mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-08 16:24:45 +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 - **App** (`app/`): unpublished application code with import prefix `app.*`.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on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated.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>
110 lines
3.4 KiB
Python
110 lines
3.4 KiB
Python
"""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.agents.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.agents.checkpointer.provider`.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import contextlib
|
|
import logging
|
|
from collections.abc import AsyncIterator
|
|
|
|
from langgraph.types import Checkpointer
|
|
|
|
from deerflow.agents.checkpointer.provider import (
|
|
POSTGRES_CONN_REQUIRED,
|
|
POSTGRES_INSTALL,
|
|
SQLITE_INSTALL,
|
|
_resolve_sqlite_conn_str,
|
|
)
|
|
from deerflow.config.app_config import get_app_config
|
|
|
|
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
|
|
|
|
import pathlib
|
|
|
|
conn_str = _resolve_sqlite_conn_str(config.connection_string or "store.db")
|
|
# Only create parent directories for real filesystem paths
|
|
if conn_str != ":memory:" and not conn_str.startswith("file:"):
|
|
pathlib.Path(conn_str).parent.mkdir(parents=True, exist_ok=True)
|
|
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 make_checkpointer() -> 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() as checkpointer:
|
|
app.state.checkpointer = checkpointer
|
|
|
|
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
|
|
|
|
async with _async_checkpointer(config.checkpointer) as saver:
|
|
yield saver
|