fix(db): re-running 0095/0096 rebuilds an invalid leftover index

A concurrent build that failed part-way leaves an INVALID index under its
name; IF NOT EXISTS kept it on the re-run, and 0095 then dropped the old
channel_id index, leaving none usable. The leftover is now dropped and
built again, and the old index goes only once the new one is valid.

backend/alembic/versions/0095_videos_channel_cover_index.py

@@ -17,10 +17,13 @@ cascade, the sync upsert, channel detail) rides this one. The old index is dropp
 tests/test_channel_list_index_only.py holds the queries and this column list together.
 
 CONCURRENTLY (autocommit_block) builds it without blocking a live prod. IF (NOT) EXISTS keeps the drift
-test's downgrade → re-upgrade round trip idempotent.
+test's downgrade → re-upgrade round trip idempotent. A re-run after a build that failed part-way rebuilds
+the INVALID leftover, and the old index is dropped only once the new one is valid: a re-run that kept the
+leftover and dropped the old one left `videos` with no usable channel_id index (E31 S5 review).
 """
 
 from alembic import op
+from sqlalchemy import text
 
 revision: str = "0095_videos_channel_cover_index"
 down_revision: str | None = "0094_plex_genres_hu_everywhere"
@@ -28,20 +31,49 @@ branch_labels: str | None = None
 depends_on: str | None = None
 
 
+def _valid(name: str) -> bool | None:
+    """The index's `indisvalid`, or None when there is no index of that name."""
+    row = op.get_bind().execute(
+        text(
+            "SELECT i.indisvalid FROM pg_index i JOIN pg_class c ON c.oid = i.indexrelid "
+            "WHERE c.relname = :name"
+        ),
+        {"name": name},
+    ).first()
+    return None if row is None else bool(row[0])
+
+
+def _build(name: str, ddl: str) -> None:
+    """CREATE INDEX CONCURRENTLY `name` (`ddl` is what follows the name), re-runnable. A build that
+    failed part-way leaves an INVALID index under the name, and `IF NOT EXISTS` would keep it: the
+    planner never uses it, and nothing says so (E31 S5 review). Such a leftover is dropped and built
+    again."""
+    if _valid(name) is False:
+        op.execute(f"DROP INDEX CONCURRENTLY IF EXISTS {name}")
+    op.execute(f"CREATE INDEX CONCURRENTLY IF NOT EXISTS {name} {ddl}")
+
+
+def _swap(build: str, ddl: str, drop: str) -> None:
+    _build(build, ddl)
+    if not _valid(build):
+        raise RuntimeError(f"{build} did not build valid; {drop} is kept")
+    op.execute(f"DROP INDEX CONCURRENTLY IF EXISTS {drop}")
+
+
 def upgrade() -> None:
     with op.get_context().autocommit_block():
-        op.execute(
+        _swap(
-            "CREATE INDEX CONCURRENTLY IF NOT EXISTS ix_videos_channel_pub_cover "
+            "ix_videos_channel_pub_cover",
             "ON videos (channel_id, published_at DESC NULLS LAST, id) "
-            "INCLUDE (duration_seconds, unavailable_since, via_explore, is_short, live_status)"
+            "INCLUDE (duration_seconds, unavailable_since, via_explore, is_short, live_status)",
+            "ix_videos_channel_pub_desc",
         )
-        op.execute("DROP INDEX CONCURRENTLY IF EXISTS ix_videos_channel_pub_desc")
 
 
 def downgrade() -> None:
     with op.get_context().autocommit_block():
-        op.execute(
+        _swap(
-            "CREATE INDEX CONCURRENTLY IF NOT EXISTS ix_videos_channel_pub_desc "
+            "ix_videos_channel_pub_desc",
-            "ON videos (channel_id, published_at DESC NULLS LAST, id ASC)"
+            "ON videos (channel_id, published_at DESC NULLS LAST, id ASC)",
+            "ix_videos_channel_pub_cover",
         )
-        op.execute("DROP INDEX CONCURRENTLY IF EXISTS ix_videos_channel_pub_cover")

backend/alembic/versions/0096_videos_sort_indexes.py

@@ -28,6 +28,7 @@ test's downgrade → re-upgrade round trip idempotent.
 """
 
 from alembic import op
+from sqlalchemy import text
 
 revision: str = "0096_videos_sort_indexes"
 down_revision: str | None = "0095_videos_channel_cover_index"
@@ -47,10 +48,32 @@ INDEXES = {
 }
 
 
+def _valid(name: str) -> bool | None:
+    """The index's `indisvalid`, or None when there is no index of that name."""
+    row = op.get_bind().execute(
+        text(
+            "SELECT i.indisvalid FROM pg_index i JOIN pg_class c ON c.oid = i.indexrelid "
+            "WHERE c.relname = :name"
+        ),
+        {"name": name},
+    ).first()
+    return None if row is None else bool(row[0])
+
+
+def _build(name: str, ddl: str) -> None:
+    """CREATE INDEX CONCURRENTLY `name` (`ddl` is what follows the name), re-runnable. A build that
+    failed part-way leaves an INVALID index under the name, and `IF NOT EXISTS` would keep it: the
+    planner never uses it, and nothing says so (E31 S5 review). Such a leftover is dropped and built
+    again."""
+    if _valid(name) is False:
+        op.execute(f"DROP INDEX CONCURRENTLY IF EXISTS {name}")
+    op.execute(f"CREATE INDEX CONCURRENTLY IF NOT EXISTS {name} {ddl}")
+
+
 def upgrade() -> None:
     with op.get_context().autocommit_block():
         for name, columns in INDEXES.items():
-            op.execute(f"CREATE INDEX CONCURRENTLY IF NOT EXISTS {name} ON videos ({columns})")
+            _build(name, f"ON videos ({columns})")
 
 
 def downgrade() -> None:

backend/tests/test_migration_rerun_invalid_index.py

@@ -0,0 +1,53 @@
+"""A concurrent index build that failed part-way, then re-run (E31 S5 review), DB-lane.
+
+CREATE INDEX CONCURRENTLY that fails leaves an INVALID index under its name, and alembic_version is not
+stamped, so the next start runs the migration again. `IF NOT EXISTS` matched the name and kept the
+leftover, which the planner never uses; 0095 then dropped the old channel_id index, leaving `videos`
+with no usable one. A re-run now rebuilds the leftover and drops the old index only once the new one is
+valid.
+"""
+
+from alembic import command
+from alembic.config import Config
+from sqlalchemy import text
+
+from app.db import engine
+
+
+def _index(name: str) -> tuple[bool, str] | None:
+    with engine.connect() as conn:
+        row = conn.execute(
+            text(
+                "SELECT i.indisvalid, pg_get_indexdef(i.indexrelid) FROM pg_index i "
+                "JOIN pg_class c ON c.oid = i.indexrelid WHERE c.relname = :name"
+            ),
+            {"name": name},
+        ).first()
+    return None if row is None else (bool(row[0]), row[1])
+
+
+def _leave_invalid(name: str) -> None:
+    """What a build that failed part-way leaves behind: the name taken, the index INVALID."""
+    with engine.connect().execution_options(isolation_level="AUTOCOMMIT") as conn:
+        conn.execute(text(f"CREATE INDEX {name} ON videos (id)"))
+        conn.execute(
+            text(f"UPDATE pg_index SET indisvalid = false WHERE indexrelid = '{name}'::regclass")
+        )
+
+
+def test_a_rerun_rebuilds_an_invalid_leftover_before_dropping_the_old_index(db):
+    db.rollback()  # CONCURRENTLY waits for every open transaction, this session's too
+    cfg = Config("alembic.ini")
+    command.downgrade(cfg, "0094_plex_genres_hu_everywhere")
+    try:
+        _leave_invalid("ix_videos_channel_pub_cover")
+        _leave_invalid("ix_videos_views_desc")
+    finally:
+        command.upgrade(cfg, "head")
+
+    cover = _index("ix_videos_channel_pub_cover")
+    assert cover is not None and cover[0], cover
+    assert "INCLUDE (duration_seconds" in cover[1]
+    assert _index("ix_videos_channel_pub_desc") is None
+    views = _index("ix_videos_views_desc")
+    assert views is not None and views[0] and "view_count DESC NULLS LAST" in views[1], views