Force shorter AI responses — max 1-2 sentences

- Much stronger prompt language: "no more than 2 sentences EVER"
- Added "DO NOT ramble" instruction
- Reduced max_tokens back to 100 as hard limit

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

backend/services/llm.py

@@ -124,7 +124,7 @@ class LLMService:
                         json={
                             "model": self.openrouter_model,
                             "messages": messages,
-                            "max_tokens": 150,
+                            "max_tokens": 100,
                         },
                     )
                     response.raise_for_status()