feat: Introduce DB migrations

alembic.ini

@@ -0,0 +1,82 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = migrations
+
+# 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.
+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 = newline
+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 = sqlite:///codegate_volume/db/codegate.db
+
+
+[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

migrations/README

@@ -0,0 +1 @@
+Generic single-database configuration.

migrations/env.py

@@ -0,0 +1,72 @@
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+
+# 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
+target_metadata = None
+
+# 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 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,
+    )
+    print(config.config_ini_section)
+    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()

migrations/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"}

migrations/versions/30d0144e1a50_init_db.py

@@ -0,0 +1,83 @@
+"""init db
+
+Revision ID: 30d0144e1a50
+Revises:
+Create Date: 2025-01-15 09:30:00.490697
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "30d0144e1a50"
+down_revision: Union[str, None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # Schema for codegate database using SQLite
+    # Prompts table
+    op.execute(
+        """
+        CREATE TABLE prompts (
+            id TEXT PRIMARY KEY,  -- UUID stored as TEXT
+            timestamp DATETIME NOT NULL,
+            provider TEXT,       -- VARCHAR(255)
+            request TEXT NOT NULL,  -- Record the full request that arrived to the server
+            type TEXT NOT NULL -- VARCHAR(50) (e.g. "fim", "chat")
+        );
+        """
+    )
+    # Outputs table
+    op.execute(
+        """
+        CREATE TABLE outputs (
+            id TEXT PRIMARY KEY,  -- UUID stored as TEXT
+            prompt_id TEXT NOT NULL,
+            timestamp DATETIME NOT NULL,
+            output TEXT NOT NULL,   -- Record the full response. If stream will be a list of objects
+            FOREIGN KEY (prompt_id) REFERENCES prompts(id)
+        );
+        """
+    )
+    # Alerts table
+    op.execute(
+        """
+        CREATE TABLE alerts (
+            id TEXT PRIMARY KEY,  -- UUID stored as TEXT
+            prompt_id TEXT NOT NULL,
+            code_snippet TEXT,
+            trigger_string TEXT, -- VARCHAR(255)
+            trigger_type TEXT NOT NULL,   -- VARCHAR(50)
+            trigger_category TEXT,
+            timestamp DATETIME NOT NULL,
+            FOREIGN KEY (prompt_id) REFERENCES prompts(id)
+        );
+        """
+    )
+    # Settings table
+    op.execute(
+        """
+        CREATE TABLE settings (
+            id TEXT PRIMARY KEY,  -- UUID stored as TEXT
+            ip TEXT,             -- VARCHAR(45)
+            port INTEGER,
+            llm_model TEXT,      -- VARCHAR(255)
+            system_prompt TEXT,
+            other_settings TEXT  -- JSON stored as TEXT
+        );
+        """
+    )
+    # Create indexes for foreign keys and frequently queried columns
+    op.execute("CREATE INDEX idx_outputs_prompt_id ON outputs(prompt_id);")
+    op.execute("CREATE INDEX idx_alerts_prompt_id ON alerts(prompt_id);")
+    op.execute("CREATE INDEX idx_prompts_timestamp ON prompts(timestamp);")
+    op.execute("CREATE INDEX idx_outputs_timestamp ON outputs(timestamp);")
+    op.execute("CREATE INDEX idx_alerts_timestamp ON alerts(timestamp);")
+
+
+def downgrade() -> None:
+    pass

pyproject.toml

@@ -27,6 +27,7 @@ tree-sitter-javascript = ">=0.23.1"
 tree-sitter-python = ">=0.23.6"
 tree-sitter-rust = ">=0.23.2"
 sqlite-vec-sl-tmp = "^0.0.4"
+alembic = ">=1.14.0"
 
 [tool.poetry.group.dev.dependencies]
 pytest = ">=7.4.0"