refactor: remove dead OptimizedFileContent::Mmap variant

OptimizedFileContent::Mmap was constructed nowhere — the documented "Tier 2:
memory-mapped I/O (10-100 MB)" path was never wired, so optimized_inner only
ever returns Bytes (<10 MB) or Stream (>=10 MB). The variant survived only as
an enum case plus two dead match arms in the file and share download handlers.

Remove the variant and its arms, and fix the now-misleading retrieval-service
tier docs (everything >=10 MB streams via CDC chunk reassembly with the
backend read-ahead; there is no mmap tier). Behaviour is unchanged — the
deleted arms were unreachable.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JG5yYZ9s868mJwqT2Qz7ez

src/application/ports/file_ports.rs

@@ -93,7 +93,7 @@ pub trait FileUploadUseCase: Send + Sync + 'static {
 /// Optimized file content returned by the retrieval service.
 ///
 /// The handler only needs to map each variant to the appropriate HTTP
-/// response; all caching / transcoding / mmap decisions happen in the
+/// response; all caching / transcoding decisions happen in the
 /// application layer.
 pub enum OptimizedFileContent {
     /// Small-file content (possibly transcoded / compressed) already in RAM.
@@ -102,9 +102,7 @@ pub enum OptimizedFileContent {
         mime_type: Arc<str>,
         was_transcoded: bool,
     },
-    /// Memory-mapped file (10–100 MB).
-    Mmap(Bytes),
-    /// Streaming download for very large files (≥100 MB).
+    /// Streaming download for everything above the in-RAM cache threshold.
     Stream(Pin<Box<dyn Stream<Item = Result<Bytes, std::io::Error>> + Send>>),
 }
 

src/application/services/file_retrieval_service.rs

@@ -26,8 +26,8 @@ const CACHE_THRESHOLD: u64 = 10 * 1024 * 1024;
 /// Implements a multi-tier download strategy:
 /// - Tier 0: Write-behind cache (just-uploaded files still in RAM)
 /// - Tier 1: Hot cache + optional WebP transcoding (<10 MB)
-/// - Tier 2: Memory-mapped I/O (10–100 MB)
-/// - Tier 3: Streaming (≥100 MB)
+/// - Tier 2: Streaming for everything ≥10 MB — CDC chunk reassembly with the
+///   backend's read-ahead (`read_prefetch`); no whole-file buffering.
 pub struct FileRetrievalService {
     file_read: Arc<FileBlobReadRepository>,
     content_cache: Option<Arc<FileContentCache>>,