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/config/subagents_config.py

@@ -0,0 +1,102 @@
+"""Configuration for the subagent system loaded from config.yaml."""
+
+import logging
+
+from pydantic import BaseModel, Field
+
+logger = logging.getLogger(__name__)
+
+
+class SubagentOverrideConfig(BaseModel):
+    """Per-agent configuration overrides."""
+
+    timeout_seconds: int | None = Field(
+        default=None,
+        ge=1,
+        description="Timeout in seconds for this subagent (None = use global default)",
+    )
+    max_turns: int | None = Field(
+        default=None,
+        ge=1,
+        description="Maximum turns for this subagent (None = use global or builtin default)",
+    )
+
+
+class SubagentsAppConfig(BaseModel):
+    """Configuration for the subagent system."""
+
+    timeout_seconds: int = Field(
+        default=900,
+        ge=1,
+        description="Default timeout in seconds for all subagents (default: 900 = 15 minutes)",
+    )
+    max_turns: int | None = Field(
+        default=None,
+        ge=1,
+        description="Optional default max-turn override for all subagents (None = keep builtin defaults)",
+    )
+    agents: dict[str, SubagentOverrideConfig] = Field(
+        default_factory=dict,
+        description="Per-agent configuration overrides keyed by agent name",
+    )
+
+    def get_timeout_for(self, agent_name: str) -> int:
+        """Get the effective timeout for a specific agent.
+
+        Args:
+            agent_name: The name of the subagent.
+
+        Returns:
+            The timeout in seconds, using per-agent override if set, otherwise global default.
+        """
+        override = self.agents.get(agent_name)
+        if override is not None and override.timeout_seconds is not None:
+            return override.timeout_seconds
+        return self.timeout_seconds
+
+    def get_max_turns_for(self, agent_name: str, builtin_default: int) -> int:
+        """Get the effective max_turns for a specific agent."""
+        override = self.agents.get(agent_name)
+        if override is not None and override.max_turns is not None:
+            return override.max_turns
+        if self.max_turns is not None:
+            return self.max_turns
+        return builtin_default
+
+
+_subagents_config: SubagentsAppConfig = SubagentsAppConfig()
+
+
+def get_subagents_app_config() -> SubagentsAppConfig:
+    """Get the current subagents configuration."""
+    return _subagents_config
+
+
+def load_subagents_config_from_dict(config_dict: dict) -> None:
+    """Load subagents configuration from a dictionary."""
+    global _subagents_config
+    _subagents_config = SubagentsAppConfig(**config_dict)
+
+    overrides_summary = {}
+    for name, override in _subagents_config.agents.items():
+        parts = []
+        if override.timeout_seconds is not None:
+            parts.append(f"timeout={override.timeout_seconds}s")
+        if override.max_turns is not None:
+            parts.append(f"max_turns={override.max_turns}")
+        if parts:
+            overrides_summary[name] = ", ".join(parts)
+
+    if overrides_summary:
+        logger.info(
+            "Subagents config loaded: default timeout=%ss, default max_turns=%s, per-agent overrides=%s",
+            _subagents_config.timeout_seconds,
+            _subagents_config.max_turns,
+            overrides_summary,
+        )
+    else:
+        logger.info(
+            "Subagents config loaded: default timeout=%ss, default max_turns=%s, no per-agent overrides",
+            _subagents_config.timeout_seconds,
+            _subagents_config.max_turns,
+        )