diff --git a/app/services/llm_service.py b/app/services/llm_service.py
index eae30ae..01a0b9d 100644
--- a/app/services/llm_service.py
+++ b/app/services/llm_service.py
@@ -101,23 +101,26 @@ class LLMService:
 
     def get_prompt(self, key: str, model_id: str = None, provider: str = None) -> str:
         """
-        WP-25b: Hochpräziser Prompt-Lookup.
-        Hierarchie: Exakte Modell-ID -> Provider-Name -> Globaler Default.
+        WP-25b: Hochpräziser Prompt-Lookup mit detailliertem Trace-Logging.
         """
         data = self.prompts.get(key, "")
         if not isinstance(data, dict):
             return str(data)
 
-        # 1. Spezifischstes Match: Exakte Modell-ID (z.B. 'google/gemini-2.0-flash-exp:free')
+        # 1. Spezifischstes Match: Exakte Modell-ID
         if model_id and model_id in data:
+            logger.info(f"🎯 [PROMPT-TRACE] Level 1 Match: Model-specific ('{model_id}') for key '{key}'")
             return str(data[model_id])
         
-        # 2. Mittlere Ebene: Provider (z.B. 'ollama' oder 'openrouter')
+        # 2. Mittlere Ebene: Provider
         if provider and provider in data:
+            logger.info(f"📡 [PROMPT-TRACE] Level 2 Match: Provider-fallback ('{provider}') for key '{key}'")
             return str(data[provider])
         
-        # 3. Fallback: Bekannte Keys oder Default aus prompts.yaml
-        return str(data.get("default", data.get("gemini", data.get("ollama", ""))))
+        # 3. Globaler Fallback
+        default_val = data.get("default", data.get("gemini", data.get("ollama", "")))
+        logger.info(f"⚓ [PROMPT-TRACE] Level 3 Match: Global Default for key '{key}'")
+        return str(default_val)
 
     async def generate_raw_response(
         self,