From 20c43d205614d675bf6d4512031abed8e0197833 Mon Sep 17 00:00:00 2001
From: LyAhn <admin@jezz.wtf>
Date: Sun, 7 Jun 2026 22:30:02 +0100
Subject: [PATCH] fix: address P1 and P2 review issues from PR #8 round 7

indexer: clear duplicate scan cache (folder + global) at the end of
every do_index so stale groups are never presented after a reindex;
previously a file modified or replaced on disk would still appear as a
duplicate candidate from the cached result until a manual rescan

db/vector: replace timestamp-based HNSW revision with a monotonically
incremented integer counter (app_kv.embedding_revision); mark_embedding_ready
atomically increments the counter so two embeddings saved within the same
second correctly advance the revision; get_embedding_revision now reads
this counter instead of MAX(embedding_updated_at), preventing the HNSW
cache from serving stale vectors after same-second batch updates
---
 src-tauri/src/db.rs      | 14 ++++++++++++++
 src-tauri/src/indexer.rs |  5 +++++
 src-tauri/src/vector.rs  | 18 +++++++++++-------
 3 files changed, 30 insertions(+), 7 deletions(-)

diff --git a/src-tauri/src/db.rs b/src-tauri/src/db.rs
index 83d9ac2..572212d 100644
--- a/src-tauri/src/db.rs
+++ b/src-tauri/src/db.rs
@@ -263,6 +263,13 @@ pub fn migrate(conn: &Connection) -> Result<()> {
             groups_json     TEXT NOT NULL
         );
 
+        CREATE TABLE IF NOT EXISTS app_kv (
+            key   TEXT PRIMARY KEY,
+            value INTEGER NOT NULL DEFAULT 0
+        );
+
+        INSERT OR IGNORE INTO app_kv (key, value) VALUES ('embedding_revision', 0);
+
         CREATE INDEX IF NOT EXISTS idx_images_folder_id ON images(folder_id);
         CREATE INDEX IF NOT EXISTS idx_images_modified_at ON images(modified_at);
         CREATE INDEX IF NOT EXISTS idx_embedding_jobs_status ON embedding_jobs(status);
@@ -915,6 +922,13 @@ pub fn mark_embedding_ready(conn: &Connection, image_id: i64, model: &str) -> Re
         params![image_id, model],
     )?;
     conn.execute("DELETE FROM embedding_jobs WHERE image_id = ?1", [image_id])?;
+    // Advance the monotonic revision so the HNSW cache is always rebuilt after
+    // any embedding change, regardless of clock resolution.
+    conn.execute(
+        "INSERT INTO app_kv (key, value) VALUES ('embedding_revision', 1)
+         ON CONFLICT(key) DO UPDATE SET value = value + 1",
+        [],
+    )?;
     Ok(())
 }
 
diff --git a/src-tauri/src/indexer.rs b/src-tauri/src/indexer.rs
index a5d062d..25b4c94 100644
--- a/src-tauri/src/indexer.rs
+++ b/src-tauri/src/indexer.rs
@@ -373,6 +373,11 @@ fn do_index(app: AppHandle, pool: &DbPool, folder_id: i64, folder_path: PathBuf)
         let _ = db::backfill_embedding_jobs(&conn)?;
         db::update_folder_count(&conn, folder_id)?;
         let _ = db::clear_folder_scan_error(&conn, folder_id);
+        // Invalidate duplicate scan cache — any reindex can change file contents
+        // or the set of files, making cached duplicate groups stale.
+        let folder_scope = format!("folder:{}", folder_id);
+        let _ = db::clear_duplicate_scan_cache(&conn, &folder_scope);
+        let _ = db::clear_duplicate_scan_cache(&conn, "all");
     }
 
     emit_progress(
diff --git a/src-tauri/src/vector.rs b/src-tauri/src/vector.rs
index 644ece8..25a3220 100644
--- a/src-tauri/src/vector.rs
+++ b/src-tauri/src/vector.rs
@@ -215,13 +215,17 @@ pub fn get_image_embedding(conn: &Connection, image_id: i64) -> Result<Option<Ve
 }
 
 pub fn get_embedding_revision(conn: &Connection) -> Result<String> {
-    let count: i64 = conn.query_row("SELECT COUNT(*) FROM image_vec", [], |row| row.get(0))?;
-    let max_updated_at: Option<String> = conn.query_row(
-        "SELECT MAX(embedding_updated_at) FROM images WHERE embedding_status = 'ready'",
-        [],
-        |row| row.get(0),
-    )?;
-    Ok(format!("{}:{}", count, max_updated_at.unwrap_or_default()))
+    // Use the monotonically incremented app_kv counter so that two embeddings
+    // saved within the same clock second still advance the revision, preventing
+    // the HNSW cache from serving stale vectors.
+    let revision: i64 = conn
+        .query_row(
+            "SELECT COALESCE((SELECT value FROM app_kv WHERE key = 'embedding_revision'), 0)",
+            [],
+            |row| row.get(0),
+        )
+        .unwrap_or(0);
+    Ok(revision.to_string())
 }
 
 // fn image_ids_for_folder(