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_provisioner_kubeconfig.py

@@ -0,0 +1,99 @@
+"""Regression tests for provisioner kubeconfig path handling."""
+
+from __future__ import annotations
+
+
+def test_wait_for_kubeconfig_rejects_directory(tmp_path, provisioner_module):
+    """Directory mount at kubeconfig path should fail fast with clear error."""
+    kubeconfig_dir = tmp_path / "config_dir"
+    kubeconfig_dir.mkdir()
+
+    provisioner_module.KUBECONFIG_PATH = str(kubeconfig_dir)
+
+    try:
+        provisioner_module._wait_for_kubeconfig(timeout=1)
+        raise AssertionError("Expected RuntimeError for directory kubeconfig path")
+    except RuntimeError as exc:
+        assert "directory" in str(exc)
+
+
+def test_wait_for_kubeconfig_accepts_file(tmp_path, provisioner_module):
+    """Regular file mount should pass readiness wait."""
+    kubeconfig_file = tmp_path / "config"
+    kubeconfig_file.write_text("apiVersion: v1\n")
+
+    provisioner_module.KUBECONFIG_PATH = str(kubeconfig_file)
+
+    # Should return immediately without raising.
+    provisioner_module._wait_for_kubeconfig(timeout=1)
+
+
+def test_init_k8s_client_rejects_directory_path(tmp_path, provisioner_module):
+    """KUBECONFIG_PATH that resolves to a directory should be rejected."""
+    kubeconfig_dir = tmp_path / "config_dir"
+    kubeconfig_dir.mkdir()
+
+    provisioner_module.KUBECONFIG_PATH = str(kubeconfig_dir)
+
+    try:
+        provisioner_module._init_k8s_client()
+        raise AssertionError("Expected RuntimeError for directory kubeconfig path")
+    except RuntimeError as exc:
+        assert "expected a file" in str(exc)
+
+
+def test_init_k8s_client_uses_file_kubeconfig(tmp_path, monkeypatch, provisioner_module):
+    """When file exists, provisioner should load kubeconfig file path."""
+    kubeconfig_file = tmp_path / "config"
+    kubeconfig_file.write_text("apiVersion: v1\n")
+
+    called: dict[str, object] = {}
+
+    def fake_load_kube_config(config_file: str):
+        called["config_file"] = config_file
+
+    monkeypatch.setattr(
+        provisioner_module.k8s_config,
+        "load_kube_config",
+        fake_load_kube_config,
+    )
+    monkeypatch.setattr(
+        provisioner_module.k8s_client,
+        "CoreV1Api",
+        lambda *args, **kwargs: "core-v1",
+    )
+
+    provisioner_module.KUBECONFIG_PATH = str(kubeconfig_file)
+
+    result = provisioner_module._init_k8s_client()
+
+    assert called["config_file"] == str(kubeconfig_file)
+    assert result == "core-v1"
+
+
+def test_init_k8s_client_falls_back_to_incluster_when_missing(tmp_path, monkeypatch, provisioner_module):
+    """When kubeconfig file is missing, in-cluster config should be attempted."""
+    missing_path = tmp_path / "missing-config"
+
+    calls: dict[str, int] = {"incluster": 0}
+
+    def fake_load_incluster_config():
+        calls["incluster"] += 1
+
+    monkeypatch.setattr(
+        provisioner_module.k8s_config,
+        "load_incluster_config",
+        fake_load_incluster_config,
+    )
+    monkeypatch.setattr(
+        provisioner_module.k8s_client,
+        "CoreV1Api",
+        lambda *args, **kwargs: "core-v1",
+    )
+
+    provisioner_module.KUBECONFIG_PATH = str(missing_path)
+
+    result = provisioner_module._init_k8s_client()
+
+    assert calls["incluster"] == 1
+    assert result == "core-v1"