refactor(auth): migrate user repository to SQLAlchemy ORM

Move the users table into the shared persistence engine so auth
matches the pattern of threads_meta, runs, run_events, and feedback —
one engine, one session factory, one schema init codepath.

New files
---------
- persistence/user/__init__.py, persistence/user/model.py: UserRow
  ORM class with partial unique index on (oauth_provider, oauth_id)
- Registered in persistence/models/__init__.py so
  Base.metadata.create_all() picks it up

Modified
--------
- auth/repositories/sqlite.py: rewritten as async SQLAlchemy,
  identical constructor pattern to the other four repositories
  (def __init__(self, session_factory) + self._sf = session_factory)
- auth/config.py: drop users_db_path field — storage is configured
  through config.database like every other table
- deps.py/get_local_provider: construct SQLiteUserRepository with
  the shared session factory, fail fast if engine is not initialised
- tests/test_auth.py: rewrite test_sqlite_round_trip_new_fields to
  use the shared engine (init_engine + close_engine in a tempdir)
- tests/test_auth_type_system.py: add per-test autouse fixture that
  spins up a scratch engine and resets deps._cached_* singletons
This commit is contained in:
greatmengqi
2026-04-08 11:49:24 +08:00
parent f0b065bef6
commit ceeccabc98
8 changed files with 254 additions and 216 deletions
@@ -7,6 +7,7 @@ The actual ORM classes have moved to entity-specific subpackages:
- ``deerflow.persistence.thread_meta``
- ``deerflow.persistence.run``
- ``deerflow.persistence.feedback``
- ``deerflow.persistence.user``
``RunEventRow`` remains in ``deerflow.persistence.models.run_event`` because
its storage implementation lives in ``deerflow.runtime.events.store.db`` and
@@ -17,5 +18,6 @@ from deerflow.persistence.feedback.model import FeedbackRow
from deerflow.persistence.models.run_event import RunEventRow
from deerflow.persistence.run.model import RunRow
from deerflow.persistence.thread_meta.model import ThreadMetaRow
from deerflow.persistence.user.model import UserRow
__all__ = ["FeedbackRow", "RunEventRow", "RunRow", "ThreadMetaRow"]
__all__ = ["FeedbackRow", "RunEventRow", "RunRow", "ThreadMetaRow", "UserRow"]
@@ -0,0 +1,12 @@
"""User storage subpackage.
Holds the ORM model for the ``users`` table. The concrete repository
implementation (``SQLiteUserRepository``) lives in the app layer
(``app.gateway.auth.repositories.sqlite``) because it converts
between the ORM row and the auth module's pydantic ``User`` class.
This keeps the harness package free of any dependency on app code.
"""
from deerflow.persistence.user.model import UserRow
__all__ = ["UserRow"]
@@ -0,0 +1,59 @@
"""ORM model for the users table.
Lives in the harness persistence package so it is picked up by
``Base.metadata.create_all()`` alongside ``threads_meta``, ``runs``,
``run_events``, and ``feedback``. Using the shared engine means:
- One SQLite/Postgres database, one connection pool
- One schema initialisation codepath
- Consistent async sessions across auth and persistence reads
"""
from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import Boolean, DateTime, Index, String, text
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
class UserRow(Base):
__tablename__ = "users"
# UUIDs are stored as 36-char strings for cross-backend portability.
id: Mapped[str] = mapped_column(String(36), primary_key=True)
email: Mapped[str] = mapped_column(String(320), unique=True, nullable=False, index=True)
password_hash: Mapped[str | None] = mapped_column(String(128), nullable=True)
# "admin" | "user" — kept as plain string to avoid ALTER TABLE pain
# when new roles are introduced.
system_role: Mapped[str] = mapped_column(String(16), nullable=False, default="user")
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
nullable=False,
default=lambda: datetime.now(UTC),
)
# OAuth linkage (optional). A partial unique index enforces one
# account per (provider, oauth_id) pair, leaving NULL/NULL rows
# unconstrained so plain password accounts can coexist.
oauth_provider: Mapped[str | None] = mapped_column(String(32), nullable=True)
oauth_id: Mapped[str | None] = mapped_column(String(128), nullable=True)
# Auth lifecycle flags
needs_setup: Mapped[bool] = mapped_column(Boolean, nullable=False, default=False)
token_version: Mapped[int] = mapped_column(nullable=False, default=0)
__table_args__ = (
Index(
"idx_users_oauth_identity",
"oauth_provider",
"oauth_id",
unique=True,
sqlite_where=text("oauth_provider IS NOT NULL AND oauth_id IS NOT NULL"),
),
)