mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-08-12 07:49:00 +00:00
* feat(agents): database-backed storage for custom agent definitions Add an agent_storage.backend switch (default file, behaviour-unchanged) with a db backend that stores each custom agent as a row in the shared SQL persistence layer, so a multi-instance deployment sees the same agents on every node (#4331, #4357). Introduces an AgentStore interface routing all read/write surfaces, an agents table + migration 0006, startup validation, and a file->db importer. Follows the thread_meta store / run_events backend-switch / 0003_scheduled_tasks migration patterns; no new dependency. * fix(agents): make db storage path production-ready (review round 1) Addresses review feedback on the db/sync agent-storage path: - sql.py: mirror the async engine's per-connection SQLite PRAGMAs on the sync engine (busy_timeout=30000, synchronous=NORMAL, foreign_keys=ON, WAL) so both engines behave identically against the shared DB; guard the engine cache with a lock (double-checked) so concurrent first-touch cannot build duplicate engines or register the connect listener twice. - routers/agents.py + routers/assistants_compat.py: offload the sync-store reads that ran on the event loop (list/get/check, update's pre-read + legacy guard + refresh, and assistants_compat's four list routes) via asyncio.to_thread — on db+postgres each was a network round trip stalling the loop. Writes were already offloaded. - file.py: translate the create() mkdir(exist_ok=False) race FileExistsError into AgentExistsError (router 409, matching SqlAgentStore's IntegrityError path); correct the _write docstring — per-file atomic replace, two commits sequential not transactional. Tests: sync-engine PRAGMA + engine-cache reuse assertions; file create-race -> AgentExistsError; strict Blockbuster anchor over the read endpoints so a regression back onto the loop fails CI. * fix(agents): address round-2 review on the db store path - update_agent tool: align the docstring/inline comment with FileAgentStore._write. Cross-field write atomicity is db-only; the file backend commits config then soul via two sequential os.replace (a crash between them can leave a fresh config.yaml beside a stale SOUL.md). The dropped partial-write *reporting* is an intentional tradeoff — the stage-then-replace safety is preserved (test_update_agent_soul_failure_does_not_replace_config still holds). - SqlAgentStore.update(): true upsert. Catch IntegrityError on the insert-on-missing branch, re-fetch and apply, so two concurrent first-time writes (e.g. two setup_agent handshakes) converge instead of surfacing a raw UNIQUE(user_id, name) violation as a 500. Symmetric with create(). - get_agent_store(): document the graph-subprocess config-resolution invariant (the except->file fallback is a genuine no-config path, not a mask for a misconfigured graph process) and pin it with two tests driving the real get_app_config() file resolution: db resolves from an on-disk config.yaml, file fallback when config is unresolvable. * test(agents): cover SqlAgentStore.update() write-race upsert recovery Mandatory-TDD test for the round-2 fix in 0680340a: two concurrent first-time update()s where the loser's insert hits UNIQUE(user_id, name). Deterministically forces the IntegrityError recovery path by making the first _row probe miss the committed winner, and asserts last-writer-wins instead of a surfaced 500.
151 lines
5.2 KiB
Python
151 lines
5.2 KiB
Python
"""Concurrency safety tests for ``bootstrap_schema``.
|
|
|
|
The contract: N concurrent callers against the same DB always converge to
|
|
``alembic_version == head`` without exceptions and without duplicate schema
|
|
mutations.
|
|
|
|
We model concurrency at the *async-task* level here (multiple coroutines
|
|
inside one process). SQLite is single-node by deployment, so within-process
|
|
serialisation -- which is what the per-engine ``_SQLITE_LOCKS`` entry
|
|
provides -- is the realistic boundary. Cross-process serialisation falls
|
|
through to SQLite's own write lock + ``PRAGMA busy_timeout`` plus the
|
|
idempotent revision helpers.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
import sqlalchemy as sa
|
|
from sqlalchemy.ext.asyncio import create_async_engine
|
|
|
|
import deerflow.persistence.models # noqa: F401
|
|
from deerflow.persistence import bootstrap as bootstrap_mod
|
|
from deerflow.persistence.bootstrap import bootstrap_schema
|
|
|
|
pytestmark = pytest.mark.asyncio
|
|
|
|
|
|
HEAD = "0006_agents"
|
|
|
|
|
|
def _url(tmp_path: Path) -> str:
|
|
return f"sqlite+aiosqlite:///{(tmp_path / 'concurrent.db').as_posix()}"
|
|
|
|
|
|
async def _alembic_version(engine) -> str | None:
|
|
async with engine.connect() as conn:
|
|
row = await conn.execute(sa.text("SELECT version_num FROM alembic_version"))
|
|
return row.scalar()
|
|
|
|
|
|
async def _runs_columns(engine) -> set[str]:
|
|
async with engine.connect() as conn:
|
|
return await conn.run_sync(lambda c: {col["name"] for col in sa.inspect(c).get_columns("runs")})
|
|
|
|
|
|
async def test_two_concurrent_bootstrap_callers_converge(tmp_path: Path) -> None:
|
|
engine = create_async_engine(_url(tmp_path))
|
|
try:
|
|
await asyncio.gather(
|
|
bootstrap_schema(engine, backend="sqlite"),
|
|
bootstrap_schema(engine, backend="sqlite"),
|
|
)
|
|
assert await _alembic_version(engine) == HEAD
|
|
assert "token_usage_by_model" in await _runs_columns(engine)
|
|
finally:
|
|
await engine.dispose()
|
|
|
|
|
|
async def test_five_concurrent_bootstrap_callers_converge(tmp_path: Path) -> None:
|
|
engine = create_async_engine(_url(tmp_path))
|
|
try:
|
|
await asyncio.gather(*(bootstrap_schema(engine, backend="sqlite") for _ in range(5)))
|
|
assert await _alembic_version(engine) == HEAD
|
|
finally:
|
|
await engine.dispose()
|
|
|
|
|
|
async def test_cancelled_caller_does_not_block_others(tmp_path: Path) -> None:
|
|
"""Cancelling one task mid-bootstrap must not strand the lock or the DB.
|
|
|
|
After the cancel, a subsequent ``bootstrap_schema`` call must still reach
|
|
head.
|
|
"""
|
|
engine = create_async_engine(_url(tmp_path))
|
|
try:
|
|
task = asyncio.create_task(bootstrap_schema(engine, backend="sqlite"))
|
|
# Give the event loop a turn so the task can start; then cancel.
|
|
await asyncio.sleep(0)
|
|
task.cancel()
|
|
# Cancelled task may have raced past the lock; swallow either outcome.
|
|
try:
|
|
await task
|
|
except (asyncio.CancelledError, Exception): # noqa: BLE001
|
|
pass
|
|
|
|
# Lock must be free for the next caller.
|
|
await bootstrap_schema(engine, backend="sqlite")
|
|
assert await _alembic_version(engine) == HEAD
|
|
finally:
|
|
await engine.dispose()
|
|
|
|
|
|
async def test_late_caller_after_head_is_noop(monkeypatch, tmp_path: Path) -> None:
|
|
"""When the first caller leaves the DB at head, the second observes
|
|
'versioned' and skips create_all / stamp -- it only runs upgrade head,
|
|
which is alembic-no-op.
|
|
|
|
We use a monkeypatched ``_upgrade`` counter to assert the second caller's
|
|
upgrade ran but did no real work (no new revision applied).
|
|
"""
|
|
engine = create_async_engine(_url(tmp_path))
|
|
try:
|
|
# First caller: empty branch.
|
|
await bootstrap_schema(engine, backend="sqlite")
|
|
first_version = await _alembic_version(engine)
|
|
assert first_version == HEAD
|
|
|
|
upgrade_calls: list[str] = []
|
|
original_upgrade = bootstrap_mod._upgrade
|
|
|
|
def counting_upgrade(cfg, rev: str) -> None:
|
|
upgrade_calls.append(rev)
|
|
original_upgrade(cfg, rev)
|
|
|
|
monkeypatch.setattr(bootstrap_mod, "_upgrade", counting_upgrade)
|
|
|
|
# Second caller: versioned branch -> calls _upgrade('head').
|
|
await bootstrap_schema(engine, backend="sqlite")
|
|
assert upgrade_calls == ["head"]
|
|
assert await _alembic_version(engine) == HEAD
|
|
finally:
|
|
await engine.dispose()
|
|
|
|
|
|
async def test_slow_upgrade_does_not_corrupt_concurrent_state(monkeypatch, tmp_path: Path) -> None:
|
|
"""Inject a delay into the upgrade path; concurrent callers must still
|
|
converge to head with no exceptions."""
|
|
engine = create_async_engine(_url(tmp_path))
|
|
try:
|
|
original_upgrade = bootstrap_mod._upgrade
|
|
|
|
def slow_upgrade(cfg, rev: str) -> None:
|
|
import time # noqa: PLC0415
|
|
|
|
time.sleep(0.2)
|
|
original_upgrade(cfg, rev)
|
|
|
|
monkeypatch.setattr(bootstrap_mod, "_upgrade", slow_upgrade)
|
|
|
|
await asyncio.gather(
|
|
bootstrap_schema(engine, backend="sqlite"),
|
|
bootstrap_schema(engine, backend="sqlite"),
|
|
bootstrap_schema(engine, backend="sqlite"),
|
|
)
|
|
assert await _alembic_version(engine) == HEAD
|
|
finally:
|
|
await engine.dispose()
|