Codex
67 lines
2.9 KiB
Python
67 lines
2.9 KiB
Python
"""source subscriptions and raw items
|
|
|
|
Revision ID: 202605080900
|
|
Revises: 202605071200
|
|
Create Date: 2026-05-08 09:00:00
|
|
"""
|
|
|
|
from typing import Sequence, Union
|
|
|
|
from alembic import op
|
|
import sqlalchemy as sa
|
|
|
|
revision: str = "202605080900"
|
|
down_revision: Union[str, None] = "202605071200"
|
|
branch_labels: Union[str, Sequence[str], None] = None
|
|
depends_on: Union[str, Sequence[str], None] = None
|
|
|
|
|
|
def upgrade() -> None:
|
|
# Subscriptions are stable source inputs that run before model-side search.
|
|
op.create_table(
|
|
"source_subscriptions",
|
|
sa.Column("id", sa.Integer(), primary_key=True),
|
|
sa.Column("name", sa.String(length=160), nullable=False, unique=True),
|
|
sa.Column("source_type", sa.String(length=32), nullable=False),
|
|
sa.Column("url", sa.Text(), nullable=False),
|
|
sa.Column("url_hash", sa.String(length=64), nullable=False, unique=True),
|
|
sa.Column("category", sa.String(length=120), nullable=False),
|
|
sa.Column("enabled", sa.Boolean(), nullable=False, server_default=sa.true()),
|
|
sa.Column("created_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
|
|
sa.Column("updated_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
|
|
)
|
|
|
|
# Raw items preserve source evidence before the final signal layer deduplicates and summarizes it.
|
|
op.create_table(
|
|
"raw_items",
|
|
sa.Column("id", sa.Integer(), primary_key=True),
|
|
sa.Column("run_id", sa.Integer(), sa.ForeignKey("agent_runs.id"), nullable=False),
|
|
sa.Column(
|
|
"subscription_id",
|
|
sa.Integer(),
|
|
sa.ForeignKey("source_subscriptions.id"),
|
|
nullable=False,
|
|
),
|
|
sa.Column("title", sa.String(length=300), nullable=False),
|
|
sa.Column("summary", sa.Text(), nullable=False),
|
|
sa.Column("source_url", sa.Text(), nullable=False),
|
|
sa.Column("source_url_hash", sa.String(length=64), nullable=False),
|
|
sa.Column("source_name", sa.String(length=200), nullable=False),
|
|
sa.Column("category", sa.String(length=120), nullable=False),
|
|
sa.Column("published_at", sa.DateTime(), nullable=True),
|
|
sa.Column("raw_payload", sa.JSON(), nullable=False),
|
|
sa.Column("created_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
|
|
sa.UniqueConstraint("source_url_hash", name="uq_raw_items_source_url_hash"),
|
|
)
|
|
op.create_index("ix_raw_items_run_id", "raw_items", ["run_id"])
|
|
op.create_index("ix_raw_items_subscription_id", "raw_items", ["subscription_id"])
|
|
op.create_index("ix_raw_items_category", "raw_items", ["category"])
|
|
|
|
|
|
def downgrade() -> None:
|
|
op.drop_index("ix_raw_items_category", table_name="raw_items")
|
|
op.drop_index("ix_raw_items_subscription_id", table_name="raw_items")
|
|
op.drop_index("ix_raw_items_run_id", table_name="raw_items")
|
|
op.drop_table("raw_items")
|
|
op.drop_table("source_subscriptions")
|