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_thread_data_middleware.py

@@ -0,0 +1,58 @@
+import pytest
+from langgraph.runtime import Runtime
+
+from deerflow.agents.middlewares.thread_data_middleware import ThreadDataMiddleware
+
+
+def _as_posix(path: str) -> str:
+    return path.replace("\\", "/")
+
+
+class TestThreadDataMiddleware:
+    def test_before_agent_returns_paths_when_thread_id_present_in_context(self, tmp_path):
+        middleware = ThreadDataMiddleware(base_dir=str(tmp_path), lazy_init=True)
+
+        result = middleware.before_agent(state={}, runtime=Runtime(context={"thread_id": "thread-123"}))
+
+        assert result is not None
+        assert _as_posix(result["thread_data"]["workspace_path"]).endswith("threads/thread-123/user-data/workspace")
+        assert _as_posix(result["thread_data"]["uploads_path"]).endswith("threads/thread-123/user-data/uploads")
+        assert _as_posix(result["thread_data"]["outputs_path"]).endswith("threads/thread-123/user-data/outputs")
+
+    def test_before_agent_uses_thread_id_from_configurable_when_context_is_none(self, tmp_path, monkeypatch):
+        middleware = ThreadDataMiddleware(base_dir=str(tmp_path), lazy_init=True)
+        runtime = Runtime(context=None)
+        monkeypatch.setattr(
+            "deerflow.agents.middlewares.thread_data_middleware.get_config",
+            lambda: {"configurable": {"thread_id": "thread-from-config"}},
+        )
+
+        result = middleware.before_agent(state={}, runtime=runtime)
+
+        assert result is not None
+        assert _as_posix(result["thread_data"]["workspace_path"]).endswith("threads/thread-from-config/user-data/workspace")
+        assert runtime.context is None
+
+    def test_before_agent_uses_thread_id_from_configurable_when_context_missing_thread_id(self, tmp_path, monkeypatch):
+        middleware = ThreadDataMiddleware(base_dir=str(tmp_path), lazy_init=True)
+        runtime = Runtime(context={})
+        monkeypatch.setattr(
+            "deerflow.agents.middlewares.thread_data_middleware.get_config",
+            lambda: {"configurable": {"thread_id": "thread-from-config"}},
+        )
+
+        result = middleware.before_agent(state={}, runtime=runtime)
+
+        assert result is not None
+        assert _as_posix(result["thread_data"]["uploads_path"]).endswith("threads/thread-from-config/user-data/uploads")
+        assert runtime.context == {}
+
+    def test_before_agent_raises_clear_error_when_thread_id_missing_everywhere(self, tmp_path, monkeypatch):
+        middleware = ThreadDataMiddleware(base_dir=str(tmp_path), lazy_init=True)
+        monkeypatch.setattr(
+            "deerflow.agents.middlewares.thread_data_middleware.get_config",
+            lambda: {"configurable": {}},
+        )
+
+        with pytest.raises(ValueError, match="Thread ID is required in runtime context or config.configurable"):
+            middleware.before_agent(state={}, runtime=Runtime(context=None))