fix: Update default chat model to grok-4-1-fast-reasoning and enhance logging for LLM responses

services/langchain_xai_service.py

@@ -17,7 +17,7 @@ class LangChainXAIService:
     
     Usage:
         service = LangChainXAIService(ctx)
-        model = service.get_chat_model(model="grok-2-latest")
+        model = service.get_chat_model(model="grok-4-1-fast-reasoning")
         model_with_tools = service.bind_file_search(model, collection_id)
         result = await service.invoke_chat(model_with_tools, messages)
     """
@@ -46,7 +46,7 @@ class LangChainXAIService:
     
     def get_chat_model(
         self,
-        model: str = "grok-2-latest",
+        model: str = "grok-4-1-fast-reasoning",
         temperature: float = 0.7,
         max_tokens: Optional[int] = None
     ):
@@ -54,7 +54,7 @@ class LangChainXAIService:
         Initialisiert ChatXAI Model.
         
         Args:
-            model: Model name (default: grok-2-latest)
+            model: Model name (default: grok-4-1-fast-reasoning)
             temperature: Sampling temperature 0.0-1.0
             max_tokens: Optional max tokens for response
             

steps/ai/chat_completions_api_step.py

@@ -317,6 +317,18 @@ async def invoke_and_format_response(
             "total_tokens": getattr(u, 'input_tokens', 0) + getattr(u, 'output_tokens', 0)
         }
     
+    # Log complete LLM response
+    ctx.logger.info("=" * 80)
+    ctx.logger.info("📤 LLM RESPONSE")
+    ctx.logger.info("-" * 80)
+    ctx.logger.info(f"Model: {model_name}")
+    ctx.logger.info(f"Completion ID: {completion_id}")
+    ctx.logger.info(f"Usage: {usage['prompt_tokens']} prompt + {usage['completion_tokens']} completion = {usage['total_tokens']} total tokens")
+    ctx.logger.info("-" * 80)
+    ctx.logger.info("Content:")
+    ctx.logger.info(content)
+    ctx.logger.info("=" * 80)
+    
     # Format OpenAI-compatible response
     response_body = {
         'id': completion_id,