feat: add support for claude code goal mode for bedrock opus output config

litellm/llms/anthropic/chat/transformation.py

@@ -1793,7 +1793,10 @@ def update_headers_with_optional_anthropic_beta(
             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
             )

litellm/llms/anthropic/experimental_pass_through/messages/transformation.py

@@ -427,8 +427,13 @@ def _update_headers_with_anthropic_beta(
                     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
             )

litellm/llms/bedrock/chat/converse_transformation.py

@@ -77,6 +77,7 @@
     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
@@ -447,10 +448,16 @@ def _handle_reasoning_effort_parameter(
                             value=reasoning_effort,
                             llm_provider="bedrock_converse",
                         )
+                    output_config = {"effort": mapped_effort}
+                    normalize_bedrock_opus_output_config_effort(
+                        model=model,
+                        output_config=output_config,
+                    )
+                    mapped_effort = output_config["effort"]
                     self._validate_anthropic_adaptive_effort(
                         model=model, effort=mapped_effort
                     )
-                    optional_params["output_config"] = {"effort": mapped_effort}
+                    optional_params["output_config"] = output_config
 
     @staticmethod
     def _validate_anthropic_adaptive_effort(model: str, effort: str) -> None:
@@ -1216,8 +1223,17 @@ def _prepare_request_params(
 
         # 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)
@@ -1227,6 +1243,21 @@ def _prepare_request_params(
         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"),
+            )
 
         # keep supported params in 'inference_params', and set all model-specific params in 'additional_request_params'
         additional_request_params = {
@@ -1272,7 +1303,6 @@ def _prepare_request_params(
         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
@@ -1283,6 +1313,10 @@ def _prepare_request_params(
                         model,
                     )
                 else:
+                    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(

litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude3_transformation.py

@@ -16,8 +16,11 @@
     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
@@ -157,6 +160,13 @@ def _build_bedrock_anthropic_request_base(
             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 +180,20 @@ def _build_bedrock_anthropic_request_base(
 
         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,

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 +60,69 @@ 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.
+    """
+    schema = output_format.get("schema")
+    if not schema:
+        return
+
+    messages = request_body.get("messages", [])
+    if not messages:
+        return
+
+    last_user_message = None
+    for message in reversed(messages):
+        if isinstance(message, dict) and message.get("role") == "user":
+            last_user_message = message
+            break
+
+    if last_user_message is None:
+        return
+
+    content = last_user_message.get("content", [])
+    if isinstance(content, str):
+        content = [{"type": "text", "text": content}]
+        last_user_message["content"] = content
+
+    if isinstance(content, list):
+        content.append({"type": "text", "text": json.dumps(schema)})
+
+
 def remove_custom_field_from_tools(request_body: dict) -> None:
     """
     Remove ``custom`` field from each tool in the request body.
@@ -603,6 +675,62 @@ 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 ("xhigh", "max"):
+        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