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 - **App** (`app/`): unpublished application code with import prefix `app.*`.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on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated.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>
99 lines
2.9 KiB
Python
99 lines
2.9 KiB
Python
"""Abstract base class for sandbox provisioning backends."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
import time
|
|
from abc import ABC, abstractmethod
|
|
|
|
import requests
|
|
|
|
from .sandbox_info import SandboxInfo
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def wait_for_sandbox_ready(sandbox_url: str, timeout: int = 30) -> bool:
|
|
"""Poll sandbox health endpoint until ready or timeout.
|
|
|
|
Args:
|
|
sandbox_url: URL of the sandbox (e.g. http://k3s:30001).
|
|
timeout: Maximum time to wait in seconds.
|
|
|
|
Returns:
|
|
True if sandbox is ready, False otherwise.
|
|
"""
|
|
start_time = time.time()
|
|
while time.time() - start_time < timeout:
|
|
try:
|
|
response = requests.get(f"{sandbox_url}/v1/sandbox", timeout=5)
|
|
if response.status_code == 200:
|
|
return True
|
|
except requests.exceptions.RequestException:
|
|
pass
|
|
time.sleep(1)
|
|
return False
|
|
|
|
|
|
class SandboxBackend(ABC):
|
|
"""Abstract base for sandbox provisioning backends.
|
|
|
|
Two implementations:
|
|
- LocalContainerBackend: starts Docker/Apple Container locally, manages ports
|
|
- RemoteSandboxBackend: connects to a pre-existing URL (K8s service, external)
|
|
"""
|
|
|
|
@abstractmethod
|
|
def create(self, thread_id: str, sandbox_id: str, extra_mounts: list[tuple[str, str, bool]] | None = None) -> SandboxInfo:
|
|
"""Create/provision a new sandbox.
|
|
|
|
Args:
|
|
thread_id: Thread ID for which the sandbox is being created. Useful for backends that want to organize sandboxes by thread.
|
|
sandbox_id: Deterministic sandbox identifier.
|
|
extra_mounts: Additional volume mounts as (host_path, container_path, read_only) tuples.
|
|
Ignored by backends that don't manage containers (e.g., remote).
|
|
|
|
Returns:
|
|
SandboxInfo with connection details.
|
|
"""
|
|
...
|
|
|
|
@abstractmethod
|
|
def destroy(self, info: SandboxInfo) -> None:
|
|
"""Destroy/cleanup a sandbox and release its resources.
|
|
|
|
Args:
|
|
info: The sandbox metadata to destroy.
|
|
"""
|
|
...
|
|
|
|
@abstractmethod
|
|
def is_alive(self, info: SandboxInfo) -> bool:
|
|
"""Quick check whether a sandbox is still alive.
|
|
|
|
This should be a lightweight check (e.g., container inspect)
|
|
rather than a full health check.
|
|
|
|
Args:
|
|
info: The sandbox metadata to check.
|
|
|
|
Returns:
|
|
True if the sandbox appears to be alive.
|
|
"""
|
|
...
|
|
|
|
@abstractmethod
|
|
def discover(self, sandbox_id: str) -> SandboxInfo | None:
|
|
"""Try to discover an existing sandbox by its deterministic ID.
|
|
|
|
Used for cross-process recovery: when another process started a sandbox,
|
|
this process can discover it by the deterministic container name or URL.
|
|
|
|
Args:
|
|
sandbox_id: The deterministic sandbox ID to look for.
|
|
|
|
Returns:
|
|
SandboxInfo if found and healthy, None otherwise.
|
|
"""
|
|
...
|