Ryker_Feng 063d62c3c3
feat(persistence): support custom postgres schema (#3442)
* feat(persistence): support custom postgres schema

* fix(persistence): address CI lint/test failures and review feedback

- Map missing psycopg import to actionable POSTGRES_INSTALL guidance in
  sync/async schema-creation helpers
- Accept SQLAlchemy compound DSN schemes (postgresql+asyncpg) when
  injecting search_path, normalizing to a libpq-consumable DSN
- Guard keyword-DSN tests with importorskip so they skip without psycopg
- Set database=None in sync checkpointer none-fix test to avoid MagicMock
  backend resolution
- Apply ruff import sort and format

* fix(persistence): address pg-schema review feedback

- Restrict postgres_schema regex to lowercase-only so the quoted CREATE
  SCHEMA matches the unquoted search_path (PG case-folds it), fixing the
  mixed-case bug where tables silently fell back to public.
- Replace shlex.join/split with libpq-correct backslash escaping for the
  options parameter so values containing spaces survive intact.
- Add normalize_libpq_dsn() and route the async checkpointer pool through
  dsn_with_search_path() so a +asyncpg suffix is stripped and existing DSN
  options (e.g. statement_timeout) are merged instead of overridden.
- Extract shared ensure_postgres_schema()/ensure_postgres_schema_async()
  helpers (mapping missing psycopg to the install hint) used by all four
  provider sites.
- Tests: reject mixed-case schemas, preserve space-containing libpq option,
  cover normalize_libpq_dsn, and assert pool search_path via DSN.

* fix(persistence): align pg-schema test with merged store API

The main merge moved the sync Store factory to the single-path
_resolve_store_config/_sync_store_cm design, dropping the PR's
_sync_store_from_database helper. The integration test still imported
the removed symbol, breaking test collection (backend-unit-tests).
Resolve the store config from a DatabaseConfig and drive it through
_sync_store_cm instead.

* fix(persistence): address pg-schema review feedback

- reject trailing/leading whitespace in postgres_schema via re.fullmatch
  (a $-anchored re.match let "deerflow\n" through, silently landing tables
  in public)
- re-escape all whitespace (TAB/CR/LF) when re-joining libpq options so a
  caller's pre-existing options value round-trips losslessly
- re-validate the identifier inside create_schema_sql as defense-in-depth
  at the SQL-emitting boundary
- accept the postgres:// short scheme in the alembic search_path injection
- close the sync psycopg connection explicitly (psycopg3 __exit__ does not
  close()), mirroring the async path
- drop the partial checkpointer/store reset on a database config change;
  database is restart-required and the ORM engine is not rebuilt, so a
  partial reset would half-migrate the deployment

* docs(config): complete the postgres_schema migration checklist

Address PR review (P1): the documented `public`->schema migration only
moved runs, run_events, threads_meta, feedback, and users. That strands
every other DeerFlow-owned table -- the four channel_* tables, both
scheduled_* tables, agents, and (critically) alembic_version -- in
`public`. On restart bootstrap treats the partially-populated target
schema as unversioned, re-baselines it, and replays migrations while the
real rows stay invisible in `public`.

List the full owned set explicitly, call out alembic_version as required,
and keep the "discover the rest" query for version-drift safety.

* refactor(checkpointer): drop test-only _sync_checkpointer_from_database

Address PR review: the helper was only reached by the env-gated
integration test and re-implemented the DatabaseConfig->CheckpointerConfig
backend resolution that _resolve_checkpointer_config already owns, so a
future backend added there would silently miss this path. Mirror the store
side of the same test, which reuses the production path directly:
_resolve_checkpointer_config(...) + _sync_checkpointer_cm(...).
2026-07-30 13:51:17 +08:00

233 lines
9.1 KiB
Python

"""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
import threading
from collections.abc import Iterator
from langgraph.types import Checkpointer
from deerflow.config.app_config import AppConfig, get_app_config
from deerflow.config.checkpointer_config import CheckpointerConfig, ensure_config_loaded, get_checkpointer_config
from deerflow.persistence.postgres_schema import dsn_with_search_path, ensure_postgres_schema
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 the package extra with: pip install 'deerflow-harness[postgres]' (or use: uv sync --all-packages --extra postgres when developing locally)"
)
POSTGRES_CONN_REQUIRED = "checkpointer.connection_string is required for the postgres backend"
def _ensure_postgres_schema(conn_string: str, schema: str) -> None:
"""Create the configured schema before LangGraph creates its tables."""
ensure_postgres_schema(conn_string, schema, install_hint=POSTGRES_INSTALL)
# ---------------------------------------------------------------------------
# Config resolution
# ---------------------------------------------------------------------------
def _resolve_checkpointer_config(app_config: AppConfig) -> CheckpointerConfig:
"""Resolve the checkpointer backend from legacy or unified application config.
The legacy ``checkpointer`` section remains authoritative when present so
Checkpointer and Store keep using the same backend. Otherwise the unified
``database`` section drives the checkpointer, matching the async
:func:`~deerflow.runtime.checkpointer.async_provider.make_checkpointer`
factory and the sync Store provider's ``_resolve_store_config``.
"""
if app_config.checkpointer is not None:
return app_config.checkpointer
database = app_config.database
if database is None or database.backend == "memory":
return CheckpointerConfig(type="memory")
if database.backend == "sqlite":
return CheckpointerConfig(type="sqlite", connection_string=database.checkpointer_sqlite_path)
if database.backend == "postgres":
if not database.postgres_url:
raise ValueError("database.postgres_url is required for the postgres backend")
return CheckpointerConfig(type="postgres", connection_string=database.postgres_url, postgres_schema=database.postgres_schema)
raise ValueError(f"Unknown database backend: {database.backend!r}")
def _get_checkpointer_config() -> CheckpointerConfig:
"""Load checkpointer config without holding the provider singleton lock."""
ensure_config_loaded()
# Preserve callers that initialise the legacy config singleton directly.
legacy_config = get_checkpointer_config()
if legacy_config is not None:
return legacy_config
try:
app_config = get_app_config()
except FileNotFoundError:
return CheckpointerConfig(type="memory")
return _resolve_checkpointer_config(app_config)
# ---------------------------------------------------------------------------
# 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)
_ensure_postgres_schema(config.connection_string, config.postgres_schema)
conn_string = dsn_with_search_path(config.connection_string, config.postgres_schema)
with PostgresSaver.from_conn_string(conn_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
_checkpointer_lock = threading.Lock()
def get_checkpointer() -> Checkpointer:
"""Return the global sync checkpointer singleton, creating it on first call.
The legacy ``checkpointer`` section takes precedence when configured;
otherwise the unified ``database`` section selects the backend. Returns an
``InMemorySaver`` when neither selects a persistent backend.
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 loading can reset both persistence singletons. Resolve the full
# config outside this provider lock to avoid cross-provider lock-order inversion.
config = _get_checkpointer_config()
with _checkpointer_lock:
if _checkpointer is not None:
return _checkpointer
checkpointer_ctx = _sync_checkpointer_cm(config)
checkpointer = checkpointer_ctx.__enter__()
_checkpointer_ctx = checkpointer_ctx
_checkpointer = checkpointer
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
with _checkpointer_lock:
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() -> 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() as cp:
graph.invoke(input, config={"configurable": {"thread_id": "1"}})
The legacy ``checkpointer`` section takes precedence when configured;
otherwise the unified ``database`` section selects the backend. Yields an
``InMemorySaver`` when neither selects a persistent backend.
"""
config = _resolve_checkpointer_config(get_app_config())
with _sync_checkpointer_cm(config) as saver:
yield saver