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

View File

@@ -39,6 +39,7 @@ dependencies = [
"quart-cors>=0.8.0",
"requests>=2.32.3",
"slack-sdk>=3.35.0",
"alembic>=1.15.0",
"sqlalchemy[asyncio]>=2.0.40",
"sqlmodel>=0.0.24",
"telegramify-markdown>=0.5.1",
@@ -111,7 +112,7 @@ requires = ["setuptools>=61.0", "wheel"]
build-backend = "setuptools.build_meta"
[tool.setuptools]
package-data = { "langbot" = ["templates/**", "pkg/provider/modelmgr/requesters/*", "pkg/platform/sources/*", "web/dist/**"] }
package-data = { "langbot" = ["templates/**", "pkg/provider/modelmgr/requesters/*", "pkg/platform/sources/*", "web/dist/**", "pkg/persistence/alembic/**"] }
[dependency-groups]
dev = [

View File

@@ -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()

View File

@@ -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"}

View File

@@ -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

View File

@@ -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

View File

@@ -0,0 +1,68 @@
"""Programmatic Alembic runner for LangBot.
Usage from async code:
from langbot.pkg.persistence.alembic_runner import run_alembic_upgrade
await run_alembic_upgrade(async_engine)
"""
from __future__ import annotations
import os
from typing import TYPE_CHECKING
from alembic.config import Config
from alembic import command
from alembic.runtime.migration import MigrationContext
if TYPE_CHECKING:
from sqlalchemy.ext.asyncio import AsyncEngine
from sqlalchemy.engine import Connection
_ALEMBIC_DIR = os.path.join(os.path.dirname(__file__), 'alembic')
def _build_config(connection: Connection) -> Config:
"""Build an Alembic Config with sync connection attached."""
cfg = Config()
cfg.set_main_option('script_location', _ALEMBIC_DIR)
cfg.attributes['connection'] = connection
return cfg
def _do_upgrade(connection: Connection, revision: str = 'head') -> None:
"""Synchronous upgrade — runs inside run_sync."""
cfg = _build_config(connection)
command.upgrade(cfg, revision)
def _do_stamp(connection: Connection, revision: str = 'head') -> None:
"""Synchronous stamp — runs inside run_sync."""
cfg = _build_config(connection)
command.stamp(cfg, revision)
def _do_get_current(connection: Connection) -> str | None:
"""Get current alembic revision synchronously."""
ctx = MigrationContext.configure(connection)
return ctx.get_current_revision()
async def run_alembic_upgrade(async_engine: AsyncEngine, revision: str = 'head') -> None:
"""Run Alembic upgrade to the given revision."""
async with async_engine.connect() as conn:
await conn.run_sync(_do_upgrade, revision)
await conn.commit()
async def run_alembic_stamp(async_engine: AsyncEngine, revision: str = 'head') -> None:
"""Stamp the database with a revision without running migrations."""
async with async_engine.connect() as conn:
await conn.run_sync(_do_stamp, revision)
await conn.commit()
async def get_alembic_current(async_engine: AsyncEngine) -> str | None:
"""Get current alembic revision, or None if not stamped."""
async with async_engine.connect() as conn:
return await conn.run_sync(_do_get_current)

View File

@@ -76,6 +76,9 @@ class PersistenceManager:
self.ap.logger.info(f'Successfully upgraded database to version {last_migration_number}.')
# Run Alembic migrations (new migration system)
await self._run_alembic_migrations()
await self.write_space_model_providers()
async def create_tables(self):
@@ -135,6 +138,28 @@ class PersistenceManager:
# =================================
async def _run_alembic_migrations(self):
"""Run Alembic-based migrations after legacy migrations complete."""
from . import alembic_runner
engine = self.get_db_engine()
try:
current_rev = await alembic_runner.get_alembic_current(engine)
if current_rev is None:
# First time: stamp baseline so Alembic knows existing schema is up-to-date
self.ap.logger.info('Alembic: no revision found, stamping baseline...')
await alembic_runner.run_alembic_stamp(engine, '0001_baseline')
current_rev = '0001_baseline'
# Upgrade to head
await alembic_runner.run_alembic_upgrade(engine, 'head')
self.ap.logger.info('Alembic migrations completed.')
except Exception as e:
self.ap.logger.error(f'Alembic migration failed: {e}', exc_info=True)
raise
async def execute_async(self, *args, **kwargs) -> sqlalchemy.engine.cursor.CursorResult:
async with self.get_db_engine().connect() as conn:
result = await conn.execute(*args, **kwargs)