async_run_agentic_loop

litellm/integrations/websearch_interception/handler.py

@@ -120,6 +120,8 @@ class WebSearchInterceptionLogger(CustomLogger):
         verbose_logger.debug(f"WebSearchInterception: Response type: {type(response)}")
 
         # Check if provider should be intercepted
+        # Note: custom_llm_provider is already normalized by get_llm_provider()
+        # (e.g., "bedrock/invoke/..." -> "bedrock")
         if custom_llm_provider not in self.enabled_providers:
             verbose_logger.debug(
                 f"WebSearchInterception: Skipping provider {custom_llm_provider} (not in enabled list: {self.enabled_providers})"
@@ -183,6 +185,7 @@ class WebSearchInterceptionLogger(CustomLogger):
             messages=messages,
             tool_calls=tool_calls,
             anthropic_messages_optional_request_params=anthropic_messages_optional_request_params,
+            logging_obj=logging_obj,
             stream=stream,
             kwargs=kwargs,
         )
@@ -193,6 +196,7 @@ class WebSearchInterceptionLogger(CustomLogger):
         messages: List[Dict],
         tool_calls: List[Dict],
         anthropic_messages_optional_request_params: Dict,
+        logging_obj: Any,
         stream: bool,
         kwargs: Dict,
     ) -> Any:
@@ -278,10 +282,20 @@ class WebSearchInterceptionLogger(CustomLogger):
                 if k != 'max_tokens'
             }
 
+            # Get model from logging_obj.model_call_details["agentic_loop_params"]
+            # This preserves the full model name with provider prefix (e.g., "bedrock/invoke/...")
+            full_model_name = model
+            if logging_obj is not None:
+                agentic_params = logging_obj.model_call_details.get("agentic_loop_params", {})
+                full_model_name = agentic_params.get("model", model)
+            verbose_logger.debug(
+                f"WebSearchInterception: Using model name: {full_model_name}"
+            )
+            
             final_response = await anthropic_messages.acreate(
                 max_tokens=max_tokens,
                 messages=follow_up_messages,
-                model=model,
+                model=full_model_name,
                 **optional_params_without_max_tokens,
                 **kwargs,
             )

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

@@ -177,6 +177,10 @@ def anthropic_messages_handler(
     # Use provided client or create a new one
     litellm_logging_obj: LiteLLMLoggingObj = kwargs.get("litellm_logging_obj")  # type: ignore
 
+    # Store original model name before get_llm_provider strips the provider prefix
+    # This is needed by agentic hooks (e.g., websearch_interception) to make follow-up requests
+    original_model = model
+
     litellm_params = GenericLiteLLMParams(
         **kwargs,
         api_key=api_key,
@@ -194,6 +198,14 @@ def anthropic_messages_handler(
         api_base=litellm_params.api_base,
         api_key=litellm_params.api_key,
     )
+    
+    # Store agentic loop params in logging object for agentic hooks
+    # This provides original request context needed for follow-up calls
+    if litellm_logging_obj is not None:
+        litellm_logging_obj.model_call_details["agentic_loop_params"] = {
+            "model": original_model,
+            "custom_llm_provider": custom_llm_provider,
+        }
 
     if litellm_params.mock_response and isinstance(litellm_params.mock_response, str):
 

litellm/llms/custom_httpx/llm_http_handler.py

@@ -4395,6 +4395,9 @@ class BaseLLMHTTPHandler:
 
                     if should_run:
                         # Second: Execute agentic loop
+                        # Add custom_llm_provider to kwargs so the agentic loop can reconstruct the full model name
+                        kwargs_with_provider = kwargs.copy() if kwargs else {}
+                        kwargs_with_provider["custom_llm_provider"] = custom_llm_provider
                         agentic_response = await callback.async_run_agentic_loop(
                             tools=tool_calls,
                             model=model,
@@ -4404,7 +4407,7 @@ class BaseLLMHTTPHandler:
                             anthropic_messages_optional_request_params=anthropic_messages_optional_request_params,
                             logging_obj=logging_obj,
                             stream=stream,
-                            kwargs=kwargs,
+                            kwargs=kwargs_with_provider,
                         )
                         # First hook that runs agentic loop wins
                         return agentic_response

litellm/types/utils.py

@@ -109,6 +109,20 @@ class SearchContextCostPerQuery(TypedDict, total=False):
     search_context_size_high: float
 
 
+class AgenticLoopParams(TypedDict, total=False):
+    """
+    Parameters passed to agentic loop hooks (e.g., WebSearch interception).
+    
+    Stored in logging_obj.model_call_details["agentic_loop_params"] to provide
+    agentic hooks with the original request context needed for follow-up calls.
+    """
+    model: str
+    """The model string with provider prefix (e.g., 'bedrock/invoke/...')"""
+    
+    custom_llm_provider: str
+    """The LLM provider name (e.g., 'bedrock', 'anthropic')"""
+
+
 class ModelInfoBase(ProviderSpecificModelInfo, total=False):
     key: Required[str]  # the key in litellm.model_cost which is returned