perf: stream_files_in_subtree — replace Vec<File> with async Stream

Replace list_files_in_subtree (fetch_all → Vec) with stream_files_in_subtree
that returns a Pin<Box<dyn Stream<Item = Result<File/FileDto>>>> backed by a
PostgreSQL cursor via sqlx::fetch().

Changes:
- FileReadPort::stream_files_in_subtree() returns streaming cursor (no default)
- FileRetrievalUseCase::stream_files_in_subtree() maps File→FileDto on the fly
- FileBlobReadRepository: async_stream::try_stream! + sqlx::fetch() cursor
- batch_operations: consume stream into HashMap incrementally
- zip_service: consume stream into HashMap incrementally
- All stubs/mocks updated (return empty stream)

Eliminates:
- Double allocation: Vec<(9-tuple)> + Vec<File> materialized simultaneously
- Unbounded RAM proportional to subtree size (was ~500 bytes × N files)
- Latency: callers blocked until last row fetched from PG

RAM is now O(folders) for the HashMap, not O(files).

src/application/services/file_retrieval_service.rs

@@ -1,6 +1,7 @@
 use async_trait::async_trait;
 use bytes::{Bytes, BytesMut};
 use futures::{Stream, StreamExt};
+use std::pin::Pin;
 use std::sync::Arc;
 
 use crate::application::dtos::file_dto::FileDto;
@@ -308,9 +309,13 @@ impl FileRetrievalUseCase for FileRetrievalService {
         self.file_read.get_file_range_stream(id, start, end).await
     }
 
-    async fn list_files_in_subtree(&self, folder_id: &str) -> Result<Vec<FileDto>, DomainError> {
-        let files = self.file_read.list_files_in_subtree(folder_id).await?;
-        Ok(files.into_iter().map(FileDto::from).collect())
+    async fn stream_files_in_subtree(
+        &self,
+        folder_id: &str,
+    ) -> Result<Pin<Box<dyn Stream<Item = Result<FileDto, DomainError>> + Send>>, DomainError> {
+        let inner = self.file_read.stream_files_in_subtree(folder_id).await?;
+        let mapped = inner.map(|r| r.map(FileDto::from));
+        Ok(Box::pin(mapped))
     }
 
     async fn list_files_batch(