Files
deerflow-factory/deer-flow/backend/tests/test_feishu_parser.py
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

193 lines
6.6 KiB
Python

import asyncio
import json
from unittest.mock import AsyncMock, MagicMock
import pytest
from app.channels.commands import KNOWN_CHANNEL_COMMANDS
from app.channels.feishu import FeishuChannel
from app.channels.message_bus import InboundMessage, MessageBus
def _run(coro):
loop = asyncio.new_event_loop()
try:
return loop.run_until_complete(coro)
finally:
loop.close()
def test_feishu_on_message_plain_text():
bus = MessageBus()
config = {"app_id": "test", "app_secret": "test"}
channel = FeishuChannel(bus, config)
# Create mock event
event = MagicMock()
event.event.message.chat_id = "chat_1"
event.event.message.message_id = "msg_1"
event.event.message.root_id = None
event.event.sender.sender_id.open_id = "user_1"
# Plain text content
content_dict = {"text": "Hello world"}
event.event.message.content = json.dumps(content_dict)
# Call _on_message
channel._on_message(event)
# Since main_loop isn't running in this synchronous test, we can't easily assert on bus,
# but we can intercept _make_inbound to check the parsed text.
with pytest.MonkeyPatch.context() as m:
mock_make_inbound = MagicMock()
m.setattr(channel, "_make_inbound", mock_make_inbound)
channel._on_message(event)
mock_make_inbound.assert_called_once()
assert mock_make_inbound.call_args[1]["text"] == "Hello world"
def test_feishu_on_message_rich_text():
bus = MessageBus()
config = {"app_id": "test", "app_secret": "test"}
channel = FeishuChannel(bus, config)
# Create mock event
event = MagicMock()
event.event.message.chat_id = "chat_1"
event.event.message.message_id = "msg_1"
event.event.message.root_id = None
event.event.sender.sender_id.open_id = "user_1"
# Rich text content (topic group / post)
content_dict = {"content": [[{"tag": "text", "text": "Paragraph 1, part 1."}, {"tag": "text", "text": "Paragraph 1, part 2."}], [{"tag": "at", "text": "@bot"}, {"tag": "text", "text": " Paragraph 2."}]]}
event.event.message.content = json.dumps(content_dict)
with pytest.MonkeyPatch.context() as m:
mock_make_inbound = MagicMock()
m.setattr(channel, "_make_inbound", mock_make_inbound)
channel._on_message(event)
mock_make_inbound.assert_called_once()
parsed_text = mock_make_inbound.call_args[1]["text"]
# Expected text:
# Paragraph 1, part 1. Paragraph 1, part 2.
#
# @bot Paragraph 2.
assert "Paragraph 1, part 1. Paragraph 1, part 2." in parsed_text
assert "@bot Paragraph 2." in parsed_text
assert "\n\n" in parsed_text
def test_feishu_receive_file_replaces_placeholders_in_order():
async def go():
bus = MessageBus()
channel = FeishuChannel(bus, {"app_id": "test", "app_secret": "test"})
msg = InboundMessage(
channel_name="feishu",
chat_id="chat_1",
user_id="user_1",
text="before [image] middle [file] after",
thread_ts="msg_1",
files=[{"image_key": "img_key"}, {"file_key": "file_key"}],
)
channel._receive_single_file = AsyncMock(side_effect=["/mnt/user-data/uploads/a.png", "/mnt/user-data/uploads/b.pdf"])
result = await channel.receive_file(msg, "thread_1")
assert result.text == "before /mnt/user-data/uploads/a.png middle /mnt/user-data/uploads/b.pdf after"
_run(go())
def test_feishu_on_message_extracts_image_and_file_keys():
bus = MessageBus()
channel = FeishuChannel(bus, {"app_id": "test", "app_secret": "test"})
event = MagicMock()
event.event.message.chat_id = "chat_1"
event.event.message.message_id = "msg_1"
event.event.message.root_id = None
event.event.sender.sender_id.open_id = "user_1"
# Rich text with one image and one file element.
event.event.message.content = json.dumps(
{
"content": [
[
{"tag": "text", "text": "See"},
{"tag": "img", "image_key": "img_123"},
{"tag": "file", "file_key": "file_456"},
]
]
}
)
with pytest.MonkeyPatch.context() as m:
mock_make_inbound = MagicMock()
m.setattr(channel, "_make_inbound", mock_make_inbound)
channel._on_message(event)
mock_make_inbound.assert_called_once()
files = mock_make_inbound.call_args[1]["files"]
assert files == [{"image_key": "img_123"}, {"file_key": "file_456"}]
assert "[image]" in mock_make_inbound.call_args[1]["text"]
assert "[file]" in mock_make_inbound.call_args[1]["text"]
@pytest.mark.parametrize("command", sorted(KNOWN_CHANNEL_COMMANDS))
def test_feishu_recognizes_all_known_slash_commands(command):
"""Every entry in KNOWN_CHANNEL_COMMANDS must be classified as a command."""
bus = MessageBus()
config = {"app_id": "test", "app_secret": "test"}
channel = FeishuChannel(bus, config)
event = MagicMock()
event.event.message.chat_id = "chat_1"
event.event.message.message_id = "msg_1"
event.event.message.root_id = None
event.event.sender.sender_id.open_id = "user_1"
event.event.message.content = json.dumps({"text": command})
with pytest.MonkeyPatch.context() as m:
mock_make_inbound = MagicMock()
m.setattr(channel, "_make_inbound", mock_make_inbound)
channel._on_message(event)
mock_make_inbound.assert_called_once()
assert mock_make_inbound.call_args[1]["msg_type"].value == "command", f"{command!r} should be classified as COMMAND"
@pytest.mark.parametrize(
"text",
[
"/unknown",
"/mnt/user-data/outputs/prd/technical-design.md",
"/etc/passwd",
"/not-a-command at all",
],
)
def test_feishu_treats_unknown_slash_text_as_chat(text):
"""Slash-prefixed text that is not a known command must be classified as CHAT."""
bus = MessageBus()
config = {"app_id": "test", "app_secret": "test"}
channel = FeishuChannel(bus, config)
event = MagicMock()
event.event.message.chat_id = "chat_1"
event.event.message.message_id = "msg_1"
event.event.message.root_id = None
event.event.sender.sender_id.open_id = "user_1"
event.event.message.content = json.dumps({"text": text})
with pytest.MonkeyPatch.context() as m:
mock_make_inbound = MagicMock()
m.setattr(channel, "_make_inbound", mock_make_inbound)
channel._on_message(event)
mock_make_inbound.assert_called_once()
assert mock_make_inbound.call_args[1]["msg_type"].value == "chat", f"{text!r} should be classified as CHAT"