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/packages/harness/deerflow/models/patched_deepseek.py

@@ -0,0 +1,73 @@
+"""Patched ChatDeepSeek that preserves reasoning_content in multi-turn conversations.
+
+This module provides a patched version of ChatDeepSeek that properly handles
+reasoning_content when sending messages back to the API. The original implementation
+stores reasoning_content in additional_kwargs but doesn't include it when making
+subsequent API calls, which causes errors with APIs that require reasoning_content
+on all assistant messages when thinking mode is enabled.
+"""
+
+from typing import Any
+
+from langchain_core.language_models import LanguageModelInput
+from langchain_core.messages import AIMessage
+from langchain_deepseek import ChatDeepSeek
+
+
+class PatchedChatDeepSeek(ChatDeepSeek):
+    """ChatDeepSeek with proper reasoning_content preservation.
+
+    When using thinking/reasoning enabled models, the API expects reasoning_content
+    to be present on ALL assistant messages in multi-turn conversations. This patched
+    version ensures reasoning_content from additional_kwargs is included in the
+    request payload.
+    """
+
+    @classmethod
+    def is_lc_serializable(cls) -> bool:
+        return True
+
+    @property
+    def lc_secrets(self) -> dict[str, str]:
+        return {"api_key": "DEEPSEEK_API_KEY", "openai_api_key": "DEEPSEEK_API_KEY"}
+
+    def _get_request_payload(
+        self,
+        input_: LanguageModelInput,
+        *,
+        stop: list[str] | None = None,
+        **kwargs: Any,
+    ) -> dict:
+        """Get request payload with reasoning_content preserved.
+
+        Overrides the parent method to inject reasoning_content from
+        additional_kwargs into assistant messages in the payload.
+        """
+        # Get the original messages before conversion
+        original_messages = self._convert_input(input_).to_messages()
+
+        # Call parent to get the base payload
+        payload = super()._get_request_payload(input_, stop=stop, **kwargs)
+
+        # Match payload messages with original messages to restore reasoning_content
+        payload_messages = payload.get("messages", [])
+
+        # The payload messages and original messages should be in the same order
+        # Iterate through both and match by position
+        if len(payload_messages) == len(original_messages):
+            for payload_msg, orig_msg in zip(payload_messages, original_messages):
+                if payload_msg.get("role") == "assistant" and isinstance(orig_msg, AIMessage):
+                    reasoning_content = orig_msg.additional_kwargs.get("reasoning_content")
+                    if reasoning_content is not None:
+                        payload_msg["reasoning_content"] = reasoning_content
+        else:
+            # Fallback: match by counting assistant messages
+            ai_messages = [m for m in original_messages if isinstance(m, AIMessage)]
+            assistant_payloads = [(i, m) for i, m in enumerate(payload_messages) if m.get("role") == "assistant"]
+
+            for (idx, payload_msg), ai_msg in zip(assistant_payloads, ai_messages):
+                reasoning_content = ai_msg.additional_kwargs.get("reasoning_content")
+                if reasoning_content is not None:
+                    payload_messages[idx]["reasoning_content"] = reasoning_content
+
+        return payload