DealDocumentScreening/migrations/versions/0001_initial.py

235 lines
9.1 KiB
Python

"""initial schema: users, documents, reports, jobs, service_tokens, invoices
Revision ID: 0001
Revises:
Create Date: 2026-01-01
Hand-written (docs/ARCHITECTURE.md §7). status/queue/adapter columns are TEXT+CHECK
(additive migrations). UUIDs default to gen_random_uuid() server-side
(built into Postgres 13+; we run pg16).
"""
from __future__ import annotations
from collections.abc import Sequence
import sqlalchemy as sa
from alembic import op
from sqlalchemy.dialects import postgresql
# revision identifiers, used by Alembic.
revision: str = "0001"
down_revision: str | None = None
branch_labels: str | Sequence[str] | None = None
depends_on: str | Sequence[str] | None = None
def upgrade() -> None:
# ── users ────────────────────────────────────────────────────────────────
op.create_table(
"users",
sa.Column(
"id",
postgresql.UUID(as_uuid=True),
primary_key=True,
server_default=sa.text("gen_random_uuid()"),
),
sa.Column("telegram_id", sa.BigInteger, unique=True),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column("credits_left", sa.Integer, nullable=False, server_default=sa.text("0")),
sa.CheckConstraint("credits_left >= 0", name="users_credits_nonneg"),
)
# ── documents ────────────────────────────────────────────────────────────
op.create_table(
"documents",
sa.Column(
"id",
postgresql.UUID(as_uuid=True),
primary_key=True,
server_default=sa.text("gen_random_uuid()"),
),
sa.Column(
"user_id",
postgresql.UUID(as_uuid=True),
sa.ForeignKey("users.id", ondelete="CASCADE"),
nullable=False,
),
sa.Column("s3_key", sa.Text, nullable=False),
sa.Column("extracted_s3_key", sa.Text),
sa.Column("filename", sa.Text, nullable=False),
sa.Column("mime", sa.Text, nullable=False),
sa.Column("bytes", sa.BigInteger, nullable=False, server_default=sa.text("0")),
sa.Column("status", sa.String, nullable=False, server_default=sa.text("'queued'")),
sa.Column("stage", sa.Text),
sa.Column("refunded", sa.Boolean, nullable=False, server_default=sa.text("false")),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column(
"updated_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.CheckConstraint(
"status IN ('queued','extracting','ocr','analyzing','done','failed')",
name="documents_status_check",
),
)
op.create_index(
"documents_user_created_idx", "documents", ["user_id", sa.text("created_at DESC")]
)
op.create_index("documents_status_idx", "documents", ["status"])
# ── reports ──────────────────────────────────────────────────────────────
op.create_table(
"reports",
sa.Column(
"id",
postgresql.UUID(as_uuid=True),
primary_key=True,
server_default=sa.text("gen_random_uuid()"),
),
sa.Column(
"document_id",
postgresql.UUID(as_uuid=True),
sa.ForeignKey("documents.id", ondelete="CASCADE"),
nullable=False,
unique=True,
),
sa.Column("content_json", postgresql.JSONB, nullable=False),
sa.Column("markdown", sa.Text, nullable=False),
sa.Column("model_used", sa.Text),
sa.Column("prompt_tokens", sa.Integer, nullable=False, server_default=sa.text("0")),
sa.Column("eval_tokens", sa.Integer, nullable=False, server_default=sa.text("0")),
sa.Column("latency_ms", sa.Integer, nullable=False, server_default=sa.text("0")),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
)
# ── jobs ─────────────────────────────────────────────────────────────────
op.create_table(
"jobs",
sa.Column(
"id",
postgresql.UUID(as_uuid=True),
primary_key=True,
server_default=sa.text("gen_random_uuid()"),
),
sa.Column(
"document_id",
postgresql.UUID(as_uuid=True),
sa.ForeignKey("documents.id", ondelete="CASCADE"),
nullable=False,
),
sa.Column("correlation_id", postgresql.UUID(as_uuid=True), nullable=False),
sa.Column("queue", sa.String, nullable=False),
sa.Column("attempts", sa.Integer, nullable=False, server_default=sa.text("0")),
sa.Column("max_attempts", sa.Integer, nullable=False, server_default=sa.text("5")),
sa.Column("last_failure_class", sa.Text),
sa.Column("last_error", sa.Text),
sa.Column("dlq", sa.Boolean, nullable=False, server_default=sa.text("false")),
sa.Column("status", sa.String, nullable=False, server_default=sa.text("'pending'")),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column(
"updated_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.CheckConstraint("queue IN ('extract','analyze')", name="jobs_queue_check"),
sa.CheckConstraint(
"status IN ('pending','running','retrying','dlq','done')",
name="jobs_status_check",
),
)
op.create_index("jobs_correlation_idx", "jobs", ["correlation_id"])
op.create_index("jobs_document_idx", "jobs", ["document_id"])
# ── service_tokens ───────────────────────────────────────────────────────
op.create_table(
"service_tokens",
sa.Column(
"id",
postgresql.UUID(as_uuid=True),
primary_key=True,
server_default=sa.text("gen_random_uuid()"),
),
sa.Column("name", sa.Text, unique=True, nullable=False),
sa.Column("token_hash", sa.Text, nullable=False),
sa.Column("adapter", sa.String, nullable=False),
sa.Column("revoked", sa.Boolean, nullable=False, server_default=sa.text("false")),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column("last_used_at", sa.DateTime(timezone=True)),
sa.CheckConstraint("adapter IN ('bot','web','cli')", name="service_tokens_adapter_check"),
)
# ── invoices (STUB — no ЮKassa logic this refactor) ─────────────────────
op.create_table(
"invoices",
sa.Column(
"id",
postgresql.UUID(as_uuid=True),
primary_key=True,
server_default=sa.text("gen_random_uuid()"),
),
sa.Column(
"user_id",
postgresql.UUID(as_uuid=True),
sa.ForeignKey("users.id", ondelete="CASCADE"),
nullable=False,
),
sa.Column("amount", sa.Integer, nullable=False),
sa.Column("status", sa.String, nullable=False, server_default=sa.text("'draft'")),
sa.Column("provider", sa.Text),
sa.Column("external_id", sa.Text),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column("paid_at", sa.DateTime(timezone=True)),
sa.CheckConstraint(
"status IN ('draft','pending','succeeded','cancelled','refunded')",
name="invoices_status_check",
),
)
op.create_index("invoices_user_idx", "invoices", ["user_id", sa.text("created_at DESC")])
def downgrade() -> None:
op.drop_index("invoices_user_idx", table_name="invoices")
op.drop_table("invoices")
op.drop_table("service_tokens")
op.drop_index("jobs_document_idx", table_name="jobs")
op.drop_index("jobs_correlation_idx", table_name="jobs")
op.drop_table("jobs")
op.drop_table("reports")
op.drop_index("documents_status_idx", table_name="documents")
op.drop_index("documents_user_created_idx", table_name="documents")
op.drop_table("documents")
op.drop_table("users")