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/subagents/config.py

@@ -0,0 +1,28 @@
+"""Subagent configuration definitions."""
+
+from dataclasses import dataclass, field
+
+
+@dataclass
+class SubagentConfig:
+    """Configuration for a subagent.
+
+    Attributes:
+        name: Unique identifier for the subagent.
+        description: When Claude should delegate to this subagent.
+        system_prompt: The system prompt that guides the subagent's behavior.
+        tools: Optional list of tool names to allow. If None, inherits all tools.
+        disallowed_tools: Optional list of tool names to deny.
+        model: Model to use - 'inherit' uses parent's model.
+        max_turns: Maximum number of agent turns before stopping.
+        timeout_seconds: Maximum execution time in seconds (default: 900 = 15 minutes).
+    """
+
+    name: str
+    description: str
+    system_prompt: str
+    tools: list[str] | None = None
+    disallowed_tools: list[str] | None = field(default_factory=lambda: ["task"])
+    model: str = "inherit"
+    max_turns: int = 50
+    timeout_seconds: int = 900