Litellm dev bedrock anthropic 3 7 v2 (#8843)

* feat(bedrock/converse/transformation.py): support claude-3-7-sonnet reasoning_Content transformation

Closes https://github.com/BerriAI/litellm/issues/8777

* fix(bedrock/): support returning `reasoning_content` on streaming for claude-3-7

Resolves https://github.com/BerriAI/litellm/issues/8777

* feat(bedrock/): unify converse reasoning content blocks for consistency across anthropic and bedrock

* fix(anthropic/chat/transformation.py): handle deepseek-style 'reasoning_content' extraction within transformation.py

simpler logic

* feat(bedrock/): fix streaming to return blocks in consistent format

* fix: fix linting error

* test: fix test

* feat(factory.py): fix bedrock thinking block translation on tool calling

allows passing the thinking blocks back to bedrock for tool calling

* fix(types/utils.py): don't exclude provider_specific_fields on model dump

ensures consistent responses

* fix: fix linting errors

* fix(convert_dict_to_response.py): pass reasoning_content on root

* fix: test

* fix(streaming_handler.py): add helper util for setting model id

* fix(streaming_handler.py): fix setting model id on model response stream chunk

* fix(streaming_handler.py): fix linting error

* fix(streaming_handler.py): fix linting error

* fix(types/utils.py): add provider_specific_fields to model stream response

* fix(streaming_handler.py): copy provider specific fields and add them to the root of the streaming response

* fix(streaming_handler.py): fix check

* fix: fix test

* fix(types/utils.py): ensure messages content is always openai compatible

* fix(types/utils.py): fix delta object to always be openai compatible

only introduce new params if variable exists

* test: fix bedrock nova tests

* test: skip flaky test

* test: skip flaky test in ci/cd

litellm/llms/bedrock/chat/converse_transformation.py

@@ -23,6 +23,7 @@ from litellm.types.llms.openai import (
     AllMessageValues,
     ChatCompletionResponseMessage,
     ChatCompletionSystemMessage,
+    ChatCompletionThinkingBlock,
     ChatCompletionToolCallChunk,
     ChatCompletionToolCallFunctionChunk,
     ChatCompletionToolParam,
@@ -545,6 +546,37 @@ class AmazonConverseConfig(BaseConfig):
             encoding=encoding,
         )
 
+    def _transform_reasoning_content(
+        self, reasoning_content_blocks: List[BedrockConverseReasoningContentBlock]
+    ) -> str:
+        """
+        Extract the reasoning text from the reasoning content blocks
+
+        Ensures deepseek reasoning content compatible output.
+        """
+        reasoning_content_str = ""
+        for block in reasoning_content_blocks:
+            if "reasoningText" in block:
+                reasoning_content_str += block["reasoningText"]["text"]
+        return reasoning_content_str
+
+    def _transform_thinking_blocks(
+        self, thinking_blocks: List[BedrockConverseReasoningContentBlock]
+    ) -> List[ChatCompletionThinkingBlock]:
+        """Return a consistent format for thinking blocks between Anthropic and Bedrock."""
+        thinking_blocks_list: List[ChatCompletionThinkingBlock] = []
+        for block in thinking_blocks:
+            if "reasoningText" in block:
+                _thinking_block = ChatCompletionThinkingBlock(type="thinking")
+                _text = block["reasoningText"].get("text")
+                _signature = block["reasoningText"].get("signature")
+                if _text is not None:
+                    _thinking_block["thinking"] = _text
+                if _signature is not None:
+                    _thinking_block["signature_delta"] = _signature
+                thinking_blocks_list.append(_thinking_block)
+        return thinking_blocks_list
+
     def _transform_response(
         self,
         model: str,
@@ -618,6 +650,10 @@ class AmazonConverseConfig(BaseConfig):
         chat_completion_message: ChatCompletionResponseMessage = {"role": "assistant"}
         content_str = ""
         tools: List[ChatCompletionToolCallChunk] = []
+        reasoningContentBlocks: Optional[List[BedrockConverseReasoningContentBlock]] = (
+            None
+        )
+
         if message is not None:
             for idx, content in enumerate(message["content"]):
                 """
@@ -644,8 +680,22 @@ class AmazonConverseConfig(BaseConfig):
                         index=idx,
                     )
                     tools.append(_tool_response_chunk)
-        chat_completion_message["content"] = content_str
+                if "reasoningContent" in content:
+                    if reasoningContentBlocks is None:
+                        reasoningContentBlocks = []
+                    reasoningContentBlocks.append(content["reasoningContent"])
 
+        if reasoningContentBlocks is not None:
+            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["content"] = content_str
         if json_mode is True and tools is not None and len(tools) == 1:
             # to support 'json_schema' logic on bedrock models
             json_mode_content_str: Optional[str] = tools[0]["function"].get("arguments")