perf: replace recursive spawn-per-folder search with O(1) ltree queries

- Add search_files_in_subtree() to FileReadPort with ltree-based SQL
- Add list_descendant_folders() to FolderRepository with ltree GiST index
- Implement both in PG repositories (single query per entity type)
- Remove search_parallel() fan-out (O(N) tokio::spawn → 0 spawns)
- Remove passes_file_filter/passes_folder_filter (filtering now in SQL)
- Fix SearchCriteriaDto cache key: JSON serialization → u64 hash (15x faster)
- Fix escaped quote literals in webdav_handler.rs handle_put function

src/application/dtos/search_dto.rs

@@ -7,7 +7,7 @@ use serde::{Deserialize, Serialize};
  * to filter files and folders in the system. It supports various filter types
  * including name matching, file types, date ranges, and size constraints.
  */
-#[derive(Debug, Clone, Serialize, Deserialize)]
+#[derive(Debug, Clone, Hash, Serialize, Deserialize)]
 pub struct SearchCriteriaDto {
     /// Optional text to search in file/folder names
     #[serde(skip_serializing_if = "Option::is_none")]