fix(aw-sync): skip duplicate device_id folders that truncate history on pull

aw-sync/src/sync.rs

@@ -548,6 +548,19 @@ fn sync_one(
         info!("  = Synced {} new events", new_events_count);
     } else {
         info!("  ✓ Already up to date!");
+        // Resume-from-newest is one-way: events older than dest's newest are never
+        // fetched. If a short recent slice was imported first, a later pull of the
+        // complete history reports "up to date" while dest is missing most of it.
+        // Warn loudly so that case is diagnosable (ActivityWatch/aw-server-rust#683).
+        if resume_sync_at.is_some() {
+            let src_count = ds_from.get_event_count(bucket_from.id.as_str())?;
+            if src_count > eventcount_to_new {
+                warn!(
+                    "  ! Source bucket '{}' has {src_count} events but destination '{}' has {eventcount_to_new} after a resume-from-newest pull. Older history in the source was not imported. Delete the destination bucket and re-pull to recover.",
+                    bucket_from.id, bucket_to.id
+                );
+            }
+        }
     }
 
     Ok(())

aw-sync/src/sync_wrapper.rs

@@ -1,20 +1,33 @@
 use std::error::Error;
 use std::fs;
+use std::path::Path;
 
 use crate::sync::{sync_run, SyncMode, SyncSpec};
 use aw_client_rust::blocking::AwClient;
 
 pub fn pull_all(client: &AwClient) -> Result<(), Box<dyn Error>> {
-    let hostnames = crate::util::get_remotes()?;
-    for host in hostnames {
-        pull(&host, client)?
+    let sync_root = crate::dirs::get_sync_dir().map_err(|_| "Could not get sync dir")?;
+    let dbs = crate::util::list_remote_dbs(&sync_root)?;
+    let selected = crate::util::select_remote_dbs_by_device_id(dbs);
+    if selected.is_empty() {
+        info!("No remote databases found in {:?}", sync_root);
+        return Ok(());
+    }
+    info!(
+        "Pulling {} remote database(s): {:?}",
+        selected.len(),
+        selected
+            .iter()
+            .map(|d| d.path.display().to_string())
+            .collect::<Vec<_>>()
+    );
+    for remote in selected {
+        pull_db(client, &remote.hostname, &remote.path)?;
     }
     Ok(())
 }
 
 pub fn pull(host: &str, client: &AwClient) -> Result<(), Box<dyn Error>> {
-    client.wait_for_start()?;
-
     // Path to the sync folder
     // Sync folder is structured ./{hostname}/{device_id}/test.db
     let sync_root_dir = crate::dirs::get_sync_dir().map_err(|_| "Could not get sync dir")?;
@@ -45,14 +58,20 @@ pub fn pull(host: &str, client: &AwClient) -> Result<(), Box<dyn Error>> {
         .max_by_key(|entry| entry.metadata().map(|m| m.len()).unwrap_or(0))
         .ok_or_else(|| format!("No db found in sync folder {:?}", sync_dir))?;
 
+    pull_db(client, host, &db.path())
+}
+
+fn pull_db(client: &AwClient, host: &str, db_path: &Path) -> Result<(), Box<dyn Error>> {
+    client.wait_for_start()?;
+    let sync_root_dir = crate::dirs::get_sync_dir().map_err(|_| "Could not get sync dir")?;
+    let sync_dir = sync_root_dir.join(host);
     let sync_spec = SyncSpec {
-        path: sync_dir.clone(),
-        path_db: Some(db.path().clone()),
+        path: sync_dir,
+        path_db: Some(db_path.to_path_buf()),
         buckets: None, // Sync all buckets by default
         start: None,
     };
     sync_run(client, &sync_spec, SyncMode::Pull)?;
-
     Ok(())
 }