Convert Claude Code or Codex into the most intelligent Deep Research Agent. Collect, search, and synthesize web research into a persistent, searchable wiki that builds on itself. Hosted API + MCP: hyperresearch.ai
Python agentsagentskillscitationsclaude-codecodexcodex-plugincodex-skilldeep-researchdeep-research-agentdeepresearchmcp-serverresearchresearch-agentresearch-tools
"""The MCP fetch_url tool must not block the server's event loop (#118).
The fake provider's fetch blocks until another coroutine on the same loop
releases it. If fetch_url ran the fetch on the loop thread, that coroutine
could never run and the fetch would time out.
"""
from __future__ import annotations
import asyncio
import json
import os
import threading
from pathlib import Path
import pytest
from typer.testing import CliRunner
from hyperresearch.cli import app
from hyperresearch.web.base import WebResult
mcp = pytest.importorskip("hyperresearch.mcp.server")
runner = CliRunner()
@pytest.fixture
def mcp_vault(tmp_path: Path) -> Path:
vault_dir = tmp_path / "kb"
runner.invoke(app, ["init", str(vault_dir)])
os.chdir(vault_dir)
mcp._vault = None # module-global cache; force rediscovery under tmp_path
yield vault_dir
mcp._vault = None
class _BlockingProvider:
name = "fake"
def __init__(self) -> None:
self.started = threading.Event()
self.release = threading.Event()
self.fetch_thread: int | None = None
def fetch(self, url: str) -> WebResult:
self.fetch_thread = threading.get_ident()
self.started.set()
if not self.release.wait(timeout=5):
raise RuntimeError("fetch was never released: the event loop was blocked")
return WebResult(url=url, title="Fake Title", content="enough content to clear the junk gate. " * 10)
def _run_on_a_fresh_thread(coro):
"""Run ``coro`` on a new thread with its own loop.
See tests/test_web/test_fetch_many_fallback.py's ``_run``: an earlier test
can leave the main thread's asyncio state marked running. The vault is
opened inside ``coro`` too, so its sqlite connection belongs to that loop's
thread, as it does in the server.
"""
box: dict = {}
def target() -> None:
try:
box["result"] = asyncio.run(coro)
except BaseException as exc:
box["error"] = exc
thread = threading.Thread(target=target)
thread.start()
thread.join()
if "error" in box:
raise box["error"]
return box["result"]
def test_fetch_url_keeps_the_event_loop_responsive(mcp_vault, monkeypatch):
prov = _BlockingProvider()
monkeypatch.setattr("hyperresearch.web.base.get_provider", lambda *a, **k: prov)
url = "https://example.com/slow-page"
async def scenario():
loop_thread = threading.get_ident()
async def release_once_started() -> None:
# Polls on the loop; only runs at all if fetch_url yielded it.
for _ in range(500):
if prov.started.is_set():
prov.release.set()
return
await asyncio.sleep(0.01)
raise AssertionError("fetch never started")
out, _ = await asyncio.gather(mcp.fetch_url(url), release_once_started())
return loop_thread, out
loop_thread, out = _run_on_a_fresh_thread(scenario())
out = json.loads(out)
assert out["ok"] is True, out
assert prov.fetch_thread != loop_thread
assert (mcp_vault / out["data"]["path"]).exists()
def test_fetch_url_saves_the_source_row_on_the_loop_thread(mcp_vault, monkeypatch):
"""The sources INSERT uses the loop thread's sqlite connection; a second
fetch of the same URL sees it and is refused before any network call."""
prov = _BlockingProvider()
prov.release.set()
monkeypatch.setattr("hyperresearch.web.base.get_provider", lambda *a, **k: prov)
url = "https://example.com/once"
async def fetch_twice():
first = json.loads(await mcp.fetch_url(url))
prov.started.clear()
second = json.loads(await mcp.fetch_url(url))
return first, second
first, second = _run_on_a_fresh_thread(fetch_twice())
assert first["ok"] is True, first
assert second["ok"] is False
assert second["error_code"] == "DUPLICATE_URL"
assert not prov.started.is_set()