feat: Introduce database migrations

Introduce database migrations using `alembic` and create a new version.
Add a new Docker service that runs before the gateway and the scheduler
and applies any new migrations.

Signed-off-by: Phoevos Kalemkeris <[email protected]>

Author: phoevos

.github/workflows/docker.yaml

@@ -24,7 +24,7 @@ jobs:
       attestations: write
     strategy:
       matrix:
-        service: [ gateway, scheduler, ripper ]
+        service: [ gateway, scheduler, ripper, migrations ]
         include:
         - service: gateway
           image: cogstacksystems/cogstack-model-gateway
@@ -35,6 +35,9 @@ jobs:
         - service: ripper
           image: cogstacksystems/cogstack-model-gateway-ripper
           dockerfile: ./cogstack_model_gateway/ripper/Dockerfile
+        - service: migrations
+          image: cogstacksystems/cogstack-model-gateway-migrations
+          dockerfile: ./cogstack_model_gateway/migrations/Dockerfile
 
     steps:
       - uses: actions/checkout@v4

cogstack_model_gateway/migrations/Dockerfile

@@ -0,0 +1,30 @@
+FROM ubuntu:24.04
+
+ARG HTTP_PROXY
+ARG HTTPS_PROXY
+ARG NO_PROXY
+
+ENV HTTP_PROXY=$HTTP_PROXY
+ENV HTTPS_PROXY=$HTTPS_PROXY
+ENV NO_PROXY=$NO_PROXY
+ENV http_proxy=$HTTP_PROXY
+ENV https_proxy=$HTTPS_PROXY
+ENV no_proxy=$NO_PROXY
+ENV DEBIAN_FRONTEND=noninteractive
+ENV POETRY_HOME=/etc/poetry
+ENV PATH="${POETRY_HOME}/bin:${PATH}"
+
+RUN apt-get update && apt-get install -y curl python3
+RUN curl -sSL https://install.python-poetry.org | python3 -
+
+WORKDIR /app
+ENV PYTHONPATH=/app
+
+COPY pyproject.toml poetry.lock ./
+RUN poetry install --with migrations --no-root --no-directory
+
+COPY cogstack_model_gateway/common/db.py ./cogstack_model_gateway/common/db.py
+COPY cogstack_model_gateway/common/tasks.py ./cogstack_model_gateway/common/tasks.py
+COPY cogstack_model_gateway/migrations ./cogstack_model_gateway/migrations
+
+CMD ["poetry", "run", "alembic", "-c", "cogstack_model_gateway/migrations/alembic.ini", "upgrade", "head"]

cogstack_model_gateway/migrations/README

@@ -0,0 +1,6 @@
+# CogStack Model Gateway Migrations
+
+A simple service to manage migrations for the CogStack Model Gateway.
+
+A separate [pyproject.toml](./pyproject.toml) file is used to manage Poetry dependencies, in order
+to bypass Poetry limitations regarding local

cogstack_model_gateway/migrations/alembic.ini

@@ -0,0 +1,141 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts.
+# this is typically a path given in POSIX (e.g. forward slashes)
+# format, relative to the token %(here)s which refers to the location of this
+# ini file
+script_location = %(here)s
+
+# 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
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# 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.  for multiple paths, the path separator
+# is defined by "path_separator" below.
+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 and tzdata 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 <script_location>/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 "path_separator"
+# below.
+# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions
+
+# path_separator; This indicates what character is used to split lists of file
+# paths, including version_locations and prepend_sys_path within configparser
+# files such as alembic.ini.
+# The default rendered in new alembic.ini files is "os", which uses os.pathsep
+# to provide os-dependent path splitting.
+#
+# Note that in order to support legacy alembic.ini files, this default does NOT
+# take place if path_separator is not present in alembic.ini.  If this
+# option is omitted entirely, fallback logic is as follows:
+#
+# 1. Parsing of the version_locations option falls back to using the legacy
+#    "version_path_separator" key, which if absent then falls back to the legacy
+#    behavior of splitting on spaces and/or commas.
+# 2. Parsing of the prepend_sys_path option falls back to the legacy
+#    behavior of splitting on spaces, commas, or colons.
+#
+# Valid values for path_separator are:
+#
+# path_separator = :
+# path_separator = ;
+# path_separator = space
+# path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+path_separator = os
+
+# 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
+
+# database URL.  This is consumed by the user-maintained env.py script only.
+# other means of configuring database URLs may be customized within the env.py
+# file.
+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 = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration.  This is also consumed by the user-maintained
+# env.py script only.
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+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

cogstack_model_gateway/migrations/env.py

@@ -0,0 +1,109 @@
+import os
+import sys
+from logging.config import fileConfig
+from pathlib import Path
+
+from alembic import context
+from dotenv import load_dotenv
+from sqlalchemy import engine_from_config, pool
+
+sys.path.append(str(Path(__file__).parent.parent.parent))
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# 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 myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+from cogstack_model_gateway.common.tasks import SQLModel, Task  # noqa: E402, F401
+
+target_metadata = SQLModel.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.
+
+load_dotenv()
+
+user = os.getenv("CMG_DB_USER")
+password = os.getenv("CMG_DB_PASSWORD")
+host = os.getenv("CMG_DB_HOST")
+port = os.getenv("CMG_DB_PORT")
+db_name = os.getenv("CMG_DB_NAME")
+
+missing = [
+    var
+    for var, val in {
+        "CMG_DB_USER": user,
+        "CMG_DB_PASSWORD": password,
+        "CMG_DB_HOST": host,
+        "CMG_DB_PORT": port,
+        "CMG_DB_NAME": db_name,
+    }.items()
+    if not val
+]
+
+if missing:
+    raise RuntimeError(f"Missing required environment variables: {', '.join(missing)}")
+
+config.set_main_option(
+    "sqlalchemy.url", f"postgresql+psycopg2://{user}:{password}@{host}:{port}/{db_name}"
+)
+
+
+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 run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(connection=connection, target_metadata=target_metadata)
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

cogstack_model_gateway/migrations/script.py.mako

@@ -0,0 +1,30 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+import sqlmodel
+from alembic import op
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: str | Sequence[str] | None = ${repr(down_revision)}
+branch_labels: str | Sequence[str] | None = ${repr(branch_labels)}
+depends_on: str | Sequence[str] | None = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}

cogstack_model_gateway/migrations/versions/1859866dbf86_extend_task_with_request_info_and_.py

@@ -0,0 +1,45 @@
+"""Extend Task with request info and timestamps
+
+Revision ID: 1859866dbf86
+Revises:
+Create Date: 2025-06-19 17:29:59.695124
+
+"""
+
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+import sqlmodel
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "1859866dbf86"
+down_revision: str | Sequence[str] | None = None
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    op.add_column("task", sa.Column("model", sqlmodel.sql.sqltypes.AutoString(), nullable=True))
+    op.add_column("task", sa.Column("type", sqlmodel.sql.sqltypes.AutoString(), nullable=True))
+    op.add_column("task", sa.Column("source", sqlmodel.sql.sqltypes.AutoString(), nullable=True))
+    op.add_column(
+        "task", sa.Column("created_at", sqlmodel.sql.sqltypes.AutoString(), nullable=True)
+    )
+    op.add_column(
+        "task", sa.Column("started_at", sqlmodel.sql.sqltypes.AutoString(), nullable=True)
+    )
+    op.add_column(
+        "task", sa.Column("finished_at", sqlmodel.sql.sqltypes.AutoString(), nullable=True)
+    )
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    op.drop_column("task", "finished_at")
+    op.drop_column("task", "started_at")
+    op.drop_column("task", "created_at")
+    op.drop_column("task", "source")
+    op.drop_column("task", "type")
+    op.drop_column("task", "model")