fix: wrap blocking readability call with asyncio.to_thread in web_fetch (#2157)
* fix: wrap blocking readability call with asyncio.to_thread in web_fetch The readability extractor internally spawns a Node.js subprocess via readabilipy, which blocks the async event loop and causes a BlockingError when web_fetch is invoked inside LangGraph's async runtime. Wrap the synchronous extract_article call with asyncio.to_thread to offload it to a thread pool, unblocking the event loop. Note: community/infoquest/tools.py has the same latent issue and should be addressed in a follow-up PR. Closes #2152 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * test: verify web_fetch offloads extraction via asyncio.to_thread Add a regression test that monkeypatches asyncio.to_thread to confirm readability extraction is offloaded to a worker thread, preventing future refactors from reintroducing the blocking call. Addresses Copilot review feedback on #2157. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
This commit is contained in:
parent
5db71cb68c
commit
1df389b9d0
|
|
@ -1,3 +1,5 @@
|
||||||
|
import asyncio
|
||||||
|
|
||||||
from langchain.tools import tool
|
from langchain.tools import tool
|
||||||
|
|
||||||
from deerflow.community.jina_ai.jina_client import JinaClient
|
from deerflow.community.jina_ai.jina_client import JinaClient
|
||||||
|
|
@ -26,5 +28,5 @@ async def web_fetch_tool(url: str) -> str:
|
||||||
html_content = await jina_client.crawl(url, return_format="html", timeout=timeout)
|
html_content = await jina_client.crawl(url, return_format="html", timeout=timeout)
|
||||||
if isinstance(html_content, str) and html_content.startswith("Error:"):
|
if isinstance(html_content, str) and html_content.startswith("Error:"):
|
||||||
return html_content
|
return html_content
|
||||||
article = readability_extractor.extract_article(html_content)
|
article = await asyncio.to_thread(readability_extractor.extract_article, html_content)
|
||||||
return article.to_markdown()[:4096]
|
return article.to_markdown()[:4096]
|
||||||
|
|
|
||||||
|
|
@ -175,3 +175,30 @@ async def test_web_fetch_tool_returns_markdown_on_success(monkeypatch):
|
||||||
result = await web_fetch_tool.ainvoke("https://example.com")
|
result = await web_fetch_tool.ainvoke("https://example.com")
|
||||||
assert "Hello world" in result
|
assert "Hello world" in result
|
||||||
assert not result.startswith("Error:")
|
assert not result.startswith("Error:")
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.anyio
|
||||||
|
async def test_web_fetch_tool_offloads_extraction_to_thread(monkeypatch):
|
||||||
|
"""Test that readability extraction is offloaded via asyncio.to_thread to avoid blocking the event loop."""
|
||||||
|
import asyncio
|
||||||
|
|
||||||
|
async def mock_crawl(self, url, **kwargs):
|
||||||
|
return "<html><body><p>threaded</p></body></html>"
|
||||||
|
|
||||||
|
mock_config = MagicMock()
|
||||||
|
mock_config.get_tool_config.return_value = None
|
||||||
|
monkeypatch.setattr("deerflow.community.jina_ai.tools.get_app_config", lambda: mock_config)
|
||||||
|
monkeypatch.setattr(JinaClient, "crawl", mock_crawl)
|
||||||
|
|
||||||
|
to_thread_called = False
|
||||||
|
original_to_thread = asyncio.to_thread
|
||||||
|
|
||||||
|
async def tracking_to_thread(func, *args, **kwargs):
|
||||||
|
nonlocal to_thread_called
|
||||||
|
to_thread_called = True
|
||||||
|
return await original_to_thread(func, *args, **kwargs)
|
||||||
|
|
||||||
|
monkeypatch.setattr("deerflow.community.jina_ai.tools.asyncio.to_thread", tracking_to_thread)
|
||||||
|
result = await web_fetch_tool.ainvoke("https://example.com")
|
||||||
|
assert to_thread_called, "extract_article must be called via asyncio.to_thread to avoid blocking the event loop"
|
||||||
|
assert "threaded" in result
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue