mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-17 22:23:38 +00:00
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).
248 lines
9.2 KiB
Python
248 lines
9.2 KiB
Python
"""Centralized accessors for singleton objects stored on ``app.state``.
|
||
|
||
**Getters** (used by routers): raise 503 when a required dependency is
|
||
missing, except ``get_store`` which returns ``None``.
|
||
|
||
Initialization is handled directly in ``app.py`` via :class:`AsyncExitStack`.
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
from collections.abc import AsyncGenerator
|
||
from contextlib import AsyncExitStack, asynccontextmanager
|
||
from typing import TYPE_CHECKING
|
||
|
||
from fastapi import FastAPI, HTTPException, Request
|
||
|
||
from deerflow.config.app_config import AppConfig
|
||
from deerflow.runtime import RunContext, RunManager
|
||
|
||
if TYPE_CHECKING:
|
||
from app.gateway.auth.local_provider import LocalAuthProvider
|
||
from app.gateway.auth.repositories.sqlite import SQLiteUserRepository
|
||
from deerflow.persistence.thread_meta.base import ThreadMetaStore
|
||
|
||
|
||
def get_config(request: Request) -> AppConfig:
|
||
"""FastAPI dependency returning the app-scoped ``AppConfig``.
|
||
|
||
Reads from ``request.app.state.config`` which is set at startup
|
||
(``app.py`` lifespan) and swapped on config reload (``routers/mcp.py``,
|
||
``routers/skills.py``).
|
||
"""
|
||
cfg = getattr(request.app.state, "config", None)
|
||
if cfg is None:
|
||
raise HTTPException(status_code=503, detail="Configuration not available")
|
||
return cfg
|
||
|
||
|
||
@asynccontextmanager
|
||
async def langgraph_runtime(app: FastAPI) -> AsyncGenerator[None, None]:
|
||
"""Bootstrap and tear down all LangGraph runtime singletons.
|
||
|
||
Usage in ``app.py``::
|
||
|
||
async with langgraph_runtime(app):
|
||
yield
|
||
"""
|
||
from deerflow.persistence.engine import close_engine, get_session_factory, init_engine_from_config
|
||
from deerflow.runtime import make_store, make_stream_bridge
|
||
from deerflow.runtime.checkpointer.async_provider import make_checkpointer
|
||
from deerflow.runtime.events.store import make_run_event_store
|
||
|
||
async with AsyncExitStack() as stack:
|
||
# app.state.config is populated earlier in lifespan(); thread it
|
||
# explicitly into every provider below.
|
||
config = app.state.config
|
||
|
||
app.state.stream_bridge = await stack.enter_async_context(make_stream_bridge(config))
|
||
|
||
# Initialize persistence engine BEFORE checkpointer so that
|
||
# auto-create-database logic runs first (postgres backend).
|
||
await init_engine_from_config(config.database)
|
||
|
||
app.state.checkpointer = await stack.enter_async_context(make_checkpointer(config))
|
||
app.state.store = await stack.enter_async_context(make_store(config))
|
||
|
||
# Initialize repositories — one get_session_factory() call for all.
|
||
sf = get_session_factory()
|
||
if sf is not None:
|
||
from deerflow.persistence.feedback import FeedbackRepository
|
||
from deerflow.persistence.run import RunRepository
|
||
|
||
app.state.run_store = RunRepository(sf)
|
||
app.state.feedback_repo = FeedbackRepository(sf)
|
||
else:
|
||
from deerflow.runtime.runs.store.memory import MemoryRunStore
|
||
|
||
app.state.run_store = MemoryRunStore()
|
||
app.state.feedback_repo = None
|
||
|
||
from deerflow.persistence.thread_meta import make_thread_store
|
||
|
||
app.state.thread_store = make_thread_store(sf, app.state.store)
|
||
|
||
# Run event store (has its own factory with config-driven backend selection)
|
||
run_events_config = getattr(config, "run_events", None)
|
||
app.state.run_event_store = make_run_event_store(run_events_config)
|
||
|
||
# RunManager with store backing for persistence
|
||
app.state.run_manager = RunManager(store=app.state.run_store)
|
||
|
||
try:
|
||
yield
|
||
finally:
|
||
await close_engine()
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Getters – called by routers per-request
|
||
# ---------------------------------------------------------------------------
|
||
|
||
|
||
def _require(attr: str, label: str):
|
||
"""Create a FastAPI dependency that returns ``app.state.<attr>`` or 503."""
|
||
|
||
def dep(request: Request):
|
||
val = getattr(request.app.state, attr, None)
|
||
if val is None:
|
||
raise HTTPException(status_code=503, detail=f"{label} not available")
|
||
return val
|
||
|
||
dep.__name__ = dep.__qualname__ = f"get_{attr}"
|
||
return dep
|
||
|
||
|
||
get_stream_bridge = _require("stream_bridge", "Stream bridge")
|
||
get_run_manager = _require("run_manager", "Run manager")
|
||
get_checkpointer = _require("checkpointer", "Checkpointer")
|
||
get_run_event_store = _require("run_event_store", "Run event store")
|
||
get_feedback_repo = _require("feedback_repo", "Feedback")
|
||
get_run_store = _require("run_store", "Run store")
|
||
|
||
|
||
def get_store(request: Request):
|
||
"""Return the global store (may be ``None`` if not configured)."""
|
||
return getattr(request.app.state, "store", None)
|
||
|
||
|
||
def get_thread_store(request: Request) -> ThreadMetaStore:
|
||
"""Return the thread metadata store (SQL or memory-backed)."""
|
||
val = getattr(request.app.state, "thread_store", None)
|
||
if val is None:
|
||
raise HTTPException(status_code=503, detail="Thread metadata store not available")
|
||
return val
|
||
|
||
|
||
def get_run_context(request: Request) -> RunContext:
|
||
"""Build a :class:`RunContext` from ``app.state`` singletons.
|
||
|
||
Returns a *base* context with infrastructure dependencies. Callers that
|
||
need per-run fields (e.g. ``follow_up_to_run_id``) should use
|
||
``dataclasses.replace(ctx, follow_up_to_run_id=...)`` before passing it
|
||
to :func:`run_agent`.
|
||
"""
|
||
config = get_config(request)
|
||
return RunContext(
|
||
checkpointer=get_checkpointer(request),
|
||
store=get_store(request),
|
||
event_store=get_run_event_store(request),
|
||
run_events_config=getattr(config, "run_events", None),
|
||
thread_store=get_thread_store(request),
|
||
app_config=config,
|
||
)
|
||
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Auth helpers (used by authz.py and auth middleware)
|
||
# ---------------------------------------------------------------------------
|
||
|
||
# Cached singletons to avoid repeated instantiation per request
|
||
_cached_local_provider: LocalAuthProvider | None = None
|
||
_cached_repo: SQLiteUserRepository | None = None
|
||
|
||
|
||
def get_local_provider() -> LocalAuthProvider:
|
||
"""Get or create the cached LocalAuthProvider singleton.
|
||
|
||
Must be called after ``init_engine_from_config()`` — the shared
|
||
session factory is required to construct the user repository.
|
||
"""
|
||
global _cached_local_provider, _cached_repo
|
||
if _cached_repo is None:
|
||
from app.gateway.auth.repositories.sqlite import SQLiteUserRepository
|
||
from deerflow.persistence.engine import get_session_factory
|
||
|
||
sf = get_session_factory()
|
||
if sf is None:
|
||
raise RuntimeError("get_local_provider() called before init_engine_from_config(); cannot access users table")
|
||
_cached_repo = SQLiteUserRepository(sf)
|
||
if _cached_local_provider is None:
|
||
from app.gateway.auth.local_provider import LocalAuthProvider
|
||
|
||
_cached_local_provider = LocalAuthProvider(repository=_cached_repo)
|
||
return _cached_local_provider
|
||
|
||
|
||
async def get_current_user_from_request(request: Request):
|
||
"""Get the current authenticated user from the request cookie.
|
||
|
||
Raises HTTPException 401 if not authenticated.
|
||
"""
|
||
from app.gateway.auth import decode_token
|
||
from app.gateway.auth.errors import AuthErrorCode, AuthErrorResponse, TokenError, token_error_to_code
|
||
|
||
access_token = request.cookies.get("access_token")
|
||
if not access_token:
|
||
raise HTTPException(
|
||
status_code=401,
|
||
detail=AuthErrorResponse(code=AuthErrorCode.NOT_AUTHENTICATED, message="Not authenticated").model_dump(),
|
||
)
|
||
|
||
payload = decode_token(access_token)
|
||
if isinstance(payload, TokenError):
|
||
raise HTTPException(
|
||
status_code=401,
|
||
detail=AuthErrorResponse(code=token_error_to_code(payload), message=f"Token error: {payload.value}").model_dump(),
|
||
)
|
||
|
||
provider = get_local_provider()
|
||
user = await provider.get_user(payload.sub)
|
||
if user is None:
|
||
raise HTTPException(
|
||
status_code=401,
|
||
detail=AuthErrorResponse(code=AuthErrorCode.USER_NOT_FOUND, message="User not found").model_dump(),
|
||
)
|
||
|
||
# Token version mismatch → password was changed, token is stale
|
||
if user.token_version != payload.ver:
|
||
raise HTTPException(
|
||
status_code=401,
|
||
detail=AuthErrorResponse(code=AuthErrorCode.TOKEN_INVALID, message="Token revoked (password changed)").model_dump(),
|
||
)
|
||
|
||
return user
|
||
|
||
|
||
async def get_optional_user_from_request(request: Request):
|
||
"""Get optional authenticated user from request.
|
||
|
||
Returns None if not authenticated.
|
||
"""
|
||
try:
|
||
return await get_current_user_from_request(request)
|
||
except HTTPException:
|
||
return None
|
||
|
||
|
||
async def get_current_user(request: Request) -> str | None:
|
||
"""Extract user_id from request cookie, or None if not authenticated.
|
||
|
||
Thin adapter that returns the string id for callers that only need
|
||
identification (e.g., ``feedback.py``). Full-user callers should use
|
||
``get_current_user_from_request`` or ``get_optional_user_from_request``.
|
||
"""
|
||
user = await get_optional_user_from_request(request)
|
||
return str(user.id) if user else None
|