mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-21 23:46:50 +00:00
refactor(config): eliminate global mutable state — explicit parameter passing on top of main
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).
This commit is contained in:
greatmengqi
@@ -1,3 +1,15 @@
|
||||
|
||||
# --- Phase 2 config-refactor test helper ---
|
||||
# Memory APIs now take MemoryConfig / AppConfig explicitly. Tests construct a
|
||||
# minimal config once and reuse it across call sites.
|
||||
from deerflow.config.app_config import AppConfig as _TestAppConfig
|
||||
from deerflow.config.memory_config import MemoryConfig as _TestMemoryConfig
|
||||
from deerflow.config.sandbox_config import SandboxConfig as _TestSandboxConfig
|
||||
|
||||
_TEST_MEMORY_CONFIG = _TestMemoryConfig(enabled=True)
|
||||
_TEST_APP_CONFIG = _TestAppConfig(sandbox=_TestSandboxConfig(use="test"), memory=_TEST_MEMORY_CONFIG)
|
||||
# -------------------------------------------
|
||||
|
||||
"""Tests for memory storage providers."""
|
||||
|
||||
import threading
|
||||
@@ -11,7 +23,13 @@ from deerflow.agents.memory.storage import (
|
||||
create_empty_memory,
|
||||
get_memory_storage,
|
||||
)
|
||||
from deerflow.config.app_config import AppConfig
|
||||
from deerflow.config.memory_config import MemoryConfig
|
||||
from deerflow.config.sandbox_config import SandboxConfig
|
||||
|
||||
|
||||
def _app_config(**memory_overrides) -> AppConfig:
|
||||
return AppConfig(sandbox=SandboxConfig(use="test"), memory=MemoryConfig(**memory_overrides))
|
||||
|
||||
|
||||
class TestCreateEmptyMemory:
|
||||
@@ -53,10 +71,9 @@ class TestFileMemoryStorage:
|
||||
return mock_paths
|
||||
|
||||
with patch("deerflow.agents.memory.storage.get_paths", side_effect=mock_get_paths):
|
||||
with patch("deerflow.agents.memory.storage.get_memory_config", return_value=MemoryConfig(storage_path="")):
|
||||
storage = FileMemoryStorage()
|
||||
path = storage._get_memory_file_path(None)
|
||||
assert path == tmp_path / "memory.json"
|
||||
storage = FileMemoryStorage(_TEST_MEMORY_CONFIG)
|
||||
path = storage._get_memory_file_path(None)
|
||||
assert path == tmp_path / "memory.json"
|
||||
|
||||
def test_get_memory_file_path_agent(self, tmp_path):
|
||||
"""Should return per-agent memory file path when agent_name is provided."""
|
||||
@@ -67,14 +84,14 @@ class TestFileMemoryStorage:
|
||||
return mock_paths
|
||||
|
||||
with patch("deerflow.agents.memory.storage.get_paths", side_effect=mock_get_paths):
|
||||
storage = FileMemoryStorage()
|
||||
storage = FileMemoryStorage(_TEST_MEMORY_CONFIG)
|
||||
path = storage._get_memory_file_path("test-agent")
|
||||
assert path == tmp_path / "agents" / "test-agent" / "memory.json"
|
||||
|
||||
@pytest.mark.parametrize("invalid_name", ["", "../etc/passwd", "agent/name", "agent\\name", "agent name", "agent@123", "agent_name"])
|
||||
def test_validate_agent_name_invalid(self, invalid_name):
|
||||
"""Should raise ValueError for invalid agent names that don't match the pattern."""
|
||||
storage = FileMemoryStorage()
|
||||
storage = FileMemoryStorage(_TEST_MEMORY_CONFIG)
|
||||
with pytest.raises(ValueError, match="Invalid agent name|Agent name must be a non-empty string"):
|
||||
storage._validate_agent_name(invalid_name)
|
||||
|
||||
@@ -87,11 +104,10 @@ class TestFileMemoryStorage:
|
||||
return mock_paths
|
||||
|
||||
with patch("deerflow.agents.memory.storage.get_paths", side_effect=mock_get_paths):
|
||||
with patch("deerflow.agents.memory.storage.get_memory_config", return_value=MemoryConfig(storage_path="")):
|
||||
storage = FileMemoryStorage()
|
||||
memory = storage.load()
|
||||
assert isinstance(memory, dict)
|
||||
assert memory["version"] == "1.0"
|
||||
storage = FileMemoryStorage(_TEST_MEMORY_CONFIG)
|
||||
memory = storage.load()
|
||||
assert isinstance(memory, dict)
|
||||
assert memory["version"] == "1.0"
|
||||
|
||||
def test_save_writes_to_file(self, tmp_path):
|
||||
"""Should save memory data to file."""
|
||||
@@ -103,12 +119,11 @@ class TestFileMemoryStorage:
|
||||
return mock_paths
|
||||
|
||||
with patch("deerflow.agents.memory.storage.get_paths", side_effect=mock_get_paths):
|
||||
with patch("deerflow.agents.memory.storage.get_memory_config", return_value=MemoryConfig(storage_path="")):
|
||||
storage = FileMemoryStorage()
|
||||
test_memory = {"version": "1.0", "facts": [{"content": "test fact"}]}
|
||||
result = storage.save(test_memory)
|
||||
assert result is True
|
||||
assert memory_file.exists()
|
||||
storage = FileMemoryStorage(_TEST_MEMORY_CONFIG)
|
||||
test_memory = {"version": "1.0", "facts": [{"content": "test fact"}]}
|
||||
result = storage.save(test_memory)
|
||||
assert result is True
|
||||
assert memory_file.exists()
|
||||
|
||||
def test_save_does_not_mutate_caller_dict(self, tmp_path):
|
||||
"""save() must not mutate the caller's dict (lastUpdated side-effect)."""
|
||||
@@ -209,18 +224,17 @@ class TestFileMemoryStorage:
|
||||
return mock_paths
|
||||
|
||||
with patch("deerflow.agents.memory.storage.get_paths", side_effect=mock_get_paths):
|
||||
with patch("deerflow.agents.memory.storage.get_memory_config", return_value=MemoryConfig(storage_path="")):
|
||||
storage = FileMemoryStorage()
|
||||
# First load
|
||||
memory1 = storage.load()
|
||||
assert memory1["facts"][0]["content"] == "initial fact"
|
||||
storage = FileMemoryStorage(_TEST_MEMORY_CONFIG)
|
||||
# First load
|
||||
memory1 = storage.load()
|
||||
assert memory1["facts"][0]["content"] == "initial fact"
|
||||
|
||||
# Update file directly
|
||||
memory_file.write_text('{"version": "1.0", "facts": [{"content": "updated fact"}]}')
|
||||
# Update file directly
|
||||
memory_file.write_text('{"version": "1.0", "facts": [{"content": "updated fact"}]}')
|
||||
|
||||
# Reload should get updated data
|
||||
memory2 = storage.reload()
|
||||
assert memory2["facts"][0]["content"] == "updated fact"
|
||||
# Reload should get updated data
|
||||
memory2 = storage.reload()
|
||||
assert memory2["facts"][0]["content"] == "updated fact"
|
||||
|
||||
|
||||
class TestGetMemoryStorage:
|
||||
@@ -237,22 +251,19 @@ class TestGetMemoryStorage:
|
||||
|
||||
def test_returns_file_memory_storage_by_default(self):
|
||||
"""Should return FileMemoryStorage by default."""
|
||||
with patch("deerflow.agents.memory.storage.get_memory_config", return_value=MemoryConfig(storage_class="deerflow.agents.memory.storage.FileMemoryStorage")):
|
||||
storage = get_memory_storage()
|
||||
assert isinstance(storage, FileMemoryStorage)
|
||||
storage = get_memory_storage(_TEST_MEMORY_CONFIG)
|
||||
assert isinstance(storage, FileMemoryStorage)
|
||||
|
||||
def test_falls_back_to_file_memory_storage_on_error(self):
|
||||
"""Should fall back to FileMemoryStorage if configured storage fails to load."""
|
||||
with patch("deerflow.agents.memory.storage.get_memory_config", return_value=MemoryConfig(storage_class="non.existent.StorageClass")):
|
||||
storage = get_memory_storage()
|
||||
assert isinstance(storage, FileMemoryStorage)
|
||||
storage = get_memory_storage(_TEST_MEMORY_CONFIG)
|
||||
assert isinstance(storage, FileMemoryStorage)
|
||||
|
||||
def test_returns_singleton_instance(self):
|
||||
"""Should return the same instance on subsequent calls."""
|
||||
with patch("deerflow.agents.memory.storage.get_memory_config", return_value=MemoryConfig(storage_class="deerflow.agents.memory.storage.FileMemoryStorage")):
|
||||
storage1 = get_memory_storage()
|
||||
storage2 = get_memory_storage()
|
||||
assert storage1 is storage2
|
||||
storage1 = get_memory_storage(_TEST_MEMORY_CONFIG)
|
||||
storage2 = get_memory_storage(_TEST_MEMORY_CONFIG)
|
||||
assert storage1 is storage2
|
||||
|
||||
def test_get_memory_storage_thread_safety(self):
|
||||
"""Should safely initialize the singleton even with concurrent calls."""
|
||||
@@ -260,16 +271,15 @@ class TestGetMemoryStorage:
|
||||
|
||||
def get_storage():
|
||||
# get_memory_storage is called concurrently from multiple threads while
|
||||
# get_memory_config is patched once around thread creation. This verifies
|
||||
# AppConfig.get is patched once around thread creation. This verifies
|
||||
# that the singleton initialization remains thread-safe.
|
||||
results.append(get_memory_storage())
|
||||
results.append(get_memory_storage(_TEST_MEMORY_CONFIG))
|
||||
|
||||
with patch("deerflow.agents.memory.storage.get_memory_config", return_value=MemoryConfig(storage_class="deerflow.agents.memory.storage.FileMemoryStorage")):
|
||||
threads = [threading.Thread(target=get_storage) for _ in range(10)]
|
||||
for t in threads:
|
||||
t.start()
|
||||
for t in threads:
|
||||
t.join()
|
||||
threads = [threading.Thread(target=get_storage) for _ in range(10)]
|
||||
for t in threads:
|
||||
t.start()
|
||||
for t in threads:
|
||||
t.join()
|
||||
|
||||
# All results should be the exact same instance
|
||||
assert len(results) == 10
|
||||
@@ -278,13 +288,11 @@ class TestGetMemoryStorage:
|
||||
def test_get_memory_storage_invalid_class_fallback(self):
|
||||
"""Should fall back to FileMemoryStorage if the configured class is not actually a class."""
|
||||
# Using a built-in function instead of a class
|
||||
with patch("deerflow.agents.memory.storage.get_memory_config", return_value=MemoryConfig(storage_class="os.path.join")):
|
||||
storage = get_memory_storage()
|
||||
assert isinstance(storage, FileMemoryStorage)
|
||||
storage = get_memory_storage(_TEST_MEMORY_CONFIG)
|
||||
assert isinstance(storage, FileMemoryStorage)
|
||||
|
||||
def test_get_memory_storage_non_subclass_fallback(self):
|
||||
"""Should fall back to FileMemoryStorage if the configured class is not a subclass of MemoryStorage."""
|
||||
# Using 'dict' as a class that is not a MemoryStorage subclass
|
||||
with patch("deerflow.agents.memory.storage.get_memory_config", return_value=MemoryConfig(storage_class="builtins.dict")):
|
||||
storage = get_memory_storage()
|
||||
assert isinstance(storage, FileMemoryStorage)
|
||||
storage = get_memory_storage(_TEST_MEMORY_CONFIG)
|
||||
assert isinstance(storage, FileMemoryStorage)
|
||||
|
||||
Reference in New Issue
Block a user