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
@@ -0,0 +1,9 @@
|
||||
from .async_provider import make_checkpointer
|
||||
from .provider import checkpointer_context, get_checkpointer, reset_checkpointer
|
||||
|
||||
__all__ = [
|
||||
"get_checkpointer",
|
||||
"reset_checkpointer",
|
||||
"checkpointer_context",
|
||||
"make_checkpointer",
|
||||
]
|
||||
@@ -0,0 +1,157 @@
|
||||
"""Async checkpointer factory.
|
||||
|
||||
Provides an **async context manager** for long-running async servers that need
|
||||
proper resource cleanup.
|
||||
|
||||
Supported backends: memory, sqlite, postgres.
|
||||
|
||||
Usage (e.g. FastAPI lifespan)::
|
||||
|
||||
from deerflow.runtime.checkpointer.async_provider import make_checkpointer
|
||||
|
||||
async with make_checkpointer() as checkpointer:
|
||||
app.state.checkpointer = checkpointer # InMemorySaver if not configured
|
||||
|
||||
For sync usage see :mod:`deerflow.runtime.checkpointer.provider`.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import contextlib
|
||||
import logging
|
||||
from collections.abc import AsyncIterator
|
||||
|
||||
from langgraph.types import Checkpointer
|
||||
|
||||
from deerflow.config.app_config import AppConfig
|
||||
from deerflow.runtime.checkpointer.provider import (
|
||||
POSTGRES_CONN_REQUIRED,
|
||||
POSTGRES_INSTALL,
|
||||
SQLITE_INSTALL,
|
||||
)
|
||||
from deerflow.runtime.store._sqlite_utils import ensure_sqlite_parent_dir, resolve_sqlite_conn_str
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Async factory
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@contextlib.asynccontextmanager
|
||||
async def _async_checkpointer(config) -> AsyncIterator[Checkpointer]:
|
||||
"""Async context manager that constructs and tears down a checkpointer."""
|
||||
if config.type == "memory":
|
||||
from langgraph.checkpoint.memory import InMemorySaver
|
||||
|
||||
yield InMemorySaver()
|
||||
return
|
||||
|
||||
if config.type == "sqlite":
|
||||
try:
|
||||
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
|
||||
except ImportError as exc:
|
||||
raise ImportError(SQLITE_INSTALL) from exc
|
||||
|
||||
conn_str = resolve_sqlite_conn_str(config.connection_string or "store.db")
|
||||
await asyncio.to_thread(ensure_sqlite_parent_dir, conn_str)
|
||||
async with AsyncSqliteSaver.from_conn_string(conn_str) as saver:
|
||||
await saver.setup()
|
||||
yield saver
|
||||
return
|
||||
|
||||
if config.type == "postgres":
|
||||
try:
|
||||
from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
|
||||
except ImportError as exc:
|
||||
raise ImportError(POSTGRES_INSTALL) from exc
|
||||
|
||||
if not config.connection_string:
|
||||
raise ValueError(POSTGRES_CONN_REQUIRED)
|
||||
|
||||
async with AsyncPostgresSaver.from_conn_string(config.connection_string) as saver:
|
||||
await saver.setup()
|
||||
yield saver
|
||||
return
|
||||
|
||||
raise ValueError(f"Unknown checkpointer type: {config.type!r}")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Public async context manager
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@contextlib.asynccontextmanager
|
||||
async def _async_checkpointer_from_database(db_config) -> AsyncIterator[Checkpointer]:
|
||||
"""Async context manager that constructs a checkpointer from unified DatabaseConfig."""
|
||||
if db_config.backend == "memory":
|
||||
from langgraph.checkpoint.memory import InMemorySaver
|
||||
|
||||
yield InMemorySaver()
|
||||
return
|
||||
|
||||
if db_config.backend == "sqlite":
|
||||
try:
|
||||
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
|
||||
except ImportError as exc:
|
||||
raise ImportError(SQLITE_INSTALL) from exc
|
||||
|
||||
conn_str = db_config.checkpointer_sqlite_path
|
||||
ensure_sqlite_parent_dir(conn_str)
|
||||
async with AsyncSqliteSaver.from_conn_string(conn_str) as saver:
|
||||
await saver.setup()
|
||||
yield saver
|
||||
return
|
||||
|
||||
if db_config.backend == "postgres":
|
||||
try:
|
||||
from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
|
||||
except ImportError as exc:
|
||||
raise ImportError(POSTGRES_INSTALL) from exc
|
||||
|
||||
if not db_config.postgres_url:
|
||||
raise ValueError("database.postgres_url is required for the postgres backend")
|
||||
|
||||
async with AsyncPostgresSaver.from_conn_string(db_config.postgres_url) as saver:
|
||||
await saver.setup()
|
||||
yield saver
|
||||
return
|
||||
|
||||
raise ValueError(f"Unknown database backend: {db_config.backend!r}")
|
||||
|
||||
|
||||
@contextlib.asynccontextmanager
|
||||
async def make_checkpointer(app_config: AppConfig) -> AsyncIterator[Checkpointer]:
|
||||
"""Async context manager that yields a checkpointer for the caller's lifetime.
|
||||
Resources are opened on enter and closed on exit -- no global state::
|
||||
|
||||
async with make_checkpointer(app_config) as checkpointer:
|
||||
app.state.checkpointer = checkpointer
|
||||
|
||||
Yields an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
|
||||
|
||||
Priority:
|
||||
1. Legacy ``checkpointer:`` config section (backward compatible)
|
||||
2. Unified ``database:`` config section
|
||||
3. Default InMemorySaver
|
||||
"""
|
||||
|
||||
# Legacy: standalone checkpointer config takes precedence
|
||||
if app_config.checkpointer is not None:
|
||||
async with _async_checkpointer(app_config.checkpointer) as saver:
|
||||
yield saver
|
||||
return
|
||||
|
||||
# Unified database config
|
||||
db_config = getattr(app_config, "database", None)
|
||||
if db_config is not None and db_config.backend != "memory":
|
||||
async with _async_checkpointer_from_database(db_config) as saver:
|
||||
yield saver
|
||||
return
|
||||
|
||||
# Default: in-memory
|
||||
from langgraph.checkpoint.memory import InMemorySaver
|
||||
|
||||
yield InMemorySaver()
|
||||
@@ -0,0 +1,175 @@
|
||||
"""Sync checkpointer factory.
|
||||
|
||||
Provides a **sync singleton** and a **sync context manager** for LangGraph
|
||||
graph compilation and CLI tools.
|
||||
|
||||
Supported backends: memory, sqlite, postgres.
|
||||
|
||||
Usage::
|
||||
|
||||
from deerflow.runtime.checkpointer.provider import get_checkpointer, checkpointer_context
|
||||
|
||||
# Singleton — reused across calls, closed on process exit
|
||||
cp = get_checkpointer()
|
||||
|
||||
# One-shot — fresh connection, closed on block exit
|
||||
with checkpointer_context() as cp:
|
||||
graph.invoke(input, config={"configurable": {"thread_id": "1"}})
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import contextlib
|
||||
import logging
|
||||
from collections.abc import Iterator
|
||||
|
||||
from langgraph.types import Checkpointer
|
||||
|
||||
from deerflow.config.app_config import AppConfig
|
||||
from deerflow.config.checkpointer_config import CheckpointerConfig
|
||||
from deerflow.runtime.store._sqlite_utils import ensure_sqlite_parent_dir, resolve_sqlite_conn_str
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Error message constants — imported by aio.provider too
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
SQLITE_INSTALL = "langgraph-checkpoint-sqlite is required for the SQLite checkpointer. Install it with: uv add langgraph-checkpoint-sqlite"
|
||||
POSTGRES_INSTALL = "langgraph-checkpoint-postgres is required for the PostgreSQL checkpointer. Install it with: uv add langgraph-checkpoint-postgres psycopg[binary] psycopg-pool"
|
||||
POSTGRES_CONN_REQUIRED = "checkpointer.connection_string is required for the postgres backend"
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Sync factory
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@contextlib.contextmanager
|
||||
def _sync_checkpointer_cm(config: CheckpointerConfig) -> Iterator[Checkpointer]:
|
||||
"""Context manager that creates and tears down a sync checkpointer.
|
||||
|
||||
Returns a configured ``Checkpointer`` instance. Resource cleanup for any
|
||||
underlying connections or pools is handled by higher-level helpers in
|
||||
this module (such as the singleton factory or context manager); this
|
||||
function does not return a separate cleanup callback.
|
||||
"""
|
||||
if config.type == "memory":
|
||||
from langgraph.checkpoint.memory import InMemorySaver
|
||||
|
||||
logger.info("Checkpointer: using InMemorySaver (in-process, not persistent)")
|
||||
yield InMemorySaver()
|
||||
return
|
||||
|
||||
if config.type == "sqlite":
|
||||
try:
|
||||
from langgraph.checkpoint.sqlite import SqliteSaver
|
||||
except ImportError as exc:
|
||||
raise ImportError(SQLITE_INSTALL) from exc
|
||||
|
||||
conn_str = resolve_sqlite_conn_str(config.connection_string or "store.db")
|
||||
ensure_sqlite_parent_dir(conn_str)
|
||||
with SqliteSaver.from_conn_string(conn_str) as saver:
|
||||
saver.setup()
|
||||
logger.info("Checkpointer: using SqliteSaver (%s)", conn_str)
|
||||
yield saver
|
||||
return
|
||||
|
||||
if config.type == "postgres":
|
||||
try:
|
||||
from langgraph.checkpoint.postgres import PostgresSaver
|
||||
except ImportError as exc:
|
||||
raise ImportError(POSTGRES_INSTALL) from exc
|
||||
|
||||
if not config.connection_string:
|
||||
raise ValueError(POSTGRES_CONN_REQUIRED)
|
||||
|
||||
with PostgresSaver.from_conn_string(config.connection_string) as saver:
|
||||
saver.setup()
|
||||
logger.info("Checkpointer: using PostgresSaver")
|
||||
yield saver
|
||||
return
|
||||
|
||||
raise ValueError(f"Unknown checkpointer type: {config.type!r}")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Sync singleton
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
_checkpointer: Checkpointer | None = None
|
||||
_checkpointer_ctx = None # open context manager keeping the connection alive
|
||||
|
||||
|
||||
def get_checkpointer(app_config: AppConfig) -> Checkpointer:
|
||||
"""Return the global sync checkpointer singleton, creating it on first call.
|
||||
|
||||
Returns an ``InMemorySaver`` only when ``checkpointer`` is explicitly
|
||||
absent from config.yaml. Any other failure (missing config, invalid
|
||||
backend, connection error) propagates — silent degradation to in-memory
|
||||
would drop persistent-run state on process restart.
|
||||
|
||||
Raises:
|
||||
ImportError: If the required package for the configured backend is not installed.
|
||||
ValueError: If ``connection_string`` is missing for a backend that requires it.
|
||||
"""
|
||||
global _checkpointer, _checkpointer_ctx
|
||||
|
||||
if _checkpointer is not None:
|
||||
return _checkpointer
|
||||
|
||||
config = app_config.checkpointer
|
||||
if config is None:
|
||||
from langgraph.checkpoint.memory import InMemorySaver
|
||||
|
||||
logger.info("Checkpointer: using InMemorySaver (in-process, not persistent)")
|
||||
_checkpointer = InMemorySaver()
|
||||
return _checkpointer
|
||||
|
||||
_checkpointer_ctx = _sync_checkpointer_cm(config)
|
||||
_checkpointer = _checkpointer_ctx.__enter__()
|
||||
|
||||
return _checkpointer
|
||||
|
||||
|
||||
def reset_checkpointer() -> None:
|
||||
"""Reset the sync singleton, forcing recreation on the next call.
|
||||
|
||||
Closes any open backend connections and clears the cached instance.
|
||||
Useful in tests or after a configuration change.
|
||||
"""
|
||||
global _checkpointer, _checkpointer_ctx
|
||||
if _checkpointer_ctx is not None:
|
||||
try:
|
||||
_checkpointer_ctx.__exit__(None, None, None)
|
||||
except Exception:
|
||||
logger.warning("Error during checkpointer cleanup", exc_info=True)
|
||||
_checkpointer_ctx = None
|
||||
_checkpointer = None
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Sync context manager
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@contextlib.contextmanager
|
||||
def checkpointer_context(app_config: AppConfig) -> Iterator[Checkpointer]:
|
||||
"""Sync context manager that yields a checkpointer and cleans up on exit.
|
||||
|
||||
Unlike :func:`get_checkpointer`, this does **not** cache the instance —
|
||||
each ``with`` block creates and destroys its own connection. Use it in
|
||||
CLI scripts or tests where you want deterministic cleanup::
|
||||
|
||||
with checkpointer_context(app_config) as cp:
|
||||
graph.invoke(input, config={"configurable": {"thread_id": "1"}})
|
||||
|
||||
Yields an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
|
||||
"""
|
||||
if app_config.checkpointer is None:
|
||||
from langgraph.checkpoint.memory import InMemorySaver
|
||||
|
||||
yield InMemorySaver()
|
||||
return
|
||||
|
||||
with _sync_checkpointer_cm(app_config.checkpointer) as saver:
|
||||
yield saver
|
||||
Reference in New Issue
Block a user