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/summarization_config.py

@@ -0,0 +1,74 @@
+"""Configuration for conversation summarization."""
+
+from typing import Literal
+
+from pydantic import BaseModel, Field
+
+ContextSizeType = Literal["fraction", "tokens", "messages"]
+
+
+class ContextSize(BaseModel):
+    """Context size specification for trigger or keep parameters."""
+
+    type: ContextSizeType = Field(description="Type of context size specification")
+    value: int | float = Field(description="Value for the context size specification")
+
+    def to_tuple(self) -> tuple[ContextSizeType, int | float]:
+        """Convert to tuple format expected by SummarizationMiddleware."""
+        return (self.type, self.value)
+
+
+class SummarizationConfig(BaseModel):
+    """Configuration for automatic conversation summarization."""
+
+    enabled: bool = Field(
+        default=False,
+        description="Whether to enable automatic conversation summarization",
+    )
+    model_name: str | None = Field(
+        default=None,
+        description="Model name to use for summarization (None = use a lightweight model)",
+    )
+    trigger: ContextSize | list[ContextSize] | None = Field(
+        default=None,
+        description="One or more thresholds that trigger summarization. When any threshold is met, summarization runs. "
+        "Examples: {'type': 'messages', 'value': 50} triggers at 50 messages, "
+        "{'type': 'tokens', 'value': 4000} triggers at 4000 tokens, "
+        "{'type': 'fraction', 'value': 0.8} triggers at 80% of model's max input tokens",
+    )
+    keep: ContextSize = Field(
+        default_factory=lambda: ContextSize(type="messages", value=20),
+        description="Context retention policy after summarization. Specifies how much history to preserve. "
+        "Examples: {'type': 'messages', 'value': 20} keeps 20 messages, "
+        "{'type': 'tokens', 'value': 3000} keeps 3000 tokens, "
+        "{'type': 'fraction', 'value': 0.3} keeps 30% of model's max input tokens",
+    )
+    trim_tokens_to_summarize: int | None = Field(
+        default=4000,
+        description="Maximum tokens to keep when preparing messages for summarization. Pass null to skip trimming.",
+    )
+    summary_prompt: str | None = Field(
+        default=None,
+        description="Custom prompt template for generating summaries. If not provided, uses the default LangChain prompt.",
+    )
+
+
+# Global configuration instance
+_summarization_config: SummarizationConfig = SummarizationConfig()
+
+
+def get_summarization_config() -> SummarizationConfig:
+    """Get the current summarization configuration."""
+    return _summarization_config
+
+
+def set_summarization_config(config: SummarizationConfig) -> None:
+    """Set the summarization configuration."""
+    global _summarization_config
+    _summarization_config = config
+
+
+def load_summarization_config_from_dict(config_dict: dict) -> None:
+    """Load summarization configuration from a dictionary."""
+    global _summarization_config
+    _summarization_config = SummarizationConfig(**config_dict)