mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-23 16:35:59 +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:
@@ -13,6 +13,7 @@ from app.channels.base import Channel
|
||||
from app.channels.commands import KNOWN_CHANNEL_COMMANDS
|
||||
from app.channels.message_bus import InboundMessage, InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
|
||||
from deerflow.config.paths import VIRTUAL_PATH_PREFIX, get_paths
|
||||
from deerflow.runtime.user_context import get_effective_user_id
|
||||
from deerflow.sandbox.sandbox_provider import get_sandbox_provider
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -344,8 +345,9 @@ class FeishuChannel(Channel):
|
||||
return f"Failed to obtain the [{type}]"
|
||||
|
||||
paths = get_paths()
|
||||
paths.ensure_thread_dirs(thread_id)
|
||||
uploads_dir = paths.sandbox_uploads_dir(thread_id).resolve()
|
||||
user_id = get_effective_user_id()
|
||||
paths.ensure_thread_dirs(thread_id, user_id=user_id)
|
||||
uploads_dir = paths.sandbox_uploads_dir(thread_id, user_id=user_id).resolve()
|
||||
|
||||
ext = "png" if type == "image" else "bin"
|
||||
raw_filename = getattr(response, "file_name", "") or f"feishu_{file_key[-12:]}.{ext}"
|
||||
@@ -373,7 +375,9 @@ class FeishuChannel(Channel):
|
||||
virtual_path = f"{VIRTUAL_PATH_PREFIX}/uploads/{resolved_target.name}"
|
||||
|
||||
try:
|
||||
sandbox_provider = get_sandbox_provider()
|
||||
from deerflow.config.app_config import AppConfig
|
||||
|
||||
sandbox_provider = get_sandbox_provider(AppConfig.from_file())
|
||||
sandbox_id = sandbox_provider.acquire(thread_id)
|
||||
if sandbox_id != "local":
|
||||
sandbox = sandbox_provider.get(sandbox_id)
|
||||
|
||||
@@ -17,6 +17,7 @@ from langgraph_sdk.errors import ConflictError
|
||||
from app.channels.commands import KNOWN_CHANNEL_COMMANDS
|
||||
from app.channels.message_bus import InboundMessage, InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
|
||||
from app.channels.store import ChannelStore
|
||||
from deerflow.runtime.user_context import get_effective_user_id
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -342,14 +343,15 @@ def _resolve_attachments(thread_id: str, artifacts: list[str]) -> list[ResolvedA
|
||||
|
||||
attachments: list[ResolvedAttachment] = []
|
||||
paths = get_paths()
|
||||
outputs_dir = paths.sandbox_outputs_dir(thread_id).resolve()
|
||||
user_id = get_effective_user_id()
|
||||
outputs_dir = paths.sandbox_outputs_dir(thread_id, user_id=user_id).resolve()
|
||||
for virtual_path in artifacts:
|
||||
# Security: only allow files from the agent outputs directory
|
||||
if not virtual_path.startswith(_OUTPUTS_VIRTUAL_PREFIX):
|
||||
logger.warning("[Manager] rejected non-outputs artifact path: %s", virtual_path)
|
||||
continue
|
||||
try:
|
||||
actual = paths.resolve_virtual_path(thread_id, virtual_path)
|
||||
actual = paths.resolve_virtual_path(thread_id, virtual_path, user_id=user_id)
|
||||
# Verify the resolved path is actually under the outputs directory
|
||||
# (guards against path-traversal even after prefix check)
|
||||
try:
|
||||
|
||||
@@ -4,13 +4,16 @@ from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
from typing import Any
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
from app.channels.base import Channel
|
||||
from app.channels.manager import DEFAULT_GATEWAY_URL, DEFAULT_LANGGRAPH_URL, ChannelManager
|
||||
from app.channels.message_bus import MessageBus
|
||||
from app.channels.store import ChannelStore
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from deerflow.config.app_config import AppConfig
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Channel name → import path for lazy loading
|
||||
@@ -75,14 +78,11 @@ class ChannelService:
|
||||
self._running = False
|
||||
|
||||
@classmethod
|
||||
def from_app_config(cls) -> ChannelService:
|
||||
"""Create a ChannelService from the application config."""
|
||||
from deerflow.config.app_config import get_app_config
|
||||
|
||||
config = get_app_config()
|
||||
def from_app_config(cls, app_config: AppConfig) -> ChannelService:
|
||||
"""Create a ChannelService from an explicit application config."""
|
||||
channels_config = {}
|
||||
# extra fields are allowed by AppConfig (extra="allow")
|
||||
extra = config.model_extra or {}
|
||||
extra = app_config.model_extra or {}
|
||||
if "channels" in extra:
|
||||
channels_config = extra["channels"]
|
||||
return cls(channels_config=channels_config)
|
||||
@@ -201,12 +201,12 @@ def get_channel_service() -> ChannelService | None:
|
||||
return _channel_service
|
||||
|
||||
|
||||
async def start_channel_service() -> ChannelService:
|
||||
async def start_channel_service(app_config: AppConfig) -> ChannelService:
|
||||
"""Create and start the global ChannelService from app config."""
|
||||
global _channel_service
|
||||
if _channel_service is not None:
|
||||
return _channel_service
|
||||
_channel_service = ChannelService.from_app_config()
|
||||
_channel_service = ChannelService.from_app_config(app_config)
|
||||
await _channel_service.start()
|
||||
return _channel_service
|
||||
|
||||
|
||||
Reference in New Issue
Block a user