fix(translate): add EXPLORE logging for LLM JSON parse failures

Preview + executor now log the raw LLM response (first 1000 chars)
when JSON parsing fails, enabling debugging of malformed LLM output.

Previously ValueErrors from JSON parse failures were silently returned
as 400 without any diagnostic data in logs.

backend/src/api/routes/translate/_preview_routes.py

@@ -51,6 +51,7 @@ async def preview_translation(
         )
         return result
     except ValueError as e:
+        logger.explore("preview_translation validation failed", extra={"src": "translate_routes", "error": str(e)})
         raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
     except Exception as e:
         logger.explore("preview_translation failed", extra={"src": "translate_routes", "error": str(e)})