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.
31 lines
949 B
Python
31 lines
949 B
Python
"""Tests for SSE frame formatting utilities."""
|
|
|
|
import json
|
|
|
|
|
|
def _format_sse(event: str, data, *, event_id: str | None = None) -> str:
|
|
from app.gateway.services import format_sse
|
|
|
|
return format_sse(event, data, event_id=event_id)
|
|
|
|
|
|
def test_sse_end_event_data_null():
|
|
"""End event should have data: null."""
|
|
frame = _format_sse("end", None)
|
|
assert "data: null" in frame
|
|
|
|
|
|
def test_sse_metadata_event():
|
|
"""Metadata event should include run_id and attempt."""
|
|
frame = _format_sse("metadata", {"run_id": "abc", "attempt": 1}, event_id="123-0")
|
|
assert "event: metadata" in frame
|
|
assert "id: 123-0" in frame
|
|
|
|
|
|
def test_sse_error_format():
|
|
"""Error event should use message/name format."""
|
|
frame = _format_sse("error", {"message": "boom", "name": "ValueError"})
|
|
parsed = json.loads(frame.split("data: ")[1].split("\n")[0])
|
|
assert parsed["message"] == "boom"
|
|
assert parsed["name"] == "ValueError"
|