Files
deer-flow/backend/packages/harness/deerflow/persistence/thread_meta/sql.py
T
greatmengqi 3aa3e37532 test(auth): port AUTH test plan docs + lint/format pass
- Port backend/docs/AUTH_TEST_PLAN.md and AUTH_UPGRADE.md from PR #1728
- Rename metadata.user_id → metadata.owner_id in AUTH_TEST_PLAN.md
  (4 occurrences from the original PR doc)
- ruff auto-fix UP037 in sentinel type annotations: drop quotes around
  "str | None | _AutoSentinel" now that from __future__ import
  annotations makes them implicit string forms
- ruff format: 2 files (app/gateway/app.py, runtime/user_context.py)

Note on test coverage additions:
- conftest.py autouse fixture was already added in commit 4 (had to
  be co-located with the repository changes to keep pre-existing
  persistence tests passing)
- cross-user isolation E2E tests (test_owner_isolation.py) deferred
  — enforcement is already proven by the 98-test repository suite
  via the autouse fixture + explicit _AUTO sentinel exercises
- New test cases (TC-API-17..20, TC-ATK-13, TC-MIG-01..07) listed
  in AUTH_TEST_PLAN.md are deferred to a follow-up PR — they are
  manual-QA test cases rather than pytest code, and the spec-level
  coverage is already met by test_user_context.py + the 98-test
  repository suite.

Final test results:
- Auth suite (test_auth*, test_langgraph_auth, test_ensure_admin,
  test_user_context): 186 passed
- Persistence suite (test_run_event_store, test_run_repository,
  test_thread_meta_repo, test_feedback): 98 passed
- Lint: ruff check + ruff format both clean
2026-04-08 11:12:30 +08:00

208 lines
8.3 KiB
Python

"""SQLAlchemy-backed thread metadata repository."""
from __future__ import annotations
from datetime import UTC, datetime
from typing import Any
from sqlalchemy import select, update
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker
from deerflow.persistence.thread_meta.base import ThreadMetaStore
from deerflow.persistence.thread_meta.model import ThreadMetaRow
from deerflow.runtime.user_context import AUTO, _AutoSentinel, resolve_owner_id
class ThreadMetaRepository(ThreadMetaStore):
def __init__(self, session_factory: async_sessionmaker[AsyncSession]) -> None:
self._sf = session_factory
@staticmethod
def _row_to_dict(row: ThreadMetaRow) -> dict[str, Any]:
d = row.to_dict()
d["metadata"] = d.pop("metadata_json", {})
for key in ("created_at", "updated_at"):
val = d.get(key)
if isinstance(val, datetime):
d[key] = val.isoformat()
return d
async def create(
self,
thread_id: str,
*,
assistant_id: str | None = None,
owner_id: str | None | _AutoSentinel = AUTO,
display_name: str | None = None,
metadata: dict | None = None,
) -> dict:
# Auto-resolve owner_id from contextvar when AUTO; explicit None
# creates an orphan row (used by migration scripts).
resolved_owner_id = resolve_owner_id(owner_id, method_name="ThreadMetaRepository.create")
now = datetime.now(UTC)
row = ThreadMetaRow(
thread_id=thread_id,
assistant_id=assistant_id,
owner_id=resolved_owner_id,
display_name=display_name,
metadata_json=metadata or {},
created_at=now,
updated_at=now,
)
async with self._sf() as session:
session.add(row)
await session.commit()
await session.refresh(row)
return self._row_to_dict(row)
async def get(
self,
thread_id: str,
*,
owner_id: str | None | _AutoSentinel = AUTO,
) -> dict | None:
resolved_owner_id = resolve_owner_id(owner_id, method_name="ThreadMetaRepository.get")
async with self._sf() as session:
row = await session.get(ThreadMetaRow, thread_id)
if row is None:
return None
# Enforce owner filter unless explicitly bypassed (owner_id=None).
if resolved_owner_id is not None and row.owner_id != resolved_owner_id:
return None
return self._row_to_dict(row)
async def list_by_owner(self, owner_id: str, *, limit: int = 100, offset: int = 0) -> list[dict]:
stmt = select(ThreadMetaRow).where(ThreadMetaRow.owner_id == owner_id).order_by(ThreadMetaRow.updated_at.desc()).limit(limit).offset(offset)
async with self._sf() as session:
result = await session.execute(stmt)
return [self._row_to_dict(r) for r in result.scalars()]
async def check_access(self, thread_id: str, owner_id: str) -> bool:
"""Check if owner_id has access to thread_id.
Returns True if: row doesn't exist (untracked thread), owner_id
is None on the row (shared thread), or owner_id matches.
"""
async with self._sf() as session:
row = await session.get(ThreadMetaRow, thread_id)
if row is None:
return True
if row.owner_id is None:
return True
return row.owner_id == owner_id
async def search(
self,
*,
metadata: dict | None = None,
status: str | None = None,
limit: int = 100,
offset: int = 0,
owner_id: str | None | _AutoSentinel = AUTO,
) -> list[dict]:
"""Search threads with optional metadata and status filters.
Owner filter is enforced by default: caller must be in a user
context. Pass ``owner_id=None`` to bypass (migration/CLI).
"""
resolved_owner_id = resolve_owner_id(owner_id, method_name="ThreadMetaRepository.search")
stmt = select(ThreadMetaRow).order_by(ThreadMetaRow.updated_at.desc())
if resolved_owner_id is not None:
stmt = stmt.where(ThreadMetaRow.owner_id == resolved_owner_id)
if status:
stmt = stmt.where(ThreadMetaRow.status == status)
if metadata:
# When metadata filter is active, fetch a larger window and filter
# in Python. TODO(Phase 2): use JSON DB operators (Postgres @>,
# SQLite json_extract) for server-side filtering.
stmt = stmt.limit(limit * 5 + offset)
async with self._sf() as session:
result = await session.execute(stmt)
rows = [self._row_to_dict(r) for r in result.scalars()]
rows = [r for r in rows if all(r.get("metadata", {}).get(k) == v for k, v in metadata.items())]
return rows[offset : offset + limit]
else:
stmt = stmt.limit(limit).offset(offset)
async with self._sf() as session:
result = await session.execute(stmt)
return [self._row_to_dict(r) for r in result.scalars()]
async def _check_ownership(self, session: AsyncSession, thread_id: str, resolved_owner_id: str | None) -> bool:
"""Return True if the row exists and is owned (or filter bypassed)."""
if resolved_owner_id is None:
return True # explicit bypass
row = await session.get(ThreadMetaRow, thread_id)
return row is not None and row.owner_id == resolved_owner_id
async def update_display_name(
self,
thread_id: str,
display_name: str,
*,
owner_id: str | None | _AutoSentinel = AUTO,
) -> None:
"""Update the display_name (title) for a thread."""
resolved_owner_id = resolve_owner_id(owner_id, method_name="ThreadMetaRepository.update_display_name")
async with self._sf() as session:
if not await self._check_ownership(session, thread_id, resolved_owner_id):
return
await session.execute(update(ThreadMetaRow).where(ThreadMetaRow.thread_id == thread_id).values(display_name=display_name, updated_at=datetime.now(UTC)))
await session.commit()
async def update_status(
self,
thread_id: str,
status: str,
*,
owner_id: str | None | _AutoSentinel = AUTO,
) -> None:
resolved_owner_id = resolve_owner_id(owner_id, method_name="ThreadMetaRepository.update_status")
async with self._sf() as session:
if not await self._check_ownership(session, thread_id, resolved_owner_id):
return
await session.execute(update(ThreadMetaRow).where(ThreadMetaRow.thread_id == thread_id).values(status=status, updated_at=datetime.now(UTC)))
await session.commit()
async def update_metadata(
self,
thread_id: str,
metadata: dict,
*,
owner_id: str | None | _AutoSentinel = AUTO,
) -> None:
"""Merge ``metadata`` into ``metadata_json``.
Read-modify-write inside a single session/transaction so concurrent
callers see consistent state. No-op if the row does not exist or
the owner_id check fails.
"""
resolved_owner_id = resolve_owner_id(owner_id, method_name="ThreadMetaRepository.update_metadata")
async with self._sf() as session:
row = await session.get(ThreadMetaRow, thread_id)
if row is None:
return
if resolved_owner_id is not None and row.owner_id != resolved_owner_id:
return
merged = dict(row.metadata_json or {})
merged.update(metadata)
row.metadata_json = merged
row.updated_at = datetime.now(UTC)
await session.commit()
async def delete(
self,
thread_id: str,
*,
owner_id: str | None | _AutoSentinel = AUTO,
) -> None:
resolved_owner_id = resolve_owner_id(owner_id, method_name="ThreadMetaRepository.delete")
async with self._sf() as session:
row = await session.get(ThreadMetaRow, thread_id)
if row is None:
return
if resolved_owner_id is not None and row.owner_id != resolved_owner_id:
return
await session.delete(row)
await session.commit()