mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-03 06:12:14 +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 - **App** (`app/`): unpublished application code with import prefix `app.*`.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on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated.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>
154 lines
5.3 KiB
Python
154 lines
5.3 KiB
Python
"""ChannelStore — persists IM chat-to-DeerFlow thread mappings."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import logging
|
|
import tempfile
|
|
import threading
|
|
import time
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class ChannelStore:
|
|
"""JSON-file-backed store that maps IM conversations to DeerFlow threads.
|
|
|
|
Data layout (on disk)::
|
|
|
|
{
|
|
"<channel_name>:<chat_id>": {
|
|
"thread_id": "<uuid>",
|
|
"user_id": "<platform_user>",
|
|
"created_at": 1700000000.0,
|
|
"updated_at": 1700000000.0
|
|
},
|
|
...
|
|
}
|
|
|
|
The store is intentionally simple — a single JSON file that is atomically
|
|
rewritten on every mutation. For production workloads with high concurrency,
|
|
this can be swapped for a proper database backend.
|
|
"""
|
|
|
|
def __init__(self, path: str | Path | None = None) -> None:
|
|
if path is None:
|
|
from deerflow.config.paths import get_paths
|
|
|
|
path = Path(get_paths().base_dir) / "channels" / "store.json"
|
|
self._path = Path(path)
|
|
self._path.parent.mkdir(parents=True, exist_ok=True)
|
|
self._data: dict[str, dict[str, Any]] = self._load()
|
|
self._lock = threading.Lock()
|
|
|
|
# -- persistence -------------------------------------------------------
|
|
|
|
def _load(self) -> dict[str, dict[str, Any]]:
|
|
if self._path.exists():
|
|
try:
|
|
return json.loads(self._path.read_text(encoding="utf-8"))
|
|
except (json.JSONDecodeError, OSError):
|
|
logger.warning("Corrupt channel store at %s, starting fresh", self._path)
|
|
return {}
|
|
|
|
def _save(self) -> None:
|
|
fd = tempfile.NamedTemporaryFile(
|
|
mode="w",
|
|
dir=self._path.parent,
|
|
suffix=".tmp",
|
|
delete=False,
|
|
)
|
|
try:
|
|
json.dump(self._data, fd, indent=2)
|
|
fd.close()
|
|
Path(fd.name).replace(self._path)
|
|
except BaseException:
|
|
fd.close()
|
|
Path(fd.name).unlink(missing_ok=True)
|
|
raise
|
|
|
|
# -- key helpers -------------------------------------------------------
|
|
|
|
@staticmethod
|
|
def _key(channel_name: str, chat_id: str, topic_id: str | None = None) -> str:
|
|
if topic_id:
|
|
return f"{channel_name}:{chat_id}:{topic_id}"
|
|
return f"{channel_name}:{chat_id}"
|
|
|
|
# -- public API --------------------------------------------------------
|
|
|
|
def get_thread_id(self, channel_name: str, chat_id: str, topic_id: str | None = None) -> str | None:
|
|
"""Look up the DeerFlow thread_id for a given IM conversation/topic."""
|
|
entry = self._data.get(self._key(channel_name, chat_id, topic_id))
|
|
return entry["thread_id"] if entry else None
|
|
|
|
def set_thread_id(
|
|
self,
|
|
channel_name: str,
|
|
chat_id: str,
|
|
thread_id: str,
|
|
*,
|
|
topic_id: str | None = None,
|
|
user_id: str = "",
|
|
) -> None:
|
|
"""Create or update the mapping for an IM conversation/topic."""
|
|
with self._lock:
|
|
key = self._key(channel_name, chat_id, topic_id)
|
|
now = time.time()
|
|
existing = self._data.get(key)
|
|
self._data[key] = {
|
|
"thread_id": thread_id,
|
|
"user_id": user_id,
|
|
"created_at": existing["created_at"] if existing else now,
|
|
"updated_at": now,
|
|
}
|
|
self._save()
|
|
|
|
def remove(self, channel_name: str, chat_id: str, topic_id: str | None = None) -> bool:
|
|
"""Remove a mapping.
|
|
|
|
If ``topic_id`` is provided, only that specific conversation/topic mapping is removed.
|
|
If ``topic_id`` is omitted, all mappings whose key starts with
|
|
``"<channel_name>:<chat_id>"`` (including topic-specific ones) are removed.
|
|
|
|
Returns True if at least one mapping was removed.
|
|
"""
|
|
with self._lock:
|
|
# Remove a specific conversation/topic mapping.
|
|
if topic_id is not None:
|
|
key = self._key(channel_name, chat_id, topic_id)
|
|
if key in self._data:
|
|
del self._data[key]
|
|
self._save()
|
|
return True
|
|
return False
|
|
|
|
# Remove all mappings for this channel/chat_id (base and any topic-specific keys).
|
|
prefix = self._key(channel_name, chat_id)
|
|
keys_to_delete = [k for k in self._data if k == prefix or k.startswith(prefix + ":")]
|
|
if not keys_to_delete:
|
|
return False
|
|
|
|
for k in keys_to_delete:
|
|
del self._data[k]
|
|
self._save()
|
|
return True
|
|
|
|
def list_entries(self, channel_name: str | None = None) -> list[dict[str, Any]]:
|
|
"""List all stored mappings, optionally filtered by channel."""
|
|
results = []
|
|
for key, entry in self._data.items():
|
|
parts = key.split(":", 2)
|
|
ch = parts[0]
|
|
chat = parts[1] if len(parts) > 1 else ""
|
|
topic = parts[2] if len(parts) > 2 else None
|
|
if channel_name and ch != channel_name:
|
|
continue
|
|
item: dict[str, Any] = {"channel_name": ch, "chat_id": chat, **entry}
|
|
if topic is not None:
|
|
item["topic_id"] = topic
|
|
results.append(item)
|
|
return results
|