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.
This commit is contained in:
14
deer-flow/backend/langgraph.json
Normal file
14
deer-flow/backend/langgraph.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"$schema": "https://langgra.ph/schema.json",
|
||||
"python_version": "3.12",
|
||||
"dependencies": [
|
||||
"."
|
||||
],
|
||||
"env": ".env",
|
||||
"graphs": {
|
||||
"lead_agent": "deerflow.agents:make_lead_agent"
|
||||
},
|
||||
"checkpointer": {
|
||||
"path": "./packages/harness/deerflow/agents/checkpointer/async_provider.py:make_checkpointer"
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user