DATA
6de0bf9f5b
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.
103 lines
3.6 KiB
Python
103 lines
3.6 KiB
Python
import asyncio
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
from app.gateway.routers import suggestions
|
|
|
|
|
|
def test_strip_markdown_code_fence_removes_wrapping():
|
|
text = '```json\n["a"]\n```'
|
|
assert suggestions._strip_markdown_code_fence(text) == '["a"]'
|
|
|
|
|
|
def test_strip_markdown_code_fence_no_fence_keeps_content():
|
|
text = ' ["a"] '
|
|
assert suggestions._strip_markdown_code_fence(text) == '["a"]'
|
|
|
|
|
|
def test_parse_json_string_list_filters_invalid_items():
|
|
text = '```json\n["a", " ", 1, "b"]\n```'
|
|
assert suggestions._parse_json_string_list(text) == ["a", "b"]
|
|
|
|
|
|
def test_parse_json_string_list_rejects_non_list():
|
|
text = '{"a": 1}'
|
|
assert suggestions._parse_json_string_list(text) is None
|
|
|
|
|
|
def test_format_conversation_formats_roles():
|
|
messages = [
|
|
suggestions.SuggestionMessage(role="User", content="Hi"),
|
|
suggestions.SuggestionMessage(role="assistant", content="Hello"),
|
|
suggestions.SuggestionMessage(role="system", content="note"),
|
|
]
|
|
assert suggestions._format_conversation(messages) == "User: Hi\nAssistant: Hello\nsystem: note"
|
|
|
|
|
|
def test_generate_suggestions_parses_and_limits(monkeypatch):
|
|
req = suggestions.SuggestionsRequest(
|
|
messages=[
|
|
suggestions.SuggestionMessage(role="user", content="Hi"),
|
|
suggestions.SuggestionMessage(role="assistant", content="Hello"),
|
|
],
|
|
n=3,
|
|
model_name=None,
|
|
)
|
|
fake_model = MagicMock()
|
|
fake_model.ainvoke = AsyncMock(return_value=MagicMock(content='```json\n["Q1", "Q2", "Q3", "Q4"]\n```'))
|
|
monkeypatch.setattr(suggestions, "create_chat_model", lambda **kwargs: fake_model)
|
|
|
|
result = asyncio.run(suggestions.generate_suggestions("t1", req))
|
|
|
|
assert result.suggestions == ["Q1", "Q2", "Q3"]
|
|
|
|
|
|
def test_generate_suggestions_parses_list_block_content(monkeypatch):
|
|
req = suggestions.SuggestionsRequest(
|
|
messages=[
|
|
suggestions.SuggestionMessage(role="user", content="Hi"),
|
|
suggestions.SuggestionMessage(role="assistant", content="Hello"),
|
|
],
|
|
n=2,
|
|
model_name=None,
|
|
)
|
|
fake_model = MagicMock()
|
|
fake_model.ainvoke = AsyncMock(return_value=MagicMock(content=[{"type": "text", "text": '```json\n["Q1", "Q2"]\n```'}]))
|
|
monkeypatch.setattr(suggestions, "create_chat_model", lambda **kwargs: fake_model)
|
|
|
|
result = asyncio.run(suggestions.generate_suggestions("t1", req))
|
|
|
|
assert result.suggestions == ["Q1", "Q2"]
|
|
|
|
|
|
def test_generate_suggestions_parses_output_text_block_content(monkeypatch):
|
|
req = suggestions.SuggestionsRequest(
|
|
messages=[
|
|
suggestions.SuggestionMessage(role="user", content="Hi"),
|
|
suggestions.SuggestionMessage(role="assistant", content="Hello"),
|
|
],
|
|
n=2,
|
|
model_name=None,
|
|
)
|
|
fake_model = MagicMock()
|
|
fake_model.ainvoke = AsyncMock(return_value=MagicMock(content=[{"type": "output_text", "text": '```json\n["Q1", "Q2"]\n```'}]))
|
|
monkeypatch.setattr(suggestions, "create_chat_model", lambda **kwargs: fake_model)
|
|
|
|
result = asyncio.run(suggestions.generate_suggestions("t1", req))
|
|
|
|
assert result.suggestions == ["Q1", "Q2"]
|
|
|
|
|
|
def test_generate_suggestions_returns_empty_on_model_error(monkeypatch):
|
|
req = suggestions.SuggestionsRequest(
|
|
messages=[suggestions.SuggestionMessage(role="user", content="Hi")],
|
|
n=2,
|
|
model_name=None,
|
|
)
|
|
fake_model = MagicMock()
|
|
fake_model.ainvoke = AsyncMock(side_effect=RuntimeError("boom"))
|
|
monkeypatch.setattr(suggestions, "create_chat_model", lambda **kwargs: fake_model)
|
|
|
|
result = asyncio.run(suggestions.generate_suggestions("t1", req))
|
|
|
|
assert result.suggestions == []
|