fix(web-search): fix Jina search format and fallback

This commit is contained in:
KimGLee 2026-04-05 11:50:16 +08:00 committed by Xubin Ren
parent acf652358c
commit f422de8084
2 changed files with 72 additions and 4 deletions

View File

@ -8,7 +8,7 @@ import json
import os
import re
from typing import TYPE_CHECKING, Any
from urllib.parse import urlparse
from urllib.parse import quote, urlparse
import httpx
from loguru import logger
@ -182,10 +182,10 @@ class WebSearchTool(Tool):
return await self._search_duckduckgo(query, n)
try:
headers = {"Accept": "application/json", "Authorization": f"Bearer {api_key}"}
encoded_query = quote(query, safe="")
async with httpx.AsyncClient(proxy=self.proxy) as client:
r = await client.get(
f"https://s.jina.ai/",
params={"q": query},
f"https://s.jina.ai/{encoded_query}",
headers=headers,
timeout=15.0,
)
@ -197,7 +197,8 @@ class WebSearchTool(Tool):
]
return _format_results(query, items, n)
except Exception as e:
return f"Error: {e}"
logger.warning("Jina search failed ({}), falling back to DuckDuckGo", e)
return await self._search_duckduckgo(query, n)
async def _search_duckduckgo(self, query: str, n: int) -> str:
try:

View File

@ -160,3 +160,70 @@ async def test_searxng_invalid_url():
tool = _tool(provider="searxng", base_url="not-a-url")
result = await tool.execute(query="test")
assert "Error" in result
@pytest.mark.asyncio
async def test_jina_422_falls_back_to_duckduckgo(monkeypatch):
class MockDDGS:
def __init__(self, **kw):
pass
def text(self, query, max_results=5):
return [{"title": "Fallback", "href": "https://ddg.example", "body": "DuckDuckGo fallback"}]
async def mock_get(self, url, **kw):
assert "s.jina.ai" in str(url)
raise httpx.HTTPStatusError(
"422 Unprocessable Entity",
request=httpx.Request("GET", str(url)),
response=httpx.Response(422, request=httpx.Request("GET", str(url))),
)
monkeypatch.setattr(httpx.AsyncClient, "get", mock_get)
monkeypatch.setattr("ddgs.DDGS", MockDDGS)
tool = _tool(provider="jina", api_key="jina-key")
result = await tool.execute(query="test")
assert "DuckDuckGo fallback" in result
@pytest.mark.asyncio
async def test_jina_search_uses_path_encoded_query(monkeypatch):
calls = {}
async def mock_get(self, url, **kw):
calls["url"] = str(url)
calls["params"] = kw.get("params")
return _response(json={
"data": [{"title": "Jina Result", "url": "https://jina.ai", "content": "AI search"}]
})
monkeypatch.setattr(httpx.AsyncClient, "get", mock_get)
tool = _tool(provider="jina", api_key="jina-key")
await tool.execute(query="hello world")
assert calls["url"].rstrip("/") == "https://s.jina.ai/hello%20world"
assert calls["params"] in (None, {})
@pytest.mark.asyncio
async def test_jina_422_falls_back_to_duckduckgo(monkeypatch):
class MockDDGS:
def __init__(self, **kw):
pass
def text(self, query, max_results=5):
return [{"title": "Fallback", "href": "https://ddg.example", "body": "DuckDuckGo fallback"}]
async def mock_get(self, url, **kw):
raise httpx.HTTPStatusError(
"422 Unprocessable Entity",
request=httpx.Request("GET", str(url)),
response=httpx.Response(422, request=httpx.Request("GET", str(url))),
)
monkeypatch.setattr(httpx.AsyncClient, "get", mock_get)
monkeypatch.setattr("ddgs.DDGS", MockDDGS)
tool = _tool(provider="jina", api_key="jina-key")
result = await tool.execute(query="test")
assert "DuckDuckGo fallback" in result