Files
deerflow-factory/deer-flow/backend/packages/harness/pyproject.toml
DATA 6de0bf9f5b 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.
2026-04-12 14:23:57 +02:00

48 lines
1.2 KiB
TOML

[project]
name = "deerflow-harness"
version = "0.1.0"
description = "DeerFlow agent harness framework"
requires-python = ">=3.12"
dependencies = [
"agent-client-protocol>=0.4.0",
"agent-sandbox>=0.0.19",
"dotenv>=0.9.9",
"exa-py>=1.0.0",
"httpx>=0.28.0",
"kubernetes>=30.0.0",
"langchain>=1.2.3",
"langchain-anthropic>=1.3.4",
"langchain-deepseek>=1.0.1",
"langchain-mcp-adapters>=0.1.0",
"langchain-openai>=1.1.7",
"langfuse>=3.4.1",
"langgraph>=1.0.6,<1.0.10",
"langgraph-api>=0.7.0,<0.8.0",
"langgraph-cli>=0.4.14",
"langgraph-runtime-inmem>=0.22.1",
"markdownify>=1.2.2",
"markitdown[all,xlsx]>=0.0.1a2",
"pydantic>=2.12.5",
"pyyaml>=6.0.3",
"readabilipy>=0.3.0",
"tavily-python>=0.7.17",
"firecrawl-py>=1.15.0",
"tiktoken>=0.8.0",
"ddgs>=9.10.0",
"duckdb>=1.4.4",
"langchain-google-genai>=4.2.1",
"langgraph-checkpoint-sqlite>=3.0.3",
"langgraph-sdk>=0.1.51",
]
[project.optional-dependencies]
ollama = ["langchain-ollama>=0.3.0"]
pymupdf = ["pymupdf4llm>=0.0.17"]
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.hatch.build.targets.wheel]
packages = ["deerflow"]