mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-07-09 16:08:31 +00:00
Some checks are pending
Backend Blocking IO / backend-blocking-io (push) Waiting to run
Unit Tests / backend-unit-tests (push) Waiting to run
E2E Tests / e2e-tests (push) Waiting to run
Frontend Unit Tests / frontend-unit-tests (push) Waiting to run
Lint Check / lint-backend (push) Waiting to run
Lint Check / lint-frontend (push) Waiting to run
Replay E2E (front-back contract) / Layer 1 — backend golden (no API key) (push) Waiting to run
Replay E2E (front-back contract) / Layer 2 — full-stack render (no API key) (push) Waiting to run
* feat(persistence): wire alembic migrations + bootstrap schema on startup Closes #3682. Pre-#3658 DBs lack the `runs.token_usage_by_model` column because alembic was never wired up — startup only ran `create_all`, which never ALTERs existing tables. Adds a hybrid bootstrap in FastAPI lifespan (replaces bare `create_all`): - empty DB → create_all + stamp head - legacy DB → stamp 0001_baseline + upgrade head - versioned DB → upgrade head Concurrency: Postgres `pg_advisory_lock` (cross-process); SQLite per-engine `asyncio.Lock` + 30s `PRAGMA busy_timeout` on both prod and alembic engines. Column revisions use `safe_add_column` / `safe_drop_column` idempotent helpers as fallback. Other bits: - 0001 baseline (chain root) + 0002 add `runs.token_usage_by_model` - `include_object` filter so alembic ignores LangGraph checkpointer tables - `make migrate-rev MSG="..."` for authoring new revisions (no migrate/stamp targets — startup is the only execution path) - Tests: three-branch decision, concurrency, #3682 regression, env filter, blocking-IO gate anchor - CLAUDE.md: new "Schema migrations" section * fix(style): fix lint error * perf(persistence): address review feedback on alembic bootstrap Behavioural fixes - _SQLITE_LOCKS now keyed via WeakKeyDictionary so id-reuse after GC cannot return a stale, loop-bound lock and the cache cannot leak one entry per disposed engine. - safe_add_column compares nullable / server_default against the desired column when the name already exists and emits a warning on drift, surfacing manual-ALTER workarounds instead of silently no-op'ing. - _postgres_lock issues SET LOCAL idle_in_transaction_session_timeout=0 before pg_advisory_lock, so managed Postgres cannot kill the idle lock-holding session mid-upgrade and silently release the advisory lock. - legacy branch now backfills missing baseline tables via a restricted create_all (Base.metadata.create_all scoped to _BASELINE_TABLE_NAMES). Restores pre-#1930 upgraders whose channel_* tables were never provisioned, without pre-empting future create_table revisions for newly-added models. Schema parity - runs.token_usage_by_model gains server_default=text("'{}'") in both the ORM model and the 0001_baseline create_table, matching what 0002 adds via ALTER. create_all and alembic-upgrade paths now produce identical column definitions. - New parity test compares Base.metadata.create_all output against a pure alembic upgrade base->head, asserting column-set, nullable, and server_default agree across all tables (normalized through the same helper safe_add_column's drift check uses). Guards - test_baseline_table_names_constant_matches_0001 pins _BASELINE_TABLE_NAMES to 0001_baseline.upgrade()'s actual output -- the constant cannot drift silently when someone edits 0001. - test_legacy_backfill_skips_non_baseline_tables verifies the restricted backfill does not create a phantom table on Base.metadata, modelling a future revision that would otherwise collide on op.create_table. Doc residuals - Three-branch decision table is now consistent across bootstrap.py top docstring, engine.py comment, test module docstring, and CLAUDE.md. - Stale test anchor in blocking_io/test_persistence_engine_sqlite.py docstring now points at the real file. * fix(style): fix lint error * fix(persistence): close drift detection holes - _check_column_drift compares column type via a family equivalence allowlist ({JSON, JSONB}). Catches the wrong-type workaround `TEXT NOT NULL DEFAULT '{}'` that previously slipped through silently, while keeping Postgres JSON/JSONB dialect reflection quiet. Reflected and desired type are also echoed in every drift warning's payload for operator triage. - Extract _escape_url_for_alembic so bootstrap._alembic_safe_url and scripts/_autogen_revision share the ConfigParser % escape rule instead of duplicating it. - backend/README.md: add `make migrate-rev MSG=...` to Commands and a Schema Migrations section per the repo's README/CLAUDE.md sync policy. - test_base_to_dict.py: scope the test ORM class to an isolated MetaData so the create_all-vs-alembic parity test (added in the previous commit) is not polluted by the phantom table on the full pytest session.
102 lines
4.2 KiB
Python
102 lines
4.2 KiB
Python
"""Tests for ``scripts/_autogen_revision.py`` (``make migrate-rev``).
|
|
|
|
The script must work in a clean checkout without any pre-existing data
|
|
directory -- this is the failure mode reported as P2: a bare ``alembic
|
|
revision --autogenerate`` would crash with
|
|
``sqlite3.OperationalError: unable to open database file`` because
|
|
``alembic.ini``'s default URL points at ``./data/deerflow.db`` which doesn't
|
|
exist yet.
|
|
|
|
The fix: the script builds its own temp DB by running the existing alembic
|
|
chain to head and runs autogenerate against THAT, instead of relying on
|
|
``alembic.ini``'s URL or runtime ``create_all`` bootstrap.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import importlib.util
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
import sqlalchemy as sa
|
|
|
|
import deerflow.persistence.models # noqa: F401
|
|
from deerflow.persistence.base import Base
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def autogen_module():
|
|
"""Load ``scripts/_autogen_revision.py`` as an importable module.
|
|
|
|
The file lives outside the package tree (under ``backend/scripts/``) so we
|
|
load it directly via ``spec_from_file_location``.
|
|
"""
|
|
script_path = Path(__file__).resolve().parents[1] / "scripts/_autogen_revision.py"
|
|
assert script_path.exists(), f"missing autogen script at {script_path}"
|
|
spec = importlib.util.spec_from_file_location("_autogen_revision_under_test", script_path)
|
|
assert spec is not None and spec.loader is not None
|
|
module = importlib.util.module_from_spec(spec)
|
|
spec.loader.exec_module(module)
|
|
return module
|
|
|
|
|
|
def test_autogen_builds_temp_db_at_head_without_data_dir(autogen_module, monkeypatch) -> None:
|
|
"""The temp-DB builder must succeed even when ``./data/`` does not exist.
|
|
|
|
We chdir to an empty directory to mimic a clean checkout where the
|
|
alembic.ini default URL would explode.
|
|
"""
|
|
import os # noqa: PLC0415
|
|
import tempfile # noqa: PLC0415
|
|
|
|
workdir = tempfile.mkdtemp(prefix="deerflow-autogen-test-")
|
|
monkeypatch.chdir(workdir)
|
|
# Sanity: this directory has no ``./data/`` -- so the alembic.ini default
|
|
# URL would fail if used.
|
|
assert not os.path.exists("data")
|
|
|
|
url = autogen_module._build_temp_db_at_head()
|
|
assert url.startswith("sqlite+aiosqlite:///"), f"unexpected URL shape: {url}"
|
|
# The temp DB file should now exist.
|
|
db_path = url.replace("sqlite+aiosqlite:///", "")
|
|
assert os.path.exists(db_path), f"temp DB file not created at {db_path}"
|
|
|
|
|
|
def test_autogen_temp_db_is_at_head(autogen_module) -> None:
|
|
"""The temp DB the autogen script builds must be at head, so the
|
|
autogenerate diff against current models is empty (or only reflects
|
|
intentional, in-progress model changes)."""
|
|
import sqlite3 # noqa: PLC0415
|
|
|
|
url = autogen_module._build_temp_db_at_head()
|
|
db_path = url.replace("sqlite+aiosqlite:///", "")
|
|
with sqlite3.connect(db_path) as raw:
|
|
row = raw.execute("SELECT version_num FROM alembic_version").fetchone()
|
|
assert row is not None, "autogen temp DB has no alembic_version row -- bootstrap failed"
|
|
# head is whatever the script tree currently says; we just assert it's there.
|
|
assert row[0]
|
|
|
|
|
|
def test_autogen_temp_db_comes_from_migration_history_not_current_metadata(autogen_module) -> None:
|
|
"""Pending ORM changes must remain visible to autogenerate.
|
|
|
|
If the helper accidentally uses runtime ``bootstrap_schema`` /
|
|
``Base.metadata.create_all`` again, this probe table would be created in
|
|
the temp DB and the test would fail. A temp DB built from alembic history
|
|
only contains objects that committed revisions know how to create.
|
|
"""
|
|
import sqlite3 # noqa: PLC0415
|
|
|
|
probe_name = "__autogen_probe_pending_migration__"
|
|
probe_table = sa.Table(probe_name, Base.metadata, sa.Column("id", sa.Integer, primary_key=True))
|
|
try:
|
|
url = autogen_module._build_temp_db_at_head()
|
|
db_path = url.replace("sqlite+aiosqlite:///", "")
|
|
with sqlite3.connect(db_path) as raw:
|
|
exists = raw.execute(
|
|
"SELECT count(*) FROM sqlite_master WHERE type='table' AND name=?",
|
|
(probe_name,),
|
|
).fetchone()[0]
|
|
assert exists == 0, "temp DB was built from current ORM metadata instead of migration history"
|
|
finally:
|
|
Base.metadata.remove(probe_table)
|