perf: fix issues #1,#2,#3,#13 from performance audit

- #1  image_transcode: dedicated rayon pool + moka cache (no tokio blocking)
- #2  ltree materialized paths: eliminate N+1 folder/file queries
- #3  compute_content_hash: read blob_hash column instead of loading file into RAM
- #13 event delegation + DocumentFragment: ~15 delegated listeners replace ~19k per-item listeners

Backend: 82/82 tests pass, cargo check clean.
Frontend: ui.js and app.js syntax-validated via Node.js.

src/application/ports/dedup_ports.rs

@@ -159,9 +159,6 @@ pub trait DedupPort: Send + Sync + 'static {
     /// Returns `true` if the blob was deleted (ref_count reached 0).
     async fn remove_reference(&self, hash: &str) -> Result<bool, DomainError>;
 
-    /// Calculate SHA-256 hash of in-memory content.
-    fn hash_bytes(&self, content: &[u8]) -> String;
-
     /// Calculate SHA-256 hash of a file (streaming).
     async fn hash_file(&self, path: &Path) -> Result<String, DomainError>;
 

src/application/ports/storage_ports.rs

@@ -57,6 +57,12 @@ pub trait FileReadPort: Send + Sync + 'static {
     /// Gets the parent folder ID from a path (WebDAV).
     async fn get_parent_folder_id(&self, path: &str) -> Result<String, DomainError>;
 
+    /// Gets the content-addressable blob hash for a file (O(1) DB lookup).
+    ///
+    /// Returns the SHA-256 hash stored in `storage.files.blob_hash`.
+    /// Used for dedup reference tracking without loading file content.
+    async fn get_blob_hash(&self, file_id: &str) -> Result<String, DomainError>;
+
     /// Find a file by its logical path (folder_name/.../file_name).
     ///
     /// The default implementation falls back to `list_files(None)` + linear