"""Add superseded column to downloads

Revision ID: 003
Revises: 002
Create Date: 2026-03-18

"""
from typing import Sequence, Union

from alembic import op
import sqlalchemy as sa


revision: str = '003'
down_revision: Union[str, None] = '002'
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None


def upgrade() -> None:
    # Add superseded column with default False
    op.add_column(
        'downloads',
        sa.Column('superseded', sa.Boolean(), nullable=False, server_default='false')
    )

    # Backfill: mark FAILED downloads as superseded where a later COMPLETED
    # download exists for the same source. REQUIRED — without this, all
    # previously-superseded failures reappear in the dashboard immediately.
    op.execute("""
        UPDATE downloads d
        SET superseded = TRUE
        WHERE d.status = 'failed'
          AND EXISTS (
            SELECT 1 FROM downloads d2
            WHERE d2.source_id = d.source_id
              AND d2.status = 'completed'
              AND d2.created_at > d.created_at
          )
    """)

    # Partial index covering the dominant query pattern: status + superseded = FALSE.
    # A single boolean column index would be ignored in favour of status indexes;
    # this form matches the WHERE clauses at all three affected query sites.
    op.create_index(
        'idx_downloads_not_superseded',
        'downloads',
        ['status'],
        postgresql_where=sa.text('superseded = FALSE')
    )


def downgrade() -> None:
    op.drop_index('idx_downloads_not_superseded', table_name='downloads')
    op.drop_column('downloads', 'superseded')