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.

deer-flow/backend/tests/test_docker_sandbox_mode_detection.py

@@ -0,0 +1,106 @@
+"""Regression tests for docker sandbox mode detection logic."""
+
+from __future__ import annotations
+
+import subprocess
+import tempfile
+from pathlib import Path
+from shutil import which
+
+import pytest
+
+REPO_ROOT = Path(__file__).resolve().parents[2]
+SCRIPT_PATH = REPO_ROOT / "scripts" / "docker.sh"
+BASH_CANDIDATES = [
+    Path(r"C:\Program Files\Git\bin\bash.exe"),
+    Path(which("bash")) if which("bash") else None,
+]
+BASH_EXECUTABLE = next(
+    (str(path) for path in BASH_CANDIDATES if path is not None and path.exists() and "WindowsApps" not in str(path)),
+    None,
+)
+
+if BASH_EXECUTABLE is None:
+    pytestmark = pytest.mark.skip(reason="bash is required for docker.sh detection tests")
+
+
+def _detect_mode_with_config(config_content: str) -> str:
+    """Write config content into a temp project root and execute detect_sandbox_mode."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        tmp_root = Path(tmpdir)
+        (tmp_root / "config.yaml").write_text(config_content, encoding="utf-8")
+
+        command = f"source '{SCRIPT_PATH}' && PROJECT_ROOT='{tmp_root}' && detect_sandbox_mode"
+
+        output = subprocess.check_output(
+            [BASH_EXECUTABLE, "-lc", command],
+            text=True,
+            encoding="utf-8",
+        ).strip()
+
+        return output
+
+
+def test_detect_mode_defaults_to_local_when_config_missing():
+    """No config file should default to local mode."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        command = f"source '{SCRIPT_PATH}' && PROJECT_ROOT='{tmpdir}' && detect_sandbox_mode"
+        output = subprocess.check_output(
+            [BASH_EXECUTABLE, "-lc", command],
+            text=True,
+            encoding="utf-8",
+        ).strip()
+
+    assert output == "local"
+
+
+def test_detect_mode_local_provider():
+    """Local sandbox provider should map to local mode."""
+    config = """
+sandbox:
+  use: deerflow.sandbox.local:LocalSandboxProvider
+""".strip()
+
+    assert _detect_mode_with_config(config) == "local"
+
+
+def test_detect_mode_aio_without_provisioner_url():
+    """AIO sandbox without provisioner_url should map to aio mode."""
+    config = """
+sandbox:
+  use: deerflow.community.aio_sandbox:AioSandboxProvider
+""".strip()
+
+    assert _detect_mode_with_config(config) == "aio"
+
+
+def test_detect_mode_provisioner_with_url():
+    """AIO sandbox with provisioner_url should map to provisioner mode."""
+    config = """
+sandbox:
+  use: deerflow.community.aio_sandbox:AioSandboxProvider
+  provisioner_url: http://provisioner:8002
+""".strip()
+
+    assert _detect_mode_with_config(config) == "provisioner"
+
+
+def test_detect_mode_ignores_commented_provisioner_url():
+    """Commented provisioner_url should not activate provisioner mode."""
+    config = """
+sandbox:
+  use: deerflow.community.aio_sandbox:AioSandboxProvider
+  # provisioner_url: http://provisioner:8002
+""".strip()
+
+    assert _detect_mode_with_config(config) == "aio"
+
+
+def test_detect_mode_unknown_provider_falls_back_to_local():
+    """Unknown sandbox provider should default to local mode."""
+    config = """
+sandbox:
+  use: custom.module:UnknownProvider
+""".strip()
+
+    assert _detect_mode_with_config(config) == "local"