DATA
6de0bf9f5b
Vendored deer-flow upstream (bytedance/deer-flow) plus prompt-injection hardening: - New deerflow.security package: content_delimiter, html_cleaner, sanitizer (8 layers — invisible chars, control chars, symbols, NFC, PUA, tag chars, horizontal whitespace collapse with newline/tab preservation, length cap) - New deerflow.community.searx package: web_search, web_fetch, image_search backed by a private SearX instance, every external string sanitized and wrapped in <<<EXTERNAL_UNTRUSTED_CONTENT>>> delimiters - All native community web providers (ddg_search, tavily, exa, firecrawl, jina_ai, infoquest, image_search) replaced with hard-fail stubs that raise NativeWebToolDisabledError at import time, so a misconfigured tool.use path fails loud rather than silently falling back to unsanitized output - Native client back-doors (jina_client.py, infoquest_client.py) stubbed too - Native-tool tests quarantined under tests/_disabled_native/ (collect_ignore_glob via local conftest.py) - Sanitizer Layer 7 fix: only collapse horizontal whitespace, preserve newlines and tabs so list/table structure survives - Hardened runtime config.yaml references only the searx-backed tools - Factory overlay (backend/) kept in sync with deer-flow tree as a reference / source See HARDENING.md for the full audit trail and verification steps.
47 lines
1.7 KiB
Python
47 lines
1.7 KiB
Python
"""Boundary check: harness layer must not import from app layer.
|
|
|
|
The deerflow-harness package (packages/harness/deerflow/) is a standalone,
|
|
publishable agent framework. It must never depend on the app layer (app/).
|
|
|
|
This test scans all Python files in the harness package and fails if any
|
|
``from app.`` or ``import app.`` statement is found.
|
|
"""
|
|
|
|
import ast
|
|
from pathlib import Path
|
|
|
|
HARNESS_ROOT = Path(__file__).parent.parent / "packages" / "harness" / "deerflow"
|
|
|
|
BANNED_PREFIXES = ("app.",)
|
|
|
|
|
|
def _collect_imports(filepath: Path) -> list[tuple[int, str]]:
|
|
"""Return (line_number, module_path) for every import in *filepath*."""
|
|
source = filepath.read_text(encoding="utf-8")
|
|
try:
|
|
tree = ast.parse(source, filename=str(filepath))
|
|
except SyntaxError:
|
|
return []
|
|
|
|
results: list[tuple[int, str]] = []
|
|
for node in ast.walk(tree):
|
|
if isinstance(node, ast.Import):
|
|
for alias in node.names:
|
|
results.append((node.lineno, alias.name))
|
|
elif isinstance(node, ast.ImportFrom):
|
|
if node.module:
|
|
results.append((node.lineno, node.module))
|
|
return results
|
|
|
|
|
|
def test_harness_does_not_import_app():
|
|
violations: list[str] = []
|
|
|
|
for py_file in sorted(HARNESS_ROOT.rglob("*.py")):
|
|
for lineno, module in _collect_imports(py_file):
|
|
if any(module == prefix.rstrip(".") or module.startswith(prefix) for prefix in BANNED_PREFIXES):
|
|
rel = py_file.relative_to(HARNESS_ROOT.parent.parent.parent)
|
|
violations.append(f" {rel}:{lineno} imports {module}")
|
|
|
|
assert not violations, "Harness layer must not import from app layer:\n" + "\n".join(violations)
|