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/app/gateway/routers/assistants_compat.py

@@ -0,0 +1,149 @@
+"""Assistants compatibility endpoints.
+
+Provides LangGraph Platform-compatible assistants API backed by the
+``langgraph.json`` graph registry and ``config.yaml`` agent definitions.
+
+This is a minimal stub that satisfies the ``useStream`` React hook's
+initialization requirements (``assistants.search()`` and ``assistants.get()``).
+"""
+
+from __future__ import annotations
+
+import logging
+from datetime import UTC, datetime
+from typing import Any
+
+from fastapi import APIRouter, HTTPException
+from pydantic import BaseModel, Field
+
+logger = logging.getLogger(__name__)
+router = APIRouter(prefix="/api/assistants", tags=["assistants-compat"])
+
+
+class AssistantResponse(BaseModel):
+    assistant_id: str
+    graph_id: str
+    name: str
+    config: dict[str, Any] = Field(default_factory=dict)
+    metadata: dict[str, Any] = Field(default_factory=dict)
+    description: str | None = None
+    created_at: str = ""
+    updated_at: str = ""
+    version: int = 1
+
+
+class AssistantSearchRequest(BaseModel):
+    graph_id: str | None = None
+    name: str | None = None
+    metadata: dict[str, Any] | None = None
+    limit: int = 10
+    offset: int = 0
+
+
+def _get_default_assistant() -> AssistantResponse:
+    """Return the default lead_agent assistant."""
+    now = datetime.now(UTC).isoformat()
+    return AssistantResponse(
+        assistant_id="lead_agent",
+        graph_id="lead_agent",
+        name="lead_agent",
+        config={},
+        metadata={"created_by": "system"},
+        description="DeerFlow lead agent",
+        created_at=now,
+        updated_at=now,
+        version=1,
+    )
+
+
+def _list_assistants() -> list[AssistantResponse]:
+    """List all available assistants from config."""
+    assistants = [_get_default_assistant()]
+
+    # Also include custom agents from config.yaml agents directory
+    try:
+        from deerflow.config.agents_config import list_custom_agents
+
+        for agent_cfg in list_custom_agents():
+            now = datetime.now(UTC).isoformat()
+            assistants.append(
+                AssistantResponse(
+                    assistant_id=agent_cfg.name,
+                    graph_id="lead_agent",  # All agents use the same graph
+                    name=agent_cfg.name,
+                    config={},
+                    metadata={"created_by": "user"},
+                    description=agent_cfg.description or "",
+                    created_at=now,
+                    updated_at=now,
+                    version=1,
+                )
+            )
+    except Exception:
+        logger.debug("Could not load custom agents for assistants list")
+
+    return assistants
+
+
+@router.post("/search", response_model=list[AssistantResponse])
+async def search_assistants(body: AssistantSearchRequest | None = None) -> list[AssistantResponse]:
+    """Search assistants.
+
+    Returns all registered assistants (lead_agent + custom agents from config).
+    """
+    assistants = _list_assistants()
+
+    if body and body.graph_id:
+        assistants = [a for a in assistants if a.graph_id == body.graph_id]
+    if body and body.name:
+        assistants = [a for a in assistants if body.name.lower() in a.name.lower()]
+
+    offset = body.offset if body else 0
+    limit = body.limit if body else 10
+    return assistants[offset : offset + limit]
+
+
+@router.get("/{assistant_id}", response_model=AssistantResponse)
+async def get_assistant_compat(assistant_id: str) -> AssistantResponse:
+    """Get an assistant by ID."""
+    for a in _list_assistants():
+        if a.assistant_id == assistant_id:
+            return a
+    raise HTTPException(status_code=404, detail=f"Assistant {assistant_id} not found")
+
+
+@router.get("/{assistant_id}/graph")
+async def get_assistant_graph(assistant_id: str) -> dict:
+    """Get the graph structure for an assistant.
+
+    Returns a minimal graph description. Full graph introspection is
+    not supported in the Gateway — this stub satisfies SDK validation.
+    """
+    found = any(a.assistant_id == assistant_id for a in _list_assistants())
+    if not found:
+        raise HTTPException(status_code=404, detail=f"Assistant {assistant_id} not found")
+
+    return {
+        "graph_id": "lead_agent",
+        "nodes": [],
+        "edges": [],
+    }
+
+
+@router.get("/{assistant_id}/schemas")
+async def get_assistant_schemas(assistant_id: str) -> dict:
+    """Get JSON schemas for an assistant's input/output/state.
+
+    Returns empty schemas — full introspection not supported in Gateway.
+    """
+    found = any(a.assistant_id == assistant_id for a in _list_assistants())
+    if not found:
+        raise HTTPException(status_code=404, detail=f"Assistant {assistant_id} not found")
+
+    return {
+        "graph_id": "lead_agent",
+        "input_schema": {},
+        "output_schema": {},
+        "state_schema": {},
+        "config_schema": {},
+    }