diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py index 0e4ceb0214..6591e152a1 100644 --- a/litellm/llms/bedrock/chat/converse_transformation.py +++ b/litellm/llms/bedrock/chat/converse_transformation.py @@ -30,6 +30,8 @@ from litellm.litellm_core_utils.prompt_templates.factory import ( from litellm.llms.anthropic.chat.transformation import AnthropicConfig from litellm.llms.base_llm.chat.transformation import BaseConfig, BaseLLMException from litellm.types.llms.bedrock import * + +from ..common_utils import is_claude_4_5_on_bedrock from litellm.types.llms.openai import ( AllMessageValues, ChatCompletionAssistantMessage, @@ -924,6 +926,7 @@ class AmazonConverseConfig(BaseConfig): ChatCompletionAssistantMessage, ], block_type: Literal["system"], + model: Optional[str] = None, ) -> Optional[SystemContentBlock]: pass @@ -937,6 +940,7 @@ class AmazonConverseConfig(BaseConfig): ChatCompletionAssistantMessage, ], block_type: Literal["content_block"], + model: Optional[str] = None, ) -> Optional[ContentBlock]: pass @@ -949,6 +953,7 @@ class AmazonConverseConfig(BaseConfig): ChatCompletionAssistantMessage, ], block_type: Literal["system", "content_block"], + model: Optional[str] = None, ) -> Optional[Union[SystemContentBlock, ContentBlock]]: cache_control = message_block.get("cache_control", None) if cache_control is None: @@ -957,8 +962,9 @@ class AmazonConverseConfig(BaseConfig): cache_point = CachePointBlock(type="default") if isinstance(cache_control, dict) and "ttl" in cache_control: ttl = cache_control["ttl"] - if ttl in ["5m", "1h"]: - cache_point["ttl"] = ttl + if ttl in ["5m", "1h"] and model is not None: + if is_claude_4_5_on_bedrock(model): + cache_point["ttl"] = ttl if block_type == "system": return SystemContentBlock(cachePoint=cache_point) @@ -966,7 +972,7 @@ class AmazonConverseConfig(BaseConfig): return ContentBlock(cachePoint=cache_point) def _transform_system_message( - self, messages: List[AllMessageValues] + self, messages: List[AllMessageValues], model: Optional[str] = None ) -> Tuple[List[AllMessageValues], List[SystemContentBlock]]: system_prompt_indices = [] system_content_blocks: List[SystemContentBlock] = [] @@ -978,7 +984,7 @@ class AmazonConverseConfig(BaseConfig): SystemContentBlock(text=message["content"]) ) cache_block = self._get_cache_point_block( - message, block_type="system" + message, block_type="system", model=model ) if cache_block: system_content_blocks.append(cache_block) @@ -989,7 +995,7 @@ class AmazonConverseConfig(BaseConfig): SystemContentBlock(text=m["text"]) ) cache_block = self._get_cache_point_block( - m, block_type="system" + m, block_type="system", model=model ) if cache_block: system_content_blocks.append(cache_block) @@ -1258,7 +1264,9 @@ class AmazonConverseConfig(BaseConfig): litellm_params: dict, headers: Optional[dict] = None, ) -> RequestObject: - messages, system_content_blocks = self._transform_system_message(messages) + messages, system_content_blocks = self._transform_system_message( + messages, model=model + ) # Convert last user message to guarded_text if guardrailConfig is present messages = self._convert_consecutive_user_messages_to_guarded_text( @@ -1314,7 +1322,9 @@ class AmazonConverseConfig(BaseConfig): litellm_params: dict, headers: Optional[dict] = None, ) -> RequestObject: - messages, system_content_blocks = self._transform_system_message(messages) + messages, system_content_blocks = self._transform_system_message( + messages, model=model + ) # Convert last user message to guarded_text if guardrailConfig is present messages = self._convert_consecutive_user_messages_to_guarded_text( diff --git a/litellm/llms/bedrock/common_utils.py b/litellm/llms/bedrock/common_utils.py index 65d237bdbd..4c87f6fa99 100644 --- a/litellm/llms/bedrock/common_utils.py +++ b/litellm/llms/bedrock/common_utils.py @@ -446,6 +446,29 @@ def get_bedrock_base_model(model: str) -> str: return model +def is_claude_4_5_on_bedrock(model: str) -> bool: + """ + Check if the model is a Claude 4.5 model on Bedrock. + Claude 4.5 models support prompt caching with '5m' and '1h' TTL on Bedrock. + """ + model_lower = model.lower() + claude_4_5_patterns = [ + "sonnet-4.5", + "sonnet_4.5", + "sonnet-4-5", + "sonnet_4_5", + "haiku-4.5", + "haiku_4.5", + "haiku-4-5", + "haiku_4_5", + "opus-4.5", + "opus_4.5", + "opus-4-5", + "opus_4_5", + ] + return any(pattern in model_lower for pattern in claude_4_5_patterns) + + # Import after standalone functions to avoid circular imports from litellm.llms.bedrock.count_tokens.bedrock_token_counter import BedrockTokenCounter @@ -815,21 +838,23 @@ def get_anthropic_beta_from_headers(headers: dict) -> List[str]: # If it's already a list, return it if isinstance(anthropic_beta_header, list): return anthropic_beta_header - + # Try to parse as JSON array first (e.g., '["interleaved-thinking-2025-05-14", "claude-code-20250219"]') if isinstance(anthropic_beta_header, str): anthropic_beta_header = anthropic_beta_header.strip() - if anthropic_beta_header.startswith("[") and anthropic_beta_header.endswith("]"): + if anthropic_beta_header.startswith("[") and anthropic_beta_header.endswith( + "]" + ): try: parsed = json.loads(anthropic_beta_header) if isinstance(parsed, list): return [str(beta).strip() for beta in parsed] except json.JSONDecodeError: pass # Fall through to comma-separated parsing - + # Fall back to comma-separated values return [beta.strip() for beta in anthropic_beta_header.split(",")] - + return [] diff --git a/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py b/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py index d9f9ec8f4b..90de67a822 100644 --- a/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py +++ b/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py @@ -23,7 +23,10 @@ from litellm.llms.bedrock.chat.invoke_handler import AWSEventStreamDecoder from litellm.llms.bedrock.chat.invoke_transformations.base_invoke_transformation import ( AmazonInvokeConfig, ) -from litellm.llms.bedrock.common_utils import get_anthropic_beta_from_headers +from litellm.llms.bedrock.common_utils import ( + get_anthropic_beta_from_headers, + is_claude_4_5_on_bedrock, +) from litellm.types.llms.anthropic import ANTHROPIC_TOOL_SEARCH_BETA_HEADER from litellm.types.llms.openai import AllMessageValues from litellm.types.router import GenericLiteLLMParams @@ -147,8 +150,6 @@ class AmazonAnthropicClaudeMessagesConfig( ttl = cache_control["ttl"] if is_claude_4_5 and ttl in ["5m", "1h"]: continue - if ttl in ["5m", "1h"]: - continue cache_control.pop("ttl", None) @@ -218,22 +219,7 @@ class AmazonAnthropicClaudeMessagesConfig( Returns: True if the model is Claude 4.5 """ - model_lower = model.lower() - claude_4_5_patterns = [ - "sonnet-4.5", - "sonnet_4.5", - "sonnet-4-5", - "sonnet_4_5", - "haiku-4.5", - "haiku_4.5", - "haiku-4-5", - "haiku_4_5", - "opus-4.5", - "opus_4.5", - "opus-4-5", - "opus_4_5", - ] - return any(pattern in model_lower for pattern in claude_4_5_patterns) + return is_claude_4_5_on_bedrock(model) def _supports_tool_search_on_bedrock(self, model: str) -> bool: """