feat: 业务库切换 MySQL + 修复定时任务运行详情递归与重名 500

- 业务 ORM 数据支持 MySQL 后端(asyncmy),新增 PortableJSON/
  BeijingDateTime 可移植列类型、迁移脚本与切库脚本
- 修复 GET /api/scheduled-tasks/runs/{id} 的 _load_run 无限递归
  (误调用自身,应委托 service.get_run)导致的 RecursionError 500
- 定时任务名按用户唯一:create/update/admin_update 主动校验,
  冲突抛 DuplicateTaskNameError,路由转 409 而非裸 IntegrityError 500
- 补充回归测试 test_scheduled_task_run_lookup / _name_uniqueness

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
吉鑫升andClaude Opus 4.7 committed 2026-05-18 19:34:14 +08:00
1 parent d6f018e581
commit 358d5c72a6
40 files changed
+2128 -190

No files matched your search

@@ -4,10 +4,11 @@ from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import Boolean, DateTime, String
from sqlalchemy import Boolean, String
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime
class AgentRow(Base):
@@ -16,9 +17,9 @@ class AgentRow(Base):
# Stored as a plain string so the same id can be used as the filesystem
# directory name under {base_dir}/agents/{id}/.
id: Mapped[str] = mapped_column(String(64), primary_key=True)
name: Mapped[str] = mapped_column(String(256), nullable=False, index=True)
name: Mapped[str] = mapped_column(String(191), nullable=False, index=True)
description: Mapped[str] = mapped_column(String(1024), nullable=False, default="")
user_id: Mapped[str | None] = mapped_column(String(64), nullable=True, index=True)
published: Mapped[bool] = mapped_column(Boolean, nullable=False, default=False, index=True)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), nullable=False, default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(BeijingDateTime(), nullable=False, default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
@@ -10,10 +10,13 @@ None and fall back to in-memory implementations.
from __future__ import annotations
import json
import logging
from sqlalchemy.ext.asyncio import AsyncEngine, AsyncSession, async_sessionmaker, create_async_engine
import json
import logging
import sys
from importlib.util import find_spec
from pathlib import Path
from sqlalchemy.ext.asyncio import AsyncEngine, AsyncSession, async_sessionmaker, create_async_engine
def _json_serializer(obj: object) -> str:
@@ -23,11 +26,37 @@ def _json_serializer(obj: object) -> str:
logger = logging.getLogger(__name__)
_engine: AsyncEngine | None = None
_session_factory: async_sessionmaker[AsyncSession] | None = None
async def _auto_create_postgres_db(url: str) -> None:
_engine: AsyncEngine | None = None
_session_factory: async_sessionmaker[AsyncSession] | None = None
def _add_runtime_vendor_path() -> None:
"""Allow offline deployments to place optional DB drivers in DEER_FLOW_HOME.
The offline Docker image keeps the Python environment inside the image, while
``/app/backend/.deer-flow`` is a persistent bind mount. The MySQL switch
script installs ``asyncmy`` into ``{DEER_FLOW_HOME}/python-vendor`` so the
unchanged startup script can still import it after container recreation.
"""
try:
from deerflow.config.runtime_paths import runtime_home
vendor_dir = runtime_home() / "python-vendor"
except Exception:
vendor_dir = Path(".deer-flow/python-vendor").resolve()
vendor = str(vendor_dir)
if vendor_dir.exists() and vendor not in sys.path:
sys.path.insert(0, vendor)
def _mysql_driver_name(url: str) -> str:
if url.startswith("mysql+aiomysql://"):
return "aiomysql"
return "asyncmy"
async def _auto_create_postgres_db(url: str) -> None:
"""Connect to the ``postgres`` maintenance DB and CREATE DATABASE.
The target database name is extracted from *url*. The connection is
@@ -65,8 +94,8 @@ async def init_engine(
"""Create the async engine and session factory, then auto-create tables.
Args:
backend: "memory", "sqlite", or "postgres".
url: SQLAlchemy async URL (for sqlite/postgres).
backend: "memory", "sqlite", "postgres", or "mysql".
url: SQLAlchemy async URL (for sqlite/postgres/mysql).
echo: Echo SQL to log.
pool_size: Postgres connection pool size.
sqlite_dir: Directory to create for SQLite (ensured to exist).
@@ -77,11 +106,20 @@ async def init_engine(
logger.info("Persistence backend=memory -- ORM engine not initialized")
return
if backend == "postgres":
try:
import asyncpg # noqa: F401
except ImportError:
raise ImportError("database.backend is set to 'postgres' but asyncpg is not installed.\nInstall it with:\n uv sync --extra postgres\nOr switch to backend: sqlite in config.yaml for single-node deployment.") from None
if backend == "postgres":
try:
import asyncpg # noqa: F401
except ImportError:
raise ImportError("database.backend is set to 'postgres' but asyncpg is not installed.\nInstall it with:\n uv sync --extra postgres\nOr switch to backend: sqlite in config.yaml for single-node deployment.") from None
if backend == "mysql":
_add_runtime_vendor_path()
driver = _mysql_driver_name(url)
if find_spec(driver) is None:
raise ImportError(
"database.backend is set to 'mysql' but the MySQL async driver is not installed.\n"
"Install asyncmy, or run switch_database_to_mysql.sh so it can install asyncmy into "
f"{Path('.deer-flow/python-vendor')} from the offline wheelhouse."
)
if backend == "sqlite":
import os
@@ -112,16 +150,25 @@ async def init_engine(
cursor.execute("PRAGMA foreign_keys=ON;")
finally:
cursor.close()
elif backend == "postgres":
_engine = create_async_engine(
url,
echo=echo,
pool_size=pool_size,
pool_pre_ping=True,
json_serializer=_json_serializer,
)
else:
raise ValueError(f"Unknown persistence backend: {backend!r}")
elif backend == "postgres":
_engine = create_async_engine(
url,
echo=echo,
pool_size=pool_size,
pool_pre_ping=True,
json_serializer=_json_serializer,
)
elif backend == "mysql":
_engine = create_async_engine(
url,
echo=echo,
pool_size=pool_size,
pool_pre_ping=True,
pool_recycle=1800,
json_serializer=_json_serializer,
)
else:
raise ValueError(f"Unknown persistence backend: {backend!r}")
_session_factory = async_sessionmaker(_engine, expire_on_commit=False)
@@ -162,10 +209,10 @@ async def init_engine_from_config(config) -> None:
await init_engine("memory")
return
await init_engine(
backend=config.backend,
url=config.app_sqlalchemy_url,
echo=config.echo_sql,
pool_size=config.pool_size,
backend=config.backend,
url=config.app_sqlalchemy_url,
echo=config.echo_sql,
pool_size=config.pool_size,
sqlite_dir=config.sqlite_dir if config.backend == "sqlite" else "",
)
@@ -4,10 +4,11 @@ from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import DateTime, String, Text, UniqueConstraint
from sqlalchemy import String, Text, UniqueConstraint
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime
class FeedbackRow(Base):
@@ -29,4 +30,4 @@ class FeedbackRow(Base):
comment: Mapped[str | None] = mapped_column(Text)
# Optional text feedback from the user
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC))
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
@@ -4,10 +4,11 @@ from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import DateTime, Float, Integer, String, Text
from sqlalchemy import Float, Integer, String, Text
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime
class LlmCallMetricRow(Base):
@@ -18,7 +19,7 @@ class LlmCallMetricRow(Base):
id: Mapped[str] = mapped_column(String(64), primary_key=True)
# Wall-clock time the LLM call ended. Indexed because admin views always
# sort/filter by recency.
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC), index=True)
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC), index=True)
user_id: Mapped[str | None] = mapped_column(String(64), index=True)
thread_id: Mapped[str | None] = mapped_column(String(64), index=True)
@@ -44,12 +44,13 @@ def run_migrations_offline() -> None:
context.run_migrations()
def do_run_migrations(connection):
context.configure(
connection=connection,
target_metadata=target_metadata,
render_as_batch=True, # Required for SQLite ALTER TABLE support
)
def do_run_migrations(connection):
render_as_batch = connection.dialect.name == "sqlite"
context.configure(
connection=connection,
target_metadata=target_metadata,
render_as_batch=render_as_batch, # Required for SQLite ALTER TABLE support
)
with context.begin_transaction():
context.run_migrations()
@@ -7,9 +7,11 @@ Create Date: 2026-05-12
from __future__ import annotations
from alembic import op
from sqlalchemy import inspect
import sqlalchemy as sa
from alembic import op
from sqlalchemy import inspect
import sqlalchemy as sa
from deerflow.persistence.types import PortableJSON
revision = "20260512_01"
@@ -23,9 +25,9 @@ def _has_column(table_name: str, column_name: str) -> bool:
return any(column["name"] == column_name for column in inspector.get_columns(table_name))
def upgrade() -> None:
if not _has_column("scheduled_task_runs", "result_json"):
op.add_column("scheduled_task_runs", sa.Column("result_json", sa.JSON(), nullable=True))
def upgrade() -> None:
if not _has_column("scheduled_task_runs", "result_json"):
op.add_column("scheduled_task_runs", sa.Column("result_json", PortableJSON(), nullable=True))
def downgrade() -> None:
@@ -30,7 +30,7 @@ def upgrade() -> None:
op.create_table(
"agents",
sa.Column("id", sa.String(64), primary_key=True),
sa.Column("name", sa.String(256), nullable=False),
sa.Column("name", sa.String(191), nullable=False),
sa.Column("description", sa.String(1024), nullable=False, server_default=""),
sa.Column("user_id", sa.String(64), nullable=True),
sa.Column("published", sa.Boolean(), nullable=False, server_default=sa.false()),
@@ -28,7 +28,7 @@ def upgrade() -> None:
op.create_table(
"tags",
sa.Column("id", sa.String(64), primary_key=True),
sa.Column("name", sa.String(256), nullable=False),
sa.Column("name", sa.String(159), nullable=False),
sa.Column("tag_type", sa.String(32), nullable=False),
sa.Column("color", sa.String(16), nullable=False, server_default="gray"),
sa.Column("description", sa.String(1024), nullable=False, server_default=""),
@@ -4,10 +4,11 @@ from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import JSON, DateTime, Index, String, Text, UniqueConstraint
from sqlalchemy import Index, String, Text, UniqueConstraint
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime, PortableJSON
class RunEventRow(Base):
@@ -24,9 +25,9 @@ class RunEventRow(Base):
category: Mapped[str] = mapped_column(String(16), nullable=False)
# "message" | "trace" | "lifecycle"
content: Mapped[str] = mapped_column(Text, default="")
event_metadata: Mapped[dict] = mapped_column(JSON, default=dict)
event_metadata: Mapped[dict] = mapped_column(PortableJSON(), default=dict)
seq: Mapped[int] = mapped_column(nullable=False)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC))
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
__table_args__ = (
UniqueConstraint("thread_id", "seq", name="uq_events_thread_seq"),
@@ -5,10 +5,11 @@ from __future__ import annotations
from datetime import UTC, datetime
from typing import Any
from sqlalchemy import JSON, Boolean, DateTime, String, Text
from sqlalchemy import Boolean, String, Text
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime, PortableJSON
class NotificationRow(Base):
@@ -19,6 +20,6 @@ class NotificationRow(Base):
type: Mapped[str] = mapped_column(String(64), nullable=False)
title: Mapped[str] = mapped_column(String(256), nullable=False, default="")
body: Mapped[str] = mapped_column(Text, nullable=False, default="")
payload: Mapped[dict[str, Any]] = mapped_column(JSON, nullable=False, default=dict)
payload: Mapped[dict[str, Any]] = mapped_column(PortableJSON(), nullable=False, default=dict)
read: Mapped[bool] = mapped_column(Boolean, nullable=False, default=False, index=True)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, default=lambda: datetime.now(UTC), index=True)
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), nullable=False, default=lambda: datetime.now(UTC), index=True)
@@ -4,10 +4,11 @@ from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import DateTime, Integer, String, Text
from sqlalchemy import Integer, String, Text
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime
class RecommendedQuestionRow(Base):
@@ -17,5 +18,5 @@ class RecommendedQuestionRow(Base):
title: Mapped[str] = mapped_column(String(256), nullable=False)
content: Mapped[str] = mapped_column(Text, nullable=False)
sort_order: Mapped[int] = mapped_column(Integer, nullable=False, default=0, index=True)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), nullable=False, default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(BeijingDateTime(), nullable=False, default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
@@ -4,10 +4,11 @@ from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import JSON, DateTime, Index, String, Text
from sqlalchemy import Index, String, Text
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime, PortableJSON
class RunRow(Base):
@@ -22,8 +23,8 @@ class RunRow(Base):
model_name: Mapped[str | None] = mapped_column(String(128))
multitask_strategy: Mapped[str] = mapped_column(String(20), default="reject")
metadata_json: Mapped[dict] = mapped_column(JSON, default=dict)
kwargs_json: Mapped[dict] = mapped_column(JSON, default=dict)
metadata_json: Mapped[dict] = mapped_column(PortableJSON(), default=dict)
kwargs_json: Mapped[dict] = mapped_column(PortableJSON(), default=dict)
error: Mapped[str | None] = mapped_column(Text)
# Convenience fields (for listing pages without querying RunEventStore)
@@ -43,7 +44,7 @@ class RunRow(Base):
# Follow-up association
follow_up_to_run_id: Mapped[str | None] = mapped_column(String(64))
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
__table_args__ = (Index("ix_runs_thread_status", "thread_id", "status"),)
@@ -4,10 +4,11 @@ from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import JSON, Boolean, DateTime, Integer, String, Text, UniqueConstraint
from sqlalchemy import Boolean, Integer, String, Text, UniqueConstraint
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime, PortableJSON
class SchedulerThreadRow(Base):
@@ -15,8 +16,8 @@ class SchedulerThreadRow(Base):
user_id: Mapped[str] = mapped_column(String(64), primary_key=True)
thread_id: Mapped[str] = mapped_column(String(64), unique=True, index=True)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
class ScheduledTaskRow(Base):
@@ -29,20 +30,20 @@ class ScheduledTaskRow(Base):
source_thread_id: Mapped[str | None] = mapped_column(String(64), index=True)
source_agent_name: Mapped[str | None] = mapped_column(String(128), index=True)
execution_agent_name: Mapped[str | None] = mapped_column(String(128), index=True)
name: Mapped[str] = mapped_column(String(256))
name: Mapped[str] = mapped_column(String(127))
prompt: Mapped[str] = mapped_column(Text)
schedule_text: Mapped[str] = mapped_column(String(256))
cron_expr: Mapped[str] = mapped_column(String(128))
timezone: Mapped[str] = mapped_column(String(64), default="UTC")
enabled: Mapped[bool] = mapped_column(Boolean, default=True)
next_run_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), index=True)
last_run_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
next_run_at: Mapped[datetime | None] = mapped_column(BeijingDateTime(), index=True)
last_run_at: Mapped[datetime | None] = mapped_column(BeijingDateTime())
last_status: Mapped[str | None] = mapped_column(String(32))
execution_context_json: Mapped[dict] = mapped_column(JSON, default=dict)
execution_context_json: Mapped[dict] = mapped_column(PortableJSON(), default=dict)
published: Mapped[bool] = mapped_column(Boolean, default=False, index=True)
published_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
published_at: Mapped[datetime | None] = mapped_column(BeijingDateTime())
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
class ScheduledTaskSubscriptionRow(Base):
@@ -53,8 +54,8 @@ class ScheduledTaskSubscriptionRow(Base):
task_id: Mapped[str] = mapped_column(String(64), index=True)
user_id: Mapped[str] = mapped_column(String(64), index=True)
notify_element: Mapped[bool] = mapped_column(Boolean, default=False)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
class ScheduledTaskRunRow(Base):
@@ -66,25 +67,25 @@ class ScheduledTaskRunRow(Base):
user_id: Mapped[str] = mapped_column(String(64), index=True)
scheduler_thread_id: Mapped[str] = mapped_column(String(64), index=True)
agent_run_id: Mapped[str | None] = mapped_column(String(64), index=True)
scheduled_for: Mapped[datetime] = mapped_column(DateTime(timezone=True), index=True)
started_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
finished_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
scheduled_for: Mapped[datetime] = mapped_column(BeijingDateTime(), index=True)
started_at: Mapped[datetime | None] = mapped_column(BeijingDateTime())
finished_at: Mapped[datetime | None] = mapped_column(BeijingDateTime())
status: Mapped[str] = mapped_column(String(32), default="pending")
error: Mapped[str | None] = mapped_column(Text)
result_json: Mapped[dict | None] = mapped_column(JSON, default=dict)
result_json: Mapped[dict | None] = mapped_column(PortableJSON(), default=dict)
# Number of recovery attempts made after the first try. A run is retried
# when it overruns the per-attempt timeout or is found orphaned in the
# "running" state (e.g. after a service restart). See ScheduledTaskService.
retry_count: Mapped[int] = mapped_column(Integer, default=0, server_default="0")
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
class ScheduledTaskDeliveryProfileRow(Base):
__tablename__ = "scheduled_task_delivery_profiles"
user_id: Mapped[str] = mapped_column(String(64), primary_key=True)
element_user_id: Mapped[str | None] = mapped_column(String(256), index=True)
element_user_id: Mapped[str | None] = mapped_column(String(191), index=True)
element_room_id: Mapped[str | None] = mapped_column(String(256), nullable=True)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
@@ -14,10 +14,11 @@ from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import DateTime, String, UniqueConstraint
from sqlalchemy import String, UniqueConstraint
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime
# Allowed tag/target types. Kept here so persistence + API share one source.
TAG_TYPES: tuple[str, ...] = ("agent", "skill", "scheduled_task")
@@ -28,12 +29,12 @@ class TagRow(Base):
__table_args__ = (UniqueConstraint("tag_type", "name", name="uq_tags_type_name"),)
id: Mapped[str] = mapped_column(String(64), primary_key=True)
name: Mapped[str] = mapped_column(String(256), nullable=False)
name: Mapped[str] = mapped_column(String(159), nullable=False)
tag_type: Mapped[str] = mapped_column(String(32), nullable=False, index=True)
color: Mapped[str] = mapped_column(String(16), nullable=False, default="gray")
description: Mapped[str] = mapped_column(String(1024), nullable=False, default="")
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), nullable=False, default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(BeijingDateTime(), nullable=False, default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
class TagAssignmentRow(Base):
@@ -44,4 +45,4 @@ class TagAssignmentRow(Base):
tag_id: Mapped[str] = mapped_column(String(64), nullable=False, index=True)
target_type: Mapped[str] = mapped_column(String(32), nullable=False, index=True)
target_id: Mapped[str] = mapped_column(String(64), nullable=False, index=True)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, default=lambda: datetime.now(UTC))
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), nullable=False, default=lambda: datetime.now(UTC))
@@ -4,10 +4,11 @@ from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import JSON, DateTime, String
from sqlalchemy import String
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime, PortableJSON
class ThreadMetaRow(Base):
@@ -18,6 +19,6 @@ class ThreadMetaRow(Base):
user_id: Mapped[str | None] = mapped_column(String(64), index=True)
display_name: Mapped[str | None] = mapped_column(String(256))
status: Mapped[str] = mapped_column(String(20), default="idle")
metadata_json: Mapped[dict] = mapped_column(JSON, default=dict)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
metadata_json: Mapped[dict] = mapped_column(PortableJSON(), default=dict)
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
@@ -10,10 +10,11 @@ from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import Boolean, DateTime, String
from sqlalchemy import Boolean, String
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime
class ThreadShareRow(Base):
@@ -33,4 +34,4 @@ class ThreadShareRow(Base):
# "view" — a public, read-only static page anyone can open without
# logging in; viewers cannot send new messages.
mode: Mapped[str] = mapped_column(String(16), nullable=False, default="import", server_default="import")
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, default=lambda: datetime.now(UTC))
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), nullable=False, default=lambda: datetime.now(UTC))
@@ -0,0 +1,85 @@
"""Portable SQLAlchemy column types."""
from __future__ import annotations
import json
from datetime import datetime, timedelta, timezone
from typing import Any
from sqlalchemy import JSON, DateTime, Text
from sqlalchemy.types import TypeDecorator
# China Standard Time. China has observed UTC+8 with no DST since 1991, so a
# fixed offset is exact and avoids depending on the `tzdata` package (which the
# stdlib `zoneinfo` needs on Windows / minimal containers).
BEIJING_TZ = timezone(timedelta(hours=8))
class PortableJSON(TypeDecorator):
"""Use native JSON where available, and TEXT on older MySQL servers."""
impl = JSON
cache_ok = True
def load_dialect_impl(self, dialect):
if dialect.name == "mysql":
return dialect.type_descriptor(Text())
return dialect.type_descriptor(JSON())
def process_bind_param(self, value: Any, dialect) -> Any:
if dialect.name != "mysql" or value is None:
return value
return json.dumps(value, ensure_ascii=False)
def process_result_value(self, value: Any, dialect) -> Any:
if dialect.name != "mysql" or value is None or not isinstance(value, str):
return value
if not value:
return None
return json.loads(value)
class BeijingDateTime(TypeDecorator):
"""Store timestamps as Beijing (UTC+8) wall-clock time.
The application works in UTC internally (``datetime.now(UTC)`` everywhere).
MySQL ``DATETIME`` and SQLite have no timezone, so the driver serializes the
wall-clock fields of whatever datetime it is given and drops ``tzinfo``.
Without conversion a row stores the UTC wall clock and an operator browsing
the table sees a time 8 hours behind Beijing.
This decorator converts UTC-aware values to Beijing on the way in (stored as
naive Beijing wall-clock) and re-attaches the Beijing zone on the way out, so
the database holds Beijing time while Python keeps receiving correct
timezone-aware datetimes — instant comparisons stay correct either way.
PostgreSQL has a real ``TIMESTAMP WITH TIME ZONE`` type and stores the
instant unambiguously, so values pass through unchanged there.
"""
impl = DateTime
cache_ok = True
def load_dialect_impl(self, dialect):
# timezone=True keeps PostgreSQL on timestamptz; MySQL/SQLite ignore it.
return dialect.type_descriptor(DateTime(timezone=True))
def process_bind_param(self, value: Any, dialect) -> Any:
if not isinstance(value, datetime):
return value
if dialect.name == "postgresql":
return value
if value.tzinfo is None:
# Naive values follow the codebase convention of being UTC.
value = value.replace(tzinfo=timezone.utc)
return value.astimezone(BEIJING_TZ).replace(tzinfo=None)
def process_result_value(self, value: Any, dialect) -> Any:
if not isinstance(value, datetime):
return value
if dialect.name == "postgresql":
return value
if value.tzinfo is None:
# Stored as naive Beijing wall-clock; re-attach the zone.
return value.replace(tzinfo=BEIJING_TZ)
return value.astimezone(BEIJING_TZ)
@@ -13,10 +13,11 @@ from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import Boolean, DateTime, Index, String, text
from sqlalchemy import Boolean, Index, String, text
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime
class UserRow(Base):
@@ -25,7 +26,7 @@ class UserRow(Base):
# 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)
email: Mapped[str] = mapped_column(String(191), 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
@@ -33,7 +34,7 @@ class UserRow(Base):
system_role: Mapped[str] = mapped_column(String(16), nullable=False, default="user")
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
BeijingDateTime(),
nullable=False,
default=lambda: datetime.now(UTC),
)