Replace Alembic with plain SQL schema

- Fix scalar_first() bug in persistent_conversation.py (use scalars().first())
- Add schema.sql with all 7 tables (users, user_preferences, user_facts, guilds, guild_members, conversations, messages)
- Update database.py to run schema.sql on startup
- Remove Alembic directory and configuration
- Remove alembic from requirements.txt
This commit is contained in:
2026-01-12 18:30:55 +01:00
parent 707410e2ce
commit 94abdca2f7
8 changed files with 139 additions and 389 deletions

View File

@@ -1,71 +0,0 @@
# Alembic Configuration File
[alembic]
# path to migration scripts
script_location = alembic
# template used to generate migration file names
file_template = %%(year)d%%(month).2d%%(day).2d_%%(hour).2d%%(minute).2d_%%(rev)s_%%(slug)s
# sys.path path prepend for the migration environment
prepend_sys_path = src
# timezone to use when rendering the date within the migration file
timezone = UTC
# 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
revision_environment = false
# set to 'true' to allow .pyc and .pyo files without a source .py file
sourceless = false
# version number format
version_num_width = 4
# version path separator
version_path_separator = os
# output encoding used when revision files are written
output_encoding = utf-8
# Database URL - will be overridden by env.py from settings
sqlalchemy.url = driver://user:pass@localhost/dbname
[post_write_hooks]
[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

View File

@@ -1,86 +0,0 @@
"""Alembic migration environment configuration."""
import asyncio
from logging.config import fileConfig
from sqlalchemy import pool
from sqlalchemy.ext.asyncio import async_engine_from_config
from alembic import context
from daemon_boyfriend.config import settings
from daemon_boyfriend.models import Base
# this is the Alembic Config object
config = context.config
# Interpret the config file for Python logging
if config.config_file_name is not None:
fileConfig(config.config_file_name)
# Model metadata for autogenerate support
target_metadata = Base.metadata
def get_url() -> str:
"""Get database URL from settings."""
url = settings.database_url
if not url:
raise ValueError("DATABASE_URL must be set for migrations")
return url
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 = get_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) -> None:
"""Run migrations with the given connection."""
context.configure(connection=connection, target_metadata=target_metadata)
with context.begin_transaction():
context.run_migrations()
async def run_async_migrations() -> None:
"""Run migrations in async mode."""
configuration = config.get_section(config.config_ini_section, {})
configuration["sqlalchemy.url"] = get_url()
connectable = async_engine_from_config(
configuration,
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()

View File

@@ -1,26 +0,0 @@
"""${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"}

View File

@@ -1,200 +0,0 @@
"""Initial schema with users, conversations, messages, and guilds.
Revision ID: 0001
Revises:
Create Date: 2025-01-12
"""
from typing import Sequence, Union
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql
from alembic import op
# revision identifiers, used by Alembic.
revision: str = "0001"
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:
# Users table
op.create_table(
"users",
sa.Column("id", sa.BigInteger(), autoincrement=True, nullable=False),
sa.Column("discord_id", sa.BigInteger(), nullable=False),
sa.Column("discord_username", sa.String(255), nullable=False),
sa.Column("discord_display_name", sa.String(255), nullable=True),
sa.Column("custom_name", sa.String(255), nullable=True),
sa.Column("first_seen_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("last_seen_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("is_active", sa.Boolean(), nullable=False, server_default="true"),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.PrimaryKeyConstraint("id", name=op.f("pk_users")),
sa.UniqueConstraint("discord_id", name=op.f("uq_users_discord_id")),
)
op.create_index(op.f("ix_users_discord_id"), "users", ["discord_id"])
op.create_index(op.f("ix_users_last_seen_at"), "users", ["last_seen_at"])
# User preferences table
op.create_table(
"user_preferences",
sa.Column("id", sa.BigInteger(), autoincrement=True, nullable=False),
sa.Column("user_id", sa.BigInteger(), nullable=False),
sa.Column("preference_key", sa.String(100), nullable=False),
sa.Column("preference_value", sa.Text(), nullable=True),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.ForeignKeyConstraint(
["user_id"],
["users.id"],
name=op.f("fk_user_preferences_user_id_users"),
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint("id", name=op.f("pk_user_preferences")),
sa.UniqueConstraint("user_id", "preference_key", name="uq_user_preferences_user_key"),
)
op.create_index(op.f("ix_user_preferences_user_id"), "user_preferences", ["user_id"])
# User facts table
op.create_table(
"user_facts",
sa.Column("id", sa.BigInteger(), autoincrement=True, nullable=False),
sa.Column("user_id", sa.BigInteger(), nullable=False),
sa.Column("fact_type", sa.String(50), nullable=False),
sa.Column("fact_content", sa.Text(), nullable=False),
sa.Column("confidence", sa.Float(), server_default="1.0"),
sa.Column("source", sa.String(50), server_default="conversation"),
sa.Column("is_active", sa.Boolean(), nullable=False, server_default="true"),
sa.Column("learned_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("last_referenced_at", sa.DateTime(timezone=True), nullable=True),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.ForeignKeyConstraint(
["user_id"],
["users.id"],
name=op.f("fk_user_facts_user_id_users"),
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint("id", name=op.f("pk_user_facts")),
)
op.create_index(op.f("ix_user_facts_user_id"), "user_facts", ["user_id"])
op.create_index(op.f("ix_user_facts_fact_type"), "user_facts", ["fact_type"])
op.create_index(op.f("ix_user_facts_is_active"), "user_facts", ["is_active"])
# Guilds table
op.create_table(
"guilds",
sa.Column("id", sa.BigInteger(), autoincrement=True, nullable=False),
sa.Column("discord_id", sa.BigInteger(), nullable=False),
sa.Column("name", sa.String(255), nullable=False),
sa.Column("joined_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("is_active", sa.Boolean(), nullable=False, server_default="true"),
sa.Column("settings", postgresql.JSONB(), server_default="{}"),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.PrimaryKeyConstraint("id", name=op.f("pk_guilds")),
sa.UniqueConstraint("discord_id", name=op.f("uq_guilds_discord_id")),
)
op.create_index(op.f("ix_guilds_discord_id"), "guilds", ["discord_id"])
# Guild members table
op.create_table(
"guild_members",
sa.Column("id", sa.BigInteger(), autoincrement=True, nullable=False),
sa.Column("guild_id", sa.BigInteger(), nullable=False),
sa.Column("user_id", sa.BigInteger(), nullable=False),
sa.Column("guild_nickname", sa.String(255), nullable=True),
sa.Column("roles", postgresql.ARRAY(sa.Text()), nullable=True),
sa.Column("joined_guild_at", sa.DateTime(timezone=True), nullable=True),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.ForeignKeyConstraint(
["guild_id"],
["guilds.id"],
name=op.f("fk_guild_members_guild_id_guilds"),
ondelete="CASCADE",
),
sa.ForeignKeyConstraint(
["user_id"],
["users.id"],
name=op.f("fk_guild_members_user_id_users"),
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint("id", name=op.f("pk_guild_members")),
sa.UniqueConstraint("guild_id", "user_id", name="uq_guild_members_guild_user"),
)
op.create_index(op.f("ix_guild_members_guild_id"), "guild_members", ["guild_id"])
op.create_index(op.f("ix_guild_members_user_id"), "guild_members", ["user_id"])
# Conversations table
op.create_table(
"conversations",
sa.Column("id", sa.BigInteger(), autoincrement=True, nullable=False),
sa.Column("user_id", sa.BigInteger(), nullable=False),
sa.Column("guild_id", sa.BigInteger(), nullable=True),
sa.Column("channel_id", sa.BigInteger(), nullable=True),
sa.Column("started_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("last_message_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("message_count", sa.Integer(), server_default="0"),
sa.Column("is_active", sa.Boolean(), nullable=False, server_default="true"),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.ForeignKeyConstraint(
["user_id"],
["users.id"],
name=op.f("fk_conversations_user_id_users"),
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint("id", name=op.f("pk_conversations")),
)
op.create_index(op.f("ix_conversations_user_id"), "conversations", ["user_id"])
op.create_index(op.f("ix_conversations_channel_id"), "conversations", ["channel_id"])
op.create_index(op.f("ix_conversations_last_message_at"), "conversations", ["last_message_at"])
op.create_index(op.f("ix_conversations_is_active"), "conversations", ["is_active"])
# Messages table
op.create_table(
"messages",
sa.Column("id", sa.BigInteger(), autoincrement=True, nullable=False),
sa.Column("conversation_id", sa.BigInteger(), nullable=False),
sa.Column("user_id", sa.BigInteger(), nullable=False),
sa.Column("discord_message_id", sa.BigInteger(), nullable=True),
sa.Column("role", sa.String(20), nullable=False),
sa.Column("content", sa.Text(), nullable=False),
sa.Column("has_images", sa.Boolean(), nullable=False, server_default="false"),
sa.Column("image_urls", postgresql.ARRAY(sa.Text()), nullable=True),
sa.Column("token_count", sa.Integer(), nullable=True),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.ForeignKeyConstraint(
["conversation_id"],
["conversations.id"],
name=op.f("fk_messages_conversation_id_conversations"),
ondelete="CASCADE",
),
sa.ForeignKeyConstraint(
["user_id"],
["users.id"],
name=op.f("fk_messages_user_id_users"),
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint("id", name=op.f("pk_messages")),
)
op.create_index(op.f("ix_messages_conversation_id"), "messages", ["conversation_id"])
op.create_index(op.f("ix_messages_user_id"), "messages", ["user_id"])
op.create_index(op.f("ix_messages_created_at"), "messages", ["created_at"])
def downgrade() -> None:
op.drop_table("messages")
op.drop_table("conversations")
op.drop_table("guild_members")
op.drop_table("guilds")
op.drop_table("user_facts")
op.drop_table("user_preferences")
op.drop_table("users")

View File

@@ -17,4 +17,3 @@ python-dotenv>=1.0.0
# Database
asyncpg>=0.29.0
sqlalchemy[asyncio]>=2.0.0
alembic>=1.13.0

119
schema.sql Normal file
View File

@@ -0,0 +1,119 @@
-- Daemon Boyfriend Database Schema
-- Run with: psql -U postgres -d daemon_boyfriend -f schema.sql
-- Users table
CREATE TABLE IF NOT EXISTS users (
id BIGSERIAL PRIMARY KEY,
discord_id BIGINT NOT NULL UNIQUE,
discord_username VARCHAR(255) NOT NULL,
discord_display_name VARCHAR(255),
custom_name VARCHAR(255),
first_seen_at TIMESTAMPTZ DEFAULT NOW(),
last_seen_at TIMESTAMPTZ DEFAULT NOW(),
is_active BOOLEAN NOT NULL DEFAULT TRUE,
created_at TIMESTAMPTZ DEFAULT NOW(),
updated_at TIMESTAMPTZ DEFAULT NOW()
);
CREATE INDEX IF NOT EXISTS ix_users_discord_id ON users(discord_id);
CREATE INDEX IF NOT EXISTS ix_users_last_seen_at ON users(last_seen_at);
-- User preferences table
CREATE TABLE IF NOT EXISTS user_preferences (
id BIGSERIAL PRIMARY KEY,
user_id BIGINT NOT NULL REFERENCES users(id) ON DELETE CASCADE,
preference_key VARCHAR(100) NOT NULL,
preference_value TEXT,
created_at TIMESTAMPTZ DEFAULT NOW(),
updated_at TIMESTAMPTZ DEFAULT NOW(),
UNIQUE(user_id, preference_key)
);
CREATE INDEX IF NOT EXISTS ix_user_preferences_user_id ON user_preferences(user_id);
-- User facts table
CREATE TABLE IF NOT EXISTS user_facts (
id BIGSERIAL PRIMARY KEY,
user_id BIGINT NOT NULL REFERENCES users(id) ON DELETE CASCADE,
fact_type VARCHAR(50) NOT NULL,
fact_content TEXT NOT NULL,
confidence FLOAT DEFAULT 1.0,
source VARCHAR(50) DEFAULT 'conversation',
is_active BOOLEAN NOT NULL DEFAULT TRUE,
learned_at TIMESTAMPTZ DEFAULT NOW(),
last_referenced_at TIMESTAMPTZ,
created_at TIMESTAMPTZ DEFAULT NOW(),
updated_at TIMESTAMPTZ DEFAULT NOW()
);
CREATE INDEX IF NOT EXISTS ix_user_facts_user_id ON user_facts(user_id);
CREATE INDEX IF NOT EXISTS ix_user_facts_fact_type ON user_facts(fact_type);
CREATE INDEX IF NOT EXISTS ix_user_facts_is_active ON user_facts(is_active);
-- Guilds table
CREATE TABLE IF NOT EXISTS guilds (
id BIGSERIAL PRIMARY KEY,
discord_id BIGINT NOT NULL UNIQUE,
name VARCHAR(255) NOT NULL,
joined_at TIMESTAMPTZ DEFAULT NOW(),
is_active BOOLEAN NOT NULL DEFAULT TRUE,
settings JSONB DEFAULT '{}',
created_at TIMESTAMPTZ DEFAULT NOW(),
updated_at TIMESTAMPTZ DEFAULT NOW()
);
CREATE INDEX IF NOT EXISTS ix_guilds_discord_id ON guilds(discord_id);
-- Guild members table
CREATE TABLE IF NOT EXISTS guild_members (
id BIGSERIAL PRIMARY KEY,
guild_id BIGINT NOT NULL REFERENCES guilds(id) ON DELETE CASCADE,
user_id BIGINT NOT NULL REFERENCES users(id) ON DELETE CASCADE,
guild_nickname VARCHAR(255),
roles TEXT[],
joined_guild_at TIMESTAMPTZ,
created_at TIMESTAMPTZ DEFAULT NOW(),
updated_at TIMESTAMPTZ DEFAULT NOW(),
UNIQUE(guild_id, user_id)
);
CREATE INDEX IF NOT EXISTS ix_guild_members_guild_id ON guild_members(guild_id);
CREATE INDEX IF NOT EXISTS ix_guild_members_user_id ON guild_members(user_id);
-- Conversations table
CREATE TABLE IF NOT EXISTS conversations (
id BIGSERIAL PRIMARY KEY,
user_id BIGINT NOT NULL REFERENCES users(id) ON DELETE CASCADE,
guild_id BIGINT,
channel_id BIGINT,
started_at TIMESTAMPTZ DEFAULT NOW(),
last_message_at TIMESTAMPTZ DEFAULT NOW(),
message_count INTEGER DEFAULT 0,
is_active BOOLEAN NOT NULL DEFAULT TRUE,
created_at TIMESTAMPTZ DEFAULT NOW(),
updated_at TIMESTAMPTZ DEFAULT NOW()
);
CREATE INDEX IF NOT EXISTS ix_conversations_user_id ON conversations(user_id);
CREATE INDEX IF NOT EXISTS ix_conversations_channel_id ON conversations(channel_id);
CREATE INDEX IF NOT EXISTS ix_conversations_last_message_at ON conversations(last_message_at);
CREATE INDEX IF NOT EXISTS ix_conversations_is_active ON conversations(is_active);
-- Messages table
CREATE TABLE IF NOT EXISTS messages (
id BIGSERIAL PRIMARY KEY,
conversation_id BIGINT NOT NULL REFERENCES conversations(id) ON DELETE CASCADE,
user_id BIGINT NOT NULL REFERENCES users(id) ON DELETE CASCADE,
discord_message_id BIGINT,
role VARCHAR(20) NOT NULL,
content TEXT NOT NULL,
has_images BOOLEAN NOT NULL DEFAULT FALSE,
image_urls TEXT[],
token_count INTEGER,
created_at TIMESTAMPTZ DEFAULT NOW(),
updated_at TIMESTAMPTZ DEFAULT NOW()
);
CREATE INDEX IF NOT EXISTS ix_messages_conversation_id ON messages(conversation_id);
CREATE INDEX IF NOT EXISTS ix_messages_user_id ON messages(user_id);
CREATE INDEX IF NOT EXISTS ix_messages_created_at ON messages(created_at);

View File

@@ -2,15 +2,19 @@
import logging
from contextlib import asynccontextmanager
from pathlib import Path
from typing import AsyncGenerator
from sqlalchemy import text
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
from daemon_boyfriend.config import settings
from daemon_boyfriend.models.base import Base
logger = logging.getLogger(__name__)
# Path to schema.sql (project root)
SCHEMA_PATH = Path(__file__).parent.parent.parent.parent / "schema.sql"
class DatabaseService:
"""Manages database connections and sessions."""
@@ -62,13 +66,24 @@ class DatabaseService:
logger.info("Database connection closed")
async def create_tables(self) -> None:
"""Create all tables (for development/testing)."""
"""Create all tables from schema.sql."""
if not self._engine:
raise RuntimeError("Database not initialized")
if not SCHEMA_PATH.exists():
logger.warning(f"schema.sql not found at {SCHEMA_PATH}, skipping table creation")
return
schema_sql = SCHEMA_PATH.read_text()
async with self._engine.begin() as conn:
await conn.run_sync(Base.metadata.create_all)
logger.info("Database tables created")
# Execute each statement separately (PostgreSQL doesn't like multiple in one)
for statement in schema_sql.split(";"):
statement = statement.strip()
if statement and not statement.startswith("--"):
await conn.execute(text(statement))
logger.info("Database tables created from schema.sql")
@asynccontextmanager
async def session(self) -> AsyncGenerator[AsyncSession, None]:

View File

@@ -52,7 +52,7 @@ class PersistentConversationManager:
stmt = stmt.order_by(Conversation.last_message_at.desc())
result = await self._session.execute(stmt)
conversation = result.scalar_first()
conversation = result.scalars().first()
if conversation:
logger.debug(