mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-02 22:02:13 +08:00
* refactor: extract shared utils to break harness→app cross-layer imports Move _validate_skill_frontmatter to src/skills/validation.py and CONVERTIBLE_EXTENSIONS + convert_file_to_markdown to src/utils/file_conversion.py. This eliminates the two reverse dependencies from client.py (harness layer) into gateway/routers/ (app layer), preparing for the harness/app package split. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor: split backend/src into harness (deerflow.*) and app (app.*) Physically split the monolithic backend/src/ package into two layers: - **Harness** (`packages/harness/deerflow/`): publishable agent framework package with import prefix `deerflow.*`. Contains agents, sandbox, tools, models, MCP, skills, config, and all core infrastructure. - **App** (`app/`): unpublished application code with import prefix `app.*`. Contains gateway (FastAPI REST API) and channels (IM integrations). Key changes: - Move 13 harness modules to packages/harness/deerflow/ via git mv - Move gateway + channels to app/ via git mv - Rename all imports: src.* → deerflow.* (harness) / app.* (app layer) - Set up uv workspace with deerflow-harness as workspace member - Update langgraph.json, config.example.yaml, all scripts, Docker files - Add build-system (hatchling) to harness pyproject.toml - Add PYTHONPATH=. to gateway startup commands for app.* resolution - Update ruff.toml with known-first-party for import sorting - Update all documentation to reflect new directory structure Boundary rule enforced: harness code never imports from app. All 429 tests pass. Lint clean. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: add harness→app boundary check test and update docs Add test_harness_boundary.py that scans all Python files in packages/harness/deerflow/ and fails if any `from app.*` or `import app.*` statement is found. This enforces the architectural rule that the harness layer never depends on the app layer. Update CLAUDE.md to document the harness/app split architecture, import conventions, and the boundary enforcement test. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add config versioning with auto-upgrade on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated. This adds a config_version field and auto-upgrade mechanism so breaking changes (like src.* → deerflow.* renames) are applied automatically before services start. - Add config_version: 1 to config.example.yaml - Add startup version check warning in AppConfig.from_file() - Add scripts/config-upgrade.sh with migration registry for value replacements - Add `make config-upgrade` target - Auto-run config-upgrade in serve.sh and start-daemon.sh before starting services - Add config error hints in service failure messages Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix comments * fix: update src.* import in test_sandbox_tools_security to deerflow.* Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: handle empty config and search parent dirs for config.example.yaml Address Copilot review comments on PR #1131: - Guard against yaml.safe_load() returning None for empty config files - Search parent directories for config.example.yaml instead of only looking next to config.yaml, fixing detection in common setups Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: correct skills root path depth and config_version type coercion - loader.py: fix get_skills_root_path() to use 5 parent levels (was 3) after harness split, file lives at packages/harness/deerflow/skills/ so parent×3 resolved to backend/packages/harness/ instead of backend/ - app_config.py: coerce config_version to int() before comparison in _check_config_version() to prevent TypeError when YAML stores value as string (e.g. config_version: "1") - tests: add regression tests for both fixes Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: update test imports from src.* to deerflow.*/app.* after harness refactor Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
202 lines
7.3 KiB
Python
202 lines
7.3 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.agents.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 get_app_config
|
|
from deerflow.config.checkpointer_config import CheckpointerConfig
|
|
from deerflow.config.paths import resolve_path
|
|
|
|
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
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def _resolve_sqlite_conn_str(raw: str) -> str:
|
|
"""Return a SQLite connection string ready for use with ``SqliteSaver``.
|
|
|
|
SQLite special strings (``":memory:"`` and ``file:`` URIs) are returned
|
|
unchanged. Plain filesystem paths — relative or absolute — are resolved
|
|
to an absolute string via :func:`resolve_path`.
|
|
"""
|
|
if raw == ":memory:" or raw.startswith("file:"):
|
|
return raw
|
|
return str(resolve_path(raw))
|
|
|
|
|
|
@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")
|
|
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() -> Checkpointer:
|
|
"""Return the global sync checkpointer singleton, creating it on first call.
|
|
|
|
Returns an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
|
|
|
|
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
|
|
|
|
# Ensure app config is loaded before checking checkpointer config
|
|
# This prevents returning InMemorySaver when config.yaml actually has a checkpointer section
|
|
# but hasn't been loaded yet
|
|
from deerflow.config.app_config import _app_config
|
|
from deerflow.config.checkpointer_config import get_checkpointer_config
|
|
|
|
if _app_config is None:
|
|
# Only load config if it hasn't been initialized yet
|
|
# In tests, config may be set directly via set_checkpointer_config()
|
|
try:
|
|
get_app_config()
|
|
except FileNotFoundError:
|
|
# In test environments without config.yaml, this is expected
|
|
# Tests will set config directly via set_checkpointer_config()
|
|
pass
|
|
|
|
config = get_checkpointer_config()
|
|
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() -> 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"}})
|
|
|
|
Yields an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
|
|
"""
|
|
|
|
config = get_app_config()
|
|
if config.checkpointer is None:
|
|
from langgraph.checkpoint.memory import InMemorySaver
|
|
|
|
yield InMemorySaver()
|
|
return
|
|
|
|
with _sync_checkpointer_cm(config.checkpointer) as saver:
|
|
yield saver
|