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_harness_boundary.py

@@ -0,0 +1,46 @@
+"""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)