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/agents/thread_state.py

@@ -0,0 +1,55 @@
+from typing import Annotated, NotRequired, TypedDict
+
+from langchain.agents import AgentState
+
+
+class SandboxState(TypedDict):
+    sandbox_id: NotRequired[str | None]
+
+
+class ThreadDataState(TypedDict):
+    workspace_path: NotRequired[str | None]
+    uploads_path: NotRequired[str | None]
+    outputs_path: NotRequired[str | None]
+
+
+class ViewedImageData(TypedDict):
+    base64: str
+    mime_type: str
+
+
+def merge_artifacts(existing: list[str] | None, new: list[str] | None) -> list[str]:
+    """Reducer for artifacts list - merges and deduplicates artifacts."""
+    if existing is None:
+        return new or []
+    if new is None:
+        return existing
+    # Use dict.fromkeys to deduplicate while preserving order
+    return list(dict.fromkeys(existing + new))
+
+
+def merge_viewed_images(existing: dict[str, ViewedImageData] | None, new: dict[str, ViewedImageData] | None) -> dict[str, ViewedImageData]:
+    """Reducer for viewed_images dict - merges image dictionaries.
+
+    Special case: If new is an empty dict {}, it clears the existing images.
+    This allows middlewares to clear the viewed_images state after processing.
+    """
+    if existing is None:
+        return new or {}
+    if new is None:
+        return existing
+    # Special case: empty dict means clear all viewed images
+    if len(new) == 0:
+        return {}
+    # Merge dictionaries, new values override existing ones for same keys
+    return {**existing, **new}
+
+
+class ThreadState(AgentState):
+    sandbox: NotRequired[SandboxState | None]
+    thread_data: NotRequired[ThreadDataState | None]
+    title: NotRequired[str | None]
+    artifacts: Annotated[list[str], merge_artifacts]
+    todos: NotRequired[list | None]
+    uploaded_files: NotRequired[list[dict] | None]
+    viewed_images: Annotated[dict[str, ViewedImageData], merge_viewed_images]  # image_path -> {base64, mime_type}