perf: findings 6.1, 6.2, 2.6 — async Argon2, moka cache, full streaming migration

- 6.1: PasswordHasherPort now async_trait with spawn_blocking for Argon2
- 6.2: OIDC pending maps migrated from std::sync::Mutex to moka::sync::Cache with TTL
- 2.6: All file download paths migrated to 64KB streaming (get_file_stream / read_blob_stream)
  - WOPI, dedup, batch ZIP, file_retrieval_service consumers migrated
  - WebDAV COPY uses zero-copy dedup (copy_file)
  - Removed dead code: get_file_content, get_file_mmap, read_blob, read_blob_bytes
    from traits, impls, stubs, and mocks (18 files touched)

src/application/ports/dedup_ports.rs

@@ -122,15 +122,7 @@ pub trait DedupPort: Send + Sync + 'static {
     /// Get metadata for a blob.
     async fn get_blob_metadata(&self, hash: &str) -> Option<BlobMetadataDto>;
 
-    /// Read blob content as raw bytes.
-    async fn read_blob(&self, hash: &str) -> Result<Vec<u8>, DomainError>;
-
-    /// Read blob content as `Bytes`.
-    async fn read_blob_bytes(&self, hash: &str) -> Result<Bytes, DomainError>;
-
     /// Stream blob content in chunks (64 KB default) — constant memory usage.
-    ///
-    /// Unlike `read_blob()`, this never loads the entire file into RAM.
     async fn read_blob_stream(
         &self,
         hash: &str,