Merge pull request #593 from stacklok/db-migrations

feat: Introduce DB migrations

alembic.ini

@@ -0,0 +1,19 @@
+# Database configuration.
+# See the full list of options at:
+# https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = migrations
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# version path separator; is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+version_path_separator = os  # Use os.pathsep.
+
+# DB connection string
+sqlalchemy.url = sqlite:///codegate_volume/db/codegate.db

migrations/README

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

migrations/env.py

@@ -0,0 +1,67 @@
+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
+
+# 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"