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 - **App** (`app/`): unpublished application code with import prefix `app.*`.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on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated.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>
91 lines
3.2 KiB
Python
91 lines
3.2 KiB
Python
from typing import NotRequired, override
|
|
|
|
from langchain.agents import AgentState
|
|
from langchain.agents.middleware import AgentMiddleware
|
|
from langgraph.runtime import Runtime
|
|
|
|
from deerflow.agents.thread_state import ThreadDataState
|
|
from deerflow.config.paths import Paths, get_paths
|
|
|
|
|
|
class ThreadDataMiddlewareState(AgentState):
|
|
"""Compatible with the `ThreadState` schema."""
|
|
|
|
thread_data: NotRequired[ThreadDataState | None]
|
|
|
|
|
|
class ThreadDataMiddleware(AgentMiddleware[ThreadDataMiddlewareState]):
|
|
"""Create thread data directories for each thread execution.
|
|
|
|
Creates the following directory structure:
|
|
- {base_dir}/threads/{thread_id}/user-data/workspace
|
|
- {base_dir}/threads/{thread_id}/user-data/uploads
|
|
- {base_dir}/threads/{thread_id}/user-data/outputs
|
|
|
|
Lifecycle Management:
|
|
- With lazy_init=True (default): Only compute paths, directories created on-demand
|
|
- With lazy_init=False: Eagerly create directories in before_agent()
|
|
"""
|
|
|
|
state_schema = ThreadDataMiddlewareState
|
|
|
|
def __init__(self, base_dir: str | None = None, lazy_init: bool = True):
|
|
"""Initialize the middleware.
|
|
|
|
Args:
|
|
base_dir: Base directory for thread data. Defaults to Paths resolution.
|
|
lazy_init: If True, defer directory creation until needed.
|
|
If False, create directories eagerly in before_agent().
|
|
Default is True for optimal performance.
|
|
"""
|
|
super().__init__()
|
|
self._paths = Paths(base_dir) if base_dir else get_paths()
|
|
self._lazy_init = lazy_init
|
|
|
|
def _get_thread_paths(self, thread_id: str) -> dict[str, str]:
|
|
"""Get the paths for a thread's data directories.
|
|
|
|
Args:
|
|
thread_id: The thread ID.
|
|
|
|
Returns:
|
|
Dictionary with workspace_path, uploads_path, and outputs_path.
|
|
"""
|
|
return {
|
|
"workspace_path": str(self._paths.sandbox_work_dir(thread_id)),
|
|
"uploads_path": str(self._paths.sandbox_uploads_dir(thread_id)),
|
|
"outputs_path": str(self._paths.sandbox_outputs_dir(thread_id)),
|
|
}
|
|
|
|
def _create_thread_directories(self, thread_id: str) -> dict[str, str]:
|
|
"""Create the thread data directories.
|
|
|
|
Args:
|
|
thread_id: The thread ID.
|
|
|
|
Returns:
|
|
Dictionary with the created directory paths.
|
|
"""
|
|
self._paths.ensure_thread_dirs(thread_id)
|
|
return self._get_thread_paths(thread_id)
|
|
|
|
@override
|
|
def before_agent(self, state: ThreadDataMiddlewareState, runtime: Runtime) -> dict | None:
|
|
thread_id = runtime.context.get("thread_id")
|
|
if thread_id is None:
|
|
raise ValueError("Thread ID is required in the context")
|
|
|
|
if self._lazy_init:
|
|
# Lazy initialization: only compute paths, don't create directories
|
|
paths = self._get_thread_paths(thread_id)
|
|
else:
|
|
# Eager initialization: create directories immediately
|
|
paths = self._create_thread_directories(thread_id)
|
|
print(f"Created thread data directories for thread {thread_id}")
|
|
|
|
return {
|
|
"thread_data": {
|
|
**paths,
|
|
}
|
|
}
|