Datadog LLM Observability**: `DD_API_KEY` is **REQUIRED** even when using the Datadog Agent (`LITELLM_DD_AGENT_HOST`). The agent acts as a proxy but the API key header is mandatory for the LLM Observability endpoint.
+
 **Step 3**: Start the proxy, make a test request
 
 Start proxy
@@ -203,5 +206,5 @@ LiteLLM supports customizing the following Datadog environment variables
 | `POD_NAME` | Pod name tag (useful for Kubernetes deployments) | "unknown" | ❌ No |
 
 \* **Required when using Direct API** (default): `DD_API_KEY` and `DD_SITE` are required  
-\* **Optional when using DataDog Agent**: Set `LITELLM_DD_AGENT_HOST` to use agent mode; `DD_API_KEY` and `DD_SITE` are not required
+\* **Optional when using DataDog Agent**: Set `LITELLM_DD_AGENT_HOST` to use agent mode; `DD_API_KEY` and `DD_SITE` are not required for **Datadog Logs**. (**Note: `DD_API_KEY` IS REQUIRED for Datadog LLM Observability**)
 
diff --git a/litellm/integrations/datadog/datadog.py b/litellm/integrations/datadog/datadog.py
index 503e8d8c87..735d1005d2 100644
--- a/litellm/integrations/datadog/datadog.py
+++ b/litellm/integrations/datadog/datadog.py
@@ -32,6 +32,7 @@ from litellm.integrations.datadog.datadog_handler import (
     get_datadog_service,
     get_datadog_source,
     get_datadog_tags,
+    get_datadog_base_url_from_env,
 )
 from litellm.litellm_core_utils.dd_tracing import tracer
 from litellm.llms.custom_httpx.http_handler import (
@@ -100,7 +101,9 @@ class DataDogLogger(
                 self._configure_dd_direct_api()
 
             # Optional override for testing
-            self._apply_dd_base_url_override()
+            dd_base_url = get_datadog_base_url_from_env()
+            if dd_base_url:
+                self.intake_url = f"{dd_base_url}/api/v2/logs"
             self.sync_client = _get_httpx_client()
             asyncio.create_task(self.periodic_flush())
             self.flush_lock = asyncio.Lock()
@@ -159,18 +162,6 @@ class DataDogLogger(
         self.DD_API_KEY = os.getenv("DD_API_KEY")
         self.intake_url = f"https://http-intake.logs.{os.getenv('DD_SITE')}/api/v2/logs"
 
-    def _apply_dd_base_url_override(self) -> None:
-        """
-        Apply base URL override for testing purposes
-        """
-        dd_base_url: Optional[str] = (
-            os.getenv("_DATADOG_BASE_URL")
-            or os.getenv("DATADOG_BASE_URL")
-            or os.getenv("DD_BASE_URL")
-        )
-        if dd_base_url is not None:
-            self.intake_url = f"{dd_base_url}/api/v2/logs"
-
     async def async_log_success_event(self, kwargs, response_obj, start_time, end_time):
         """
         Async Log success events to Datadog
diff --git a/litellm/integrations/datadog/datadog_handler.py b/litellm/integrations/datadog/datadog_handler.py
index 26fab77759..e2f30f2f61 100644
--- a/litellm/integrations/datadog/datadog_handler.py
+++ b/litellm/integrations/datadog/datadog_handler.py
@@ -20,6 +20,14 @@ def get_datadog_hostname() -> str:
     return os.getenv("HOSTNAME", "")
 
 
+def get_datadog_base_url_from_env() -> Optional[str]:
+    """
+    Get base URL override from common DD_BASE_URL env var.
+    This is useful for testing or custom endpoints.
+    """
+    return os.getenv("DD_BASE_URL")
+
+
 def get_datadog_env() -> str:
     return os.getenv("DD_ENV", "unknown")
 
diff --git a/litellm/integrations/datadog/datadog_llm_obs.py b/litellm/integrations/datadog/datadog_llm_obs.py
index 6ffdbc0a00..4f6a5b339a 100644
--- a/litellm/integrations/datadog/datadog_llm_obs.py
+++ b/litellm/integrations/datadog/datadog_llm_obs.py
@@ -21,6 +21,7 @@ from litellm.integrations.custom_batch_logger import CustomBatchLogger
 from litellm.integrations.datadog.datadog_handler import (
     get_datadog_service,
     get_datadog_tags,
+    get_datadog_base_url_from_env,
 )
 from litellm.litellm_core_utils.dd_tracing import tracer
 from litellm.litellm_core_utils.prompt_templates.common_utils import (
@@ -43,24 +44,22 @@ class DataDogLLMObsLogger(CustomBatchLogger):
     def __init__(self, **kwargs):
         try:
             verbose_logger.debug("DataDogLLMObs: Initializing logger")
-            if os.getenv("DD_API_KEY", None) is None:
-                raise Exception("DD_API_KEY is not set, set 'DD_API_KEY=<>'")
-            if os.getenv("DD_SITE", None) is None:
-                raise Exception(
-                    "DD_SITE is not set, set 'DD_SITE=<>', example sit = `us5.datadoghq.com`"
-                )
+            # Configure DataDog endpoint (Agent or Direct API)
+            # Use LITELLM_DD_AGENT_HOST to avoid conflicts with ddtrace's DD_AGENT_HOST
+            dd_agent_host = os.getenv("LITELLM_DD_AGENT_HOST")
 
             self.async_client = get_async_httpx_client(
                 llm_provider=httpxSpecialProvider.LoggingCallback
             )
             self.DD_API_KEY = os.getenv("DD_API_KEY")
-            self.DD_SITE = os.getenv("DD_SITE")
-            self.intake_url = (
-                f"https://api.{self.DD_SITE}/api/intake/llm-obs/v1/trace/spans"
-            )
 
-            # testing base url
-            dd_base_url = os.getenv("DD_BASE_URL")
+            if dd_agent_host:
+                self._configure_dd_agent(dd_agent_host=dd_agent_host)
+            else:
+                self._configure_dd_direct_api()
+
+            # Optional override for testing
+            dd_base_url = get_datadog_base_url_from_env()
             if dd_base_url:
                 self.intake_url = f"{dd_base_url}/api/intake/llm-obs/v1/trace/spans"
 
@@ -78,6 +77,38 @@ class DataDogLLMObsLogger(CustomBatchLogger):
             verbose_logger.exception(f"DataDogLLMObs: Error initializing - {str(e)}")
             raise e
 
+    def _configure_dd_agent(self, dd_agent_host: str):
+        """
+        Configure the Datadog logger to send traces to the Agent.
+        """
+        # When using the Agent, LLM Observability Intake does NOT require the API Key
+        # Reference: https://docs.datadoghq.com/llm_observability/setup/sdk/#agent-setup
+
+        # Use specific port for LLM Obs (Trace Agent) to avoid conflict with Logs Agent (10518)
+        agent_port = os.getenv("LITELLM_DD_LLM_OBS_PORT", "8126")
+        self.DD_SITE = "localhost"  # Not used for URL construction in agent mode
+        self.intake_url = (
+            f"http://{dd_agent_host}:{agent_port}/api/intake/llm-obs/v1/trace/spans"
+        )
+        verbose_logger.debug(f"DataDogLLMObs: Using DD Agent at {self.intake_url}")
+
+    def _configure_dd_direct_api(self):
+        """
+        Configure the Datadog logger to send traces directly to the Datadog API.
+        """
+        if not self.DD_API_KEY:
+            raise Exception("DD_API_KEY is not set, set 'DD_API_KEY=<>'")
+
+        self.DD_SITE = os.getenv("DD_SITE")
+        if not self.DD_SITE:
+            raise Exception(
+                "DD_SITE is not set, set 'DD_SITE=<>', example site = `us5.datadoghq.com`"
+            )
+
+        self.intake_url = (
+            f"https://api.{self.DD_SITE}/api/intake/llm-obs/v1/trace/spans"
+        )
+
     def _get_datadog_llm_obs_params(self) -> Dict:
         """
         Get the datadog_llm_observability_params from litellm.datadog_llm_observability_params
@@ -164,13 +195,14 @@ class DataDogLLMObsLogger(CustomBatchLogger):
 
             json_payload = safe_dumps(payload)
 
+            headers = {"Content-Type": "application/json"}
+            if self.DD_API_KEY:
+                headers["DD-API-KEY"] = self.DD_API_KEY
+
             response = await self.async_client.post(
                 url=self.intake_url,
                 content=json_payload,
-                headers={
-                    "DD-API-KEY": self.DD_API_KEY,
-                    "Content-Type": "application/json",
-                },
+                headers=headers,
             )
 
             if response.status_code != 202:
diff --git a/tests/test_litellm/integrations/datadog/test_datadog_llm_obs_agent.py b/tests/test_litellm/integrations/datadog/test_datadog_llm_obs_agent.py
new file mode 100644
index 0000000000..2bb51e1e1b
--- /dev/null
+++ b/tests/test_litellm/integrations/datadog/test_datadog_llm_obs_agent.py
@@ -0,0 +1,62 @@
+import os
+from unittest.mock import patch
+from litellm.integrations.datadog.datadog_llm_obs import DataDogLLMObsLogger
+
+
+def test_datadog_llm_obs_agent_configuration():
+    """
+    Test that DataDog LLM Obs logger correctly configures agent endpoint.
+    """
+    test_env = {
+        "LITELLM_DD_AGENT_HOST": "localhost",
+        "LITELLM_DD_LLM_OBS_PORT": "10518",
+        "DD_API_KEY": "test-api-key",  # Optional, but checking if it's preserved
+    }
+
+    # Ensure DD_SITE is NOT set to verify we don't need it in agent mode
+
+    with patch.dict(os.environ, test_env, clear=True):
+        with patch("asyncio.create_task"):  # Prevent periodic flush task from running
+            dd_logger = DataDogLLMObsLogger()
+
+        expected_url = "http://localhost:10518/api/intake/llm-obs/v1/trace/spans"
+        assert dd_logger.intake_url == expected_url
+        assert dd_logger.DD_API_KEY == "test-api-key"
+
+
+def test_datadog_llm_obs_agent_no_api_key_ok():
+    """
+    Test that agent mode works WITHOUT DD_API_KEY (agent handles auth).
+    """
+    test_env = {
+        "LITELLM_DD_AGENT_HOST": "localhost",
+        # No DD_API_KEY
+    }
+
+    with patch.dict(os.environ, test_env, clear=True):
+        with patch("asyncio.create_task"):
+            # Should NOT raise exception anymore
+            dd_logger = DataDogLLMObsLogger()
+
+            assert dd_logger.DD_API_KEY is None
+            # Default port is 8126 if not set
+            expected_url = "http://localhost:8126/api/intake/llm-obs/v1/trace/spans"
+            assert dd_logger.intake_url == expected_url
+
+
+def test_datadog_llm_obs_direct_api_configuration():
+    """
+    Test that direct API configuration still works as expected.
+    """
+    test_env = {
+        "DD_API_KEY": "direct-api-key",
+        "DD_SITE": "us5.datadoghq.com",
+    }
+
+    with patch.dict(os.environ, test_env, clear=True):
+        with patch("asyncio.create_task"):
+            dd_logger = DataDogLLMObsLogger()
+
+        expected_url = "https://api.us5.datadoghq.com/api/intake/llm-obs/v1/trace/spans"
+        assert dd_logger.intake_url == expected_url
+        assert dd_logger.DD_API_KEY == "direct-api-key"

From 06a749708d5b9d0a2851ce85400aee107dd469bb Mon Sep 17 00:00:00 2001
From: Harshit Jain <48647625+Harshit28j@users.noreply.github.com>
Date: Fri, 23 Jan 2026 09:22:14 +0530
Subject: [PATCH 07/11] feat: add datadog cost management support and fix
 startup callback issue (#19584)

---
 docs/my-website/docs/observability/datadog.md |  45 ++++
 litellm/integrations/callback_configs.json    |  29 ++-
 .../datadog/datadog_cost_management.py        | 202 ++++++++++++++++++
 litellm/proxy/common_utils/callback_utils.py  |  45 ++--
 .../integrations/datadog_cost_management.py   |  27 +++
 .../datadog/test_datadog_cost_management.py   | 169 +++++++++++++++
 6 files changed, 498 insertions(+), 19 deletions(-)
 create mode 100644 litellm/integrations/datadog/datadog_cost_management.py
 create mode 100644 litellm/types/integrations/datadog_cost_management.py
 create mode 100644 tests/test_litellm/integrations/datadog/test_datadog_cost_management.py

diff --git a/docs/my-website/docs/observability/datadog.md b/docs/my-website/docs/observability/datadog.md
index 0f50cbd5c9..6f785be101 100644
--- a/docs/my-website/docs/observability/datadog.md
+++ b/docs/my-website/docs/observability/datadog.md
@@ -7,6 +7,7 @@ import TabItem from '@theme/TabItem';
 LiteLLM Supports logging to the following Datdog Integrations:
 - `datadog` [Datadog Logs](https://docs.datadoghq.com/logs/)
 - `datadog_llm_observability` [Datadog LLM Observability](https://www.datadoghq.com/product/llm-observability/)
+- `datadog_cost_management` [Datadog Cloud Cost Management](#datadog-cloud-cost-management)
 - `ddtrace-run` [Datadog Tracing](#datadog-tracing)
 
 ## Datadog Logs
@@ -164,6 +165,50 @@ On the Datadog LLM Observability page, you should see that both input messages a
 
 
 
+<Image img={require('../../img/dd_llm_obs.png')} />
+
+
+## Datadog Cloud Cost Management
+
+| Feature | Details |
+|---------|---------|
+| **What is logged** | Aggregated LLM Costs (FOCUS format) |
+| **Events** | Periodic Uploads of Aggregated Cost Data |
+| **Product Link** | [Datadog Cloud Cost Management](https://docs.datadoghq.com/cost_management/) |
+
+We will use the `--config` to set `litellm.callbacks = ["datadog_cost_management"]`. This will periodically upload aggregated LLM cost data to Datadog.
+
+**Step 1**: Create a `config.yaml` file and set `litellm_settings`: `success_callback`
+
+```yaml
+model_list:
+ - model_name: gpt-3.5-turbo
+    litellm_params:
+      model: gpt-3.5-turbo
+litellm_settings:
+  callbacks: ["datadog_cost_management"]
+```
+
+**Step 2**: Set Required env variables
+
+```shell
+DD_API_KEY="your-api-key"
+DD_APP_KEY="your-app-key" # REQUIRED for Cost Management
+DD_SITE="us5.datadoghq.com"
+```
+
+**Step 3**: Start the proxy
+
+```shell
+litellm --config config.yaml
+```
+
+**How it works**
+* LiteLLM aggregates costs in-memory by Provider, Model, Date, and Tags.
+* Requires `DD_APP_KEY` for the Custom Costs API.
+* Costs are uploaded periodically (flushed).
+
+
 ### Datadog Tracing
 
 Use `ddtrace-run` to enable [Datadog Tracing](https://ddtrace.readthedocs.io/en/stable/installation_quickstart.html) on litellm proxy
diff --git a/litellm/integrations/callback_configs.json b/litellm/integrations/callback_configs.json
index 6b30b6b736..6a003b8c49 100644
--- a/litellm/integrations/callback_configs.json
+++ b/litellm/integrations/callback_configs.json
@@ -83,6 +83,33 @@
     },
     "description": "Datadog Logging Integration"
   },
+  {
+    "id": "datadog_cost_management",
+    "displayName": "Datadog Cost Management",
+    "logo": "datadog.png",
+    "supports_key_team_logging": false,
+    "dynamic_params": {
+      "dd_api_key": {
+        "type": "password",
+        "ui_name": "API Key",
+        "description": "Datadog API key for authentication",
+        "required": true
+      },
+      "dd_app_key": {
+        "type": "password",
+        "ui_name": "App Key",
+        "description": "Datadog Application Key for Cloud Cost Management",
+        "required": true
+      },
+      "dd_site": {
+        "type": "text",
+        "ui_name": "Site",
+        "description": "Datadog site URL (e.g., us5.datadoghq.com)",
+        "required": true
+      }
+    },
+    "description": "Datadog Cloud Cost Management Integration"
+  },
   {
     "id": "lago",
     "displayName": "Lago",
@@ -407,4 +434,4 @@
     },
     "description": "SQS Queue (AWS) Logging Integration"
   }
-]
+]
\ No newline at end of file
diff --git a/litellm/integrations/datadog/datadog_cost_management.py b/litellm/integrations/datadog/datadog_cost_management.py
new file mode 100644
index 0000000000..9bfb2aba71
--- /dev/null
+++ b/litellm/integrations/datadog/datadog_cost_management.py
@@ -0,0 +1,202 @@
+import asyncio
+import os
+import time
+from datetime import datetime
+from typing import Dict, List, Optional
+
+from litellm._logging import verbose_logger
+from litellm.integrations.custom_batch_logger import CustomBatchLogger
+from litellm.llms.custom_httpx.http_handler import (
+    get_async_httpx_client,
+    httpxSpecialProvider,
+)
+from litellm.types.integrations.datadog_cost_management import (
+    DatadogFOCUSCostEntry,
+)
+from litellm.types.utils import StandardLoggingPayload
+
+
+class DatadogCostManagementLogger(CustomBatchLogger):
+    def __init__(self, **kwargs):
+        self.dd_api_key = os.getenv("DD_API_KEY")
+        self.dd_app_key = os.getenv("DD_APP_KEY")
+        self.dd_site = os.getenv("DD_SITE", "datadoghq.com")
+
+        if not self.dd_api_key or not self.dd_app_key:
+            verbose_logger.warning(
+                "Datadog Cost Management: DD_API_KEY and DD_APP_KEY are required. Integration will not work."
+            )
+
+        self.upload_url = f"https://api.{self.dd_site}/api/v2/cost/custom_costs"
+
+        self.async_client = get_async_httpx_client(
+            llm_provider=httpxSpecialProvider.LoggingCallback
+        )
+
+        # Initialize lock and start periodic flush task
+        self.flush_lock = asyncio.Lock()
+        asyncio.create_task(self.periodic_flush())
+
+        # Check if flush_lock is already in kwargs to avoid double passing (unlikely but safe)
+        if "flush_lock" not in kwargs:
+            kwargs["flush_lock"] = self.flush_lock
+
+        super().__init__(**kwargs)
+
+    async def async_log_success_event(self, kwargs, response_obj, start_time, end_time):
+        try:
+            standard_logging_object: Optional[StandardLoggingPayload] = kwargs.get(
+                "standard_logging_object", None
+            )
+
+            if standard_logging_object is None:
+                return
+
+            # Only log if there is a cost associated
+            if standard_logging_object.get("response_cost", 0) > 0:
+                self.log_queue.append(standard_logging_object)
+
+                if len(self.log_queue) >= self.batch_size:
+                    await self.async_send_batch()
+
+        except Exception as e:
+            verbose_logger.exception(
+                f"Datadog Cost Management: Error in async_log_success_event: {str(e)}"
+            )
+
+    async def async_send_batch(self):
+        if not self.log_queue:
+            return
+
+        try:
+            # Aggregate costs from the batch
+            aggregated_entries = self._aggregate_costs(self.log_queue)
+
+            if not aggregated_entries:
+                return
+
+            # Send to Datadog
+            await self._upload_to_datadog(aggregated_entries)
+
+            # Clear queue only on success (or if we decide to drop on failure)
+            # CustomBatchLogger clears queue in flush_queue, so we just process here
+
+        except Exception as e:
+            verbose_logger.exception(
+                f"Datadog Cost Management: Error in async_send_batch: {str(e)}"
+            )
+
+    def _aggregate_costs(
+        self, logs: List[StandardLoggingPayload]
+    ) -> List[DatadogFOCUSCostEntry]:
+        """
+        Aggregates costs by Provider, Model, and Date.
+        Returns a list of DatadogFOCUSCostEntry.
+        """
+        aggregator: Dict[str, DatadogFOCUSCostEntry] = {}
+
+        for log in logs:
+            try:
+                # Extract keys for aggregation
+                provider = log.get("custom_llm_provider") or "unknown"
+                model = log.get("model") or "unknown"
+                cost = log.get("response_cost", 0)
+
+                if cost == 0:
+                    continue
+
+                # Get date strings (FOCUS format requires specific keys, but for aggregation we group by Day)
+                # UTC date
+                # We interpret "ChargePeriod" as the day of the request.
+                ts = log.get("startTime") or time.time()
+                dt = datetime.fromtimestamp(ts)
+                date_str = dt.strftime("%Y-%m-%d")
+
+                # ChargePeriodStart and End
+                # If we want daily granularity, end date is usually same day or next day?
+                # Datadog Custom Costs usually expects periods.
+                # "ChargePeriodStart": "2023-01-01", "ChargePeriodEnd": "2023-12-31" in example.
+                # If we send daily, we can say Start=Date, End=Date.
+
+                # Grouping Key: Provider + Model + Date + Tags?
+                # For simplicity, let's aggregate by Provider + Model + Date first.
+                # If we handle tags, we need to include them in the key.
+
+                tags = self._extract_tags(log)
+                tags_key = tuple(sorted(tags.items())) if tags else ()
+
+                key = (provider, model, date_str, tags_key)
+
+                if key not in aggregator:
+                    aggregator[key] = {
+                        "ProviderName": provider,
+                        "ChargeDescription": f"LLM Usage for {model}",
+                        "ChargePeriodStart": date_str,
+                        "ChargePeriodEnd": date_str,
+                        "BilledCost": 0.0,
+                        "BillingCurrency": "USD",
+                        "Tags": tags if tags else None,
+                    }
+
+                aggregator[key]["BilledCost"] += cost
+
+            except Exception as e:
+                verbose_logger.warning(
+                    f"Error processing log for cost aggregation: {e}"
+                )
+                continue
+
+        return list(aggregator.values())
+
+    def _extract_tags(self, log: StandardLoggingPayload) -> Dict[str, str]:
+        from litellm.integrations.datadog.datadog_handler import (
+            get_datadog_env,
+            get_datadog_hostname,
+            get_datadog_pod_name,
+            get_datadog_service,
+        )
+
+        tags = {
+            "env": get_datadog_env(),
+            "service": get_datadog_service(),
+            "host": get_datadog_hostname(),
+            "pod_name": get_datadog_pod_name(),
+        }
+
+        # Add metadata as tags
+        metadata = log.get("metadata", {})
+        if metadata:
+            # Add user info
+            if "user_api_key_alias" in metadata:
+                tags["user"] = str(metadata["user_api_key_alias"])
+            if "user_api_key_team_alias" in metadata:
+                tags["team"] = str(metadata["user_api_key_team_alias"])
+            if "model_group" in metadata:
+                tags["model_group"] = str(metadata["model_group"])
+
+        return tags
+
+    async def _upload_to_datadog(self, payload: List[Dict]):
+        if not self.dd_api_key or not self.dd_app_key:
+            return
+
+        headers = {
+            "Content-Type": "application/json",
+            "DD-API-KEY": self.dd_api_key,
+            "DD-APPLICATION-KEY": self.dd_app_key,
+        }
+
+        # The API endpoint expects a list of objects directly in the body (file content behavior)
+        from litellm.litellm_core_utils.safe_json_dumps import safe_dumps
+
+        data_json = safe_dumps(payload)
+
+        response = await self.async_client.put(
+            self.upload_url, content=data_json, headers=headers
+        )
+
+        response.raise_for_status()
+
+        verbose_logger.debug(
+            f"Datadog Cost Management: Uploaded {len(payload)} cost entries. Status: {response.status_code}"
+        )
diff --git a/litellm/proxy/common_utils/callback_utils.py b/litellm/proxy/common_utils/callback_utils.py
index cb434da55b..a9e9bd237b 100644
--- a/litellm/proxy/common_utils/callback_utils.py
+++ b/litellm/proxy/common_utils/callback_utils.py
@@ -274,11 +274,20 @@ def initialize_callbacks_on_proxy(  # noqa: PLR0915
                     WebSearchInterceptionLogger,
                 )
 
-                websearch_interception_obj = WebSearchInterceptionLogger.initialize_from_proxy_config(
-                    litellm_settings=litellm_settings,
-                    callback_specific_params=callback_specific_params,
+                websearch_interception_obj = (
+                    WebSearchInterceptionLogger.initialize_from_proxy_config(
+                        litellm_settings=litellm_settings,
+                        callback_specific_params=callback_specific_params,
+                    )
                 )
                 imported_list.append(websearch_interception_obj)
+            elif isinstance(callback, str) and callback == "datadog_cost_management":
+                from litellm.integrations.datadog.datadog_cost_management import (
+                    DatadogCostManagementLogger,
+                )
+
+                datadog_cost_management_obj = DatadogCostManagementLogger()
+                imported_list.append(datadog_cost_management_obj)
             elif isinstance(callback, CustomLogger):
                 imported_list.append(callback)
             else:
@@ -353,17 +362,17 @@ def get_remaining_tokens_and_requests_from_request_data(data: Dict) -> Dict[str,
     remaining_requests_variable_name = f"litellm-key-remaining-requests-{model_group}"
     remaining_requests = _metadata.get(remaining_requests_variable_name, None)
     if remaining_requests:
-        headers[f"x-litellm-key-remaining-requests-{h11_model_group_name}"] = (
-            remaining_requests
-        )
+        headers[
+            f"x-litellm-key-remaining-requests-{h11_model_group_name}"
+        ] = remaining_requests
 
     # Remaining Tokens
     remaining_tokens_variable_name = f"litellm-key-remaining-tokens-{model_group}"
     remaining_tokens = _metadata.get(remaining_tokens_variable_name, None)
     if remaining_tokens:
-        headers[f"x-litellm-key-remaining-tokens-{h11_model_group_name}"] = (
-            remaining_tokens
-        )
+        headers[
+            f"x-litellm-key-remaining-tokens-{h11_model_group_name}"
+        ] = remaining_tokens
 
     return headers
 
@@ -412,9 +421,9 @@ def add_guardrail_response_to_standard_logging_object(
 ):
     if litellm_logging_obj is None:
         return
-    standard_logging_object: Optional[StandardLoggingPayload] = (
-        litellm_logging_obj.model_call_details.get("standard_logging_object")
-    )
+    standard_logging_object: Optional[
+        StandardLoggingPayload
+    ] = litellm_logging_obj.model_call_details.get("standard_logging_object")
     if standard_logging_object is None:
         return
     guardrail_information = standard_logging_object.get("guardrail_information", [])
@@ -443,7 +452,9 @@ def get_metadata_variable_name_from_kwargs(
     return "litellm_metadata" if "litellm_metadata" in kwargs else "metadata"
 
 
-def process_callback(_callback: str, callback_type: str, environment_variables: dict) -> dict:
+def process_callback(
+    _callback: str, callback_type: str, environment_variables: dict
+) -> dict:
     """Process a single callback and return its data with environment variables"""
     env_vars = CustomLogger.get_callback_env_vars(_callback)
 
@@ -455,11 +466,9 @@ def process_callback(_callback: str, callback_type: str, environment_variables:
         else:
             env_vars_dict[_var] = env_variable
 
-    return {
-        "name": _callback,
-        "variables": env_vars_dict,
-        "type": callback_type
-    }
+    return {"name": _callback, "variables": env_vars_dict, "type": callback_type}
+
+
 def normalize_callback_names(callbacks: Iterable[Any]) -> List[Any]:
     if callbacks is None:
         return []
diff --git a/litellm/types/integrations/datadog_cost_management.py b/litellm/types/integrations/datadog_cost_management.py
new file mode 100644
index 0000000000..fe04f43ea0
--- /dev/null
+++ b/litellm/types/integrations/datadog_cost_management.py
@@ -0,0 +1,27 @@
+from typing import Dict, Optional, TypedDict
+
+
+from litellm.types.integrations.custom_logger import StandardCustomLoggerInitParams
+
+
+class DatadogCostManagementInitParams(StandardCustomLoggerInitParams):
+    """
+    Init params for Datadog Cost Management
+    """
+
+    datadog_cost_management_params: Optional[Dict] = None
+
+
+class DatadogFOCUSCostEntry(TypedDict):
+    """
+    Represents a single cost line item in the FOCUS format.
+    Ref: https://focus.finops.org/#specification
+    """
+
+    ProviderName: str
+    ChargeDescription: str
+    ChargePeriodStart: str
+    ChargePeriodEnd: str
+    BilledCost: float
+    BillingCurrency: str
+    Tags: Optional[Dict[str, str]]
diff --git a/tests/test_litellm/integrations/datadog/test_datadog_cost_management.py b/tests/test_litellm/integrations/datadog/test_datadog_cost_management.py
new file mode 100644
index 0000000000..be2084969a
--- /dev/null
+++ b/tests/test_litellm/integrations/datadog/test_datadog_cost_management.py
@@ -0,0 +1,169 @@
+import os
+import time
+from unittest.mock import AsyncMock
+
+import pytest
+from httpx import Response
+
+from litellm.integrations.datadog.datadog_cost_management import (
+    DatadogCostManagementLogger,
+)
+from litellm.types.utils import StandardLoggingPayload
+
+
+@pytest.fixture
+def clean_env():
+    # Save original env
+    original_api_key = os.environ.get("DD_API_KEY")
+    original_app_key = os.environ.get("DD_APP_KEY")
+    original_site = os.environ.get("DD_SITE")
+
+    # Set test env
+    os.environ["DD_API_KEY"] = "test_api_key"
+    os.environ["DD_APP_KEY"] = "test_app_key"
+    os.environ["DD_SITE"] = "test.datadoghq.com"
+
+    yield
+
+    # Restore original env
+    if original_api_key:
+        os.environ["DD_API_KEY"] = original_api_key
+    else:
+        del os.environ["DD_API_KEY"]
+
+    if original_app_key:
+        os.environ["DD_APP_KEY"] = original_app_key
+    else:
+        del os.environ["DD_APP_KEY"]
+
+    if original_site:
+        os.environ["DD_SITE"] = original_site
+    else:
+        del os.environ["DD_SITE"]
+
+
+@pytest.mark.asyncio
+async def test_init(clean_env):
+    """
+    Test initialization sets up clients and url correctly
+    """
+    logger = DatadogCostManagementLogger()
+    assert logger.dd_api_key == "test_api_key"
+    assert logger.dd_app_key == "test_app_key"
+    assert (
+        logger.upload_url == "https://api.test.datadoghq.com/api/v2/cost/custom_costs"
+    )
+
+
+@pytest.mark.asyncio
+async def test_aggregate_costs(clean_env):
+    """
+    Test that costs are correctly aggregated by provider, model, and date
+    """
+    logger = DatadogCostManagementLogger()
+
+    # Mock some log payloads
+    now = time.time()
+    day_str = time.strftime("%Y-%m-%d", time.localtime(now))
+
+    logs = [
+        StandardLoggingPayload(
+            custom_llm_provider="openai",
+            model="gpt-4",
+            response_cost=0.01,
+            startTime=now,
+            metadata={"user_api_key_team_alias": "team-a"},
+        ),
+        StandardLoggingPayload(
+            custom_llm_provider="openai",
+            model="gpt-4",
+            response_cost=0.02,
+            startTime=now,
+            metadata={"user_api_key_team_alias": "team-a"},
+        ),
+        StandardLoggingPayload(
+            custom_llm_provider="anthropic",
+            model="claude-3",
+            response_cost=0.05,
+            startTime=now,
+        ),
+    ]
+
+    aggregated = logger._aggregate_costs(logs)
+
+    assert len(aggregated) == 2
+
+    # Check OpenAI entry
+    openai_entry = next(e for e in aggregated if e["ProviderName"] == "openai")
+    assert openai_entry["BilledCost"] == 0.03
+    assert openai_entry["ChargeDescription"] == "LLM Usage for gpt-4"
+    assert openai_entry["ChargePeriodStart"] == day_str
+    assert openai_entry["Tags"]["team"] == "team-a"
+    assert "env" in openai_entry["Tags"]
+    assert "service" in openai_entry["Tags"]
+
+    # Check Anthropic entry
+    anthropic_entry = next(e for e in aggregated if e["ProviderName"] == "anthropic")
+    assert anthropic_entry["BilledCost"] == 0.05
+
+
+@pytest.mark.asyncio
+async def test_async_log_success_event(clean_env):
+    """
+    Test that logs are added to queue
+    """
+    logger = DatadogCostManagementLogger(batch_size=10)
+
+    await logger.async_log_success_event(
+        kwargs={"standard_logging_object": {"response_cost": 0.01}},
+        response_obj={},
+        start_time=time.time(),
+        end_time=time.time(),
+    )
+
+    assert len(logger.log_queue) == 1
+    assert logger.log_queue[0]["response_cost"] == 0.01
+
+    # Test zero cost ignored
+    await logger.async_log_success_event(
+        kwargs={"standard_logging_object": {"response_cost": 0.0}},
+        response_obj={},
+        start_time=time.time(),
+        end_time=time.time(),
+    )
+
+    assert len(logger.log_queue) == 1
+
+
+@pytest.mark.asyncio
+async def test_async_send_batch(clean_env):
+    """
+    Test that batch is aggregated and uploaded
+    """
+    logger = DatadogCostManagementLogger()
+    logger.async_client = AsyncMock()
+    logger.async_client.put.return_value = Response(202, json={"status": "ok"})
+
+    # Add logs directly to queue
+    logger.log_queue = [
+        StandardLoggingPayload(
+            custom_llm_provider="openai",
+            model="gpt-4",
+            response_cost=0.01,
+            startTime=time.time(),
+        )
+    ]
+
+    await logger.async_send_batch()
+
+    # Verify API called
+    assert logger.async_client.put.called
+    call_args = logger.async_client.put.call_args
+    assert call_args[0][0] == "https://api.test.datadoghq.com/api/v2/cost/custom_costs"
+
+    import json
+
+    # Use call_args.kwargs['content']
+    content = json.loads(call_args[1]["content"])
+    assert content[0]["ProviderName"] == "openai"
+    assert content[0]["BilledCost"] == 0.01

From 89ecdc405dd95ac7739d450cd2718153ec270964 Mon Sep 17 00:00:00 2001
From: Harshit Jain <48647625+Harshit28j@users.noreply.github.com>
Date: Fri, 23 Jan 2026 09:26:41 +0530
Subject: [PATCH 08/11] fix: recursive pydantic issue (#19531)

---
 litellm/integrations/custom_guardrail.py      | 16 +++-
 litellm/integrations/langfuse/langfuse.py     | 14 ++--
 .../test_custom_guardrail_recursion.py        | 73 +++++++++++++++++++
 3 files changed, 94 insertions(+), 9 deletions(-)
 create mode 100644 tests/test_litellm/integrations/test_custom_guardrail_recursion.py

diff --git a/litellm/integrations/custom_guardrail.py b/litellm/integrations/custom_guardrail.py
index 6a76b57e7f..a5bb530fc5 100644
--- a/litellm/integrations/custom_guardrail.py
+++ b/litellm/integrations/custom_guardrail.py
@@ -516,7 +516,9 @@ class CustomGuardrail(CustomLogger):
         from litellm.types.utils import GuardrailMode
 
         # Use event_type if provided, otherwise fall back to self.event_hook
-        guardrail_mode: Union[GuardrailEventHooks, GuardrailMode, List[GuardrailEventHooks]]
+        guardrail_mode: Union[
+            GuardrailEventHooks, GuardrailMode, List[GuardrailEventHooks]
+        ]
         if event_type is not None:
             guardrail_mode = event_type
         elif isinstance(self.event_hook, Mode):
@@ -524,11 +526,21 @@ class CustomGuardrail(CustomLogger):
         else:
             guardrail_mode = self.event_hook  # type: ignore[assignment]
 
+        from litellm.litellm_core_utils.core_helpers import (
+            filter_exceptions_from_params,
+        )
+
+        # Sanitize the response to ensure it's JSON serializable and free of circular refs
+        # This prevents RecursionErrors in downstream loggers (Langfuse, Datadog, etc.)
+        clean_guardrail_response = filter_exceptions_from_params(
+            guardrail_json_response
+        )
+
         slg = StandardLoggingGuardrailInformation(
             guardrail_name=self.guardrail_name,
             guardrail_provider=guardrail_provider,
             guardrail_mode=guardrail_mode,
-            guardrail_response=guardrail_json_response,
+            guardrail_response=clean_guardrail_response,
             guardrail_status=guardrail_status,
             start_time=start_time,
             end_time=end_time,
diff --git a/litellm/integrations/langfuse/langfuse.py b/litellm/integrations/langfuse/langfuse.py
index 8087c17caf..b64af66ce9 100644
--- a/litellm/integrations/langfuse/langfuse.py
+++ b/litellm/integrations/langfuse/langfuse.py
@@ -23,6 +23,7 @@ from litellm.constants import MAX_LANGFUSE_INITIALIZED_CLIENTS
 from litellm.litellm_core_utils.core_helpers import (
     safe_deep_copy,
     reconstruct_model_name,
+    filter_exceptions_from_params,
 )
 from litellm.litellm_core_utils.redact_messages import redact_user_api_key_info
 from litellm.llms.custom_httpx.http_handler import _get_httpx_client
@@ -71,9 +72,8 @@ def _extract_cache_read_input_tokens(usage_obj) -> int:
     # Check prompt_tokens_details.cached_tokens (used by Gemini and other providers)
     if hasattr(usage_obj, "prompt_tokens_details"):
         prompt_tokens_details = getattr(usage_obj, "prompt_tokens_details", None)
-        if (
-            prompt_tokens_details is not None
-            and hasattr(prompt_tokens_details, "cached_tokens")
+        if prompt_tokens_details is not None and hasattr(
+            prompt_tokens_details, "cached_tokens"
         ):
             cached_tokens = getattr(prompt_tokens_details, "cached_tokens", None)
             if (
@@ -526,7 +526,6 @@ class LangFuseLogger:
         verbose_logger.debug("Langfuse Layer Logging - logging to langfuse v2")
 
         try:
-            metadata = metadata or {}
             standard_logging_object: Optional[StandardLoggingPayload] = cast(
                 Optional[StandardLoggingPayload],
                 kwargs.get("standard_logging_object", None),
@@ -692,9 +691,10 @@ class LangFuseLogger:
 
             clean_metadata["litellm_response_cost"] = cost
             if standard_logging_object is not None:
-                clean_metadata["hidden_params"] = standard_logging_object[
-                    "hidden_params"
-                ]
+                hidden_params = standard_logging_object.get("hidden_params", {})
+                clean_metadata["hidden_params"] = filter_exceptions_from_params(
+                    hidden_params
+                )
 
             if (
                 litellm.langfuse_default_tags is not None
diff --git a/tests/test_litellm/integrations/test_custom_guardrail_recursion.py b/tests/test_litellm/integrations/test_custom_guardrail_recursion.py
new file mode 100644
index 0000000000..f05b5848bd
--- /dev/null
+++ b/tests/test_litellm/integrations/test_custom_guardrail_recursion.py
@@ -0,0 +1,73 @@
+import pytest
+from litellm.integrations.custom_guardrail import CustomGuardrail
+from litellm.types.guardrails import GuardrailEventHooks
+import json
+
+
+class TestCustomGuardrailRecursion:
+    """
+    Specific tests for the circular reference / RecursionError fix in logging.
+    """
+
+    def test_log_guardrail_information_handles_circular_references(self):
+        """
+        Test that add_standard_logging method sanitizes input data containing circular references
+        instead of crashing.
+
+        This reproduces the Langfuse crash scenario:
+        Request -> Metadata -> GuardrailResponse -> DebugContext -> Request
+        """
+        guardrail = CustomGuardrail(
+            guardrail_name="recursion_test_guardrail",
+            event_hook=GuardrailEventHooks.pre_call,
+        )
+
+        # 1. Setup Circular Data
+        request_data = {"user_id": "test_recursive_user"}
+        metadata = {"session_id": "123"}
+        request_data["metadata"] = metadata
+
+        # Create the danger: Guardrail Response holding a reference back to request_data
+        dirty_response = {
+            "flagged": False,
+            "debug_context": request_data,  # <--- ACCESS TO ROOT (Circular Ref)
+        }
+
+        # 2. Invoke the logging method
+        # If the fix is working, this will NOT raise RecursionError
+        try:
+            guardrail.add_standard_logging_guardrail_information_to_request_data(
+                guardrail_json_response=dirty_response,
+                request_data=request_data,
+                guardrail_status="success",
+                start_time=1.0,
+                end_time=2.0,
+                duration=1.0,
+                masked_entity_count={},
+                event_type=GuardrailEventHooks.pre_call,
+            )
+        except RecursionError:
+            pytest.fail(
+                "RecursionError raised! The cyclic reference sanitization failed."
+            )
+
+        # 3. Verify the data stored is safe
+        stored_info = request_data["metadata"][
+            "standard_logging_guardrail_information"
+        ][0]
+        stored_response = stored_info["guardrail_response"]
+
+        # Check that we can dump it to JSON without crashing (Ultimate proof)
+        try:
+            json.dumps(stored_response)
+        except Exception as e:
+            pytest.fail(f"Stored data is not JSON serializable: {e}")
+
+        # Check content - keys should be preserved but recursion broken
+        assert "debug_context" in stored_response
+        debug_context = stored_response["debug_context"]
+
+        # In a sanitized copy, the nested metadata should be a copy, not the original live dict
+        assert debug_context["user_id"] == "test_recursive_user"
+        # The 'metadata' inside 'debug_context' would be where recursion stops or is filtered
+        assert "metadata" in debug_context

From 188c2315adaaa401669072cdf04d9b0b80678f58 Mon Sep 17 00:00:00 2001
From: Chesars <cesarponce19544@gmail.com>
Date: Fri, 23 Jan 2026 15:11:37 -0300
Subject: [PATCH 09/11] feat(vercel_ai_gateway): add embeddings support

Add support for /embeddings endpoint via Vercel AI Gateway.

Closes #19658

Changes:
- Add VercelAIGatewayEmbeddingConfig in litellm/llms/vercel_ai_gateway/embedding/
- Register provider in utils.py and main.py
- Add unit tests for embedding transformation
- Update documentation with embeddings examples

Usage:
```python
from litellm import embedding

response = embedding(
    model="vercel_ai_gateway/openai/text-embedding-3-small",
    input="Hello world",
    api_key="your-api-key"
)
```
---
 .../docs/providers/vercel_ai_gateway.md       |  36 ++-
 .../vercel_ai_gateway/embedding/__init__.py   |   0
 .../embedding/transformation.py               | 176 ++++++++++++++
 litellm/main.py                               |  30 +++
 litellm/utils.py                              |   6 +
 .../vercel_ai_gateway/embedding/__init__.py   |   0
 .../test_vercel_ai_gateway_embedding.py       | 218 ++++++++++++++++++
 7 files changed, 464 insertions(+), 2 deletions(-)
 create mode 100644 litellm/llms/vercel_ai_gateway/embedding/__init__.py
 create mode 100644 litellm/llms/vercel_ai_gateway/embedding/transformation.py
 create mode 100644 tests/test_litellm/llms/vercel_ai_gateway/embedding/__init__.py
 create mode 100644 tests/test_litellm/llms/vercel_ai_gateway/embedding/test_vercel_ai_gateway_embedding.py

diff --git a/docs/my-website/docs/providers/vercel_ai_gateway.md b/docs/my-website/docs/providers/vercel_ai_gateway.md
index 91f0a18ea1..3ff007171e 100644
--- a/docs/my-website/docs/providers/vercel_ai_gateway.md
+++ b/docs/my-website/docs/providers/vercel_ai_gateway.md
@@ -11,7 +11,7 @@ import TabItem from '@theme/TabItem';
 | Provider Route on LiteLLM | `vercel_ai_gateway/` |
 | Link to Provider Doc | [Vercel AI Gateway Documentation ↗](https://vercel.com/docs/ai-gateway) |
 | Base URL | `https://ai-gateway.vercel.sh/v1` |
-| Supported Operations | `/chat/completions`, `/models` |
+| Supported Operations | `/chat/completions`, `/embeddings`, `/models` |
 
 <br />
 <br />
@@ -73,7 +73,7 @@ messages = [{"content": "Hello, how are you?", "role": "user"}]
 
 # Vercel AI Gateway call with streaming
 response = completion(
-    model="vercel_ai_gateway/openai/gpt-4o", 
+    model="vercel_ai_gateway/openai/gpt-4o",
     messages=messages,
     stream=True
 )
@@ -82,6 +82,33 @@ for chunk in response:
     print(chunk)
 ```
 
+### Embeddings
+
+```python showLineNumbers title="Vercel AI Gateway Embeddings"
+import os
+from litellm import embedding
+
+os.environ["VERCEL_AI_GATEWAY_API_KEY"] = "your-api-key"
+
+# Vercel AI Gateway embedding call
+response = embedding(
+    model="vercel_ai_gateway/openai/text-embedding-3-small",
+    input="Hello world"
+)
+
+print(response.data[0]["embedding"][:5])  # Print first 5 dimensions
+```
+
+You can also specify the `dimensions` parameter:
+
+```python showLineNumbers title="Vercel AI Gateway Embeddings with Dimensions"
+response = embedding(
+    model="vercel_ai_gateway/openai/text-embedding-3-small",
+    input=["Hello world", "Goodbye world"],
+    dimensions=768
+)
+```
+
 ## Usage - LiteLLM Proxy
 
 Add the following to your LiteLLM Proxy configuration file:
@@ -97,6 +124,11 @@ model_list:
     litellm_params:
       model: vercel_ai_gateway/anthropic/claude-4-sonnet
       api_key: os.environ/VERCEL_AI_GATEWAY_API_KEY
+
+  - model_name: text-embedding-3-small-gateway
+    litellm_params:
+      model: vercel_ai_gateway/openai/text-embedding-3-small
+      api_key: os.environ/VERCEL_AI_GATEWAY_API_KEY
 ```
 
 Start your LiteLLM Proxy server:
diff --git a/litellm/llms/vercel_ai_gateway/embedding/__init__.py b/litellm/llms/vercel_ai_gateway/embedding/__init__.py
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/litellm/llms/vercel_ai_gateway/embedding/transformation.py b/litellm/llms/vercel_ai_gateway/embedding/transformation.py
new file mode 100644
index 0000000000..7238b05f10
--- /dev/null
+++ b/litellm/llms/vercel_ai_gateway/embedding/transformation.py
@@ -0,0 +1,176 @@
+"""
+Vercel AI Gateway Embedding API Configuration.
+
+This module provides the configuration for Vercel AI Gateway's Embedding API.
+Vercel AI Gateway is OpenAI-compatible and supports embeddings via the /v1/embeddings endpoint.
+
+Docs: https://vercel.com/docs/ai-gateway/openai-compat/embeddings
+"""
+
+from typing import TYPE_CHECKING, Any, Optional
+
+import httpx
+
+from litellm.llms.base_llm.embedding.transformation import BaseEmbeddingConfig
+from litellm.secret_managers.main import get_secret_str
+from litellm.types.llms.openai import AllEmbeddingInputValues
+from litellm.types.utils import EmbeddingResponse
+from litellm.utils import convert_to_model_response_object
+
+from ..common_utils import VercelAIGatewayException
+
+if TYPE_CHECKING:
+    from litellm.litellm_core_utils.litellm_logging import Logging as _LiteLLMLoggingObj
+
+    LiteLLMLoggingObj = _LiteLLMLoggingObj
+else:
+    LiteLLMLoggingObj = Any
+
+
+class VercelAIGatewayEmbeddingConfig(BaseEmbeddingConfig):
+    """
+    Configuration for Vercel AI Gateway's Embedding API.
+
+    Reference: https://vercel.com/docs/ai-gateway/openai-compat/embeddings
+    """
+
+    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:
+        """
+        Validate environment and set up headers for Vercel AI Gateway API.
+
+        Vercel AI Gateway requires:
+        - Authorization header with Bearer token (API key or OIDC token)
+        """
+        vercel_headers = {
+            "Content-Type": "application/json",
+        }
+
+        # Add Authorization header if api_key is provided
+        if api_key:
+            vercel_headers["Authorization"] = f"Bearer {api_key}"
+
+        # Merge with existing headers (user's extra_headers take priority)
+        merged_headers = {**vercel_headers, **headers}
+
+        return merged_headers
+
+    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:
+        """
+        Get the complete URL for Vercel AI Gateway Embedding API endpoint.
+        """
+        if api_base:
+            api_base = api_base.rstrip("/")
+        else:
+            api_base = (
+                get_secret_str("VERCEL_AI_GATEWAY_API_BASE")
+                or "https://ai-gateway.vercel.sh/v1"
+            )
+
+        return f"{api_base}/embeddings"
+
+    def transform_embedding_request(
+        self,
+        model: str,
+        input: AllEmbeddingInputValues,
+        optional_params: dict,
+        headers: dict,
+    ) -> dict:
+        """
+        Transform embedding request to Vercel AI Gateway format (OpenAI-compatible).
+        """
+        # Ensure input is a list
+        if isinstance(input, str):
+            input = [input]
+
+        # Strip 'vercel_ai_gateway/' prefix if present
+        if model.startswith("vercel_ai_gateway/"):
+            model = model.replace("vercel_ai_gateway/", "", 1)
+
+        return {
+            "model": model,
+            "input": input,
+            **optional_params,
+        }
+
+    def transform_embedding_response(
+        self,
+        model: str,
+        raw_response: httpx.Response,
+        model_response: EmbeddingResponse,
+        logging_obj: LiteLLMLoggingObj,
+        api_key: Optional[str],
+        request_data: dict,
+        optional_params: dict,
+        litellm_params: dict,
+    ) -> EmbeddingResponse:
+        """
+        Transform embedding response from Vercel AI Gateway format (OpenAI-compatible).
+        """
+        logging_obj.post_call(original_response=raw_response.text)
+
+        # Vercel AI Gateway returns standard OpenAI-compatible embedding response
+        response_json = raw_response.json()
+
+        return convert_to_model_response_object(
+            response_object=response_json,
+            model_response_object=model_response,
+            response_type="embedding",
+        )
+
+    def get_supported_openai_params(self, model: str) -> list:
+        """
+        Get list of supported OpenAI parameters for Vercel AI Gateway embeddings.
+
+        Vercel AI Gateway supports the standard OpenAI embeddings parameters
+        and auto-maps 'dimensions' to each provider's expected field.
+        """
+        return [
+            "timeout",
+            "dimensions",
+            "encoding_format",
+            "user",
+        ]
+
+    def map_openai_params(
+        self,
+        non_default_params: dict,
+        optional_params: dict,
+        model: str,
+        drop_params: bool,
+    ) -> dict:
+        """
+        Map OpenAI parameters to Vercel AI Gateway format.
+        """
+        for param, value in non_default_params.items():
+            if param in self.get_supported_openai_params(model):
+                optional_params[param] = value
+        return optional_params
+
+    def get_error_class(
+        self, error_message: str, status_code: int, headers: Any
+    ) -> Any:
+        """
+        Get the error class for Vercel AI Gateway errors.
+        """
+        return VercelAIGatewayException(
+            message=error_message,
+            status_code=status_code,
+            headers=headers,
+        )
diff --git a/litellm/main.py b/litellm/main.py
index ea41919e19..24aac661db 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -4863,6 +4863,36 @@ def embedding(  # noqa: PLR0915
 
             headers = openrouter_headers
 
+            response = base_llm_http_handler.embedding(
+                model=model,
+                input=input,
+                custom_llm_provider=custom_llm_provider,
+                api_base=api_base,
+                api_key=api_key,
+                logging_obj=logging,
+                timeout=timeout,
+                model_response=EmbeddingResponse(),
+                optional_params=optional_params,
+                client=client,
+                aembedding=aembedding,
+                litellm_params=litellm_params_dict,
+                headers=headers,
+            )
+        elif custom_llm_provider == "vercel_ai_gateway":
+            api_base = (
+                api_base
+                or litellm.api_base
+                or get_secret_str("VERCEL_AI_GATEWAY_API_BASE")
+                or "https://ai-gateway.vercel.sh/v1"
+            )
+
+            api_key = (
+                api_key
+                or litellm.api_key
+                or get_secret_str("VERCEL_AI_GATEWAY_API_KEY")
+                or get_secret_str("VERCEL_OIDC_TOKEN")
+            )
+
             response = base_llm_http_handler.embedding(
                 model=model,
                 input=input,
diff --git a/litellm/utils.py b/litellm/utils.py
index 06eceefe0c..21d096b97c 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -8014,6 +8014,12 @@ class ProviderConfigManager:
             )
 
             return OpenrouterEmbeddingConfig()
+        elif litellm.LlmProviders.VERCEL_AI_GATEWAY == provider:
+            from litellm.llms.vercel_ai_gateway.embedding.transformation import (
+                VercelAIGatewayEmbeddingConfig,
+            )
+
+            return VercelAIGatewayEmbeddingConfig()
         elif litellm.LlmProviders.GIGACHAT == provider:
             return litellm.GigaChatEmbeddingConfig()
         elif litellm.LlmProviders.SAGEMAKER == provider:
diff --git a/tests/test_litellm/llms/vercel_ai_gateway/embedding/__init__.py b/tests/test_litellm/llms/vercel_ai_gateway/embedding/__init__.py
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/tests/test_litellm/llms/vercel_ai_gateway/embedding/test_vercel_ai_gateway_embedding.py b/tests/test_litellm/llms/vercel_ai_gateway/embedding/test_vercel_ai_gateway_embedding.py
new file mode 100644
index 0000000000..af1e1df92f
--- /dev/null
+++ b/tests/test_litellm/llms/vercel_ai_gateway/embedding/test_vercel_ai_gateway_embedding.py
@@ -0,0 +1,218 @@
+import os
+import sys
+from unittest.mock import MagicMock, patch
+
+import httpx
+import pytest
+
+sys.path.insert(
+    0, os.path.abspath("../../../../..")
+)  # Adds the parent directory to the system path
+
+from litellm.llms.vercel_ai_gateway.embedding.transformation import (
+    VercelAIGatewayEmbeddingConfig,
+)
+from litellm.llms.vercel_ai_gateway.common_utils import VercelAIGatewayException
+from litellm.types.utils import EmbeddingResponse
+
+
+def test_vercel_ai_gateway_embedding_get_complete_url():
+    """Test URL generation for embeddings endpoint"""
+    config = VercelAIGatewayEmbeddingConfig()
+
+    # Test with default API base
+    url = config.get_complete_url(
+        api_base=None,
+        api_key=None,
+        model="openai/text-embedding-3-small",
+        optional_params={},
+        litellm_params={},
+    )
+    assert url == "https://ai-gateway.vercel.sh/v1/embeddings"
+
+    # Test with custom API base
+    url = config.get_complete_url(
+        api_base="https://custom.vercel.sh/v1",
+        api_key=None,
+        model="openai/text-embedding-3-small",
+        optional_params={},
+        litellm_params={},
+    )
+    assert url == "https://custom.vercel.sh/v1/embeddings"
+
+    # Test with trailing slash
+    url = config.get_complete_url(
+        api_base="https://custom.vercel.sh/v1/",
+        api_key=None,
+        model="openai/text-embedding-3-small",
+        optional_params={},
+        litellm_params={},
+    )
+    assert url == "https://custom.vercel.sh/v1/embeddings"
+
+
+def test_vercel_ai_gateway_embedding_transform_request():
+    """Test request transformation for embeddings"""
+    config = VercelAIGatewayEmbeddingConfig()
+
+    # Test with string input
+    request = config.transform_embedding_request(
+        model="openai/text-embedding-3-small",
+        input="Hello world",
+        optional_params={},
+        headers={},
+    )
+    assert request["model"] == "openai/text-embedding-3-small"
+    assert request["input"] == ["Hello world"]
+
+    # Test with list input
+    request = config.transform_embedding_request(
+        model="openai/text-embedding-3-small",
+        input=["Hello", "World"],
+        optional_params={},
+        headers={},
+    )
+    assert request["model"] == "openai/text-embedding-3-small"
+    assert request["input"] == ["Hello", "World"]
+
+    # Test stripping vercel_ai_gateway/ prefix
+    request = config.transform_embedding_request(
+        model="vercel_ai_gateway/openai/text-embedding-3-small",
+        input="Hello",
+        optional_params={},
+        headers={},
+    )
+    assert request["model"] == "openai/text-embedding-3-small"
+
+
+def test_vercel_ai_gateway_embedding_transform_request_with_dimensions():
+    """Test request transformation with dimensions parameter"""
+    config = VercelAIGatewayEmbeddingConfig()
+
+    request = config.transform_embedding_request(
+        model="openai/text-embedding-3-small",
+        input="Hello world",
+        optional_params={"dimensions": 768},
+        headers={},
+    )
+    assert request["model"] == "openai/text-embedding-3-small"
+    assert request["input"] == ["Hello world"]
+    assert request["dimensions"] == 768
+
+
+def test_vercel_ai_gateway_embedding_validate_environment():
+    """Test header validation and setup"""
+    config = VercelAIGatewayEmbeddingConfig()
+
+    headers = config.validate_environment(
+        headers={},
+        model="openai/text-embedding-3-small",
+        messages=[],
+        optional_params={},
+        litellm_params={},
+        api_key="test_key",
+    )
+    assert headers["Content-Type"] == "application/json"
+    assert headers["Authorization"] == "Bearer test_key"
+
+    # Test with existing headers (should merge)
+    headers = config.validate_environment(
+        headers={"X-Custom": "value"},
+        model="openai/text-embedding-3-small",
+        messages=[],
+        optional_params={},
+        litellm_params={},
+        api_key="test_key",
+    )
+    assert headers["X-Custom"] == "value"
+    assert headers["Authorization"] == "Bearer test_key"
+
+
+def test_vercel_ai_gateway_embedding_get_supported_params():
+    """Test supported OpenAI parameters"""
+    config = VercelAIGatewayEmbeddingConfig()
+    supported = config.get_supported_openai_params("openai/text-embedding-3-small")
+
+    assert "dimensions" in supported
+    assert "encoding_format" in supported
+    assert "timeout" in supported
+    assert "user" in supported
+
+
+def test_vercel_ai_gateway_embedding_map_openai_params():
+    """Test OpenAI parameter mapping"""
+    config = VercelAIGatewayEmbeddingConfig()
+
+    optional_params = config.map_openai_params(
+        non_default_params={"dimensions": 768, "encoding_format": "float"},
+        optional_params={},
+        model="openai/text-embedding-3-small",
+        drop_params=False,
+    )
+    assert optional_params["dimensions"] == 768
+    assert optional_params["encoding_format"] == "float"
+
+
+def test_vercel_ai_gateway_embedding_error_class():
+    """Test error class creation"""
+    config = VercelAIGatewayEmbeddingConfig()
+
+    error = config.get_error_class(
+        error_message="Test error",
+        status_code=400,
+        headers={"Content-Type": "application/json"},
+    )
+
+    assert isinstance(error, VercelAIGatewayException)
+    assert error.message == "Test error"
+    assert error.status_code == 400
+
+
+def test_vercel_ai_gateway_embedding_transform_response():
+    """Test response transformation"""
+    config = VercelAIGatewayEmbeddingConfig()
+
+    mock_response = MagicMock(spec=httpx.Response)
+    mock_response.text = '{"object":"list","data":[{"object":"embedding","index":0,"embedding":[0.1,0.2,0.3]}],"model":"openai/text-embedding-3-small","usage":{"prompt_tokens":2,"total_tokens":2}}'
+    mock_response.json.return_value = {
+        "object": "list",
+        "data": [{"object": "embedding", "index": 0, "embedding": [0.1, 0.2, 0.3]}],
+        "model": "openai/text-embedding-3-small",
+        "usage": {"prompt_tokens": 2, "total_tokens": 2},
+    }
+
+    mock_logging = MagicMock()
+
+    response = config.transform_embedding_response(
+        model="openai/text-embedding-3-small",
+        raw_response=mock_response,
+        model_response=EmbeddingResponse(),
+        logging_obj=mock_logging,
+        api_key="test_key",
+        request_data={},
+        optional_params={},
+        litellm_params={},
+    )
+
+    assert response is not None
+    mock_logging.post_call.assert_called_once()
+
+
+def test_vercel_ai_gateway_embedding_env_vars():
+    """Test environment variable handling"""
+    config = VercelAIGatewayEmbeddingConfig()
+
+    with patch.dict(
+        os.environ,
+        {
+            "VERCEL_AI_GATEWAY_API_BASE": "https://env.vercel.sh/v1",
+        },
+    ):
+        url = config.get_complete_url(
+            api_base=None,
+            api_key=None,
+            model="openai/text-embedding-3-small",
+            optional_params={},
+            litellm_params={},
+        )
+        assert url == "https://env.vercel.sh/v1/embeddings"

From 154ad179af74f03c756be6e0c5bc262f4c9bbb5c Mon Sep 17 00:00:00 2001
From: Sameer Kankute <sameer@berri.ai>
Date: Tue, 27 Jan 2026 16:39:56 +0530
Subject: [PATCH 10/11] Revert poetry lock

---
 poetry.lock | 67 +++++++++++++++++++----------------------------------
 1 file changed, 24 insertions(+), 43 deletions(-)

diff --git a/poetry.lock b/poetry.lock
index e5ef1750da..462a56fe42 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.2.0 and should not be changed by hand.
 
 [[package]]
 name = "a2a-sdk"
@@ -343,7 +343,7 @@ zookeeper = ["kazoo"]
 name = "async-timeout"
 version = "5.0.1"
 description = "Timeout context manager for asyncio programs"
-optional = false
+optional = true
 python-versions = ">=3.8"
 groups = ["main"]
 markers = "python_full_version < \"3.11.3\" and (extra == \"extra-proxy\" or extra == \"proxy\" or python_version < \"3.11\")"
@@ -593,8 +593,8 @@ files = [
 jmespath = ">=0.7.1,<2.0.0"
 python-dateutil = ">=2.1,<3.0.0"
 urllib3 = [
-    {version = ">=1.25.4,<1.27", markers = "python_version < \"3.10\""},
     {version = ">=1.25.4,<2.2.0 || >2.2.0,<3", markers = "python_version >= \"3.10\""},
+    {version = ">=1.25.4,<1.27", markers = "python_version < \"3.10\""},
 ]
 
 [package.extras]
@@ -902,7 +902,7 @@ files = [
     {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
     {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
 ]
-markers = {main = "platform_system == \"Windows\" or sys_platform == \"win32\" and python_version < \"3.14\" and (extra == \"utils\" or extra == \"semantic-router\") or sys_platform == \"win32\" and extra == \"utils\" or python_version < \"3.14\" and extra == \"semantic-router\"", dev = "platform_system == \"Windows\" or sys_platform == \"win32\"", proxy-dev = "platform_system == \"Windows\""}
+markers = {main = "platform_system == \"Windows\" or sys_platform == \"win32\" and python_version < \"3.14\" and (extra == \"utils\" or extra == \"semantic-router\") or sys_platform == \"win32\" and extra == \"utils\" or python_version <= \"3.13\" and extra == \"semantic-router\"", dev = "platform_system == \"Windows\" or sys_platform == \"win32\"", proxy-dev = "platform_system == \"Windows\""}
 
 [[package]]
 name = "coloredlogs"
@@ -2028,7 +2028,7 @@ description = "Google API client core library"
 optional = true
 python-versions = ">=3.7"
 groups = ["main"]
-markers = "python_version == \"3.9\" and (extra == \"google\" or extra == \"extra-proxy\") or python_version < \"3.14\" and (extra == \"extra-proxy\" or extra == \"google\")"
+markers = "(extra == \"extra-proxy\" or extra == \"google\") and python_version < \"3.14\""
 files = [
     {file = "google_api_core-2.28.1-py3-none-any.whl", hash = "sha256:4021b0f8ceb77a6fb4de6fde4502cecab45062e66ff4f2895169e0b35bc9466c"},
     {file = "google_api_core-2.28.1.tar.gz", hash = "sha256:2b405df02d68e68ce0fbc138559e6036559e685159d148ae5861013dc201baf8"},
@@ -2038,12 +2038,12 @@ files = [
 google-auth = ">=2.14.1,<3.0.0"
 googleapis-common-protos = ">=1.56.2,<2.0.0"
 grpcio = [
-    {version = ">=1.33.2,<2.0.0", optional = true, markers = "extra == \"grpc\""},
     {version = ">=1.49.1,<2.0.0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
+    {version = ">=1.33.2,<2.0.0", optional = true, markers = "python_version < \"3.11\" and extra == \"grpc\""},
 ]
 grpcio-status = [
-    {version = ">=1.33.2,<2.0.0", optional = true, markers = "extra == \"grpc\""},
     {version = ">=1.49.1,<2.0.0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
+    {version = ">=1.33.2,<2.0.0", optional = true, markers = "extra == \"grpc\""},
 ]
 proto-plus = [
     {version = ">=1.22.3,<2.0.0"},
@@ -2457,7 +2457,7 @@ files = [
     {file = "googleapis_common_protos-1.72.0-py3-none-any.whl", hash = "sha256:4299c5a82d5ae1a9702ada957347726b167f9f8d1fc352477702a1e851ff4038"},
     {file = "googleapis_common_protos-1.72.0.tar.gz", hash = "sha256:e55a601c1b32b52d7a3e65f43563e2aa61bcd737998ee672ac9b951cd49319f5"},
 ]
-markers = {main = "extra == \"extra-proxy\" or extra == \"google\" or python_version == \"3.9\" and (extra == \"google\" or extra == \"extra-proxy\")"}
+markers = {main = "extra == \"extra-proxy\" or extra == \"google\""}
 
 [package.dependencies]
 grpcio = {version = ">=1.44.0,<2.0.0", optional = true, markers = "extra == \"grpc\""}
@@ -2687,7 +2687,7 @@ files = [
     {file = "grpcio-1.76.0-cp39-cp39-win_amd64.whl", hash = "sha256:acab0277c40eff7143c2323190ea57b9ee5fd353d8190ee9652369fae735668a"},
     {file = "grpcio-1.76.0.tar.gz", hash = "sha256:7be78388d6da1a25c0d5ec506523db58b18be22d9c37d8d3a32c08be4987bd73"},
 ]
-markers = {main = "extra == \"extra-proxy\" or extra == \"grpc\""}
+markers = {main = "extra == \"extra-proxy\" or extra == \"google\" or extra == \"grpc\""}
 
 [package.dependencies]
 typing-extensions = ">=4.12,<5.0"
@@ -2720,7 +2720,7 @@ description = "WSGI HTTP Server for UNIX"
 optional = true
 python-versions = ">=3.7"
 groups = ["main"]
-markers = "(python_version < \"3.14\" or extra == \"mlflow\" or extra == \"proxy\") and (platform_system != \"Windows\" or extra == \"proxy\") and (python_version >= \"3.10\" or extra == \"proxy\") and (extra == \"proxy\" or extra == \"mlflow\")"
+markers = "extra == \"proxy\" or python_version >= \"3.10\" and (extra == \"proxy\" or extra == \"mlflow\") and platform_system != \"Windows\""
 files = [
     {file = "gunicorn-23.0.0-py3-none-any.whl", hash = "sha256:ec400d38950de4dfd418cff8328b2c8faed0edb0d517d3394e457c317908ca4d"},
     {file = "gunicorn-23.0.0.tar.gz", hash = "sha256:f014447a0101dc57e294f6c18ca6b40227a4c90e9bdb586042628030cba004ec"},
@@ -3426,15 +3426,15 @@ files = [
 
 [[package]]
 name = "litellm-proxy-extras"
-version = "0.4.25"
+version = "0.4.27"
 description = "Additional files for the LiteLLM Proxy. Reduces the size of the main litellm package."
 optional = true
 python-versions = "!=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,>=3.8"
 groups = ["main"]
 markers = "extra == \"proxy\""
 files = [
-    {file = "litellm_proxy_extras-0.4.25-py3-none-any.whl", hash = "sha256:da79e1a7a999020a82ec33c45d8fd35eb390ff3d0bc3d7686542b3529aff2cda"},
-    {file = "litellm_proxy_extras-0.4.25.tar.gz", hash = "sha256:a03790e574ec6b8098c74d49836313651c0a0e72354a716c76c50ed16b087815"},
+    {file = "litellm_proxy_extras-0.4.27-py3-none-any.whl", hash = "sha256:752c1faabc86ce3d2b1fa451495d34de82323798e37b9cb5c0fea93deae1c5c8"},
+    {file = "litellm_proxy_extras-0.4.27.tar.gz", hash = "sha256:81059120016cfc03c82aa9664424912bdcffad103f66a5f925fef6b26f2cc151"},
 ]
 
 [[package]]
@@ -3777,10 +3777,10 @@ files = [
 
 [package.dependencies]
 numpy = [
-    {version = ">1.20"},
     {version = ">=1.23.3", markers = "python_version >= \"3.11\""},
-    {version = ">=1.21.2", markers = "python_version >= \"3.10\""},
     {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
+    {version = ">1.20"},
+    {version = ">=1.21.2", markers = "python_version >= \"3.10\""},
 ]
 
 [package.extras]
@@ -4191,7 +4191,7 @@ description = "Fundamental package for array computing in Python"
 optional = true
 python-versions = ">=3.9"
 groups = ["main"]
-markers = "python_version < \"3.12\" and (extra == \"extra-proxy\" or extra == \"semantic-router\" or extra == \"google\" or python_version >= \"3.10\") and (extra == \"extra-proxy\" or extra == \"semantic-router\" or extra == \"google\" or extra == \"mlflow\")"
+markers = "(python_version >= \"3.10\" or extra == \"extra-proxy\" or extra == \"semantic-router\" or extra == \"google\") and python_version < \"3.12\" and (extra == \"extra-proxy\" or extra == \"semantic-router\" or extra == \"google\" or extra == \"mlflow\")"
 files = [
     {file = "numpy-1.26.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9ff0f4f29c51e2803569d7a51c2304de5554655a60c5d776e35b4a41413830d0"},
     {file = "numpy-1.26.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2e4ee3380d6de9c9ec04745830fd9e2eccb3e6cf790d39d7b98ffd19b0dd754a"},
@@ -4708,8 +4708,8 @@ files = [
 [package.dependencies]
 numpy = [
     {version = ">=1.23.2", markers = "python_version == \"3.11\""},
-    {version = ">=1.22.4", markers = "python_version < \"3.11\""},
     {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
+    {version = ">=1.22.4", markers = "python_version < \"3.11\""},
 ]
 python-dateutil = ">=2.8.2"
 pytz = ">=2020.1"
@@ -5169,7 +5169,7 @@ description = "Beautiful, Pythonic protocol buffers"
 optional = true
 python-versions = ">=3.7"
 groups = ["main"]
-markers = "extra == \"google\" or extra == \"extra-proxy\""
+markers = "extra == \"extra-proxy\" or extra == \"google\""
 files = [
     {file = "proto_plus-1.26.1-py3-none-any.whl", hash = "sha256:13285478c2dcf2abb829db158e1047e2f1e8d63a077d94263c2b88b043c75a66"},
     {file = "proto_plus-1.26.1.tar.gz", hash = "sha256:21a515a4c4c0088a773899e23c7bbade3d18f9c66c73edd4c7ee3816bc96a012"},
@@ -5316,7 +5316,7 @@ files = [
     {file = "pycparser-2.23-py3-none-any.whl", hash = "sha256:e5c6e8d3fbad53479cab09ac03729e0a9faf2bee3db8208a550daf5af81a5934"},
     {file = "pycparser-2.23.tar.gz", hash = "sha256:78816d4f24add8f10a06d6f05b4d424ad9e96cfebf68a4ddc99c65c0720d00c2"},
 ]
-markers = {main = "implementation_name != \"PyPy\" and (platform_python_implementation != \"PyPy\" or extra == \"proxy\")", dev = "platform_python_implementation != \"PyPy\" and implementation_name != \"PyPy\"", proxy-dev = "platform_python_implementation != \"PyPy\" and implementation_name != \"PyPy\""}
+markers = {main = "implementation_name != \"PyPy\" and (platform_python_implementation != \"PyPy\" or extra == \"proxy\")", dev = "implementation_name != \"PyPy\" and platform_python_implementation != \"PyPy\"", proxy-dev = "implementation_name != \"PyPy\" and platform_python_implementation != \"PyPy\""}
 
 [[package]]
 name = "pydantic"
@@ -5617,7 +5617,7 @@ description = "A python implementation of GNU readline."
 optional = true
 python-versions = ">=3.8"
 groups = ["main"]
-markers = "extra == \"extra-proxy\" and sys_platform == \"win32\" and python_version < \"3.14\""
+markers = "sys_platform == \"win32\" and extra == \"extra-proxy\" and python_version < \"3.14\""
 files = [
     {file = "pyreadline3-3.5.4-py3-none-any.whl", hash = "sha256:eaf8e6cc3c49bcccf145fc6067ba8643d1df34d604a1ec0eccbf7a18e6d3fae6"},
     {file = "pyreadline3-3.5.4.tar.gz", hash = "sha256:8d57d53039a1c75adba8e50dd3d992b28143480816187ea5efbd5c78e6c885b7"},
@@ -7450,26 +7450,6 @@ examples = ["aiosqlite (>=0.21.0)", "fastapi (>=0.115.12)", "sqlalchemy[asyncio]
 granian = ["granian (>=2.3.1)"]
 uvicorn = ["uvicorn (>=0.34.0)"]
 
-[[package]]
-name = "starlette"
-version = "0.49.3"
-description = "The little ASGI library that shines."
-optional = false
-python-versions = ">=3.9"
-groups = ["main", "dev"]
-files = [
-    {file = "starlette-0.49.3-py3-none-any.whl", hash = "sha256:b579b99715fdc2980cf88c8ec96d3bf1ce16f5a8051a7c2b84ef9b1cdecaea2f"},
-    {file = "starlette-0.49.3.tar.gz", hash = "sha256:1c14546f299b5901a1ea0e34410575bc33bbd741377a10484a54445588d00284"},
-]
-markers = {main = "python_version == \"3.9\" and extra == \"proxy\"", dev = "python_version == \"3.9\""}
-
-[package.dependencies]
-anyio = ">=3.6.2,<5"
-typing-extensions = {version = ">=4.10.0", markers = "python_version < \"3.13\""}
-
-[package.extras]
-full = ["httpx (>=0.27.0,<0.29.0)", "itsdangerous", "jinja2", "python-multipart (>=0.0.18)", "pyyaml"]
-
 [[package]]
 name = "starlette"
 version = "0.50.0"
@@ -7481,7 +7461,7 @@ files = [
     {file = "starlette-0.50.0-py3-none-any.whl", hash = "sha256:9e5391843ec9b6e472eed1365a78c8098cfceb7a74bfd4d6b1c0c0095efb3bca"},
     {file = "starlette-0.50.0.tar.gz", hash = "sha256:a2a17b22203254bcbc2e1f926d2d55f3f9497f769416b3190768befe598fa3ca"},
 ]
-markers = {main = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"proxy\")", dev = "python_version >= \"3.10\""}
+markers = {main = "(extra == \"mlflow\" or extra == \"proxy\") and python_version >= \"3.10\" or extra == \"proxy\""}
 
 [package.dependencies]
 anyio = ">=3.6.2,<5"
@@ -7530,7 +7510,7 @@ description = "Retry code until it succeeds"
 optional = true
 python-versions = ">=3.9"
 groups = ["main"]
-markers = "(extra == \"extra-proxy\" or extra == \"google\") and (python_version < \"3.14\" or extra == \"google\")"
+markers = "(extra == \"extra-proxy\" or extra == \"google\") and python_version < \"3.14\" or extra == \"google\""
 files = [
     {file = "tenacity-9.1.2-py3-none-any.whl", hash = "sha256:f77bf36710d8b73a50b2dd155c97b870017ad21afe6ab300326b0371b3b05138"},
     {file = "tenacity-9.1.2.tar.gz", hash = "sha256:1169d376c297e7de388d18b4481760d478b0e99a777cad3a9c86e556f4b697cb"},
@@ -8483,6 +8463,7 @@ type = ["pytest-mypy"]
 caching = ["diskcache"]
 extra-proxy = ["a2a-sdk", "azure-identity", "azure-keyvault-secrets", "google-cloud-iam", "google-cloud-kms", "prisma", "redisvl", "resend"]
 google = ["google-cloud-aiplatform"]
+grpc = ["grpcio", "grpcio"]
 mlflow = ["mlflow"]
 proxy = ["PyJWT", "apscheduler", "azure-identity", "azure-storage-blob", "backoff", "boto3", "cryptography", "fastapi", "fastapi-sso", "gunicorn", "litellm-enterprise", "litellm-proxy-extras", "mcp", "orjson", "polars", "pynacl", "python-multipart", "pyyaml", "rich", "rq", "soundfile", "uvicorn", "uvloop", "websockets"]
 semantic-router = ["semantic-router"]
@@ -8491,4 +8472,4 @@ utils = ["numpydoc"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<4.0"
-content-hash = "76f5b5fb10667c2dcf428976292672e7a1f3f2eb5f5bf78998e2192899f5037e"
+content-hash = "73b5e1ab0badbee6c564d5e056e4f9c320c2f722bf176ce97d42e77110e37d60"

From f30742fe6e8e0ae3a753f37631f1c20fd0124f0f Mon Sep 17 00:00:00 2001
From: Sameer Kankute <sameer@berri.ai>
Date: Tue, 27 Jan 2026 16:49:39 +0530
Subject: [PATCH 11/11] Fix mypy and code quality issues

---
 .../integrations/datadog/datadog_cost_management.py    | 10 ++++++----
 litellm/llms/bedrock/chat/converse_transformation.py   |  2 +-
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/litellm/integrations/datadog/datadog_cost_management.py b/litellm/integrations/datadog/datadog_cost_management.py
index 9bfb2aba71..2eb94b59dd 100644
--- a/litellm/integrations/datadog/datadog_cost_management.py
+++ b/litellm/integrations/datadog/datadog_cost_management.py
@@ -2,7 +2,7 @@ import asyncio
 import os
 import time
 from datetime import datetime
-from typing import Dict, List, Optional
+from typing import Dict, List, Optional, Tuple
 
 from litellm._logging import verbose_logger
 from litellm.integrations.custom_batch_logger import CustomBatchLogger
@@ -93,7 +93,7 @@ class DatadogCostManagementLogger(CustomBatchLogger):
         Aggregates costs by Provider, Model, and Date.
         Returns a list of DatadogFOCUSCostEntry.
         """
-        aggregator: Dict[str, DatadogFOCUSCostEntry] = {}
+        aggregator: Dict[Tuple[str, str, str, Tuple[Tuple[str, str], ...]], DatadogFOCUSCostEntry] = {}
 
         for log in logs:
             try:
@@ -171,8 +171,10 @@ class DatadogCostManagementLogger(CustomBatchLogger):
                 tags["user"] = str(metadata["user_api_key_alias"])
             if "user_api_key_team_alias" in metadata:
                 tags["team"] = str(metadata["user_api_key_team_alias"])
-            if "model_group" in metadata:
-                tags["model_group"] = str(metadata["model_group"])
+            # model_group is not in StandardLoggingMetadata TypedDict, so we need to access it via dict.get()
+            model_group = metadata.get("model_group")  # type: ignore[misc]
+            if model_group:
+                tags["model_group"] = str(model_group)
 
         return tags
 
diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py
index 2ec27a7af0..ec66514207 100644
--- a/litellm/llms/bedrock/chat/converse_transformation.py
+++ b/litellm/llms/bedrock/chat/converse_transformation.py
@@ -1501,7 +1501,7 @@ class AmazonConverseConfig(BaseConfig):
 
         return content_str, tools, reasoningContentBlocks, citationsContentBlocks
 
-    def _transform_response(
+    def _transform_response( # noqa: PLR0915
         self,
         model: str,
         response: httpx.Response,