crates/archivr-core/src/archive.rs

@@ -28,8 +28,6 @@ pub struct EntrySummary {
     pub parent_entry_uid: Option<String>,
     /// True if a `favicon` artifact exists for this entry.
     pub has_favicon: bool,
-    /// Bytes of blobs already on disk from an earlier entry (precomputed at capture time).
-    pub cached_bytes: i64,
 }
 
 #[derive(Debug, Clone, PartialEq, Eq, serde::Serialize)]
@@ -208,8 +206,7 @@ pub fn list_root_entries(conn: &rusqlite::Connection, caller_bits: u32) -> Resul
             COUNT(ea.id) AS artifact_count,
             COALESCE(SUM(b.byte_size), 0) AS total_artifact_bytes,
             NULL AS parent_entry_uid,
-            EXISTS(SELECT 1 FROM entry_artifacts fav WHERE fav.entry_id = e.id AND fav.artifact_role = 'favicon') AS has_favicon,
+            EXISTS(SELECT 1 FROM entry_artifacts fav WHERE fav.entry_id = e.id AND fav.artifact_role = 'favicon') AS has_favicon
-            e.cached_bytes
          FROM archived_entries e
          JOIN source_identities si ON si.id = e.source_identity_id
          LEFT JOIN entry_artifacts ea ON ea.entry_id = e.id
@@ -241,7 +238,6 @@ pub fn list_root_entries(conn: &rusqlite::Connection, caller_bits: u32) -> Resul
                 total_artifact_bytes: row.get(8)?,
                 parent_entry_uid: row.get(9)?,
                 has_favicon: row.get::<_, i64>(10)? != 0,
-                cached_bytes: row.get(11)?,
             })
         })?
         .collect::<rusqlite::Result<Vec<_>>>()?;
@@ -429,7 +425,6 @@ pub fn list_entries_for_collection(
                 total_artifact_bytes: row.get(8)?,
                 parent_entry_uid: row.get(9)?,
                 has_favicon: row.get::<_, i64>(10)? != 0,
-                cached_bytes: row.get(11)?,
             })
         })?
         .collect::<rusqlite::Result<Vec<_>>>()?;
@@ -544,8 +539,7 @@ const ENTRY_SELECT_COLS: &str =
     e.visibility, si.canonical_url, COUNT(ea.id) AS artifact_count, \
     COALESCE(SUM(b.byte_size), 0) AS total_artifact_bytes, \
     parent.entry_uid AS parent_entry_uid, \
-    EXISTS(SELECT 1 FROM entry_artifacts fav WHERE fav.entry_id = e.id AND fav.artifact_role = 'favicon') AS has_favicon, \
+    EXISTS(SELECT 1 FROM entry_artifacts fav WHERE fav.entry_id = e.id AND fav.artifact_role = 'favicon') AS has_favicon";
-    e.cached_bytes";
 
 const ENTRY_FROM_JOINS: &str =
     "FROM archived_entries e \
@@ -655,7 +649,6 @@ pub fn search_entries(
                 total_artifact_bytes: row.get(8)?,
                 parent_entry_uid: row.get(9)?,
                 has_favicon: row.get::<_, i64>(10)? != 0,
-                cached_bytes: row.get(11)?,
             })
         })?
         .collect::<rusqlite::Result<Vec<_>>>()?;
@@ -817,8 +810,7 @@ pub fn entries_for_tag(
                 e.visibility, si.canonical_url, COUNT(ea.id) AS artifact_count,
                 COALESCE(SUM(b.byte_size), 0) AS total_artifact_bytes,
                 parent.entry_uid AS parent_entry_uid,
-                EXISTS(SELECT 1 FROM entry_artifacts fav WHERE fav.entry_id = e.id AND fav.artifact_role = 'favicon') AS has_favicon,
+                EXISTS(SELECT 1 FROM entry_artifacts fav WHERE fav.entry_id = e.id AND fav.artifact_role = 'favicon') AS has_favicon
-                e.cached_bytes
          FROM archived_entries e
          JOIN source_identities si ON si.id = e.source_identity_id
          LEFT JOIN entry_artifacts ea ON ea.entry_id = e.id
@@ -843,7 +835,6 @@ pub fn entries_for_tag(
                 total_artifact_bytes: row.get(8)?,
                 parent_entry_uid: row.get(9)?,
                 has_favicon: row.get::<_, i64>(10)? != 0,
-                cached_bytes: row.get(11)?,
             })
         })?
         .collect::<rusqlite::Result<Vec<_>>>()?;

crates/archivr-core/src/capture.rs

@@ -751,7 +751,7 @@ pub fn perform_capture(
                     let _ = fs::remove_dir_all(store_path.join("temp").join(&timestamp));
                 }
 
-                let entry = record_media_entry(
+                record_media_entry(
                     &conn,
                     store_path,
                     user_id,
@@ -765,7 +765,6 @@ pub fn perform_capture(
                     byte_size,
                     title_hint,
                 )?;
-                database::refresh_entry_cached_bytes(&conn, entry.id)?;
                 database::finish_archive_run(&conn, run.id)?;
                 return Ok(CaptureResult {
                     run_uid: run.run_uid.clone(),
@@ -905,9 +904,6 @@ pub fn perform_capture(
                     }
                 }
 
-                // 7. Store how many bytes this entry gets "for free" from earlier entries.
-                database::refresh_entry_cached_bytes(&conn, entry.id)?;
-
                 database::finish_archive_run(&conn, run.id)?;
                 return Ok(CaptureResult {
                     run_uid: run.run_uid.clone(),
@@ -946,7 +942,7 @@ pub fn perform_capture(
             &timestamp,
         ) {
             Ok(_) => {
-                let tweet_entry = record_tweet_entry(
+                record_tweet_entry(
                     &conn,
                     store_path,
                     user_id,
@@ -956,7 +952,6 @@ pub fn perform_capture(
                     source,
                     &tweet_id,
                 )?;
-                database::refresh_entry_cached_bytes(&conn, tweet_entry.id)?;
                 database::finish_archive_run(&conn, run.id)?;
                 return Ok(CaptureResult {
                     run_uid: run.run_uid.clone(),
@@ -1047,7 +1042,7 @@ pub fn perform_capture(
         let _ = fs::remove_dir_all(store_path.join("temp").join(&timestamp));
     }
 
-    let media_entry = record_media_entry(
+    record_media_entry(
         &conn,
         store_path,
         user_id,
@@ -1061,7 +1056,6 @@ pub fn perform_capture(
         byte_size,
         None,  // title — populated in a later task
     )?;
-    database::refresh_entry_cached_bytes(&conn, media_entry.id)?;
     database::finish_archive_run(&conn, run.id)?;
 
     Ok(CaptureResult {

crates/archivr-core/src/database.rs

@@ -251,8 +251,7 @@ pub fn initialize_schema(conn: &Connection) -> Result<()> {
             structured_root_relpath TEXT NOT NULL,
             representation_kind TEXT NOT NULL,
             source_metadata_json TEXT NOT NULL DEFAULT '{}',
-            display_metadata_json TEXT,
+            display_metadata_json TEXT
-            cached_bytes INTEGER NOT NULL DEFAULT 0
         );
 
         CREATE TABLE IF NOT EXISTS blobs (
@@ -351,38 +350,6 @@ pub fn initialize_schema(conn: &Connection) -> Result<()> {
         FROM archived_entries ae;
         "#,
     )?;
-
-    // Migration: add cached_bytes column to existing databases.
-    // New databases already have it from the DDL above; the column check is
-    // the idiomatic SQLite way to run a migration exactly once.
-    let column_exists: bool = conn.query_row(
-        "SELECT COUNT(*) FROM pragma_table_info('archived_entries') WHERE name = 'cached_bytes'",
-        [],
-        |row| row.get::<_, i64>(0),
-    )? > 0;
-    if !column_exists {
-        conn.execute_batch(
-            "ALTER TABLE archived_entries ADD COLUMN cached_bytes INTEGER NOT NULL DEFAULT 0;
-             UPDATE archived_entries
-             SET cached_bytes = (
-                 SELECT COALESCE(SUM(b.byte_size), 0)
-                 FROM entry_artifacts ea
-                 JOIN blobs b ON b.id = ea.blob_id
-                 WHERE ea.entry_id = archived_entries.id
-                   AND ea.blob_id IS NOT NULL
-                   AND EXISTS (
-                       SELECT 1
-                       FROM entry_artifacts ea2
-                       JOIN archived_entries e2 ON e2.id = ea2.entry_id
-                       WHERE ea2.blob_id = ea.blob_id
-                         AND (e2.archived_at < archived_entries.archived_at
-                              OR (e2.archived_at = archived_entries.archived_at
-                                  AND e2.id < archived_entries.id))
-                   )
-             );",
-        )?;
-    }
-
     Ok(())
 }
 
@@ -1224,82 +1191,6 @@ pub fn upsert_source_identity(
     Ok(id)
 }
 
-/// Computes and stores `cached_bytes` for a single entry.
-///
-/// Must be called after all artifacts for the entry have been inserted so the
-/// correlated subquery sees the complete artifact set. Ordering by `archived_at`
-/// (tiebreak: `id`) matches the display ordering used in listings.
-pub fn refresh_entry_cached_bytes(conn: &Connection, entry_id: i64) -> Result<()> {
-    let cached: i64 = conn.query_row(
-        "SELECT COALESCE(SUM(b.byte_size), 0)
-         FROM entry_artifacts ea
-         JOIN blobs b ON b.id = ea.blob_id
-         JOIN archived_entries e ON e.id = ea.entry_id
-         WHERE ea.entry_id = ?1
-           AND ea.blob_id IS NOT NULL
-           AND EXISTS (
-               SELECT 1
-               FROM entry_artifacts ea2
-               JOIN archived_entries e2 ON e2.id = ea2.entry_id
-               WHERE ea2.blob_id = ea.blob_id
-                 AND (e2.archived_at < e.archived_at
-                      OR (e2.archived_at = e.archived_at AND e2.id < ?1))
-           )",
-        [entry_id],
-        |row| row.get(0),
-    )?;
-    conn.execute(
-        "UPDATE archived_entries SET cached_bytes = ?1 WHERE id = ?2",
-        params![cached, entry_id],
-    )?;
-    Ok(())
-}
-
-/// Recomputes `cached_bytes` for entries that shared blobs with `entry_id` and
-/// were archived after it.
-///
-/// Must be called **before** the entry row is deleted so that the shared-blob
-/// lookup still works. The inner EXISTS deliberately excludes `entry_id` so each
-/// affected entry is recomputed as if that entry no longer exists.
-///
-/// Intended to be dispatched asynchronously: acknowledge the delete to the user
-/// first, then call this on a background thread.
-pub fn cascade_cached_bytes_after_delete(conn: &Connection, entry_id: i64) -> Result<()> {
-    conn.execute(
-        "UPDATE archived_entries
-         SET cached_bytes = (
-             SELECT COALESCE(SUM(b.byte_size), 0)
-             FROM entry_artifacts ea
-             JOIN blobs b ON b.id = ea.blob_id
-             WHERE ea.entry_id = archived_entries.id
-               AND ea.blob_id IS NOT NULL
-               AND EXISTS (
-                   SELECT 1
-                   FROM entry_artifacts ea3
-                   JOIN archived_entries e3 ON e3.id = ea3.entry_id
-                   WHERE ea3.blob_id = ea.blob_id
-                     AND e3.id != ?1
-                     AND (e3.archived_at < archived_entries.archived_at
-                          OR (e3.archived_at = archived_entries.archived_at
-                              AND e3.id < archived_entries.id))
-               )
-         )
-         WHERE id IN (
-             SELECT DISTINCT ea2.entry_id
-             FROM entry_artifacts ea_del
-             JOIN entry_artifacts ea2   ON ea2.blob_id = ea_del.blob_id
-             JOIN archived_entries e_del ON e_del.id = ea_del.entry_id
-             JOIN archived_entries e2   ON e2.id = ea2.entry_id
-             WHERE ea_del.entry_id = ?1
-               AND ea2.entry_id != ?1
-               AND (e2.archived_at > e_del.archived_at
-                    OR (e2.archived_at = e_del.archived_at AND e2.id > ?1))
-         )",
-        [entry_id],
-    )?;
-    Ok(())
-}
-
 pub fn upsert_blob(conn: &Connection, blob: &BlobRecord) -> Result<i64> {
     conn.execute(
         "INSERT OR IGNORE INTO blobs (

crates/archivr-server/static/index.html

@@ -4,8 +4,8 @@
     <meta charset="utf-8" />
     <meta name="viewport" content="width=device-width, initial-scale=1" />
     <title>Archivr</title>
-    <script type="module" crossorigin src="/assets/index-DnX_j2fa.js"></script>
+    <script type="module" crossorigin src="/assets/index-BEbGvi2K.js"></script>
-    <link rel="stylesheet" crossorigin href="/assets/index-DXhicc6w.css">
+    <link rel="stylesheet" crossorigin href="/assets/index-MrdP6h9x.css">
   </head>
   <body>
     <div id="root"></div>

docs/README.md

@@ -2,11 +2,11 @@
 
 An open-source self-hosted archiving tool. Work in progress.
 
-- [x] Archiving
+## Milestones
+
+- [ ] Archiving
   - [x] Archiving media files from social media platforms
     - [x] YouTube Videos
-    - [x] YouTube Playlists
-    - [x] YouTube Channels
     - [x] Twitter Videos
     - [x] Instagram
     - [x] Facebook
@@ -27,23 +27,14 @@ An open-source self-hosted archiving tool. Work in progress.
     - [ ] Gmail
     - [ ] Outlook
     - [ ] Yahoo Mail
-- [x] Management
+- [ ] Management
-  - [x] Deduplication
+  - [ ] Deduplication
-  - [x] Tagging system
+  - [ ] Tagging system
-  - [x] Search functionality
+  - [ ] Search functionality
   - [ ] Categorization
-  - [x] Metadata extraction and storage
+  - [ ] Metadata extraction and storage
-- [x] User Interface
+- [ ] User Interface
-  - [x] Web-based UI
+  - [ ] Web-based UI
-    - [x] Authentication and login
-    - [x] Archive setup
-    - [x] Browse and view entries
-    - [x] Tag management and filtering
-    - [x] Search entries
-    - [x] View archive runs
-    - [x] Capture dialog
-    - [x] User settings and API tokens
-    - [x] Admin panel
 - [ ] Backup and Sync
   - [ ] Cloud backup (AWS S3, Google Cloud Storage)
   - [ ] Local backup

frontend/src/components/EntryRow.jsx

@@ -39,14 +39,7 @@ export default function EntryRow({ entry, archiveId, isSelected, onSelect }) {
       <div className="col-type">
         <span className="type-pill">{valueText(entry.entity_kind)}</span>
       </div>
-      <div className="col-size">
+      <div className="col-size">{formatBytes(entry.total_artifact_bytes)}</div>
-        <span className="size-total">{formatBytes(entry.total_artifact_bytes)}</span>
-        {entry.cached_bytes > 0 && entry.total_artifact_bytes > 0 && (
-          <span className="size-cached-pct" title={`${formatBytes(entry.cached_bytes)} already on disk from an earlier entry`}>
-            {Math.round(entry.cached_bytes / entry.total_artifact_bytes * 100)}% cached
-          </span>
-        )}
-      </div>
       <div className="url-cell col-url">{valueText(entry.original_url)}</div>
     </div>
   );

frontend/src/styles.css

@@ -310,16 +310,7 @@ select {
 .col-added { width: 162px; color: var(--muted); }
 .col-title { flex: 1 1 0; min-width: 0; overflow: hidden; display: flex; align-items: center; gap: 0.42em; }
 .col-type { width: 116px; }
-.col-size { width: 100px; display: flex; flex-direction: column; justify-content: center; gap: 1px; }
+.col-size { width: 96px; }
-.size-total { font-variant-numeric: tabular-nums; }
-.size-cached-pct {
-  font-size: 10px;
-  color: var(--muted);
-  opacity: 0.8;
-  white-space: nowrap;
-  overflow: hidden;
-  text-overflow: ellipsis;
-}
 .col-url { flex: 0 0 30%; min-width: 0; overflow: hidden; }
 
 .entry-header-row > div:first-child,