feat(persistence): backfill Step 1 — workspace per user without default

For each user with NULL default_workspace_id, generate a base slug
from the email, walk past collisions/blacklist via next_available_slug,
create the workspace + owner membership, and set default_workspace_id.
Idempotent: candidates list is filtered by IS NULL, so re-running on a
populated DB is a no-op. 3 new unit tests (creation, idempotence,
blacklist-walker behaviour).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
1445043649
2026-05-13 09:09:16 +08:00
parent ad322543d0
commit e6bb220979
2 changed files with 173 additions and 4 deletions
+49 -4
View File
@@ -30,8 +30,15 @@ import asyncio
import logging
from typing import Any
from sqlalchemy import select, update
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker
from app.gateway.auth.workspace_slug import auto_slug_from_email, next_available_slug
from deerflow.persistence.user.model import UserRow
from deerflow.persistence.workspace import WorkspaceRepository
from deerflow.persistence.workspace.sql import SLUG_BLACKLIST
from deerflow.persistence.workspace_membership import WorkspaceMembershipRepository
logger = logging.getLogger(__name__)
# The legacy workspace anchor. Stage 0 LOCK'd UUID — chosen as the standard
@@ -51,11 +58,49 @@ async def _step1_create_workspaces_for_users(
) -> int:
"""Create one workspace + owner membership for each user missing default_workspace_id.
Filled in by T5.5.
Returns the count of users a workspace was created for. Idempotent —
users that already have ``default_workspace_id`` are skipped so a
crashed run can resume safely.
"""
_ = session_factory # silenced until T5.5
_ = dry_run
return 0
async with session_factory() as session:
result = await session.execute(select(UserRow.id, UserRow.email).where(UserRow.default_workspace_id.is_(None)))
candidates = [(row.id, row.email) for row in result]
if not candidates:
return 0
ws_repo = WorkspaceRepository(session_factory)
m_repo = WorkspaceMembershipRepository(session_factory)
created = 0
for user_id, email in candidates:
base_slug = auto_slug_from_email(email)
async def slug_exists(s: str) -> bool:
if s in SLUG_BLACKLIST:
return True
return (await ws_repo.get_by_slug(s)) is not None
unique_slug = await next_available_slug(base_slug, exists_check=slug_exists)
if dry_run:
logger.info("WOULD create workspace for user=%s email=%s slug=%s", user_id, email, unique_slug)
created += 1
continue
display_local = email.split("@", 1)[0]
workspace = await ws_repo.create(
name=f"{display_local}'s Workspace"[:64],
slug=unique_slug,
owner_id=user_id,
)
await m_repo.add(workspace_id=workspace["id"], user_id=user_id, role="owner")
async with session_factory() as session:
await session.execute(update(UserRow).where(UserRow.id == user_id).values(default_workspace_id=workspace["id"]))
await session.commit()
created += 1
logger.info("Created workspace %s (slug=%s) for user=%s", workspace["id"], unique_slug, user_id)
return created
async def _step2_update_table_from_users(
+124
View File
@@ -0,0 +1,124 @@
"""Tests for ``scripts/backfill_workspace_id.py`` (Stage 0 PR5).
Each step in the three-step backfill is exercised in isolation against
a SQLite-on-disk database. The script wires in ``app.gateway.auth.workspace_slug``,
so we get the same slug semantics that the registration flow uses.
Pattern mirrors :mod:`test_workspace_repo`: ``init_engine`` + per-test
tmp_path, with explicit ``close_engine`` teardown so the singleton
session factory does not leak across tests.
"""
from __future__ import annotations
import uuid
import pytest
from sqlalchemy import select
from deerflow.persistence.user.model import UserRow
from deerflow.persistence.workspace.model import WorkspaceRow
from deerflow.persistence.workspace_membership.model import WorkspaceMembershipRow
from scripts.backfill_workspace_id import _step1_create_workspaces_for_users
pytestmark = pytest.mark.anyio
@pytest.fixture
def anyio_backend() -> str:
return "asyncio"
async def _init_engine(tmp_path):
from deerflow.persistence.engine import get_session_factory, init_engine
url = f"sqlite+aiosqlite:///{tmp_path / 'test.db'}"
await init_engine("sqlite", url=url, sqlite_dir=str(tmp_path))
return get_session_factory()
async def _close():
from deerflow.persistence.engine import close_engine
await close_engine()
async def _seed_user(sf, *, email: str, default_workspace_id: str | None = None) -> str:
user_id = str(uuid.uuid4())
async with sf() as session:
session.add(UserRow(id=user_id, email=email, default_workspace_id=default_workspace_id))
await session.commit()
return user_id
# ---------------------------------------------------------------------------
# Step 1: per-user workspace creation
# ---------------------------------------------------------------------------
async def test_creates_workspace_per_user_without_default(tmp_path):
"""Each user with NULL default_workspace_id gets a workspace + owner membership."""
sf = await _init_engine(tmp_path)
try:
u_alice = await _seed_user(sf, email="alice@example.com")
u_bob = await _seed_user(sf, email="bob+spam@example.com")
count = await _step1_create_workspaces_for_users(sf, dry_run=False)
assert count == 2
async with sf() as session:
workspaces = (await session.execute(select(WorkspaceRow))).scalars().all()
memberships = (await session.execute(select(WorkspaceMembershipRow))).scalars().all()
users = {u.id: u for u in (await session.execute(select(UserRow))).scalars().all()}
# 2 workspaces, each with exactly one owner membership matching its user.
assert len(workspaces) == 2
assert len(memberships) == 2
owners_by_ws = {m.workspace_id: m.user_id for m in memberships if m.role == "owner"}
assert {m.role for m in memberships} == {"owner"}
for ws in workspaces:
assert owners_by_ws[ws.id] == ws.owner_id
assert users[ws.owner_id].default_workspace_id == ws.id
# Slug semantics: alice@ → "alice", bob+spam@ → "bob-spam".
slugs = {ws.slug for ws in workspaces}
assert slugs == {"alice", "bob-spam"}
_ = u_alice, u_bob # captured for readability
finally:
await _close()
async def test_step1_is_idempotent(tmp_path):
"""Second run is a no-op when every user already has a default_workspace_id."""
sf = await _init_engine(tmp_path)
try:
await _seed_user(sf, email="carol@example.com")
first = await _step1_create_workspaces_for_users(sf, dry_run=False)
assert first == 1
# Re-running picks up the just-populated default_workspace_id, so the
# candidate set is empty.
second = await _step1_create_workspaces_for_users(sf, dry_run=False)
assert second == 0
async with sf() as session:
ws_count = len((await session.execute(select(WorkspaceRow))).scalars().all())
mem_count = len((await session.execute(select(WorkspaceMembershipRow))).scalars().all())
assert ws_count == 1
assert mem_count == 1
finally:
await _close()
async def test_step1_skips_blacklisted_base_slug(tmp_path):
"""A user with email like admin@... gets bumped past the slug blacklist via the walker."""
sf = await _init_engine(tmp_path)
try:
await _seed_user(sf, email="admin@example.com")
await _step1_create_workspaces_for_users(sf, dry_run=False)
async with sf() as session:
ws = (await session.execute(select(WorkspaceRow))).scalar_one()
# The walker treats "admin" as taken (blacklisted), so it falls
# through to "admin-2" — the same behaviour the registration flow
# uses for reserved slugs.
assert ws.slug == "admin-2"
finally:
await _close()