feat(persistence): add SQLAlchemy 2.0 async ORM scaffold

Introduce a unified database configuration (DatabaseConfig) that
controls both the LangGraph checkpointer and the DeerFlow application
persistence layer from a single `database:` config section.

New modules:
- deerflow.config.database_config — Pydantic config with memory/sqlite/postgres backends
- deerflow.persistence — async engine lifecycle, DeclarativeBase with to_dict mixin, Alembic skeleton
- deerflow.runtime.runs.store — RunStore ABC + MemoryRunStore implementation

Gateway integration initializes/tears down the persistence engine in
the existing langgraph_runtime() context manager. Legacy checkpointer
config is preserved for backward compatibility.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
rayhpeng
2026-04-01 15:50:06 +08:00
parent 3e461d9d08
commit 1ff6b5f7ab
18 changed files with 1099 additions and 17 deletions
@@ -0,0 +1,4 @@
from deerflow.runtime.runs.store.base import RunStore
from deerflow.runtime.runs.store.memory import MemoryRunStore
__all__ = ["MemoryRunStore", "RunStore"]
@@ -0,0 +1,59 @@
"""Abstract interface for run metadata storage.
RunManager depends on this interface. Implementations:
- MemoryRunStore: in-memory dict (development, tests)
- Future: RunRepository backed by SQLAlchemy ORM
All methods accept an optional owner_id for user isolation.
When owner_id is None, no user filtering is applied (single-user mode).
"""
from __future__ import annotations
import abc
from typing import Any
class RunStore(abc.ABC):
@abc.abstractmethod
async def put(
self,
run_id: str,
*,
thread_id: str,
assistant_id: str | None = None,
owner_id: str | None = None,
status: str = "pending",
multitask_strategy: str = "reject",
metadata: dict[str, Any] | None = None,
kwargs: dict[str, Any] | None = None,
error: str | None = None,
created_at: str | None = None,
) -> None: ...
@abc.abstractmethod
async def get(self, run_id: str) -> dict[str, Any] | None: ...
@abc.abstractmethod
async def list_by_thread(
self,
thread_id: str,
*,
owner_id: str | None = None,
limit: int = 100,
) -> list[dict[str, Any]]: ...
@abc.abstractmethod
async def update_status(
self,
run_id: str,
status: str,
*,
error: str | None = None,
) -> None: ...
@abc.abstractmethod
async def delete(self, run_id: str) -> None: ...
@abc.abstractmethod
async def list_pending(self, *, before: str | None = None) -> list[dict[str, Any]]: ...
@@ -0,0 +1,69 @@
"""In-memory RunStore. Used when database.backend=memory (default) and in tests.
Equivalent to the original RunManager._runs dict behavior.
"""
from __future__ import annotations
from datetime import UTC, datetime
from typing import Any
from deerflow.runtime.runs.store.base import RunStore
class MemoryRunStore(RunStore):
def __init__(self) -> None:
self._runs: dict[str, dict[str, Any]] = {}
async def put(
self,
run_id,
*,
thread_id,
assistant_id=None,
owner_id=None,
status="pending",
multitask_strategy="reject",
metadata=None,
kwargs=None,
error=None,
created_at=None,
):
now = datetime.now(UTC).isoformat()
self._runs[run_id] = {
"run_id": run_id,
"thread_id": thread_id,
"assistant_id": assistant_id,
"owner_id": owner_id,
"status": status,
"multitask_strategy": multitask_strategy,
"metadata": metadata or {},
"kwargs": kwargs or {},
"error": error,
"created_at": created_at or now,
"updated_at": now,
}
async def get(self, run_id):
return self._runs.get(run_id)
async def list_by_thread(self, thread_id, *, owner_id=None, limit=100):
results = [r for r in self._runs.values() if r["thread_id"] == thread_id and (owner_id is None or r.get("owner_id") == owner_id)]
results.sort(key=lambda r: r["created_at"], reverse=True)
return results[:limit]
async def update_status(self, run_id, status, *, error=None):
if run_id in self._runs:
self._runs[run_id]["status"] = status
if error is not None:
self._runs[run_id]["error"] = error
self._runs[run_id]["updated_at"] = datetime.now(UTC).isoformat()
async def delete(self, run_id):
self._runs.pop(run_id, None)
async def list_pending(self, *, before=None):
now = before or datetime.now(UTC).isoformat()
results = [r for r in self._runs.values() if r["status"] == "pending" and r["created_at"] <= now]
results.sort(key=lambda r: r["created_at"])
return results