feat(sprint2): инфраструктура БД — SQLAlchemy 2.0 async + Alembic

Первый кусок Спринта 2: подключаем SQLite через SQLAlchemy 2.0 (async,
ORM-стиль) и Alembic для миграций. Схема выбрана под будущий рост —
в threads сразу заведены nullable user_id и agent_config_id, чтобы
Спринты 3+ не тащили миграции задним числом.

- requirements.txt: sqlalchemy[asyncio]==2.0.36, aiosqlite==0.20.0,
  alembic==1.14.0.
- config: database_url + sqlite_path (./data/sqlite/app.db).
- db/base.py: DeclarativeBase; db/session.py: async engine,
  async_sessionmaker, get_session — FastAPI-dependency.
- db/models/Thread: id, name, user_id?, agent_config_id?, created_at,
  updated_at; relationship messages с cascade all, delete-orphan.
- db/models/Message: id, thread_id FK CASCADE, role, text, sources_json,
  assembled_prompt, created_at.
- Alembic инициализирован через async-шаблон, env.py доработан:
  sys.path, url из settings, target_metadata = Base.metadata.
- Начальная миграция e7199587be4b применена, таблицы threads/messages
  с индексами на FK и nullable-колонки созданы в data/sqlite/app.db.
- .gitignore: исключаем data/sqlite/ (БД — артефакт, не исходник).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
AR 15 M4
2026-04-23 10:05:10 +05:00
parent 4a5695ed9c
commit 75048bb88e
14 changed files with 384 additions and 0 deletions
+1
View File
@@ -2,6 +2,7 @@ __pycache__/
*.pyc *.pyc
.env .env
data/chroma/ data/chroma/
data/sqlite/
*.egg-info/ *.egg-info/
.venv/ .venv/
.DS_Store .DS_Store
+116
View File
@@ -0,0 +1,116 @@
# 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
# 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
# URL подставляется из config.settings.database_url в migrations/env.py.
sqlalchemy.url = sqlite+aiosqlite:///./data/sqlite/app.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
# Logging configuration
[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
+2
View File
@@ -3,6 +3,8 @@ from pydantic_settings import BaseSettings
class Settings(BaseSettings): class Settings(BaseSettings):
chroma_persist_dir: str = "./data/chroma" chroma_persist_dir: str = "./data/chroma"
sqlite_path: str = "./data/sqlite/app.db"
database_url: str = "sqlite+aiosqlite:///./data/sqlite/app.db"
embedding_model: str = "intfloat/multilingual-e5-large" embedding_model: str = "intfloat/multilingual-e5-large"
deepseek_api_key: str = "" deepseek_api_key: str = ""
deepseek_model: str = "deepseek-chat" deepseek_model: str = "deepseek-chat"
View File
+5
View File
@@ -0,0 +1,5 @@
from sqlalchemy.orm import DeclarativeBase
class Base(DeclarativeBase):
pass
+4
View File
@@ -0,0 +1,4 @@
from db.models.message import Message
from db.models.thread import Thread
__all__ = ["Thread", "Message"]
+30
View File
@@ -0,0 +1,30 @@
from datetime import datetime, timezone
from typing import TYPE_CHECKING
from sqlalchemy import DateTime, ForeignKey, Integer, String, Text
from sqlalchemy.orm import Mapped, mapped_column, relationship
from db.base import Base
if TYPE_CHECKING:
from db.models.thread import Thread
def _utcnow() -> datetime:
return datetime.now(timezone.utc)
class Message(Base):
__tablename__ = "messages"
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
thread_id: Mapped[int] = mapped_column(
ForeignKey("threads.id", ondelete="CASCADE"), nullable=False, index=True
)
role: Mapped[str] = mapped_column(String(20), nullable=False) # "user" | "assistant"
text: Mapped[str] = mapped_column(Text, nullable=False)
sources_json: Mapped[str | None] = mapped_column(Text, nullable=True)
assembled_prompt: Mapped[str | None] = mapped_column(Text, nullable=True)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=_utcnow, nullable=False)
thread: Mapped["Thread"] = relationship(back_populates="messages")
+36
View File
@@ -0,0 +1,36 @@
from datetime import datetime, timezone
from typing import TYPE_CHECKING
from sqlalchemy import DateTime, Integer, String
from sqlalchemy.orm import Mapped, mapped_column, relationship
from db.base import Base
if TYPE_CHECKING:
from db.models.message import Message
def _utcnow() -> datetime:
return datetime.now(timezone.utc)
class Thread(Base):
__tablename__ = "threads"
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
name: Mapped[str] = mapped_column(String(200), nullable=False)
# Зарезервировано под Спринты 3+: мульти-пользователи и мульти-промпты.
user_id: Mapped[int | None] = mapped_column(Integer, nullable=True, index=True)
agent_config_id: Mapped[int | None] = mapped_column(Integer, nullable=True, index=True)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=_utcnow, nullable=False)
updated_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), default=_utcnow, onupdate=_utcnow, nullable=False
)
messages: Mapped[list["Message"]] = relationship(
back_populates="thread",
cascade="all, delete-orphan",
order_by="Message.created_at",
)
+14
View File
@@ -0,0 +1,14 @@
from collections.abc import AsyncIterator
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
from config import settings
engine = create_async_engine(settings.database_url, echo=False, future=True)
SessionLocal = async_sessionmaker(engine, expire_on_commit=False, class_=AsyncSession)
async def get_session() -> AsyncIterator[AsyncSession]:
async with SessionLocal() as session:
yield session
+1
View File
@@ -0,0 +1 @@
Generic single-database configuration with an async dbapi.
+90
View File
@@ -0,0 +1,90 @@
import asyncio
import os
import sys
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
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from config import settings # noqa: E402
from db.base import Base # noqa: E402
from db import models # noqa: F401, E402 — регистрация моделей в Base.metadata
config = context.config
config.set_main_option("sqlalchemy.url", settings.database_url)
if config.config_file_name is not None:
fileConfig(config.config_file_name)
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()
+26
View File
@@ -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"}
@@ -0,0 +1,56 @@
"""initial: threads and messages
Revision ID: e7199587be4b
Revises:
Create Date: 2026-04-23 10:03:23.691401
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision: str = 'e7199587be4b'
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:
# ### commands auto generated by Alembic - please adjust! ###
op.create_table('threads',
sa.Column('id', sa.Integer(), autoincrement=True, nullable=False),
sa.Column('name', sa.String(length=200), nullable=False),
sa.Column('user_id', sa.Integer(), nullable=True),
sa.Column('agent_config_id', sa.Integer(), nullable=True),
sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
sa.Column('updated_at', sa.DateTime(timezone=True), nullable=False),
sa.PrimaryKeyConstraint('id')
)
op.create_index(op.f('ix_threads_agent_config_id'), 'threads', ['agent_config_id'], unique=False)
op.create_index(op.f('ix_threads_user_id'), 'threads', ['user_id'], unique=False)
op.create_table('messages',
sa.Column('id', sa.Integer(), autoincrement=True, nullable=False),
sa.Column('thread_id', sa.Integer(), nullable=False),
sa.Column('role', sa.String(length=20), nullable=False),
sa.Column('text', sa.Text(), nullable=False),
sa.Column('sources_json', sa.Text(), nullable=True),
sa.Column('assembled_prompt', sa.Text(), nullable=True),
sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
sa.ForeignKeyConstraint(['thread_id'], ['threads.id'], ondelete='CASCADE'),
sa.PrimaryKeyConstraint('id')
)
op.create_index(op.f('ix_messages_thread_id'), 'messages', ['thread_id'], unique=False)
# ### end Alembic commands ###
def downgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
op.drop_index(op.f('ix_messages_thread_id'), table_name='messages')
op.drop_table('messages')
op.drop_index(op.f('ix_threads_user_id'), table_name='threads')
op.drop_index(op.f('ix_threads_agent_config_id'), table_name='threads')
op.drop_table('threads')
# ### end Alembic commands ###
+3
View File
@@ -7,3 +7,6 @@ pymupdf==1.25.1
python-docx==1.1.2 python-docx==1.1.2
httpx==0.28.1 httpx==0.28.1
pydantic-settings==2.7.1 pydantic-settings==2.7.1
sqlalchemy[asyncio]==2.0.36
aiosqlite==0.20.0
alembic==1.14.0