refactor(harness): remove old persistence layer from deerflow package

Remove the following deprecated modules:
- deerflow/persistence/ - old SQL persistence models and repositories
- deerflow/config/checkpointer_config.py - checkpointer configuration
- deerflow/config/database_config.py - database configuration
- deerflow/runtime/checkpointer/ - checkpointer providers
- deerflow/runtime/store/ - store providers
- deerflow/runtime/events/ - event store implementations
- deerflow/runtime/journal.py - run journal

These components are replaced by the new storage layer in app/infra/.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
rayhpeng
2026-04-22 11:25:32 +08:00
parent 2fe0856e33
commit 37fd8b0d7a
37 changed files with 0 additions and 3526 deletions
@@ -1,46 +0,0 @@
"""Configuration for LangGraph checkpointer."""
from typing import Literal
from pydantic import BaseModel, Field
CheckpointerType = Literal["memory", "sqlite", "postgres"]
class CheckpointerConfig(BaseModel):
"""Configuration for LangGraph state persistence checkpointer."""
type: CheckpointerType = Field(
description="Checkpointer backend type. "
"'memory' is in-process only (lost on restart). "
"'sqlite' persists to a local file (requires langgraph-checkpoint-sqlite). "
"'postgres' persists to PostgreSQL (requires langgraph-checkpoint-postgres)."
)
connection_string: str | None = Field(
default=None,
description="Connection string for sqlite (file path) or postgres (DSN). "
"Required for sqlite and postgres types. "
"For sqlite, use a file path like '.deer-flow/checkpoints.db' or ':memory:' for in-memory. "
"For postgres, use a DSN like 'postgresql://user:pass@localhost:5432/db'.",
)
# Global configuration instance — None means no checkpointer is configured.
_checkpointer_config: CheckpointerConfig | None = None
def get_checkpointer_config() -> CheckpointerConfig | None:
"""Get the current checkpointer configuration, or None if not configured."""
return _checkpointer_config
def set_checkpointer_config(config: CheckpointerConfig | None) -> None:
"""Set the checkpointer configuration."""
global _checkpointer_config
_checkpointer_config = config
def load_checkpointer_config_from_dict(config_dict: dict) -> None:
"""Load checkpointer configuration from a dictionary."""
global _checkpointer_config
_checkpointer_config = CheckpointerConfig(**config_dict)
@@ -1,102 +0,0 @@
"""Unified database backend configuration.
Controls BOTH the LangGraph checkpointer and the DeerFlow application
persistence layer (runs, threads metadata, users, etc.). The user
configures one backend; the system handles physical separation details.
SQLite mode: checkpointer and app share a single .db file
({sqlite_dir}/deerflow.db) with WAL journal mode enabled on every
connection. WAL allows concurrent readers and a single writer without
blocking, making a unified file safe for both workloads. Writers
that contend for the lock wait via the default 5-second sqlite3
busy timeout rather than failing immediately.
Postgres mode: both use the same database URL but maintain independent
connection pools with different lifecycles.
Memory mode: checkpointer uses MemorySaver, app uses in-memory stores.
No database is initialized.
Sensitive values (postgres_url) should use $VAR syntax in config.yaml
to reference environment variables from .env:
database:
backend: postgres
postgres_url: $DATABASE_URL
The $VAR resolution is handled by AppConfig.resolve_env_variables()
before this config is instantiated -- DatabaseConfig itself does not
need to do any environment variable processing.
"""
from __future__ import annotations
import os
from typing import Literal
from pydantic import BaseModel, Field
class DatabaseConfig(BaseModel):
backend: Literal["memory", "sqlite", "postgres"] = Field(
default="memory",
description=("Storage backend for both checkpointer and application data. 'memory' for development (no persistence across restarts), 'sqlite' for single-node deployment, 'postgres' for production multi-node deployment."),
)
sqlite_dir: str = Field(
default=".deer-flow/data",
description=("Directory for the SQLite database file. Both checkpointer and application data share {sqlite_dir}/deerflow.db."),
)
postgres_url: str = Field(
default="",
description=(
"PostgreSQL connection URL, shared by checkpointer and app. "
"Use $DATABASE_URL in config.yaml to reference .env. "
"Example: postgresql://user:pass@host:5432/deerflow "
"(the +asyncpg driver suffix is added automatically where needed)."
),
)
echo_sql: bool = Field(
default=False,
description="Echo all SQL statements to log (debug only).",
)
pool_size: int = Field(
default=5,
description="Connection pool size for the app ORM engine (postgres only).",
)
# -- Derived helpers (not user-configured) --
@property
def _resolved_sqlite_dir(self) -> str:
"""Resolve sqlite_dir to an absolute path (relative to CWD)."""
from pathlib import Path
return str(Path(self.sqlite_dir).resolve())
@property
def sqlite_path(self) -> str:
"""Unified SQLite file path shared by checkpointer and app."""
return os.path.join(self._resolved_sqlite_dir, "deerflow.db")
# Backward-compatible aliases
@property
def checkpointer_sqlite_path(self) -> str:
"""SQLite file path for the LangGraph checkpointer (alias for sqlite_path)."""
return self.sqlite_path
@property
def app_sqlite_path(self) -> str:
"""SQLite file path for application ORM data (alias for sqlite_path)."""
return self.sqlite_path
@property
def app_sqlalchemy_url(self) -> str:
"""SQLAlchemy async URL for the application ORM engine."""
if self.backend == "sqlite":
return f"sqlite+aiosqlite:///{self.sqlite_path}"
if self.backend == "postgres":
url = self.postgres_url
if url.startswith("postgresql://"):
url = url.replace("postgresql://", "postgresql+asyncpg://", 1)
return url
raise ValueError(f"No SQLAlchemy URL for backend={self.backend!r}")