chore: bump xet-core to c805591 (cas_object->xorb_object, Ulid tracking IDs)

- Update all xet-core crates from e85cf9d to c805591
- Rename cas_object crate to xorb_object (SerializedCasObject -> SerializedXorbObject)
- Add Ulid tracking ID parameter to download_stream_from_offset, download_file,
  start_clean, and upload_files calls

Author: XciD

Cargo.lock

@@ -5,15 +5,15 @@ edition = "2024"
 
 [dependencies]
 # xet-core crates
-data = { git = "https://github.com/huggingface/xet-core.git", rev = "e85cf9d" }
-mdb_shard = { git = "https://github.com/huggingface/xet-core.git", rev = "e85cf9d" }
-utils = { git = "https://github.com/huggingface/xet-core.git", rev = "e85cf9d" }
-hub_client = { git = "https://github.com/huggingface/xet-core.git", rev = "e85cf9d" }
-xet_runtime = { git = "https://github.com/huggingface/xet-core.git", rev = "e85cf9d" }
-cas_client = { git = "https://github.com/huggingface/xet-core.git", rev = "e85cf9d" }
-cas_types = { git = "https://github.com/huggingface/xet-core.git", rev = "e85cf9d" }
-cas_object = { git = "https://github.com/huggingface/xet-core.git", rev = "e85cf9d" }
-merklehash = { git = "https://github.com/huggingface/xet-core.git", rev = "e85cf9d" }
+data = { git = "https://github.com/huggingface/xet-core.git", rev = "c805591" }
+mdb_shard = { git = "https://github.com/huggingface/xet-core.git", rev = "c805591" }
+utils = { git = "https://github.com/huggingface/xet-core.git", rev = "c805591" }
+hub_client = { git = "https://github.com/huggingface/xet-core.git", rev = "c805591" }
+xet_runtime = { git = "https://github.com/huggingface/xet-core.git", rev = "c805591" }
+cas_client = { git = "https://github.com/huggingface/xet-core.git", rev = "c805591" }
+cas_types = { git = "https://github.com/huggingface/xet-core.git", rev = "c805591" }
+xorb_object = { git = "https://github.com/huggingface/xet-core.git", rev = "c805591" }
+merklehash = { git = "https://github.com/huggingface/xet-core.git", rev = "c805591" }
 
 # External crates
 fuser = "0.17"
@@ -30,6 +30,7 @@ async-trait = "0.1"
 bytes = "1"
 chrono = "0.4"
 uuid = { version = "1", features = ["v4"] }
+ulid = "1"
 nfsserve = "0.10"
 
 [[bin]]

Cargo.toml

@@ -4,7 +4,7 @@ use std::sync::{Arc, Mutex};
 use bytes::Bytes;
 use cas_client::adaptive_concurrency::ConnectionPermit;
 use cas_client::{Client, ProgressCallback, URLProvider};
-use cas_object::SerializedCasObject;
+use xorb_object::SerializedXorbObject;
 use cas_types::{BatchQueryReconstructionResponse, FileRange, QueryReconstructionResponse};
 use mdb_shard::file_structs::MDBFileInfo;
 use merklehash::MerkleHash;
@@ -103,7 +103,7 @@ impl Client for CachedXetClient {
     async fn upload_xorb(
         &self,
         prefix: &str,
-        serialized_cas_object: SerializedCasObject,
+        serialized_cas_object: SerializedXorbObject,
         progress_callback: Option<ProgressCallback>,
         upload_permit: ConnectionPermit,
     ) -> Result<u64> {
@@ -244,7 +244,7 @@ mod tests {
         async fn upload_xorb(
             &self,
             _prefix: &str,
-            _serialized_cas_object: SerializedCasObject,
+            _serialized_cas_object: SerializedXorbObject,
             _progress_callback: Option<ProgressCallback>,
             _upload_permit: ConnectionPermit,
         ) -> Result<u64> {

src/cached_xet_client.rs

@@ -4,6 +4,7 @@ use std::sync::Arc;
 use bytes::Bytes;
 use data::configurations::TranslatorConfig;
 use data::{FileDownloadSession, FileUploadSession, SingleFileCleaner, XetFileInfo};
+use ulid::Ulid;
 
 use crate::error::{Error, Result};
 
@@ -50,7 +51,7 @@ impl XetSessions {
     /// Start a streaming download from a byte offset (sync, returns an iterator-like stream).
     pub fn download_stream(&self, file_info: &XetFileInfo, offset: u64) -> Result<data::DownloadStream> {
         self.session
-            .download_stream_from_offset(file_info, offset, None)
+            .download_stream_from_offset(file_info, offset, Ulid::new())
             .map_err(|e| Error::Xet(e.to_string()))
     }
 }
@@ -66,7 +67,7 @@ impl XetOps for XetSessions {
             .await
             .map_err(|e| Error::Xet(e.to_string()))?;
         let cleaner = session
-            .start_clean(None, None, Some(mdb_shard::Sha256::default()))
+            .start_clean(None, 0, Some(mdb_shard::Sha256::default()), Ulid::new())
             .await;
         Ok(Box::new(StreamingWriter {
             cleaner,
@@ -78,7 +79,7 @@ impl XetOps for XetSessions {
     async fn download_to_file(&self, xet_hash: &str, file_size: u64, dest: &Path) -> Result<()> {
         let file_info = XetFileInfo::new(xet_hash.to_string(), file_size);
         self.session
-            .download_file(&file_info, dest, None)
+            .download_file(&file_info, dest, Ulid::new())
             .await
             .map_err(|e| Error::Xet(e.to_string()))?;
         Ok(())
@@ -96,7 +97,7 @@ impl XetOps for XetSessions {
 
         let files: Vec<_> = paths
             .iter()
-            .map(|p| (p.to_path_buf(), Some(mdb_shard::Sha256::default())))
+            .map(|p| (p.to_path_buf(), Some(mdb_shard::Sha256::default()), Ulid::new()))
             .collect();
 
         let results = upload_session

src/xet.rs

@@ -163,7 +163,7 @@ pub async fn upload_file(
         .await
         .expect("FileUploadSession::new failed");
 
-    let files = vec![(staged_path.to_path_buf(), None::<mdb_shard::Sha256>)];
+    let files = vec![(staged_path.to_path_buf(), None::<mdb_shard::Sha256>, ulid::Ulid::new())];
     let mut results = upload_session.upload_files(files).await.expect("upload_files failed");
 
     let file_info = results.pop().expect("upload returned no file info");