Initial commit: hardened DeerFlow factory

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.
This commit is contained in:
2026-04-12 14:23:57 +02:00
commit 6de0bf9f5b
889 changed files with 173052 additions and 0 deletions

View File

@@ -0,0 +1,28 @@
from deerflow.community.aio_sandbox.local_backend import _format_container_mount
def test_format_container_mount_uses_mount_syntax_for_docker_windows_paths():
args = _format_container_mount("docker", "D:/deer-flow/backend/.deer-flow/threads", "/mnt/threads", False)
assert args == [
"--mount",
"type=bind,src=D:/deer-flow/backend/.deer-flow/threads,dst=/mnt/threads",
]
def test_format_container_mount_marks_docker_readonly_mounts():
args = _format_container_mount("docker", "/host/path", "/mnt/path", True)
assert args == [
"--mount",
"type=bind,src=/host/path,dst=/mnt/path,readonly",
]
def test_format_container_mount_keeps_volume_syntax_for_apple_container():
args = _format_container_mount("container", "/host/path", "/mnt/path", True)
assert args == [
"-v",
"/host/path:/mnt/path:ro",
]