feat: integrate Alembic for database migrations

Replace manual if-sqlite/if-postgres branching with Alembic:
- Add alembic dependency
- Create programmatic alembic env (no CLI/alembic.ini needed)
- Support async engines via run_sync passthrough
- render_as_batch=True for SQLite ALTER TABLE compatibility
- Auto-stamp baseline on first run (existing DB at version 25)
- Run alembic upgrade head after legacy migrations
- Include sample migration showing schema + data migration patterns
- Add alembic dir to package-data for distribution
This commit is contained in:
RockChinQ
2026-04-08 23:33:13 +08:00
parent f29c568381
commit 9cd3544d59
9 changed files with 256 additions and 1 deletions
@@ -0,0 +1,51 @@
"""Alembic environment for LangBot.
This env.py is designed to be called programmatically (not via CLI).
It supports both SQLite and PostgreSQL.
The sync connection is passed via config attributes by the runner.
"""
from __future__ import annotations
from alembic import context
from sqlalchemy.engine import Connection
from langbot.pkg.entity.persistence.base import Base
target_metadata = Base.metadata
def run_migrations_offline() -> None:
"""Run migrations in 'offline' mode — emit SQL without a live connection."""
url = context.config.get_main_option('sqlalchemy.url')
context.configure(
url=url,
target_metadata=target_metadata,
literal_binds=True,
dialect_opts={'paramstyle': 'named'},
)
with context.begin_transaction():
context.run_migrations()
def run_migrations_online() -> None:
"""Run migrations with a live sync connection passed via config attributes."""
connection: Connection = context.config.attributes.get('connection')
if connection is None:
raise RuntimeError('connection not provided in alembic config attributes')
context.configure(
connection=connection,
target_metadata=target_metadata,
# render_as_batch=True is critical for SQLite ALTER TABLE support
render_as_batch=True,
)
with context.begin_transaction():
context.run_migrations()
if context.is_offline_mode():
run_migrations_offline()
else:
run_migrations_online()
@@ -0,0 +1,24 @@
# Alembic script.py.mako — template for auto-generated revisions
"""${message}
Revision ID: ${up_revision}
Revises: ${down_revision | comma,n}
Create Date: ${create_date}
"""
from alembic import op
import sqlalchemy as sa
${imports if imports else ""}
# revision identifiers
revision = ${repr(up_revision)}
down_revision = ${repr(down_revision)}
branch_labels = ${repr(branch_labels)}
depends_on = ${repr(depends_on)}
def upgrade() -> None:
${upgrades if upgrades else "pass"}
def downgrade() -> None:
${downgrades if downgrades else "pass"}
@@ -0,0 +1,24 @@
"""baseline: stamp existing schema (db version 25)
This is a no-op migration that marks the starting point for Alembic.
All tables already exist via create_all() + legacy DBMigration system.
Revision ID: 0001_baseline
Revises: None
Create Date: 2026-04-08
"""
revision = '0001_baseline'
down_revision = None
branch_labels = None
depends_on = None
def upgrade() -> None:
# No-op: existing schema is already at database_version=25
# This revision serves as the Alembic baseline.
pass
def downgrade() -> None:
pass
@@ -0,0 +1,62 @@
"""example: sample migration demonstrating Alembic patterns
This is a SAMPLE showing how to write migrations that work
seamlessly across SQLite and PostgreSQL. Delete or adapt as needed.
Revision ID: 0002_sample
Revises: 0001_baseline
Create Date: 2026-04-08
Patterns demonstrated:
1. Schema change (add column) — works on both DBs via render_as_batch
2. Data migration (read + modify JSON) — pure SQLAlchemy, no dialect branching
"""
revision = '0002_sample'
down_revision = '0001_baseline'
branch_labels = None
depends_on = None
def upgrade() -> None:
"""
EXAMPLE: Uncomment to use. This shows the patterns.
# --- Pattern 1: Schema change (add/drop column) ---
# render_as_batch=True in env.py makes this work on SQLite too.
#
# op.add_column('pipelines', sa.Column('description', sa.String(512), server_default=''))
# --- Pattern 2: Data migration (read + modify JSON field) ---
# No if/else for sqlite vs postgres needed!
#
# conn = op.get_bind()
# rows = conn.execute(sa.text("SELECT uuid, config FROM pipelines")).fetchall()
# for row in rows:
# config = json.loads(row[1]) if isinstance(row[1], str) else row[1]
# # Modify the config
# config.setdefault('ai', {}).setdefault('some_new_key', 'default_value')
# conn.execute(
# sa.text("UPDATE pipelines SET config = :cfg WHERE uuid = :uuid"),
# {"cfg": json.dumps(config), "uuid": row[0]}
# )
# --- Pattern 3: Create a new table ---
#
# op.create_table(
# 'audit_log',
# sa.Column('id', sa.Integer, primary_key=True, autoincrement=True),
# sa.Column('action', sa.String(255), nullable=False),
# sa.Column('detail', sa.Text),
# sa.Column('created_at', sa.DateTime, server_default=sa.func.now()),
# )
"""
pass
def downgrade() -> None:
"""
# op.drop_column('pipelines', 'description')
# op.drop_table('audit_log')
"""
pass