mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-04-28 12:48:40 +00:00
3e6a34297d
Squashes 25 PR commits onto current main. AppConfig becomes a pure value object with no ambient lookup. Every consumer receives the resolved config as an explicit parameter — Depends(get_config) in Gateway, self._app_config in DeerFlowClient, runtime.context.app_config in agent runs, AppConfig.from_file() at the LangGraph Server registration boundary. Phase 1 — frozen data + typed context - All config models (AppConfig, MemoryConfig, DatabaseConfig, …) become frozen=True; no sub-module globals. - AppConfig.from_file() is pure (no side-effect singleton loaders). - Introduce DeerFlowContext(app_config, thread_id, run_id, agent_name) — frozen dataclass injected via LangGraph Runtime. - Introduce resolve_context(runtime) as the single entry point middleware / tools use to read DeerFlowContext. Phase 2 — pure explicit parameter passing - Gateway: app.state.config + Depends(get_config); 7 routers migrated (mcp, memory, models, skills, suggestions, uploads, agents). - DeerFlowClient: __init__(config=...) captures config locally. - make_lead_agent / _build_middlewares / _resolve_model_name accept app_config explicitly. - RunContext.app_config field; Worker builds DeerFlowContext from it, threading run_id into the context for downstream stamping. - Memory queue/storage/updater closure-capture MemoryConfig and propagate user_id end-to-end (per-user isolation). - Sandbox/skills/community/factories/tools thread app_config. - resolve_context() rejects non-typed runtime.context. - Test suite migrated off AppConfig.current() monkey-patches. - AppConfig.current() classmethod deleted. Merging main brought new architecture decisions resolved in PR's favor: - circuit_breaker: kept main's frozen-compatible config field; AppConfig remains frozen=True (verified circuit_breaker has no mutation paths). - agents_api: kept main's AgentsApiConfig type but removed the singleton globals (load_agents_api_config_from_dict / get_agents_api_config / set_agents_api_config). 8 routes in agents.py now read via Depends(get_config). - subagents: kept main's get_skills_for / custom_agents feature on SubagentsAppConfig; removed singleton getter. registry.py now reads app_config.subagents directly. - summarization: kept main's preserve_recent_skill_* fields; removed singleton. - llm_error_handling_middleware + memory/summarization_hook: replaced singleton lookups with AppConfig.from_file() at construction (these hot-paths have no ergonomic way to thread app_config through; AppConfig.from_file is a pure load). - worker.py + thread_data_middleware.py: DeerFlowContext.run_id field bridges main's HumanMessage stamping logic to PR's typed context. Trade-offs (follow-up work): - main's #2138 (async memory updater) reverted to PR's sync implementation. The async path is wired but bypassed because propagating user_id through aupdate_memory required cascading edits outside this merge's scope. - tests/test_subagent_skills_config.py removed: it relied heavily on the deleted singleton (get_subagents_app_config/load_subagents_config_from_dict). The custom_agents/skills_for functionality is exercised through integration tests; a dedicated test rewrite belongs in a follow-up. Verification: backend test suite — 2560 passed, 4 skipped, 84 failures. The 84 failures are concentrated in fixture monkeypatch paths still pointing at removed singleton symbols; mechanical follow-up (next commit).
298 lines
12 KiB
Python
298 lines
12 KiB
Python
"""Unit tests for checkpointer config and singleton factory."""
|
|
|
|
import sys
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
from deerflow.config.app_config import AppConfig
|
|
from deerflow.config.checkpointer_config import CheckpointerConfig
|
|
from deerflow.config.sandbox_config import SandboxConfig
|
|
from deerflow.runtime.checkpointer import get_checkpointer, reset_checkpointer
|
|
|
|
|
|
def _make_config(checkpointer: CheckpointerConfig | None = None) -> AppConfig:
|
|
return AppConfig(sandbox=SandboxConfig(use="test"), checkpointer=checkpointer)
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def reset_state():
|
|
"""Reset singleton state before each test."""
|
|
reset_checkpointer()
|
|
yield
|
|
reset_checkpointer()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Config tests
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestCheckpointerConfig:
|
|
def test_memory_config(self):
|
|
config = CheckpointerConfig(type="memory")
|
|
assert config.type == "memory"
|
|
assert config.connection_string is None
|
|
|
|
def test_sqlite_config(self):
|
|
config = CheckpointerConfig(type="sqlite", connection_string="/tmp/test.db")
|
|
assert config.type == "sqlite"
|
|
assert config.connection_string == "/tmp/test.db"
|
|
|
|
def test_postgres_config(self):
|
|
config = CheckpointerConfig(type="postgres", connection_string="postgresql://localhost/db")
|
|
assert config.type == "postgres"
|
|
assert config.connection_string == "postgresql://localhost/db"
|
|
|
|
def test_default_connection_string_is_none(self):
|
|
config = CheckpointerConfig(type="memory")
|
|
assert config.connection_string is None
|
|
|
|
def test_invalid_type_raises(self):
|
|
with pytest.raises(Exception):
|
|
CheckpointerConfig(type="unknown")
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Factory tests
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestGetCheckpointer:
|
|
def test_returns_in_memory_saver_when_not_configured(self):
|
|
"""get_checkpointer should return InMemorySaver when not configured."""
|
|
from langgraph.checkpoint.memory import InMemorySaver
|
|
|
|
cfg = _make_config()
|
|
cp = get_checkpointer(cfg)
|
|
assert cp is not None
|
|
assert isinstance(cp, InMemorySaver)
|
|
|
|
def test_memory_returns_in_memory_saver(self):
|
|
from langgraph.checkpoint.memory import InMemorySaver
|
|
|
|
cfg = _make_config(CheckpointerConfig(type="memory"))
|
|
cp = get_checkpointer(cfg)
|
|
assert isinstance(cp, InMemorySaver)
|
|
|
|
def test_memory_singleton(self):
|
|
cfg = _make_config(CheckpointerConfig(type="memory"))
|
|
cp1 = get_checkpointer(cfg)
|
|
cp2 = get_checkpointer(cfg)
|
|
assert cp1 is cp2
|
|
|
|
def test_reset_clears_singleton(self):
|
|
cfg = _make_config(CheckpointerConfig(type="memory"))
|
|
cp1 = get_checkpointer(cfg)
|
|
reset_checkpointer()
|
|
cp2 = get_checkpointer(cfg)
|
|
assert cp1 is not cp2
|
|
|
|
def test_sqlite_raises_when_package_missing(self):
|
|
cfg = _make_config(CheckpointerConfig(type="sqlite", connection_string="/tmp/test.db"))
|
|
with patch.dict(sys.modules, {"langgraph.checkpoint.sqlite": None}):
|
|
reset_checkpointer()
|
|
with pytest.raises(ImportError, match="langgraph-checkpoint-sqlite"):
|
|
get_checkpointer(cfg)
|
|
|
|
def test_postgres_raises_when_package_missing(self):
|
|
cfg = _make_config(CheckpointerConfig(type="postgres", connection_string="postgresql://localhost/db"))
|
|
with patch.dict(sys.modules, {"langgraph.checkpoint.postgres": None}):
|
|
reset_checkpointer()
|
|
with pytest.raises(ImportError, match="langgraph-checkpoint-postgres"):
|
|
get_checkpointer(cfg)
|
|
|
|
def test_postgres_raises_when_connection_string_missing(self):
|
|
cfg = _make_config(CheckpointerConfig(type="postgres"))
|
|
mock_saver = MagicMock()
|
|
mock_module = MagicMock()
|
|
mock_module.PostgresSaver = mock_saver
|
|
with patch.dict(sys.modules, {"langgraph.checkpoint.postgres": mock_module}):
|
|
reset_checkpointer()
|
|
with pytest.raises(ValueError, match="connection_string is required"):
|
|
get_checkpointer(cfg)
|
|
|
|
def test_sqlite_creates_saver(self):
|
|
"""SQLite checkpointer is created when package is available."""
|
|
cfg = _make_config(CheckpointerConfig(type="sqlite", connection_string="/tmp/test.db"))
|
|
|
|
mock_saver_instance = MagicMock()
|
|
mock_cm = MagicMock()
|
|
mock_cm.__enter__ = MagicMock(return_value=mock_saver_instance)
|
|
mock_cm.__exit__ = MagicMock(return_value=False)
|
|
|
|
mock_saver_cls = MagicMock()
|
|
mock_saver_cls.from_conn_string = MagicMock(return_value=mock_cm)
|
|
|
|
mock_module = MagicMock()
|
|
mock_module.SqliteSaver = mock_saver_cls
|
|
|
|
with patch.dict(sys.modules, {"langgraph.checkpoint.sqlite": mock_module}):
|
|
reset_checkpointer()
|
|
cp = get_checkpointer(cfg)
|
|
|
|
assert cp is mock_saver_instance
|
|
mock_saver_cls.from_conn_string.assert_called_once()
|
|
mock_saver_instance.setup.assert_called_once()
|
|
|
|
def test_sqlite_creates_parent_dir(self):
|
|
"""Sync SQLite checkpointer should call ensure_sqlite_parent_dir before connecting.
|
|
|
|
This mirrors the async checkpointer's behaviour and prevents
|
|
'sqlite3.OperationalError: unable to open database file' when the
|
|
parent directory for the database file does not yet exist (e.g. when
|
|
using the harness package from an external virtualenv where the
|
|
.deer-flow directory has not been created).
|
|
"""
|
|
load_checkpointer_config_from_dict({"type": "sqlite", "connection_string": "relative/test.db"})
|
|
|
|
mock_saver_instance = MagicMock()
|
|
mock_cm = MagicMock()
|
|
mock_cm.__enter__ = MagicMock(return_value=mock_saver_instance)
|
|
mock_cm.__exit__ = MagicMock(return_value=False)
|
|
|
|
mock_saver_cls = MagicMock()
|
|
mock_saver_cls.from_conn_string = MagicMock(return_value=mock_cm)
|
|
|
|
mock_module = MagicMock()
|
|
mock_module.SqliteSaver = mock_saver_cls
|
|
|
|
with (
|
|
patch.dict(sys.modules, {"langgraph.checkpoint.sqlite": mock_module}),
|
|
patch("deerflow.agents.checkpointer.provider.ensure_sqlite_parent_dir") as mock_ensure,
|
|
patch(
|
|
"deerflow.agents.checkpointer.provider.resolve_sqlite_conn_str",
|
|
return_value="/tmp/resolved/relative/test.db",
|
|
),
|
|
):
|
|
reset_checkpointer()
|
|
cp = get_checkpointer()
|
|
|
|
assert cp is mock_saver_instance
|
|
mock_ensure.assert_called_once_with("/tmp/resolved/relative/test.db")
|
|
mock_saver_cls.from_conn_string.assert_called_once_with("/tmp/resolved/relative/test.db")
|
|
|
|
def test_sqlite_ensure_parent_dir_before_connect(self):
|
|
"""ensure_sqlite_parent_dir must be called before from_conn_string."""
|
|
load_checkpointer_config_from_dict({"type": "sqlite", "connection_string": "relative/test.db"})
|
|
|
|
call_order = []
|
|
|
|
mock_saver_instance = MagicMock()
|
|
mock_cm = MagicMock()
|
|
mock_cm.__enter__ = MagicMock(return_value=mock_saver_instance)
|
|
mock_cm.__exit__ = MagicMock(return_value=False)
|
|
|
|
mock_saver_cls = MagicMock()
|
|
mock_saver_cls.from_conn_string = MagicMock(side_effect=lambda *a, **kw: (call_order.append("connect"), mock_cm)[1])
|
|
|
|
mock_module = MagicMock()
|
|
mock_module.SqliteSaver = mock_saver_cls
|
|
|
|
def record_ensure(*a, **kw):
|
|
call_order.append("ensure")
|
|
|
|
with (
|
|
patch.dict(sys.modules, {"langgraph.checkpoint.sqlite": mock_module}),
|
|
patch(
|
|
"deerflow.agents.checkpointer.provider.ensure_sqlite_parent_dir",
|
|
side_effect=record_ensure,
|
|
),
|
|
patch(
|
|
"deerflow.agents.checkpointer.provider.resolve_sqlite_conn_str",
|
|
return_value="/tmp/resolved/relative/test.db",
|
|
),
|
|
):
|
|
reset_checkpointer()
|
|
get_checkpointer()
|
|
|
|
assert call_order == ["ensure", "connect"]
|
|
|
|
def test_postgres_creates_saver(self):
|
|
"""Postgres checkpointer is created when packages are available."""
|
|
cfg = _make_config(CheckpointerConfig(type="postgres", connection_string="postgresql://localhost/db"))
|
|
|
|
mock_saver_instance = MagicMock()
|
|
mock_cm = MagicMock()
|
|
mock_cm.__enter__ = MagicMock(return_value=mock_saver_instance)
|
|
mock_cm.__exit__ = MagicMock(return_value=False)
|
|
|
|
mock_saver_cls = MagicMock()
|
|
mock_saver_cls.from_conn_string = MagicMock(return_value=mock_cm)
|
|
|
|
mock_pg_module = MagicMock()
|
|
mock_pg_module.PostgresSaver = mock_saver_cls
|
|
|
|
with patch.dict(sys.modules, {"langgraph.checkpoint.postgres": mock_pg_module}):
|
|
reset_checkpointer()
|
|
cp = get_checkpointer(cfg)
|
|
|
|
assert cp is mock_saver_instance
|
|
mock_saver_cls.from_conn_string.assert_called_once_with("postgresql://localhost/db")
|
|
mock_saver_instance.setup.assert_called_once()
|
|
|
|
|
|
class TestAsyncCheckpointer:
|
|
@pytest.mark.anyio
|
|
async def test_sqlite_creates_parent_dir_via_to_thread(self):
|
|
"""Async SQLite setup should move mkdir off the event loop."""
|
|
from deerflow.runtime.checkpointer.async_provider import make_checkpointer
|
|
|
|
mock_config = MagicMock()
|
|
mock_config.checkpointer = CheckpointerConfig(type="sqlite", connection_string="relative/test.db")
|
|
|
|
mock_saver = AsyncMock()
|
|
mock_cm = AsyncMock()
|
|
mock_cm.__aenter__.return_value = mock_saver
|
|
mock_cm.__aexit__.return_value = False
|
|
|
|
mock_saver_cls = MagicMock()
|
|
mock_saver_cls.from_conn_string.return_value = mock_cm
|
|
|
|
mock_module = MagicMock()
|
|
mock_module.AsyncSqliteSaver = mock_saver_cls
|
|
|
|
with (
|
|
patch.dict(sys.modules, {"langgraph.checkpoint.sqlite.aio": mock_module}),
|
|
patch("deerflow.runtime.checkpointer.async_provider.asyncio.to_thread", new_callable=AsyncMock) as mock_to_thread,
|
|
patch(
|
|
"deerflow.runtime.checkpointer.async_provider.resolve_sqlite_conn_str",
|
|
return_value="/tmp/resolved/test.db",
|
|
),
|
|
):
|
|
async with make_checkpointer(mock_config) as saver:
|
|
assert saver is mock_saver
|
|
|
|
mock_to_thread.assert_awaited_once()
|
|
called_fn, called_path = mock_to_thread.await_args.args
|
|
assert called_fn.__name__ == "ensure_sqlite_parent_dir"
|
|
assert called_path == "/tmp/resolved/test.db"
|
|
mock_saver_cls.from_conn_string.assert_called_once_with("/tmp/resolved/test.db")
|
|
mock_saver.setup.assert_awaited_once()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# app_config.py integration
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestAppConfigLoadsCheckpointer:
|
|
def test_load_checkpointer_section(self):
|
|
"""AppConfig with checkpointer section has the correct config."""
|
|
cfg = _make_config(CheckpointerConfig(type="memory"))
|
|
assert cfg.checkpointer is not None
|
|
assert cfg.checkpointer.type == "memory"
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# DeerFlowClient falls back to config checkpointer
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestClientCheckpointerFallback:
|
|
def test_client_uses_config_checkpointer_when_none_provided(self):
|
|
"""DeerFlowClient._ensure_agent falls back to get_checkpointer(app_config) when checkpointer=None."""
|
|
# This is a structural test — verifying the fallback path exists.
|
|
cfg = _make_config(CheckpointerConfig(type="memory"))
|
|
assert cfg.checkpointer is not None
|