Merge pull request #1856 from Agenta-AI/feature/age-369-add-alembic

Feat: add Alembic support for database migration

.github/workflows/run-backend-tests.yml

@@ -29,17 +29,20 @@ jobs:
       - name: Start Docker Compose
         run: OPENAI_API_KEY=${{ secrets.NEXT_PUBLIC_OPENAI_API_KEY }} ENVIRONMENT=github docker-compose -f "docker-compose.test.yml" up -d --build
 
+      - name: Wait for Backend Service
+        run: |
+          sleep 10 && curl -i http://localhost/api/openapi.json
+
+      - name: Apply Schema Migration
+        run:  docker exec -w /app/agenta_backend/migrations/postgres agenta-backend-test alembic -c alembic.oss.ini upgrade head
+
       - name: Restart Backend Service To Fetch Template Images
         run: docker container restart agenta-backend-test
 
       - name: Check Templates Exists
         run: |
           sleep 10 && curl -i http://localhost/api/containers/templates/
 
-      - name: Wait for Backend Service
-        run: |
-          sleep 10 && curl -i http://localhost/api/openapi.json
-
       - name: Run tests
         run: sleep 10 && docker exec agenta-backend-test pytest
 

.github/workflows/run-frontend-tests.yml

@@ -46,6 +46,9 @@ jobs:
           curl http://localhost/api/organizations/own/
           curl http://localhost/api/containers/templates/
 
+      - name: Apply Schema Migration
+        run:  docker exec -w /app/agenta_backend/migrations/postgres agenta-backend-test alembic -c alembic.oss.ini upgrade head
+
       - name: Set Node.js 18
         uses: actions/setup-node@v4
         with:

agenta-backend/Dockerfile

@@ -11,13 +11,18 @@ RUN apt-get update -y \
 RUN pip install --upgrade pip \
     && pip install poetry
 
-# Copy only requirements to cache them in docker layer
-COPY pyproject.toml poetry.lock* README.md /app/
+# Copy only requirements and alembic configuration file
+# to cache them in docker layer
+COPY pyproject.toml poetry.lock* alembic.* README.md /app/
 
-# This is a hack to create a dummy module so that poetry install doesn't fail 
+# This is a hack to create a dummy module so that poetry install doesn't fail
 RUN mkdir -p /app/agenta_backend
 RUN touch /app/agenta_backend/__init__.py
 
+# Copy migrations folder
+RUN mkdir -p /app/agenta_backend/migrations/postgres
+COPY agenta_backend/migrations/postgres /app/agenta_backend/migrations/postgres
+
 # Project initialization:
 RUN poetry config virtualenvs.create false \
     && poetry install --no-interaction --no-ansi

agenta-backend/agenta_backend/main.py

@@ -1,4 +1,3 @@
-import asyncio
 from contextlib import asynccontextmanager
 
 from agenta_backend import celery_config
@@ -16,9 +15,12 @@
     configs_router,
     health_router,
 )
-from agenta_backend.utils.common import isEE, isCloudProd, isCloudDev, isOss, isCloudEE
-from agenta_backend.models.db_engine import db_engine
 from agenta_backend.open_api import open_api_tags_metadata
+from agenta_backend.utils.common import isEE, isCloudProd, isCloudDev, isOss, isCloudEE
+from agenta_backend.migrations.postgres.utils import (
+    check_for_new_migrations,
+    check_if_templates_table_exist,
+)
 
 if isEE() or isCloudProd():
     from agenta_backend.commons.services import templates_manager
@@ -53,10 +55,16 @@ async def lifespan(application: FastAPI, cache=True):
         cache: A boolean value that indicates whether to use the cached data or not.
     """
 
-    await db_engine.init_db()
-    await templates_manager.update_and_sync_templates(cache=cache)
+    if isCloudEE():
+        from agenta_backend.cloud.db.mongo_engine import initialize_mongodb
+
+        await initialize_mongodb()
+
+    await check_for_new_migrations()
+    if await check_if_templates_table_exist():
+        await templates_manager.update_and_sync_templates(cache=cache)
+
     yield
-    await db_engine.close()
 
 
 app = FastAPI(lifespan=lifespan, openapi_tags=open_api_tags_metadata)

agenta-backend/agenta_backend/migrations/postgres/README.md

@@ -0,0 +1,37 @@
+# Migrations with Alembic
+
+Generic single-database configuration with an async dbapi.
+
+## Autogenerate Migrations
+
+One of Alembic's key features is its ability to auto-generate migration scripts. By analyzing the current database state and comparing it with the application's table metadata, Alembic can automatically generate the necessary migration scripts using the `--autogenerate` flag in the alembic revision command.
+
+Note that autogenerate sometimes does not detect all database changes and it is always necessary to manually review (and correct if needed) the candidate migrations that autogenerate produces.
+
+### Making migrations
+
+To make migrations after creating a new table schema or modifying a current column in a table, run the following commands:
+
+```bash
+docker exec -it agenta-backend-1 bash
+```
+
+The above command will run the backend container on bash.
+
+```bash
+alembic -c alembic.oss.ini revision --autogenerate -m "migration message"
+```
+
+The above command will create a script that contains the changes that was made to the database schema. Kindly update "migration message" with a message that is clear to indicate what change was made. Here are some examples:
+
+- added username column in users table
+- renamed template_uri to template_repository_uri
+- etc
+
+### Applying Migrations
+
+```bash
+alembic -c alembic.oss.ini upgrade head
+```
+
+The above command will be used to apply the changes in the script created to the database table(s).

agenta-backend/agenta_backend/migrations/postgres/alembic.oss.ini

@@ -0,0 +1,114 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = /app/agenta_backend/migrations/postgres
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python>=3.9 or backports.zoneinfo library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the
+# "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to migrations/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:migrations/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url = driver://user:pass@localhost/dbname
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

agenta-backend/agenta_backend/migrations/postgres/env.py

@@ -0,0 +1,92 @@
+import asyncio
+from logging.config import fileConfig
+
+from sqlalchemy import pool
+from sqlalchemy.engine import Connection
+from sqlalchemy.ext.asyncio import async_engine_from_config
+
+from alembic import context
+
+from agenta_backend.models.db.postgres_engine import db_engine
+
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+config.set_main_option("sqlalchemy.url", db_engine.postgres_uri)  # type: ignore
+
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+from agenta_backend.models.db_models import Base  # noqa: F403
+
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = Base.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+    Calls to context.execute() here emit the given string to the
+    script output.
+    """
+    url = 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 do_run_migrations(connection: Connection) -> None:
+    context.configure(connection=connection, target_metadata=target_metadata)
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+async def run_async_migrations() -> None:
+    """In this scenario we need to create an Engine
+    and associate a connection with the context.
+    """
+
+    connectable = async_engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    async with connectable.connect() as connection:
+        await connection.run_sync(do_run_migrations)
+
+    await connectable.dispose()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode."""
+
+    asyncio.run(run_async_migrations())
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

agenta-backend/agenta_backend/migrations/postgres/script.py.mako

@@ -0,0 +1,26 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}