Files
deer-flow/backend/packages/harness/deerflow/community/aio_sandbox/aio_sandbox.py

129 lines
4.5 KiB
Python
Raw Normal View History

import base64
import logging
from agent_sandbox import Sandbox as AioSandboxClient
refactor: split backend into harness (deerflow.*) and app (app.*) (#1131) * 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 - **App** (`app/`): unpublished application code with import prefix `app.*`.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>
2026-03-14 22:55:52 +08:00
from deerflow.sandbox.sandbox import Sandbox
logger = logging.getLogger(__name__)
class AioSandbox(Sandbox):
"""Sandbox implementation using the agent-infra/sandbox Docker container.
This sandbox connects to a running AIO sandbox container via HTTP API.
"""
def __init__(self, id: str, base_url: str, home_dir: str | None = None):
"""Initialize the AIO sandbox.
Args:
id: Unique identifier for this sandbox instance.
base_url: URL of the sandbox API (e.g., http://localhost:8080).
home_dir: Home directory inside the sandbox. If None, will be fetched from the sandbox.
"""
super().__init__(id)
self._base_url = base_url
self._client = AioSandboxClient(base_url=base_url, timeout=600)
self._home_dir = home_dir
@property
def base_url(self) -> str:
return self._base_url
@property
def home_dir(self) -> str:
"""Get the home directory inside the sandbox."""
if self._home_dir is None:
context = self._client.sandbox.get_context()
self._home_dir = context.home_dir
return self._home_dir
def execute_command(self, command: str) -> str:
"""Execute a shell command in the sandbox.
Args:
command: The command to execute.
Returns:
The output of the command.
"""
try:
result = self._client.shell.exec_command(command=command)
output = result.data.output if result.data else ""
return output if output else "(no output)"
except Exception as e:
logger.error(f"Failed to execute command in sandbox: {e}")
return f"Error: {e}"
def read_file(self, path: str) -> str:
"""Read the content of a file in the sandbox.
Args:
path: The absolute path of the file to read.
Returns:
The content of the file.
"""
try:
result = self._client.file.read_file(file=path)
return result.data.content if result.data else ""
except Exception as e:
logger.error(f"Failed to read file in sandbox: {e}")
return f"Error: {e}"
def list_dir(self, path: str, max_depth: int = 2) -> list[str]:
"""List the contents of a directory in the sandbox.
Args:
path: The absolute path of the directory to list.
max_depth: The maximum depth to traverse. Default is 2.
Returns:
The contents of the directory.
"""
try:
# Use shell command to list directory with depth limit
# The -L flag limits the depth for the tree command
result = self._client.shell.exec_command(command=f"find {path} -maxdepth {max_depth} -type f -o -type d 2>/dev/null | head -500")
output = result.data.output if result.data else ""
if output:
return [line.strip() for line in output.strip().split("\n") if line.strip()]
return []
except Exception as e:
logger.error(f"Failed to list directory in sandbox: {e}")
return []
def write_file(self, path: str, content: str, append: bool = False) -> None:
"""Write content to a file in the sandbox.
Args:
path: The absolute path of the file to write to.
content: The text content to write to the file.
append: Whether to append the content to the file.
"""
try:
if append:
# Read existing content first and append
existing = self.read_file(path)
if not existing.startswith("Error:"):
content = existing + content
self._client.file.write_file(file=path, content=content)
except Exception as e:
logger.error(f"Failed to write file in sandbox: {e}")
raise
def update_file(self, path: str, content: bytes) -> None:
"""Update a file with binary content in the sandbox.
Args:
path: The absolute path of the file to update.
content: The binary content to write to the file.
"""
try:
base64_content = base64.b64encode(content).decode("utf-8")
self._client.file.write_file(file=path, content=base64_content, encoding="base64")
except Exception as e:
logger.error(f"Failed to update file in sandbox: {e}")
raise