fix(db-migration): fix 2 changes with same ID

This solve issue with 2 migrations made the same day, due to merge on pull request, DB migration is blocking

    the same version prefix:
     - 20260625000000_files_user_size_index.sql    (Dio)
     - 20260625000000_folder_tree_modified_at.sql  (Ed)
    They were renamed to ...0001 and ...0002 (disjoint versions) + protection like "IF NOT EXISTS"

    I have opt for an automated clean up of old entry:
        `DELETE FROM _sqlx_migrations WHERE version = 20260625000000;`
    runned on startup

    affected users: Dio, myself and any dev that wanted to work on this project since eb0ba58158

migrations/20260625000002_folder_tree_modified_at.sql

@@ -14,15 +14,43 @@
 -- chain on every file write and every folder mutation. Performance
 -- ceiling: O(depth) row updates per mutation; deep concurrent writes
 -- to the same root subtree can contend on the root row.
+--
+-- Idempotency note: this migration was originally numbered
+-- `20260625000000` and collided with `files_user_size_index` from a
+-- parallel branch. Both files were renamed to disjoint versions, and
+-- this body uses `IF NOT EXISTS` / `CREATE OR REPLACE` /
+-- `DROP TRIGGER IF EXISTS` throughout so the migration is safe to
+-- re-run against databases that already applied it under the old
+-- version number. An orphan row for `20260625000000` may remain in
+-- `_sqlx_migrations` on such databases — sqlx ignores rows whose
+-- version no longer maps to a source file.
 
+-- Gate the entire column-add + backfill block on column absence.
+-- A naive `ADD COLUMN IF NOT EXISTS` paired with an unconditional
+-- backfill `UPDATE` would clobber trigger-bumped values back to
+-- `updated_at` on databases that already deployed this migration
+-- under the old `20260625000000` version — every folder NC clients
+-- have synced since first deploy would suddenly look "modified",
+-- triggering a one-time re-walk. The DO block keeps the migration
+-- a true no-op for those databases: column exists → skip both
+-- statements → preserve the live trigger-maintained values.
+DO $$
+BEGIN
+    IF NOT EXISTS (
+        SELECT 1 FROM information_schema.columns
+         WHERE table_schema = 'storage'
+           AND table_name = 'folders'
+           AND column_name = 'tree_modified_at'
+    ) THEN
         ALTER TABLE storage.folders
             ADD COLUMN tree_modified_at TIMESTAMPTZ NOT NULL DEFAULT NOW();
-
--- Backfill existing rows: collapse the rollup timestamp to the
--- per-folder updated_at. Clients re-walking after deploy will see
--- one batch of "looks new to me" responses, which they handle as a
--- content-match-no-download — the expected one-time resync wave.
+        -- Backfill on first-deploy: collapse to per-folder updated_at.
+        -- Clients re-walking after deploy will see one batch of
+        -- "looks new to me" responses, handled as
+        -- content-match-no-download — the expected one-time resync.
         UPDATE storage.folders SET tree_modified_at = updated_at;
+    END IF;
+END $$;
 
 
 -- File-side trigger: any INSERT/UPDATE/DELETE on storage.files
@@ -60,6 +88,10 @@ BEGIN
 END;
 $$;
 
+-- PG 13 doesn't support `CREATE OR REPLACE TRIGGER` (added in PG 14),
+-- so use the DROP-then-CREATE pattern to stay re-runnable on the
+-- minimum supported version.
+DROP TRIGGER IF EXISTS files_bump_folder_tree_etag ON storage.files;
 CREATE TRIGGER files_bump_folder_tree_etag
     AFTER INSERT OR UPDATE OR DELETE ON storage.files
     FOR EACH ROW EXECUTE FUNCTION storage.bump_folder_tree_from_file();
@@ -99,6 +131,7 @@ BEGIN
 END;
 $$;
 
+DROP TRIGGER IF EXISTS folders_bump_folder_tree_etag ON storage.folders;
 CREATE TRIGGER folders_bump_folder_tree_etag
     AFTER INSERT OR UPDATE OR DELETE ON storage.folders
     FOR EACH ROW EXECUTE FUNCTION storage.bump_folder_tree_from_folder();

src/infrastructure/db.rs

@@ -163,6 +163,35 @@ async fn create_pool_with_retries(
 /// in a `_sqlx_migrations` table. Each migration runs in its own transaction.
 /// Migration files are embedded at compile time via `sqlx::migrate!()`.
 async fn run_migrations(pool: &PgPool) -> Result<()> {
+    // ── One-time pre-flight cleanup for the 20260625000000 collision ──
+    //
+    // Two migrations landed on the same day from parallel branches with
+    // the same version prefix:
+    //   - 20260625000000_files_user_size_index.sql    (Dio)
+    //   - 20260625000000_folder_tree_modified_at.sql  (Ed)
+    // They were renamed to ...0001 and ...0002 (disjoint versions), and
+    // both bodies were made idempotent so they re-run safely against
+    // databases that already applied either original under the shared
+    // version. However sqlx 0.8's default strict mode errors on boot
+    // when `_sqlx_migrations` contains a row whose version no longer
+    // maps to a source file ("previously applied but is missing in the
+    // resolved migrations") — which is exactly the state of every
+    // contributor DB that booted before the rename.
+    //
+    // This DELETE silently clears that stale bookkeeping row. The
+    // schema effects of whichever original ran are preserved
+    // (idempotent re-application via ...0001 / ...0002 is a no-op on
+    // already-modified schemas). On fresh databases the table doesn't
+    // exist yet, the query errors, and the `let _` swallows it —
+    // sqlx::migrate!() then creates the table cleanly on its first
+    // pass.
+    //
+    // Sunset: drop this block once the contributor base has rolled
+    // past the affected commit window. Suggested review date 2026-12.
+    let _ = sqlx::query("DELETE FROM _sqlx_migrations WHERE version = 20260625000000")
+        .execute(pool)
+        .await;
+
     match sqlx::migrate!().run(pool).await {
         Ok(()) => Ok(()),
         Err(e) => Err(DbError(format!("Migration error: {}", e))),