Merge pull request #14787 from BerriAI/litellm_dev_09_22_2025_p1

docs(provider_specific_params.md): fix docs

Author: krrishdholakia

.github/workflows/test-mcp.yml

@@ -0,0 +1,48 @@
+name: LiteLLM MCP Tests (folder - tests/mcp_tests)
+
+on:
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    timeout-minutes: 25
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Thank You Message
+      run: |
+        echo "### 🙏 Thank you for contributing to LiteLLM!" >> $GITHUB_STEP_SUMMARY
+        echo "Your PR is being tested now. We appreciate your help in making LiteLLM better!" >> $GITHUB_STEP_SUMMARY
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.12'
+
+    - name: Install Poetry
+      uses: snok/install-poetry@v1
+
+    - name: Install dependencies
+      run: |
+        poetry install --with dev,proxy-dev --extras "proxy semantic-router"
+        poetry run pip install "pytest==7.3.1"
+        poetry run pip install "pytest-retry==1.6.3"
+        poetry run pip install "pytest-cov==5.0.0"
+        poetry run pip install "pytest-asyncio==0.21.1"
+        poetry run pip install "respx==0.22.0"
+        poetry run pip install "pydantic==2.10.2"
+        poetry run pip install "mcp==1.10.1"
+        poetry run pip install pytest-xdist
+
+    - name: Setup litellm-enterprise as local package
+      run: |
+        cd enterprise
+        python -m pip install -e .
+        cd ..
+
+    - name: Run MCP tests
+      run: |
+        poetry run pytest tests/mcp_tests -x -vv -n 4 --cov=litellm --cov-report=xml --durations=5

docs/my-website/docs/completion/provider_specific_params.md

@@ -423,16 +423,17 @@ model_list:
 curl -X POST 'http://0.0.0.0:4000/chat/completions' \
 -H 'Content-Type: application/json' \
 -H 'Authorization: Bearer sk-1234' \
--D '{
+-d '{
   "model": "llama-3-8b-instruct",
   "messages": [
     {
       "role": "user",
       "content": "What'\''s the weather like in Boston today?"
     }
   ],
-  "adapater_id": "my-special-adapter-id" # 👈 PROVIDER-SPECIFIC PARAM
-  }'
+  "adapater_id": "my-special-adapter-id"
+}'
+```
 
 ## Provider-Specific Metadata Parameters
 
@@ -482,5 +483,4 @@ response = litellm.completion(
 ```
 
 </TabItem>
-</Tabs>
-```
+</Tabs>

docs/my-website/sidebars.js

@@ -546,6 +546,7 @@ const sidebars = {
       items: [
         "set_keys",
         "completion/token_usage",
+        "sdk/headers",
         "sdk_custom_pricing",
         "embedding/async_embedding",
         "embedding/moderation",

litellm/llms/bedrock/chat/converse_transformation.py

@@ -200,8 +200,8 @@ def _validate_request_metadata(self, metadata: dict) -> None:
                 llm_provider="bedrock",
             )
 
-        key_pattern = re.compile(r'^[a-zA-Z0-9\s:_@$#=/+,.-]{1,256}$')
-        value_pattern = re.compile(r'^[a-zA-Z0-9\s:_@$#=/+,.-]{0,256}$')
+        key_pattern = re.compile(r"^[a-zA-Z0-9\s:_@$#=/+,.-]{1,256}$")
+        value_pattern = re.compile(r"^[a-zA-Z0-9\s:_@$#=/+,.-]{0,256}$")
 
         for key, value in metadata.items():
             if not isinstance(key, str):
@@ -762,7 +762,9 @@ def _handle_top_k_value(self, model: str, inference_params: dict) -> dict:
 
         return {}
 
-    def _prepare_request_params(self, optional_params: dict, model: str) -> tuple[dict, dict, dict]:
+    def _prepare_request_params(
+        self, optional_params: dict, model: str
+    ) -> Tuple[dict, dict, dict]:
         """Prepare and separate request parameters."""
         inference_params = copy.deepcopy(optional_params)
         supported_converse_params = list(
@@ -797,7 +799,13 @@ def _prepare_request_params(self, optional_params: dict, model: str) -> tuple[di
 
         return inference_params, additional_request_params, request_metadata
 
-    def _process_tools_and_beta(self, original_tools: list, model: str, headers: Optional[dict], additional_request_params: dict) -> tuple[List[ToolBlock], list]:
+    def _process_tools_and_beta(
+        self,
+        original_tools: list,
+        model: str,
+        headers: Optional[dict],
+        additional_request_params: dict,
+    ) -> tuple[List[ToolBlock], list]:
         """Process tools and collect anthropic_beta values."""
         bedrock_tools: List[ToolBlock] = []
 
@@ -871,12 +879,16 @@ def _transform_request_helper(
                 )
 
         # Prepare and separate parameters
-        inference_params, additional_request_params, request_metadata = self._prepare_request_params(optional_params, model)
+        inference_params, additional_request_params, request_metadata = (
+            self._prepare_request_params(optional_params, model)
+        )
 
         original_tools = inference_params.pop("tools", [])
 
         # Process tools and collect beta values
-        bedrock_tools, anthropic_beta_list = self._process_tools_and_beta(original_tools, model, headers, additional_request_params)
+        bedrock_tools, anthropic_beta_list = self._process_tools_and_beta(
+            original_tools, model, headers, additional_request_params
+        )
 
         bedrock_tool_config: Optional[ToolConfigBlock] = None
         if len(bedrock_tools) > 0:
@@ -1157,9 +1169,7 @@ def apply_tool_call_transformation_if_needed(
 
         return message, returned_finish_reason
 
-    def _translate_message_content(
-        self, content_blocks: List[ContentBlock]
-    ) -> Tuple[
+    def _translate_message_content(self, content_blocks: List[ContentBlock]) -> Tuple[
         str,
         List[ChatCompletionToolCallChunk],
         Optional[List[BedrockConverseReasoningContentBlock]],
@@ -1174,9 +1184,9 @@ def _translate_message_content(
         """
         content_str = ""
         tools: List[ChatCompletionToolCallChunk] = []
-        reasoningContentBlocks: Optional[
-            List[BedrockConverseReasoningContentBlock]
-        ] = None
+        reasoningContentBlocks: Optional[List[BedrockConverseReasoningContentBlock]] = (
+            None
+        )
         for idx, content in enumerate(content_blocks):
             """
             - Content is either a tool response or text
@@ -1297,9 +1307,9 @@ def _transform_response(
         chat_completion_message: ChatCompletionResponseMessage = {"role": "assistant"}
         content_str = ""
         tools: List[ChatCompletionToolCallChunk] = []
-        reasoningContentBlocks: Optional[
-            List[BedrockConverseReasoningContentBlock]
-        ] = None
+        reasoningContentBlocks: Optional[List[BedrockConverseReasoningContentBlock]] = (
+            None
+        )
 
         if message is not None:
             (
@@ -1312,12 +1322,12 @@ def _transform_response(
             chat_completion_message["provider_specific_fields"] = {
                 "reasoningContentBlocks": reasoningContentBlocks,
             }
-            chat_completion_message[
-                "reasoning_content"
-            ] = self._transform_reasoning_content(reasoningContentBlocks)
-            chat_completion_message[
-                "thinking_blocks"
-            ] = self._transform_thinking_blocks(reasoningContentBlocks)
+            chat_completion_message["reasoning_content"] = (
+                self._transform_reasoning_content(reasoningContentBlocks)
+            )
+            chat_completion_message["thinking_blocks"] = (
+                self._transform_thinking_blocks(reasoningContentBlocks)
+            )
         chat_completion_message["content"] = content_str
         if (
             json_mode is True