diff --git a/litellm/llms/anthropic/chat/transformation.py b/litellm/llms/anthropic/chat/transformation.py index 0b56eb86d9..1e5118dc41 100644 --- a/litellm/llms/anthropic/chat/transformation.py +++ b/litellm/llms/anthropic/chat/transformation.py @@ -1793,7 +1793,10 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig): self._ensure_context_management_beta_header( headers, optional_params["context_management"] ) - if optional_params.get("output_format") is not None: + output_config = optional_params.get("output_config") + if optional_params.get("output_format") is not None or ( + isinstance(output_config, dict) and output_config.get("format") is not None + ): self._ensure_beta_header( headers, ANTHROPIC_BETA_HEADER_VALUES.STRUCTURED_OUTPUT_2025_09_25.value ) diff --git a/litellm/llms/anthropic/experimental_pass_through/messages/transformation.py b/litellm/llms/anthropic/experimental_pass_through/messages/transformation.py index 15f404d3f5..f94232fa45 100644 --- a/litellm/llms/anthropic/experimental_pass_through/messages/transformation.py +++ b/litellm/llms/anthropic/experimental_pass_through/messages/transformation.py @@ -427,8 +427,13 @@ class AnthropicMessagesConfig(BaseAnthropicMessagesConfig): ANTHROPIC_BETA_HEADER_VALUES.CONTEXT_MANAGEMENT_2025_06_27.value ) - # Check for structured outputs - if optional_params.get("output_format") is not None: + # Check for structured outputs. Anthropic's newer request shape nests + # the schema under output_config.format; the older top-level + # output_format remains supported for backwards compatibility. + output_config = optional_params.get("output_config") + if optional_params.get("output_format") is not None or ( + isinstance(output_config, dict) and output_config.get("format") is not None + ): beta_values.add( ANTHROPIC_BETA_HEADER_VALUES.STRUCTURED_OUTPUT_2025_09_25.value ) diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py index ae100eda8d..d58d2e2759 100644 --- a/litellm/llms/bedrock/chat/converse_transformation.py +++ b/litellm/llms/bedrock/chat/converse_transformation.py @@ -78,6 +78,7 @@ from ..common_utils import ( get_anthropic_beta_from_headers, get_bedrock_tool_name, is_claude_4_5_on_bedrock, + normalize_bedrock_opus_output_config_effort, ) # Computer use tool prefixes supported by Bedrock @@ -448,10 +449,20 @@ class AmazonConverseConfig(BaseConfig): value=reasoning_effort, llm_provider="bedrock_converse", ) + existing_output_config = optional_params.get("output_config") + if not isinstance(existing_output_config, dict): + existing_output_config = {} + existing_output_config.setdefault("effort", mapped_effort) + normalize_bedrock_opus_output_config_effort( + model=model, + output_config=existing_output_config, + ) + mapped_effort = existing_output_config["effort"] self._validate_anthropic_adaptive_effort( model=model, effort=mapped_effort ) - optional_params["output_config"] = {"effort": mapped_effort} + optional_params["output_config"] = existing_output_config + optional_params["_output_config_normalized"] = True @staticmethod def _validate_anthropic_adaptive_effort(model: str, effort: str) -> None: @@ -1201,6 +1212,12 @@ class AmazonConverseConfig(BaseConfig): self, optional_params: dict, model: str ) -> Tuple[dict, dict, dict, Optional[OutputConfigBlock]]: """Prepare and separate request parameters.""" + # Consume the internal ``_output_config_normalized`` marker set by + # ``_handle_reasoning_effort_parameter`` so it does not linger on the + # caller's ``optional_params`` after the transformation returns. + anthropic_output_config_already_normalized = bool( + optional_params.pop("_output_config_normalized", False) + ) # Filter out exception objects before deepcopy to prevent deepcopy failures # Exceptions should not be stored in optional_params (this is a defensive fix) cleaned_params = filter_exceptions_from_params(optional_params) @@ -1219,8 +1236,17 @@ class AmazonConverseConfig(BaseConfig): # Anthropic-only ``output_config`` (snake_case) — re-attached to # ``additionalModelRequestFields`` for Anthropic models below. The - # Bedrock-native ``outputConfig`` (camelCase) is handled separately. + # structured-output ``format`` subfield is consumed into Bedrock's + # native ``outputConfig`` (camelCase), which is handled separately. anthropic_output_config = inference_params.pop("output_config", None) + output_config_format = None + if isinstance(anthropic_output_config, dict): + anthropic_output_config = dict(anthropic_output_config) + candidate_output_config_format = anthropic_output_config.pop("format", None) + if isinstance(candidate_output_config_format, dict): + output_config_format = candidate_output_config_format + if not anthropic_output_config: + anthropic_output_config = None # Extract requestMetadata before processing other parameters request_metadata = inference_params.pop("requestMetadata", None) @@ -1230,6 +1256,30 @@ class AmazonConverseConfig(BaseConfig): output_config: Optional[OutputConfigBlock] = inference_params.pop( "outputConfig", None ) + base_model = BedrockModelInfo.get_base_model(model) + if ( + output_config is None + and output_config_format is not None + and output_config_format.get("type") == "json_schema" + and base_model.startswith("anthropic") + and self._supports_native_structured_outputs( + model, self.custom_llm_provider + ) + ): + output_config = self._create_output_config_for_response_format( + json_schema=output_config_format.get("schema"), + name=output_config_format.get("name"), + description=output_config_format.get("description"), + ) + elif output_config is None and output_config_format is not None: + litellm.verbose_logger.warning( + "Bedrock Converse: dropping `output_config.format` for model=%s — " + "model does not advertise `supports_native_structured_output` in " + "model_prices_and_context_window.json. The schema will not be " + "enforced; pass `response_format` to use the synthetic tool-call " + "fallback.", + model, + ) # keep supported params in 'inference_params', and set all model-specific params in 'additional_request_params' additional_request_params = { @@ -1275,7 +1325,6 @@ class AmazonConverseConfig(BaseConfig): if anthropic_output_config is not None and isinstance( anthropic_output_config, dict ): - base_model = BedrockModelInfo.get_base_model(model) if base_model.startswith("anthropic"): if ( litellm.drop_params is True @@ -1286,6 +1335,11 @@ class AmazonConverseConfig(BaseConfig): model, ) else: + if not anthropic_output_config_already_normalized: + normalize_bedrock_opus_output_config_effort( + model=model, + output_config=anthropic_output_config, + ) effort = anthropic_output_config.get("effort") if effort is not None: self._validate_anthropic_adaptive_effort( diff --git a/litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude3_transformation.py b/litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude3_transformation.py index d9599b8b9c..a13336b6c8 100644 --- a/litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude3_transformation.py +++ b/litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude3_transformation.py @@ -16,8 +16,11 @@ from litellm.llms.bedrock.chat.invoke_transformations.base_invoke_transformation AmazonInvokeConfig, ) from litellm.llms.bedrock.common_utils import ( + convert_bedrock_invoke_output_format_to_inline_schema, get_anthropic_beta_from_headers, + normalize_bedrock_opus_output_config_effort, normalize_tool_input_schema_types_for_bedrock_invoke, + pop_bedrock_invoke_output_config_format, remove_custom_field_from_tools, ) from litellm.types.llms.anthropic import ANTHROPIC_TOOL_SEARCH_BETA_HEADER @@ -75,6 +78,17 @@ class AmazonAnthropicClaudeConfig(AmazonInvokeConfig, AnthropicConfig): # Use a model name that forces tool-based approach model = "claude-3-sonnet-20240229" + # Clamp ``reasoning_effort`` to the Bedrock effort ceiling before the + # parent mapping converts it to ``output_config.effort`` and the + # downstream effort gate runs. Mirrors the converse path's + # ``_handle_reasoning_effort_parameter`` and the messages path's + # ``_clamp_adaptive_reasoning_effort_for_bedrock`` so adaptive Claude + # requests degrade ``xhigh`` -> ``max`` rather than 400-ing on + # models like Opus 4.6 that don't natively advertise xhigh. + self._clamp_adaptive_reasoning_effort_for_bedrock( + model=original_model, params=non_default_params + ) + optional_params = AnthropicConfig.map_openai_params( self, non_default_params, @@ -88,6 +102,27 @@ class AmazonAnthropicClaudeConfig(AmazonInvokeConfig, AnthropicConfig): return optional_params + @staticmethod + def _clamp_adaptive_reasoning_effort_for_bedrock(model: str, params: dict) -> None: + """Lower ``reasoning_effort`` to the Bedrock effort ceiling before mapping. + + Bedrock's adaptive Claude models accept the OpenAI-style + ``reasoning_effort`` tier, but the request validator can reject tiers + the model does not natively advertise (e.g. ``xhigh`` on Opus 4.6). + Clamp the raw tier to the model's + ``bedrock_output_config_effort_ceiling`` so Claude Code "goal mode" + keeps working. Non-adaptive models and models without a ceiling are + left untouched. + """ + if not AnthropicConfig._is_adaptive_thinking_model(model): + return + effort = params.get("reasoning_effort") + if not isinstance(effort, str): + return + clamped = {"effort": effort} + normalize_bedrock_opus_output_config_effort(model=model, output_config=clamped) + params["reasoning_effort"] = clamped["effort"] + def transform_request( self, model: str, @@ -157,6 +192,13 @@ class AmazonAnthropicClaudeConfig(AmazonInvokeConfig, AnthropicConfig): for k, v in optional_params.items() if k not in self.aws_authentication_params } + output_config = filtered_params.get("output_config") + if isinstance(output_config, dict): + filtered_params["output_config"] = dict(output_config) + normalize_bedrock_opus_output_config_effort( + model=model, + output_config=filtered_params["output_config"], + ) filtered_params = self._normalize_bedrock_tool_search_tools(filtered_params) anthropic_request = AnthropicConfig.transform_request( @@ -170,7 +212,20 @@ class AmazonAnthropicClaudeConfig(AmazonInvokeConfig, AnthropicConfig): anthropic_request.pop("model", None) anthropic_request.pop("stream", None) - anthropic_request.pop("output_format", None) + output_format = anthropic_request.pop("output_format", None) + output_config_format = pop_bedrock_invoke_output_config_format( + anthropic_request + ) + if output_format: + convert_bedrock_invoke_output_format_to_inline_schema( + output_format=output_format, + request_body=anthropic_request, + ) + elif output_config_format: + convert_bedrock_invoke_output_format_to_inline_schema( + output_format=output_config_format, + request_body=anthropic_request, + ) if not ( _supports_factory( model=model, diff --git a/litellm/llms/bedrock/common_utils.py b/litellm/llms/bedrock/common_utils.py index 4f4729e401..bdc5da321c 100644 --- a/litellm/llms/bedrock/common_utils.py +++ b/litellm/llms/bedrock/common_utils.py @@ -34,6 +34,15 @@ class BedrockError(BaseLLMException): # Lazy import cache to avoid circular imports and performance impact _get_model_info = None +BedrockOutputConfigEffort = Literal["low", "medium", "high", "max", "xhigh"] +_BEDROCK_OUTPUT_CONFIG_EFFORT_ORDER: Dict[BedrockOutputConfigEffort, int] = { + "low": 0, + "medium": 1, + "high": 2, + "max": 3, + "xhigh": 4, +} + def get_cached_model_info(): """ @@ -51,6 +60,79 @@ def get_cached_model_info(): return _get_model_info +@functools.lru_cache(maxsize=1) +def _get_local_model_cost_map() -> Dict: + from litellm.litellm_core_utils.get_model_cost_map import GetModelCostMap + + return GetModelCostMap.load_local_model_cost_map() + + +def pop_bedrock_invoke_output_config_format(request_body: Dict) -> Optional[Dict]: + """ + Remove and return Anthropic's nested ``output_config.format`` field. + + Bedrock Invoke paths convert the schema to inline message text. Any remaining + ``output_config`` keys, such as ``effort``, are left in place. + """ + output_config = request_body.get("output_config") + if not isinstance(output_config, dict): + return None + + output_format = output_config.pop("format", None) + if not output_config: + request_body.pop("output_config", None) + + if isinstance(output_format, dict): + return output_format + return None + + +def convert_bedrock_invoke_output_format_to_inline_schema( + output_format: Dict, + request_body: Dict, +) -> None: + """ + Embed an Anthropic structured-output schema into the last user message. + + Bedrock Invoke does not support ``output_format`` directly, so the schema is + appended to the final user message for prompt-engineered structured output. + The caller's ``messages`` list, message dict, and content list are not + mutated; a fresh ``messages`` list with a copied final user message is + written back to ``request_body``. + """ + schema = output_format.get("schema") + if not schema: + return + + messages = request_body.get("messages") + if not isinstance(messages, list) or not messages: + return + + last_user_idx = None + for i in range(len(messages) - 1, -1, -1): + message = messages[i] + if isinstance(message, dict) and message.get("role") == "user": + last_user_idx = i + break + + if last_user_idx is None: + return + + original = messages[last_user_idx] + content = original.get("content", []) + schema_block = {"type": "text", "text": json.dumps(schema)} + if isinstance(content, str): + new_content = [{"type": "text", "text": content}, schema_block] + elif isinstance(content, list): + new_content = [*content, schema_block] + else: + return + + new_messages = list(messages) + new_messages[last_user_idx] = {**original, "content": new_content} + request_body["messages"] = new_messages + + def remove_custom_field_from_tools(request_body: dict) -> None: """ Remove ``custom`` field from each tool in the request body. @@ -603,6 +685,62 @@ def is_claude_4_5_on_bedrock(model: str) -> bool: return any(pattern in model_lower for pattern in claude_4_5_patterns) +def normalize_bedrock_opus_output_config_effort(model: str, output_config: Any) -> None: + """ + Normalize Anthropic ``output_config.effort`` values for Bedrock Opus ids. + + Bedrock's Claude Opus request validator can accept a narrower effort + vocabulary than Anthropic's compatibility surface. The Bedrock ceiling is + read from ``model_prices_and_context_window.json`` via + ``bedrock_output_config_effort_ceiling``. + + Mutates ``output_config`` in place so callers can accept Claude Code's + ``xhigh`` input without forwarding a provider-invalid value. + """ + if not isinstance(output_config, dict): + return + + effort = output_config.get("effort") + if effort not in _BEDROCK_OUTPUT_CONFIG_EFFORT_ORDER: + return + + ceiling = _get_bedrock_output_config_effort_ceiling(model) + if ceiling is None: + return + + if ( + _BEDROCK_OUTPUT_CONFIG_EFFORT_ORDER[effort] + > _BEDROCK_OUTPUT_CONFIG_EFFORT_ORDER[ceiling] + ): + output_config["effort"] = ceiling + + +def _get_bedrock_output_config_effort_ceiling( + model: str, +) -> Optional[BedrockOutputConfigEffort]: + try: + model_info = get_cached_model_info()( + model=model, + custom_llm_provider="bedrock", + ) + except Exception: + return None + + ceiling = model_info.get("bedrock_output_config_effort_ceiling") + if isinstance(ceiling, str) and ceiling in _BEDROCK_OUTPUT_CONFIG_EFFORT_ORDER: + return ceiling # type: ignore[return-value] + + model_cost_key = model_info.get("key") + if not isinstance(model_cost_key, str): + return None + + local_model_info = _get_local_model_cost_map().get(model_cost_key, {}) + ceiling = local_model_info.get("bedrock_output_config_effort_ceiling") + if isinstance(ceiling, str) and ceiling in _BEDROCK_OUTPUT_CONFIG_EFFORT_ORDER: + return ceiling # type: ignore[return-value] + return None + + # Import after standalone functions to avoid circular imports from litellm.llms.bedrock.count_tokens.bedrock_token_counter import BedrockTokenCounter 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 69b61298d3..b223f4534f 100644 --- a/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py +++ b/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py @@ -32,10 +32,13 @@ from litellm.llms.bedrock.chat.invoke_transformations.base_invoke_transformation AmazonInvokeConfig, ) from litellm.llms.bedrock.common_utils import ( + convert_bedrock_invoke_output_format_to_inline_schema, ensure_bedrock_anthropic_messages_tool_names, get_anthropic_beta_from_headers, is_claude_4_5_on_bedrock, + normalize_bedrock_opus_output_config_effort, normalize_tool_input_schema_types_for_bedrock_invoke, + pop_bedrock_invoke_output_config_format, remove_custom_field_from_tools, ) from litellm.types.llms.anthropic import ANTHROPIC_TOOL_SEARCH_BETA_HEADER @@ -450,145 +453,15 @@ class AmazonAnthropicClaudeMessagesConfig( else: anthropic_messages_request.pop("context_management", None) - def _convert_output_format_to_inline_schema( - self, - output_format: Dict, - anthropic_messages_request: Dict, - ) -> None: - """ - Convert Anthropic output_format to inline schema in message content. - - Bedrock Invoke doesn't support the output_format parameter, so we embed - the schema directly into the user message content as text instructions. - - This approach adds the schema to the last user message, instructing the model - to respond in the specified JSON format. - - Args: - output_format: The output_format dict with 'type' and 'schema' - anthropic_messages_request: The request dict to modify in-place - - Ref: https://aws.amazon.com/blogs/machine-learning/structured-data-response-with-amazon-bedrock-prompt-engineering-and-tool-use/ - """ - import json - - # Extract schema from output_format - schema = output_format.get("schema") - if not schema: - return - - # Get messages from the request - messages = anthropic_messages_request.get("messages", []) - if not messages: - return - - # Find the last user message - last_user_message_idx = None - for idx in range(len(messages) - 1, -1, -1): - if messages[idx].get("role") == "user": - last_user_message_idx = idx - break - - if last_user_message_idx is None: - return - - last_user_message = messages[last_user_message_idx] - content = last_user_message.get("content", []) - - # Ensure content is a list - if isinstance(content, str): - content = [{"type": "text", "text": content}] - last_user_message["content"] = content - - # Add schema as text content to the message - schema_text = {"type": "text", "text": json.dumps(schema)} - content.append(schema_text) - - def transform_anthropic_messages_request( + def _get_bedrock_invoke_anthropic_beta_headers( self, model: str, messages: List[Dict], anthropic_messages_optional_request_params: Dict, - litellm_params: GenericLiteLLMParams, headers: dict, - ) -> Dict: - anthropic_messages_request = AnthropicMessagesConfig.transform_anthropic_messages_request( - self=self, - model=model, - messages=messages, - anthropic_messages_optional_request_params=anthropic_messages_optional_request_params, - litellm_params=litellm_params, - headers=headers, - ) - ######################################################### - ############## BEDROCK Invoke SPECIFIC TRANSFORMATION ### - ######################################################### - - # 1. anthropic_version is required for all claude models - if "anthropic_version" not in anthropic_messages_request: - anthropic_messages_request["anthropic_version"] = ( - self.DEFAULT_BEDROCK_ANTHROPIC_API_VERSION - ) - - # 2. `stream` is not allowed in request body for bedrock invoke - if "stream" in anthropic_messages_request: - anthropic_messages_request.pop("stream", None) - - # 3. `model` is not allowed in request body for bedrock invoke - if "model" in anthropic_messages_request: - anthropic_messages_request.pop("model", None) - - injected_thinking_for_clear_thinking = ( - self._ensure_thinking_for_clear_thinking_context_management( - anthropic_messages_request=anthropic_messages_request, - model=model, - ) - ) - - # 4. Remove `ttl` field from cache_control in messages (Bedrock doesn't support it for older models) - self._remove_ttl_from_cache_control( - anthropic_messages_request=anthropic_messages_request, model=model - ) - - # 5. Convert `output_format` to inline schema (Bedrock invoke doesn't support output_format) - output_format = anthropic_messages_request.pop("output_format", None) - if output_format: - self._convert_output_format_to_inline_schema( - output_format=output_format, - anthropic_messages_request=anthropic_messages_request, - ) - - # 5a. Bedrock Invoke supports output_config (effort) for Claude 4.6+ models, - # but older models do not — strip it to avoid request rejection. - # Ref: https://github.com/BerriAI/litellm/issues/22797 - if not ( - _supports_factory( - model=model, - custom_llm_provider="bedrock", - key="supports_output_config", - ) - or AnthropicConfig._model_supports_effort_param(model) - ): - if anthropic_messages_request.pop("output_config", None) is not None: - verbose_logger.warning( - "Bedrock Invoke: stripping unsupported `output_config` for " - "model=%s — neither `supports_output_config` nor any " - "`supports_*_reasoning_effort` flag is set in " - "model_prices_and_context_window.json. Add the capability " - "flag to the model JSON entry if this model accepts " - "`output_config`.", - model, - ) - - # 5b. Remove `custom` field from tools (Bedrock doesn't support it) - # Claude Code sends `custom: {defer_loading: true}` on tool definitions, - # which causes Bedrock to reject the request with "Extra inputs are not permitted" - # Ref: https://github.com/BerriAI/litellm/issues/22847 - remove_custom_field_from_tools(anthropic_messages_request) - normalize_tool_input_schema_types_for_bedrock_invoke(anthropic_messages_request) - ensure_bedrock_anthropic_messages_tool_names(anthropic_messages_request) - - # 6. AUTO-INJECT beta headers based on features used + anthropic_messages_request: Dict, + injected_thinking_for_clear_thinking: bool, + ) -> List[str]: anthropic_model_info = AnthropicModelInfo() tools = anthropic_messages_optional_request_params.get("tools") messages_typed = cast(List[AllMessageValues], messages) @@ -651,6 +524,160 @@ class AmazonAnthropicClaudeMessagesConfig( dropped_user_betas, ) + return filtered_betas + + def _strip_unsupported_bedrock_invoke_fields( + self, + anthropic_messages_request: Dict, + ) -> Dict: + allowed = self.BEDROCK_INVOKE_ALLOWED_TOP_LEVEL_FIELDS + stripped = sorted(k for k in anthropic_messages_request if k not in allowed) + if stripped: + verbose_logger.debug( + "Bedrock Invoke: stripping unsupported top-level request fields: %s", + stripped, + ) + return {k: v for k, v in anthropic_messages_request.items() if k in allowed} + + @staticmethod + def _clamp_adaptive_reasoning_effort_for_bedrock( + model: str, optional_params: Dict + ) -> None: + """Lower ``reasoning_effort`` to the Bedrock effort ceiling before validation. + + The shared ``/v1/messages`` effort gate rejects tiers a model does not + natively support (e.g. ``xhigh`` on Opus 4.6). Bedrock's chat paths instead + clamp the tier to the model's ``bedrock_output_config_effort_ceiling`` so + Claude Code "goal mode" keeps working; mirror that here so the messages + path degrades ``xhigh`` -> ``max`` rather than 400-ing. Non-adaptive models + and models without a ceiling are left untouched. + """ + if not AnthropicModelInfo._is_adaptive_thinking_model(model): + return + effort = optional_params.get("reasoning_effort") + if not isinstance(effort, str): + return + clamped = {"effort": effort} + normalize_bedrock_opus_output_config_effort(model=model, output_config=clamped) + optional_params["reasoning_effort"] = clamped["effort"] + + def transform_anthropic_messages_request( + self, + model: str, + messages: List[Dict], + anthropic_messages_optional_request_params: Dict, + litellm_params: GenericLiteLLMParams, + headers: dict, + ) -> Dict: + self._clamp_adaptive_reasoning_effort_for_bedrock( + model=model, + optional_params=anthropic_messages_optional_request_params, + ) + anthropic_messages_request = AnthropicMessagesConfig.transform_anthropic_messages_request( + self=self, + model=model, + messages=messages, + anthropic_messages_optional_request_params=anthropic_messages_optional_request_params, + litellm_params=litellm_params, + headers=headers, + ) + ######################################################### + ############## BEDROCK Invoke SPECIFIC TRANSFORMATION ### + ######################################################### + + # 1. anthropic_version is required for all claude models + if "anthropic_version" not in anthropic_messages_request: + anthropic_messages_request["anthropic_version"] = ( + self.DEFAULT_BEDROCK_ANTHROPIC_API_VERSION + ) + + # 2. `stream` is not allowed in request body for bedrock invoke + if "stream" in anthropic_messages_request: + anthropic_messages_request.pop("stream", None) + + # 3. `model` is not allowed in request body for bedrock invoke + if "model" in anthropic_messages_request: + anthropic_messages_request.pop("model", None) + + injected_thinking_for_clear_thinking = ( + self._ensure_thinking_for_clear_thinking_context_management( + anthropic_messages_request=anthropic_messages_request, + model=model, + ) + ) + + # 4. Remove `ttl` field from cache_control in messages (Bedrock doesn't support it for older models) + self._remove_ttl_from_cache_control( + anthropic_messages_request=anthropic_messages_request, model=model + ) + + # 5. Convert structured-output params to inline schema. + # Bedrock Invoke doesn't support top-level `output_format`; its + # accepted `output_config` subset is also narrower than Anthropic's, so + # consume the newer `output_config.format` shape here instead of + # forwarding it as an unknown nested key. + existing_output_config = anthropic_messages_request.get("output_config") + if isinstance(existing_output_config, dict): + anthropic_messages_request["output_config"] = dict(existing_output_config) + output_format = anthropic_messages_request.pop("output_format", None) + output_config_format = pop_bedrock_invoke_output_config_format( + anthropic_messages_request + ) + if output_format: + convert_bedrock_invoke_output_format_to_inline_schema( + output_format=output_format, + request_body=anthropic_messages_request, + ) + elif output_config_format: + convert_bedrock_invoke_output_format_to_inline_schema( + output_format=output_config_format, + request_body=anthropic_messages_request, + ) + normalize_bedrock_opus_output_config_effort( + model=model, + output_config=anthropic_messages_request.get("output_config"), + ) + + # 5a. Bedrock Invoke supports output_config (effort) for Claude 4.6+ models, + # but older models do not — strip it to avoid request rejection. + # Ref: https://github.com/BerriAI/litellm/issues/22797 + if not ( + _supports_factory( + model=model, + custom_llm_provider="bedrock", + key="supports_output_config", + ) + or AnthropicConfig._model_supports_effort_param(model) + ): + if anthropic_messages_request.pop("output_config", None) is not None: + verbose_logger.warning( + "Bedrock Invoke: stripping unsupported `output_config` for " + "model=%s — neither `supports_output_config` nor any " + "`supports_*_reasoning_effort` flag is set in " + "model_prices_and_context_window.json. Add the capability " + "flag to the model JSON entry if this model accepts " + "`output_config`.", + model, + ) + + # 5b. Remove `custom` field from tools (Bedrock doesn't support it) + # Claude Code sends `custom: {defer_loading: true}` on tool definitions, + # which causes Bedrock to reject the request with "Extra inputs are not permitted" + # Ref: https://github.com/BerriAI/litellm/issues/22847 + remove_custom_field_from_tools(anthropic_messages_request) + normalize_tool_input_schema_types_for_bedrock_invoke(anthropic_messages_request) + ensure_bedrock_anthropic_messages_tool_names(anthropic_messages_request) + + # 6. AUTO-INJECT beta headers based on features used + filtered_betas = self._get_bedrock_invoke_anthropic_beta_headers( + model=model, + messages=messages, + anthropic_messages_optional_request_params=anthropic_messages_optional_request_params, + headers=headers, + anthropic_messages_request=anthropic_messages_request, + injected_thinking_for_clear_thinking=injected_thinking_for_clear_thinking, + ) + if filtered_betas: anthropic_messages_request["anthropic_beta"] = filtered_betas @@ -669,16 +696,9 @@ class AmazonAnthropicClaudeMessagesConfig( # Catches Anthropic-only extensions (output_config, speed, mcp_servers, ...) # and any future additions Claude Code may start sending. ``context_management`` # has already been pre-filtered to its Bedrock-supported subset above. - allowed = self.BEDROCK_INVOKE_ALLOWED_TOP_LEVEL_FIELDS - stripped = sorted(k for k in anthropic_messages_request if k not in allowed) - if stripped: - verbose_logger.debug( - "Bedrock Invoke: stripping unsupported top-level request fields: %s", - stripped, - ) - anthropic_messages_request = { - k: v for k, v in anthropic_messages_request.items() if k in allowed - } + anthropic_messages_request = self._strip_unsupported_bedrock_invoke_fields( + anthropic_messages_request + ) return anthropic_messages_request diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index ec16f19799..62e0f6c4c3 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -982,7 +982,9 @@ "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "high" }, "anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.25e-06, @@ -1013,7 +1015,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "bedrock_output_config_effort_ceiling": "max" }, "global.anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.25e-06, @@ -1044,7 +1047,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "bedrock_output_config_effort_ceiling": "max" }, "us.anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.875e-06, @@ -1075,7 +1079,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "bedrock_output_config_effort_ceiling": "max" }, "eu.anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.875e-06, @@ -1105,7 +1110,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "bedrock_output_config_effort_ceiling": "max" }, "au.anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.875e-06, @@ -1135,7 +1141,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "bedrock_output_config_effort_ceiling": "max" }, "anthropic.claude-opus-4-7": { "cache_creation_input_token_cost": 6.25e-06, @@ -1166,7 +1173,9 @@ "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" }, "anthropic.claude-mythos-preview": { "input_cost_per_token": 0, @@ -1212,7 +1221,9 @@ "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" }, "us.anthropic.claude-opus-4-7": { "cache_creation_input_token_cost": 6.875e-06, @@ -1243,7 +1254,9 @@ "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" }, "eu.anthropic.claude-opus-4-7": { "cache_creation_input_token_cost": 6.875e-06, @@ -1273,7 +1286,9 @@ "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" }, "au.anthropic.claude-opus-4-7": { "cache_creation_input_token_cost": 6.875e-06, @@ -1303,7 +1318,9 @@ "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" }, "anthropic.claude-sonnet-4-6": { "cache_creation_input_token_cost": 3.75e-06, @@ -9804,7 +9821,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "tool_use_system_prompt_tokens": 159, + "supports_output_config": true }, "claude-opus-4-5": { "cache_creation_input_token_cost": 6.25e-06, @@ -9832,7 +9850,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "tool_use_system_prompt_tokens": 159, + "supports_output_config": true }, "claude-opus-4-6": { "cache_creation_input_token_cost": 6.25e-06, @@ -31808,7 +31827,9 @@ "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "high" }, "global.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -31837,7 +31858,9 @@ "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "high" }, "eu.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -31865,7 +31888,9 @@ "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "high" }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, diff --git a/litellm/types/llms/anthropic.py b/litellm/types/llms/anthropic.py index 1c4d31d21a..bbb892a027 100644 --- a/litellm/types/llms/anthropic.py +++ b/litellm/types/llms/anthropic.py @@ -39,7 +39,8 @@ class AnthropicOutputSchema(TypedDict, total=False): class AnthropicOutputConfig(TypedDict, total=False): """Configuration for controlling Claude's output behavior.""" - effort: Literal["high", "medium", "low"] + effort: Literal["high", "medium", "low", "xhigh", "max"] + format: AnthropicOutputSchema class AnthropicMessagesTool(TypedDict, total=False): diff --git a/litellm/types/utils.py b/litellm/types/utils.py index e7bce27170..8f471b62b5 100644 --- a/litellm/types/utils.py +++ b/litellm/types/utils.py @@ -148,6 +148,9 @@ class ProviderSpecificModelInfo(TypedDict, total=False): supports_xhigh_reasoning_effort: Optional[bool] supports_max_reasoning_effort: Optional[bool] supports_output_config: Optional[bool] + bedrock_output_config_effort_ceiling: Optional[ + Literal["low", "medium", "high", "max", "xhigh"] + ] class SearchContextCostPerQuery(TypedDict, total=False): diff --git a/litellm/utils.py b/litellm/utils.py index 760a615664..5a9dccc089 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -6036,6 +6036,9 @@ def _get_model_info_helper( # noqa: PLR0915 supports_max_reasoning_effort=_model_info.get( "supports_max_reasoning_effort", None ), + bedrock_output_config_effort_ceiling=_model_info.get( + "bedrock_output_config_effort_ceiling", None + ), supports_computer_use=_model_info.get("supports_computer_use", None), search_context_cost_per_query=_model_info.get( "search_context_cost_per_query", None diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 6e1c79c4e3..0689066e17 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -982,7 +982,9 @@ "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "high" }, "anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.25e-06, @@ -1013,7 +1015,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "bedrock_output_config_effort_ceiling": "max" }, "global.anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.25e-06, @@ -1044,7 +1047,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "bedrock_output_config_effort_ceiling": "max" }, "us.anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.875e-06, @@ -1075,7 +1079,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "bedrock_output_config_effort_ceiling": "max" }, "eu.anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.875e-06, @@ -1105,7 +1110,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "bedrock_output_config_effort_ceiling": "max" }, "au.anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.875e-06, @@ -1135,7 +1141,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "bedrock_output_config_effort_ceiling": "max" }, "anthropic.claude-opus-4-7": { "cache_creation_input_token_cost": 6.25e-06, @@ -1166,7 +1173,9 @@ "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" }, "anthropic.claude-mythos-preview": { "input_cost_per_token": 0, @@ -1212,7 +1221,9 @@ "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" }, "us.anthropic.claude-opus-4-7": { "cache_creation_input_token_cost": 6.875e-06, @@ -1243,7 +1254,9 @@ "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" }, "eu.anthropic.claude-opus-4-7": { "cache_creation_input_token_cost": 6.875e-06, @@ -1273,7 +1286,9 @@ "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" }, "au.anthropic.claude-opus-4-7": { "cache_creation_input_token_cost": 6.875e-06, @@ -1303,7 +1318,9 @@ "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" }, "anthropic.claude-sonnet-4-6": { "cache_creation_input_token_cost": 3.75e-06, @@ -9804,7 +9821,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "tool_use_system_prompt_tokens": 159, + "supports_output_config": true }, "claude-opus-4-5": { "cache_creation_input_token_cost": 6.25e-06, @@ -9832,7 +9850,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "tool_use_system_prompt_tokens": 159, + "supports_output_config": true }, "claude-opus-4-6": { "cache_creation_input_token_cost": 6.25e-06, @@ -31683,7 +31702,9 @@ "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "high" }, "global.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -31712,7 +31733,9 @@ "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "high" }, "eu.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -31740,7 +31763,9 @@ "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "high" }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, diff --git a/tests/llm_translation/reasoning_effort_grid/grid_spec.py b/tests/llm_translation/reasoning_effort_grid/grid_spec.py index 993643e0fc..2f9735274c 100644 --- a/tests/llm_translation/reasoning_effort_grid/grid_spec.py +++ b/tests/llm_translation/reasoning_effort_grid/grid_spec.py @@ -22,6 +22,7 @@ class ModelEntry: required_env: FrozenSet[str] = field(default_factory=frozenset) caps: FrozenSet[str] = field(default_factory=frozenset) fail_reason: Optional[str] = None + bedrock_effort_ceiling: Optional[str] = None def params(self) -> Dict[str, str]: return dict(self.extra_params) @@ -59,9 +60,31 @@ _ADAPTIVE_EFFORT_LABEL: Dict[str, str] = { "max": "max", } +_EFFORT_RANK: Dict[str, int] = { + "low": 0, + "medium": 1, + "high": 2, + "max": 3, + "xhigh": 4, +} + _BAD_REQUEST_EFFORTS: FrozenSet[str] = frozenset({"disabled", "invalid", ""}) +def _bedrock_clamps_effort(model: "ModelEntry", effort: str) -> bool: + """Whether Bedrock will clamp ``effort`` down to ``bedrock_effort_ceiling``. + + Bedrock chat/messages paths clamp unsupported high tiers (e.g. ``xhigh`` + on Opus 4.6) to the model's ceiling rather than rejecting them, so the + missing native capability is OK — the wire effort just degrades. + """ + if model.bedrock_effort_ceiling is None: + return False + if effort not in _EFFORT_RANK or model.bedrock_effort_ceiling not in _EFFORT_RANK: + return False + return _EFFORT_RANK[effort] > _EFFORT_RANK[model.bedrock_effort_ceiling] + + def expected(model: ModelEntry, effort: str) -> CellExpectation: if effort in ("__omit__", "none"): if model.mode == "budget": @@ -73,14 +96,20 @@ def expected(model: ModelEntry, effort: str) -> CellExpectation: if effort in ("xhigh", "max"): cap = f"supports_{effort}_reasoning_effort" - if cap not in model.caps: + if cap not in model.caps and not _bedrock_clamps_effort(model, effort): return CellExpectation(status=400, thinking_type=OMIT) if model.mode == "adaptive": + wire_effort = _ADAPTIVE_EFFORT_LABEL[effort] + if model.bedrock_effort_ceiling is not None: + wire_rank = _EFFORT_RANK[wire_effort] + ceiling_rank = _EFFORT_RANK[model.bedrock_effort_ceiling] + if wire_rank > ceiling_rank: + wire_effort = model.bedrock_effort_ceiling return CellExpectation( status=200, thinking_type="adaptive", - output_config_effort=_ADAPTIVE_EFFORT_LABEL[effort], + output_config_effort=wire_effort, ) return CellExpectation( @@ -219,6 +248,7 @@ BEDROCK_CONVERSE_MODELS: Tuple[ModelEntry, ...] = ( extra_params=(("aws_region_name", "us-east-1"),), required_env=_BEDROCK_REQ, caps=_CAPS_4_6, + bedrock_effort_ceiling="max", ), ModelEntry( alias="bedrock-claude-sonnet-4-6", @@ -247,6 +277,7 @@ BEDROCK_INVOKE_CHAT_MODELS: Tuple[ModelEntry, ...] = ( extra_params=(("aws_region_name", "us-east-1"),), required_env=_BEDROCK_REQ, caps=_CAPS_4_6, + bedrock_effort_ceiling="max", ), ModelEntry( alias="bedrock-invoke-claude-sonnet-4-6", diff --git a/tests/test_litellm/llms/anthropic/chat/test_anthropic_chat_transformation.py b/tests/test_litellm/llms/anthropic/chat/test_anthropic_chat_transformation.py index 7d9e476830..687c5a2e73 100644 --- a/tests/test_litellm/llms/anthropic/chat/test_anthropic_chat_transformation.py +++ b/tests/test_litellm/llms/anthropic/chat/test_anthropic_chat_transformation.py @@ -1622,6 +1622,29 @@ def test_effort_output_config_preservation(): assert result["output_config"]["effort"] == "medium" +def test_output_config_format_preservation_and_beta_header(): + """Test that output_config.format is preserved and treated as structured output.""" + config = AnthropicConfig() + output_format = { + "type": "json_schema", + "schema": {"type": "object", "properties": {"answer": {"type": "string"}}}, + } + optional_params = {"output_config": {"format": output_format, "effort": "xhigh"}} + + result = config.transform_request( + model="claude-opus-4-7", + messages=[{"role": "user", "content": "Test"}], + optional_params=optional_params, + litellm_params={}, + headers={}, + ) + headers = config.update_headers_with_optional_anthropic_beta({}, optional_params) + + assert result["output_config"]["format"] == output_format + assert result["output_config"]["effort"] == "xhigh" + assert "structured-outputs-2025-11-13" in headers["anthropic-beta"] + + def test_effort_beta_header_injection(): """Test that effort beta header is automatically added when output_config is detected.""" from litellm.llms.anthropic.common_utils import AnthropicModelInfo @@ -1648,7 +1671,7 @@ def test_effort_validation(): messages = [{"role": "user", "content": "Test"}] - # Valid values should work + # Valid values should work (xhigh is Opus 4.7+ only, not 4.5) for effort in ["high", "medium", "low"]: optional_params = {"output_config": {"effort": effort}} result = config.transform_request( @@ -2513,14 +2536,14 @@ def test_reasoning_effort_accepts_dict_shape_for_adaptive_model(reasoning_effort ) # thinking must be set (adaptive for 4.6+) - assert "thinking" in result, ( - f"thinking missing for reasoning_effort={reasoning_effort_value!r}" - ) + assert ( + "thinking" in result + ), f"thinking missing for reasoning_effort={reasoning_effort_value!r}" assert result["thinking"]["type"] == "adaptive" # output_config must carry the mapped effort - assert "output_config" in result, ( - f"output_config missing for reasoning_effort={reasoning_effort_value!r}" - ) + assert ( + "output_config" in result + ), f"output_config missing for reasoning_effort={reasoning_effort_value!r}" assert result["output_config"]["effort"] == "low" @@ -2532,7 +2555,9 @@ def test_reasoning_effort_accepts_dict_shape_for_adaptive_model(reasoning_effort {"effort": "low", "summary": "concise"}, ], ) -def test_reasoning_effort_accepts_dict_shape_for_non_adaptive_model(reasoning_effort_value): +def test_reasoning_effort_accepts_dict_shape_for_non_adaptive_model( + reasoning_effort_value, +): """ Non-adaptive (pre-4.6) branch: dict-shape reasoning_effort must still map to ``thinking.type='enabled'`` + ``budget_tokens``. ``output_config`` must @@ -2547,9 +2572,9 @@ def test_reasoning_effort_accepts_dict_shape_for_non_adaptive_model(reasoning_ef drop_params=False, ) - assert "thinking" in result, ( - f"thinking missing for reasoning_effort={reasoning_effort_value!r}" - ) + assert ( + "thinking" in result + ), f"thinking missing for reasoning_effort={reasoning_effort_value!r}" assert result["thinking"]["type"] == "enabled" assert "budget_tokens" in result["thinking"] assert result["thinking"]["budget_tokens"] > 0 @@ -2582,12 +2607,12 @@ def test_reasoning_effort_unparseable_dict_is_dropped(bad_value): model="claude-sonnet-4-6-20260219", drop_params=False, ) - assert "thinking" not in result, ( - f"thinking should not be set for bad value {bad_value!r}" - ) - assert "output_config" not in result, ( - f"output_config should not be set for bad value {bad_value!r}" - ) + assert ( + "thinking" not in result + ), f"thinking should not be set for bad value {bad_value!r}" + assert ( + "output_config" not in result + ), f"output_config should not be set for bad value {bad_value!r}" @pytest.mark.parametrize( diff --git a/tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_anthropic_messages_structured_outputs.py b/tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_anthropic_messages_structured_outputs.py index 3c81bfaa0f..e6d5c6f4ee 100644 --- a/tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_anthropic_messages_structured_outputs.py +++ b/tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_anthropic_messages_structured_outputs.py @@ -48,6 +48,39 @@ def test_output_format_supported_and_transforms_correctly(): assert "structured-outputs-2025-11-13" in headers["anthropic-beta"] +def test_output_config_format_supported_and_transforms_correctly(): + """Test that output_config.format is preserved and adds the structured-output beta.""" + config = AnthropicMessagesConfig() + + supported_params = config.get_supported_anthropic_messages_params("claude-opus-4-7") + assert "output_config" in supported_params + + output_format = { + "type": "json_schema", + "schema": {"type": "object", "properties": {"result": {"type": "string"}}}, + } + optional_params = { + "max_tokens": 1024, + "output_config": {"format": output_format, "effort": "xhigh"}, + } + headers = {} + + result = config.transform_anthropic_messages_request( + model="claude-opus-4-7", + messages=[{"role": "user", "content": "test"}], + anthropic_messages_optional_request_params=optional_params.copy(), + litellm_params={}, + headers=headers, + ) + + headers = config._update_headers_with_anthropic_beta(headers, optional_params) + + assert result["output_config"]["format"] == output_format + assert result["output_config"]["effort"] == "xhigh" + assert "anthropic-beta" in headers + assert "structured-outputs-2025-11-13" in headers["anthropic-beta"] + + def test_output_format_works_with_bedrock_and_azure(): """Test that output_format works with Bedrock and Azure Foundry models.""" config = AnthropicMessagesConfig() diff --git a/tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_reasoning_effort_translation.py b/tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_reasoning_effort_translation.py index 83716b8c8d..54bf0c4ac0 100644 --- a/tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_reasoning_effort_translation.py +++ b/tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_reasoning_effort_translation.py @@ -6,6 +6,9 @@ from litellm.llms.anthropic.common_utils import AnthropicError from litellm.llms.anthropic.experimental_pass_through.messages.transformation import ( AnthropicMessagesConfig, ) +from litellm.llms.bedrock.messages.invoke_transformations.anthropic_claude3_transformation import ( + AmazonAnthropicClaudeMessagesConfig, +) @pytest.mark.parametrize( @@ -102,7 +105,6 @@ def test_invalid_reasoning_effort_raises_400(bad_effort): "model,bad_effort", [ ("claude-opus-4-6", "xhigh"), - ("bedrock/invoke/us.anthropic.claude-opus-4-6-v1", "xhigh"), ("claude-sonnet-4-6", "xhigh"), ], ) @@ -123,6 +125,56 @@ def test_reasoning_effort_unsupported_tier_raises_400_messages(model, bad_effort assert "not supported by this model" in str(exc_info.value) +@pytest.mark.parametrize( + "model,effort,expected_effort", + [ + ("invoke/us.anthropic.claude-opus-4-6-v1", "xhigh", "max"), + ("invoke/us.anthropic.claude-opus-4-6-v1", "max", "max"), + ("invoke/us.anthropic.claude-opus-4-6-v1", "high", "high"), + ("invoke/us.anthropic.claude-opus-4-7", "xhigh", "xhigh"), + ], +) +def test_bedrock_invoke_messages_clamps_effort_to_ceiling( + model, effort, expected_effort +): + """Bedrock Invoke /v1/messages degrades effort to the model's ceiling. + + Claude Code "goal mode" sends ``xhigh``; Opus 4.6 must clamp to ``max`` + instead of raising, while Opus 4.7 (ceiling ``xhigh``) keeps ``xhigh``. + """ + config = AmazonAnthropicClaudeMessagesConfig() + optional_params = {"max_tokens": 1024, "reasoning_effort": effort} + + result = config.transform_anthropic_messages_request( + model=model, + messages=[{"role": "user", "content": "Hello"}], + anthropic_messages_optional_request_params=optional_params, + litellm_params={}, + headers={}, + ) + + assert result["output_config"]["effort"] == expected_effort + assert result["thinking"]["type"] == "adaptive" + + +def test_bedrock_invoke_messages_rejects_xhigh_without_ceiling(): + """Sonnet 4.6 on Bedrock has no effort ceiling, so xhigh is still rejected.""" + config = AmazonAnthropicClaudeMessagesConfig() + optional_params = {"max_tokens": 1024, "reasoning_effort": "xhigh"} + + with pytest.raises(AnthropicError) as exc_info: + config.transform_anthropic_messages_request( + model="invoke/us.anthropic.claude-sonnet-4-6", + messages=[{"role": "user", "content": "Hello"}], + anthropic_messages_optional_request_params=optional_params, + litellm_params={}, + headers={}, + ) + + assert exc_info.value.status_code == 400 + assert "not supported by this model" in str(exc_info.value) + + @pytest.mark.parametrize( "model", [ diff --git a/tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_bedrock_chat_invoke_transformations_anthropic_claude3_transformation.py b/tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_bedrock_chat_invoke_transformations_anthropic_claude3_transformation.py index b2e254901f..4c4c0e17a3 100644 --- a/tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_bedrock_chat_invoke_transformations_anthropic_claude3_transformation.py +++ b/tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_bedrock_chat_invoke_transformations_anthropic_claude3_transformation.py @@ -430,6 +430,61 @@ def test_output_config_forwarded_for_bedrock_chat_invoke_request(): assert result["max_tokens"] == 100 +def test_output_config_format_converted_for_bedrock_chat_invoke_request(): + """Bedrock Invoke chat path consumes ``output_config.format`` before forwarding.""" + config = AmazonAnthropicClaudeConfig() + schema = { + "type": "object", + "properties": {"answer": {"type": "string"}}, + } + + result = config.transform_request( + model="anthropic.claude-opus-4-7", + messages=[{"role": "user", "content": "test"}], + optional_params={ + "max_tokens": 100, + "output_config": { + "effort": "xhigh", + "format": {"type": "json_schema", "schema": schema}, + }, + }, + litellm_params={}, + headers={}, + ) + + assert result.get("output_config") == {"effort": "xhigh"} + last_content = result["messages"][0]["content"] + assert json.loads(last_content[-1]["text"]) == schema + + +@pytest.mark.parametrize( + "model,expected_effort", + [ + ("anthropic.claude-opus-4-5-20251101-v1:0", "high"), + ("anthropic.claude-opus-4-6-v1", "max"), + ("anthropic.claude-opus-4-7", "xhigh"), + ], +) +def test_output_config_effort_normalized_for_bedrock_chat_invoke_request( + model, expected_effort +): + """Bedrock Invoke chat path accepts ``xhigh`` and forwards the provider-safe effort.""" + config = AmazonAnthropicClaudeConfig() + + result = config.transform_request( + model=model, + messages=[{"role": "user", "content": "test"}], + optional_params={ + "max_tokens": 100, + "output_config": {"effort": "xhigh"}, + }, + litellm_params={}, + headers={}, + ) + + assert result.get("output_config") == {"effort": expected_effort} + + def test_bedrock_chat_invoke_checks_output_config_support_with_bedrock_provider(): config = AmazonAnthropicClaudeConfig() messages = [{"role": "user", "content": "test"}] diff --git a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py index 5f2ed3dc00..c8e72b7ac5 100644 --- a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py +++ b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py @@ -318,6 +318,7 @@ def test_reasoning_effort_none_omits_thinking_for_anthropic_converse(model): ("bedrock/converse/us.anthropic.claude-opus-4-7", "high", "high"), ("bedrock/converse/us.anthropic.claude-opus-4-7", "xhigh", "xhigh"), ("bedrock/converse/us.anthropic.claude-opus-4-7", "max", "max"), + ("bedrock/converse/us.anthropic.claude-opus-4-6-v1", "xhigh", "max"), ("bedrock/converse/us.anthropic.claude-opus-4-6-v1", "max", "max"), ("bedrock/converse/us.anthropic.claude-sonnet-4-6", "high", "high"), ("bedrock/converse/us.anthropic.claude-sonnet-4-6", "minimal", "low"), @@ -369,6 +370,132 @@ def test_output_config_effort_forwarded_into_additional_request_fields(model): assert additional.get("output_config") == {"effort": "high"} +def test_output_config_format_translated_to_native_output_config_converse(): + """``output_config.format`` becomes Bedrock ``outputConfig`` and is not forwarded raw.""" + config = AmazonConverseConfig() + schema = { + "type": "object", + "properties": {"answer": {"type": "string"}}, + } + + result = config._transform_request( + model="bedrock/converse/us.anthropic.claude-opus-4-7", + messages=[{"role": "user", "content": "hi"}], + optional_params={ + "maxTokens": 256, + "thinking": {"type": "adaptive"}, + "output_config": { + "effort": "xhigh", + "format": {"type": "json_schema", "schema": schema}, + }, + }, + litellm_params={}, + headers={}, + ) + + additional = result.get("additionalModelRequestFields", {}) + assert additional.get("output_config") == {"effort": "xhigh"} + assert "format" not in additional["output_config"] + assert result["outputConfig"]["textFormat"]["type"] == "json_schema" + parsed_schema = json.loads( + result["outputConfig"]["textFormat"]["structure"]["jsonSchema"]["schema"] + ) + assert parsed_schema == {**schema, "additionalProperties": False} + + +def test_output_config_format_dropped_on_unsupported_converse_model_warns(caplog): + """When Converse model lacks native structured-output support, the silently + dropped ``output_config.format`` must surface as a warning so callers can + diagnose plain-text responses.""" + from unittest.mock import patch + + config = AmazonConverseConfig() + schema = { + "type": "object", + "properties": {"answer": {"type": "string"}}, + } + + with patch.object( + AmazonConverseConfig, + "_supports_native_structured_outputs", + return_value=False, + ): + with caplog.at_level("WARNING"): + result = config._transform_request( + model="bedrock/converse/us.anthropic.claude-3-haiku-20240307-v1:0", + messages=[{"role": "user", "content": "hi"}], + optional_params={ + "maxTokens": 256, + "output_config": { + "format": {"type": "json_schema", "schema": schema}, + }, + }, + litellm_params={}, + headers={}, + ) + + assert "outputConfig" not in result + assert any( + "dropping `output_config.format`" in record.getMessage() + for record in caplog.records + ) + + +def test_output_config_normalized_marker_does_not_leak_into_optional_params(): + """The internal ``_output_config_normalized`` marker set by + ``_handle_reasoning_effort_parameter`` must be consumed during request + preparation so it does not linger on the caller's ``optional_params``.""" + config = AmazonConverseConfig() + + optional_params = config.map_openai_params( + non_default_params={"reasoning_effort": "xhigh"}, + optional_params={}, + model="bedrock/converse/us.anthropic.claude-opus-4-6-v1", + drop_params=False, + ) + assert optional_params.get("_output_config_normalized") is True + + config._transform_request( + model="bedrock/converse/us.anthropic.claude-opus-4-6-v1", + messages=[{"role": "user", "content": "hi"}], + optional_params=optional_params, + litellm_params={}, + headers={}, + ) + + assert "_output_config_normalized" not in optional_params + + +@pytest.mark.parametrize( + "model,expected_effort", + [ + ("bedrock/converse/us.anthropic.claude-opus-4-5-20251101-v1:0", "high"), + ("bedrock/converse/us.anthropic.claude-opus-4-6-v1", "max"), + ("bedrock/converse/us.anthropic.claude-opus-4-7", "xhigh"), + ], +) +def test_output_config_effort_normalized_for_bedrock_converse_opus( + model, expected_effort +): + """Bedrock Converse accepts ``xhigh`` and forwards the provider-safe effort.""" + config = AmazonConverseConfig() + + result = config._transform_request( + model=model, + messages=[{"role": "user", "content": "hi"}], + optional_params={ + "maxTokens": 256, + "thinking": {"type": "adaptive"}, + "output_config": {"effort": "xhigh"}, + }, + litellm_params={}, + headers={}, + ) + + additional = result.get("additionalModelRequestFields", {}) + assert additional.get("output_config") == {"effort": expected_effort} + + @pytest.mark.parametrize( "effort", ["disabled", "invalid", ""], diff --git a/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py b/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py index 2e315a535f..c92a990522 100644 --- a/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py +++ b/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py @@ -767,6 +767,163 @@ def test_bedrock_messages_forwards_output_config_with_output_format(): assert "output_format" not in result +def test_bedrock_messages_converts_output_config_format_to_inline_schema(): + """``output_config.format`` is consumed so Bedrock does not see an unknown nested key.""" + from unittest.mock import patch + + from litellm.types.router import GenericLiteLLMParams + + cfg = AmazonAnthropicClaudeMessagesConfig() + messages = [{"role": "user", "content": [{"type": "text", "text": "Hello"}]}] + schema = { + "type": "object", + "properties": {"answer": {"type": "string"}}, + } + optional_params = { + "max_tokens": 4096, + "output_config": { + "effort": "xhigh", + "format": {"type": "json_schema", "schema": schema}, + }, + } + + with patch( + "litellm.llms.bedrock.messages.invoke_transformations.anthropic_claude3_transformation._supports_factory", + return_value=True, + ): + result = cfg.transform_anthropic_messages_request( + model="anthropic.claude-opus-4-7", + messages=messages, + anthropic_messages_optional_request_params=optional_params, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert result.get("output_config") == {"effort": "xhigh"} + assert "output_format" not in result + last_content = result["messages"][0]["content"] + assert json.loads(last_content[-1]["text"]) == schema + + +@pytest.mark.parametrize( + "model,expected_effort", + [ + ("anthropic.claude-opus-4-5-20251101-v1:0", "high"), + ("anthropic.claude-opus-4-6-v1", "max"), + ("anthropic.claude-opus-4-7", "xhigh"), + ], +) +def test_bedrock_messages_normalizes_output_config_effort_for_opus( + model, expected_effort +): + """Bedrock /v1/messages accepts ``xhigh`` and forwards the provider-safe effort.""" + from unittest.mock import patch + + from litellm.types.router import GenericLiteLLMParams + + cfg = AmazonAnthropicClaudeMessagesConfig() + + with patch( + "litellm.llms.bedrock.messages.invoke_transformations.anthropic_claude3_transformation._supports_factory", + return_value=True, + ): + result = cfg.transform_anthropic_messages_request( + model=model, + messages=[{"role": "user", "content": [{"type": "text", "text": "Hello"}]}], + anthropic_messages_optional_request_params={ + "max_tokens": 4096, + "output_config": {"effort": "xhigh"}, + }, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert result.get("output_config") == {"effort": expected_effort} + + +def test_bedrock_messages_does_not_mutate_callers_messages_when_embedding_schema(): + """Inline-schema embedding must not mutate the caller's ``messages`` list, + message dicts, or content list.""" + from unittest.mock import patch + + from litellm.types.router import GenericLiteLLMParams + + cfg = AmazonAnthropicClaudeMessagesConfig() + caller_content = [{"type": "text", "text": "Hello"}] + caller_message = {"role": "user", "content": caller_content} + caller_messages = [caller_message] + schema = {"type": "object", "properties": {"answer": {"type": "string"}}} + optional_params = { + "max_tokens": 4096, + "output_config": { + "effort": "xhigh", + "format": {"type": "json_schema", "schema": schema}, + }, + } + + with patch( + "litellm.llms.bedrock.messages.invoke_transformations.anthropic_claude3_transformation._supports_factory", + return_value=True, + ): + result = cfg.transform_anthropic_messages_request( + model="anthropic.claude-opus-4-7", + messages=caller_messages, + anthropic_messages_optional_request_params=optional_params, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert caller_messages == [ + {"role": "user", "content": [{"type": "text", "text": "Hello"}]} + ] + assert caller_message == { + "role": "user", + "content": [{"type": "text", "text": "Hello"}], + } + assert caller_content == [{"type": "text", "text": "Hello"}] + last_content = result["messages"][-1]["content"] + assert json.loads(last_content[-1]["text"]) == schema + + +def test_bedrock_messages_does_not_mutate_callers_output_config(): + """`pop_bedrock_invoke_output_config_format` / effort normalization must not + leak into the caller's ``optional_params`` dict.""" + from unittest.mock import patch + + from litellm.types.router import GenericLiteLLMParams + + cfg = AmazonAnthropicClaudeMessagesConfig() + schema = { + "type": "object", + "properties": {"answer": {"type": "string"}}, + } + caller_output_config = { + "effort": "xhigh", + "format": {"type": "json_schema", "schema": schema}, + } + optional_params = { + "max_tokens": 4096, + "output_config": caller_output_config, + } + + with patch( + "litellm.llms.bedrock.messages.invoke_transformations.anthropic_claude3_transformation._supports_factory", + return_value=True, + ): + cfg.transform_anthropic_messages_request( + model="anthropic.claude-opus-4-5-20251101-v1:0", + messages=[{"role": "user", "content": [{"type": "text", "text": "Hello"}]}], + anthropic_messages_optional_request_params=optional_params, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert caller_output_config == { + "effort": "xhigh", + "format": {"type": "json_schema", "schema": schema}, + } + + def test_bedrock_messages_strips_output_config_with_output_format(): """ When both output_config and output_format are present, output_format @@ -1071,9 +1228,7 @@ def test_bedrock_messages_preserves_compact_context_management_and_adds_beta(): messages = [{"role": "user", "content": [{"type": "text", "text": "Hi"}]}] optional_params = { "max_tokens": 4096, - "context_management": { - "edits": [{"type": "compact_20260112"}] - }, + "context_management": {"edits": [{"type": "compact_20260112"}]}, } result = cfg.transform_anthropic_messages_request( @@ -1084,9 +1239,7 @@ def test_bedrock_messages_preserves_compact_context_management_and_adds_beta(): headers={}, ) - assert result.get("context_management") == { - "edits": [{"type": "compact_20260112"}] - } + assert result.get("context_management") == {"edits": [{"type": "compact_20260112"}]} assert "compact-2026-01-12" in result.get("anthropic_beta", []) assert result["max_tokens"] == 4096 @@ -1118,9 +1271,7 @@ def test_bedrock_messages_filters_unsupported_context_management_edits(): headers={}, ) - assert result.get("context_management") == { - "edits": [{"type": "compact_20260112"}] - } + assert result.get("context_management") == {"edits": [{"type": "compact_20260112"}]} assert "compact-2026-01-12" in result.get("anthropic_beta", []) diff --git a/tests/test_litellm/llms/bedrock/test_bedrock_common_utils.py b/tests/test_litellm/llms/bedrock/test_bedrock_common_utils.py index c39fb427a0..6298eeb25e 100644 --- a/tests/test_litellm/llms/bedrock/test_bedrock_common_utils.py +++ b/tests/test_litellm/llms/bedrock/test_bedrock_common_utils.py @@ -1,9 +1,7 @@ -import json import os import sys import pytest -from fastapi.testclient import TestClient sys.path.insert( 0, os.path.abspath("../../../..") @@ -12,7 +10,6 @@ sys.path.insert( from litellm.llms.bedrock.common_utils import BedrockModelInfo - # --------------------------------------------------------------------------- # # get_bedrock_response_stream_shape lazy-load tests # # --------------------------------------------------------------------------- # @@ -24,8 +21,10 @@ def _reset_bedrock_response_stream_shape_cache(): import litellm.llms.bedrock.common_utils as mod mod.get_bedrock_response_stream_shape.cache_clear() + mod._get_local_model_cost_map.cache_clear() yield mod.get_bedrock_response_stream_shape.cache_clear() + mod._get_local_model_cost_map.cache_clear() def test_bedrock_response_stream_shape_lazy_loads_once(): @@ -222,3 +221,45 @@ def test_context_window_suffix_stripped_for_cost_lookup(): get_bedrock_base_model("anthropic.claude-3-5-sonnet-20241022-v2:0:51k") == "anthropic.claude-3-5-sonnet-20241022-v2:0" ) + + +def test_output_config_effort_normalization_uses_model_info_ceiling(monkeypatch): + import litellm.llms.bedrock.common_utils as mod + + calls = [] + + def fake_get_model_info(model, custom_llm_provider=None): + calls.append((model, custom_llm_provider)) + return {"bedrock_output_config_effort_ceiling": "max"} + + monkeypatch.setattr(mod, "_get_model_info", fake_get_model_info) + output_config = {"effort": "xhigh"} + + mod.normalize_bedrock_opus_output_config_effort( + model="custom-bedrock-alias-without-opus-pattern", + output_config=output_config, + ) + + assert output_config == {"effort": "max"} + assert calls == [("custom-bedrock-alias-without-opus-pattern", "bedrock")] + + +@pytest.mark.parametrize( + "model,expected_ceiling", + [ + ("anthropic.claude-opus-4-5-20251101-v1:0", "high"), + ("anthropic.claude-opus-4-6-v1", "max"), + ("anthropic.claude-opus-4-7", "xhigh"), + ("us.anthropic.claude-opus-4-5-20251101-v1:0", "high"), + ("us.anthropic.claude-opus-4-6-v1", "max"), + ("us.anthropic.claude-opus-4-7", "xhigh"), + ], +) +def test_bundled_bedrock_opus_model_info_declares_output_config_effort_ceiling( + model, expected_ceiling +): + from litellm.litellm_core_utils.get_model_cost_map import GetModelCostMap + + model_info = GetModelCostMap.load_local_model_cost_map()[model] + + assert model_info["bedrock_output_config_effort_ceiling"] == expected_ceiling diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index e646c75eda..eaa875531e 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -859,7 +859,11 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "supports_adaptive_thinking": {"type": "boolean"}, "supports_service_tier": {"type": "boolean"}, "supports_preset": {"type": "boolean"}, - "supports_output_config": {"type": "boolean"}, + "supports_output_config": {"type": "boolean"}, + "bedrock_output_config_effort_ceiling": { + "type": "string", + "enum": ["low", "medium", "high", "max", "xhigh"], + }, "tool_use_system_prompt_tokens": {"type": "number"}, "tpm": {"type": "number"}, "provider_specific_entry": {"type": "object"},