feat: expose LLM error reason in /api/ask response and UI

- Add llm_error field to AskResponse so users know why AI summarisation was skipped
- Show orange warning banner in frontend when LLM is not configured or call fails
- Update AskEndpoint tests to assert llm_error presence

backend/routes/ask.py

@@ -272,16 +272,21 @@ async def ask_question(body: AskRequest, user: dict = Depends(require_auth)):
             events=[],
             query_info={"entity": entity, "start": start, "end": end, "event_count": 0},
             llm_used=False,
+            llm_error="LLM not used — no events found." if not LLM_API_KEY else None,
         )
 
     # Try LLM summarisation
     answer = ""
     llm_used = False
-    if LLM_API_KEY:
+    llm_error = None
+    if not LLM_API_KEY:
+        llm_error = "LLM_API_KEY is not configured. Set it in your .env to enable AI narrative summarisation."
+    else:
         try:
             answer = await _call_llm(question, events)
             llm_used = True
         except Exception as exc:
+            llm_error = f"LLM call failed: {exc}"
             logger.warning("LLM call failed, falling back to structured summary", error=str(exc))
 
     # Fallback: structured summary if LLM unavailable or failed
@@ -315,4 +320,5 @@ async def ask_question(body: AskRequest, user: dict = Depends(require_auth)):
             "mongo_query": json.dumps(query, default=str),
         },
         llm_used=llm_used,
+        llm_error=llm_error,
     )