1445043649
87ea715c2a
Flip the 4 business ORM models (ThreadMetaRow, RunRow, FeedbackRow, RunEventRow) to ``workspace_id: Mapped[str]`` with ``nullable=False``. PR5's alembic 0003 already enforces NOT NULL at the DB layer; this aligns the ORM-driven ``create_all()`` path (dev / tests) with the same invariant so a new install ends up at the post-0003 schema without running alembic. Test fallout absorbed: - `tests/conftest.py` autouse seed now produces a fully consistent pair: user row (default_workspace_id = test-workspace-autouse) plus the workspace itself. The PR5 backfill script's "users without default_workspace_id" query no longer picks the fixture up. Insert order is user → workspace → UPDATE user, walking around the chicken- and-egg FK between `workspaces.owner_id` and `users.default_workspace_id`. - `tests/test_backfill_workspace_id.py` adds a file-scoped autouse fixture that temporarily flips `column.nullable = True` for the four business tables (production correctness comes from alembic 0003; the script's own job is exactly to fill rows between 0002 and 0003 so its tests need that transient state to be representable). Its `_init_engine` also deletes the autouse seed rows to match the "fresh DB" model the tests assume. - `test_thread_meta_workspace_filter::test_create_workspace_none_bypasses` renamed to `test_create_workspace_none_rejected_by_orm` and asserts the new IntegrityError on explicit None — write paths can no longer bypass workspace scope. - 5 `test_workspace_context` tests + the auth-middleware reset test get `@pytest.mark.no_auto_workspace` so they keep testing the unset-contextvar path. - `test_workspace_repo::test_list_by_user_bypass_returns_all` switches to membership assertions instead of strict equality since the autouse fixture surfaces under `user_id=None`. 3214 passed, 30 skipped; the remaining 17 are the documented pre-existing caplog ordering flakes (all pass in isolation).
62 lines
3.9 KiB
Python
62 lines
3.9 KiB
Python
"""ORM model for run metadata."""
|
||
|
||
from __future__ import annotations
|
||
|
||
from datetime import UTC, datetime
|
||
|
||
from sqlalchemy import JSON, DateTime, ForeignKey, Index, String, Text
|
||
from sqlalchemy.orm import Mapped, mapped_column
|
||
|
||
from deerflow.persistence.base import Base
|
||
|
||
|
||
class RunRow(Base):
|
||
__tablename__ = "runs"
|
||
|
||
run_id: Mapped[str] = mapped_column(String(64), primary_key=True, comment="运行主键")
|
||
thread_id: Mapped[str] = mapped_column(String(64), nullable=False, index=True, comment="所属会话 ID（threads_meta.thread_id）")
|
||
assistant_id: Mapped[str | None] = mapped_column(String(128), comment="使用的 Assistant ID（自定义智能体名）；为 NULL 表示默认 lead agent")
|
||
user_id: Mapped[str | None] = mapped_column(String(64), index=True, comment="发起本次运行的用户 ID")
|
||
workspace_id: Mapped[str] = mapped_column(
|
||
String(36),
|
||
ForeignKey("workspaces.id", ondelete="CASCADE"),
|
||
nullable=False,
|
||
comment="所属 workspace。PR5 引入时 nullable 用于回填；alembic 0003 + PR6 仓储接入完成后 NOT NULL",
|
||
)
|
||
status: Mapped[str] = mapped_column(
|
||
String(20),
|
||
default="pending",
|
||
comment='运行状态："pending" / "running" / "success" / "error" / "timeout" / "interrupted"',
|
||
)
|
||
model_name: Mapped[str | None] = mapped_column(String(128), comment="本次运行的主模型名（来自 config.yaml.models[*].name）")
|
||
multitask_strategy: Mapped[str] = mapped_column(
|
||
String(20),
|
||
default="reject",
|
||
comment='并发策略：同一 thread 已有运行时怎么处理（"reject" / "interrupt" / "rollback" / "enqueue"）',
|
||
)
|
||
metadata_json: Mapped[dict] = mapped_column(JSON, default=dict, comment="运行级元数据（JSON），如 channel/source 等")
|
||
kwargs_json: Mapped[dict] = mapped_column(JSON, default=dict, comment="提交运行时的额外参数（JSON），如 thinking_enabled、tool 配置等")
|
||
error: Mapped[str | None] = mapped_column(Text, comment="运行失败时的错误文本；成功时为 NULL")
|
||
|
||
message_count: Mapped[int] = mapped_column(default=0, comment="本次运行产生的消息总数（便利字段，避免列表页查 RunEventStore）")
|
||
first_human_message: Mapped[str | None] = mapped_column(Text, comment="首条用户消息文本预览（用于列表展示）")
|
||
last_ai_message: Mapped[str | None] = mapped_column(Text, comment="末条 AI 消息文本预览（用于列表展示）")
|
||
|
||
total_input_tokens: Mapped[int] = mapped_column(default=0, comment="累计输入 token 数（运行结束时由 RunJournal 落盘）")
|
||
total_output_tokens: Mapped[int] = mapped_column(default=0, comment="累计输出 token 数")
|
||
total_tokens: Mapped[int] = mapped_column(default=0, comment="累计 token 总数 = input + output")
|
||
llm_call_count: Mapped[int] = mapped_column(default=0, comment="累计 LLM 调用次数")
|
||
lead_agent_tokens: Mapped[int] = mapped_column(default=0, comment="主 agent 自身消耗的 token 数")
|
||
subagent_tokens: Mapped[int] = mapped_column(default=0, comment="子 agent（task 工具委派）消耗的 token 数")
|
||
middleware_tokens: Mapped[int] = mapped_column(default=0, comment="中间件（如 summarization、title）消耗的 token 数")
|
||
|
||
follow_up_to_run_id: Mapped[str | None] = mapped_column(String(64), comment="续接的上一次运行 ID（用于'重新生成'/'继续'等链式调用）")
|
||
|
||
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC), comment="创建时间（UTC）")
|
||
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC), comment="最近更新时间（UTC，写入时自动更新）")
|
||
|
||
__table_args__ = (
|
||
Index("ix_runs_thread_status", "thread_id", "status"),
|
||
{"comment": "运行（一次完整 agent 执行）的元数据 + 累计 token 指标"},
|
||
)
|