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:
2026-04-12 14:23:57 +02:00
commit 6de0bf9f5b
889 changed files with 173052 additions and 0 deletions

View File

@@ -0,0 +1,61 @@
/**
* Run `build` or `dev` with `SKIP_ENV_VALIDATION` to skip env validation. This is especially useful
* for Docker builds.
*/
import "./src/env.js";
function getInternalServiceURL(envKey, fallbackURL) {
const configured = process.env[envKey]?.trim();
return configured && configured.length > 0
? configured.replace(/\/+$/, "")
: fallbackURL;
}
import nextra from "nextra";
const withNextra = nextra({});
/** @type {import("next").NextConfig} */
const config = {
i18n: {
locales: ["en", "zh"],
defaultLocale: "en",
},
devIndicators: false,
async rewrites() {
const rewrites = [];
const langgraphURL = getInternalServiceURL(
"DEER_FLOW_INTERNAL_LANGGRAPH_BASE_URL",
"http://127.0.0.1:2024",
);
const gatewayURL = getInternalServiceURL(
"DEER_FLOW_INTERNAL_GATEWAY_BASE_URL",
"http://127.0.0.1:8001",
);
if (!process.env.NEXT_PUBLIC_LANGGRAPH_BASE_URL) {
rewrites.push({
source: "/api/langgraph",
destination: langgraphURL,
});
rewrites.push({
source: "/api/langgraph/:path*",
destination: `${langgraphURL}/:path*`,
});
}
if (!process.env.NEXT_PUBLIC_BACKEND_BASE_URL) {
rewrites.push({
source: "/api/agents",
destination: `${gatewayURL}/api/agents`,
});
rewrites.push({
source: "/api/agents/:path*",
destination: `${gatewayURL}/api/agents/:path*`,
});
}
return rewrites;
},
};
export default withNextra(config);