mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-08-04 03:49:25 +00:00
6f84a4094d
The outer ring for the domain added in #4597: SQL repositories, the run launcher, the thread lookup, and the run-completion listener implementing the ports it declared, plus the HTTP router and the poller that drive them. All of it is instantiated in one composition root, so no route or lifespan hook builds an adapter of its own. With the ports filled, the pre-hexagonal implementation is deleted rather than left alongside: `app/scheduler/service.py` and its router mixed policy, persistence, and HTTP into one class, which is why its rules were only reachable through a live database. Keeping both would leave two implementations of the same rules writing to the same table. Three of the domain's contracts needed real work on this side rather than a straight port of the pre-#4597 adapters: - The launcher now distinguishes certain failure from doubt. Only a 4xx is certain enough to raise LaunchFailedError, which releases the task's single active slot; a 5xx, an arbitrary exception, or a reply whose identity will not decode all raise LaunchIndeterminateError and keep the slot held. Guessing "failed" after the launch request was sent is what re-opens #4452's duplicate execution. - The task repository implements the optimistic token. `save` is a conditional UPDATE on `version` rather than read-check-write, because the latter lets two savers observe the same version and both commit; every other committed write increments it. This needs a column, so it ships with migration 0011 -- the only schema change in the slice, and the reason the alembic head pins move. - The router builds commands with plain `None` for "not supplied", and maps ConcurrentUpdateError onto a retryable 409. The concurrency invariants are pinned by contract suites that run each port against both the in-memory double and real sqlite -- including a new TestOptimisticConcurrency covering what invalidates an earlier read -- plus the dispatch-race tests against a real database. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
59 lines
2.5 KiB
Python
59 lines
2.5 KiB
Python
import re
|
|
|
|
from sqlalchemy import Index
|
|
|
|
from deerflow.config.app_config import AppConfig
|
|
from deerflow.domain.schedule.model import ACTIVE_RUN_STATUSES
|
|
from deerflow.persistence.models import ScheduledTaskRow, ScheduledTaskRunRow
|
|
|
|
|
|
def test_app_config_exposes_scheduler_section():
|
|
config = AppConfig.model_validate(
|
|
{
|
|
"models": [],
|
|
"sandbox": {"use": "local"},
|
|
}
|
|
)
|
|
assert config.scheduler.enabled is False
|
|
assert config.scheduler.poll_interval_seconds == 5
|
|
assert config.scheduler.lease_seconds == 120
|
|
|
|
|
|
def test_scheduled_task_models_registered():
|
|
assert ScheduledTaskRow.__tablename__ == "scheduled_tasks"
|
|
assert ScheduledTaskRunRow.__tablename__ == "scheduled_task_runs"
|
|
|
|
|
|
def _active_run_index() -> Index:
|
|
return next(arg for arg in ScheduledTaskRunRow.__table_args__ if isinstance(arg, Index) and arg.name == "uq_scheduled_task_run_active")
|
|
|
|
|
|
def test_active_run_index_arbitrates_one_active_run_per_task():
|
|
"""The index is the atomic arbiter of the overlap rule, so its shape is a
|
|
contract, not a detail: unique, keyed on `task_id` alone."""
|
|
index = _active_run_index()
|
|
assert index.unique is True
|
|
assert [column.name for column in index.expressions] == ["task_id"]
|
|
|
|
|
|
def test_active_run_index_predicate_matches_the_domain_constant():
|
|
"""`ACTIVE_RUN_STATUSES` and this predicate must stay in lockstep.
|
|
|
|
The domain's fast path (`has_active`) and the index disagree the moment
|
|
they drift, which silently decouples the overlap check from its arbiter.
|
|
The domain tests cannot assert this -- they are deliberately
|
|
dependency-free and cannot import an ORM model -- so the assertion the
|
|
`ACTIVE_RUN_STATUSES` docstring promises lives here.
|
|
|
|
Both dialect predicates are checked: `create_all` renders the SQLite one
|
|
and production renders the Postgres one, so a drift in either is real.
|
|
"""
|
|
index = _active_run_index()
|
|
expected = {str(status) for status in ACTIVE_RUN_STATUSES}
|
|
assert expected == {"queued", "running"}, "domain constant changed -- update the ORM predicates below"
|
|
|
|
predicates = {key: str(value) for key, value in index.dialect_kwargs.items() if key.endswith("_where")}
|
|
assert set(predicates) == {"sqlite_where", "postgresql_where"}, "a dialect lost its partial-index predicate"
|
|
for dialect, predicate in predicates.items():
|
|
assert set(re.findall(r"'([^']+)'", predicate)) == expected, f"{dialect} predicate drifted from ACTIVE_RUN_STATUSES"
|