hermes-agent/tests/tools/test_web_tools_dict_urls.py
Teknium 39975613b1
test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s
Second, deeper pass over tools/gateway/hermes_cli plus first pass over
the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker,
dashboard, conformance, monitoring, secret_sources, hermes_state,
providers). Same rubric as wave 1 (AGENTS.md test policy); security,
alternation/caching invariants, issue-number regressions, and E2E kept.

Real test-quality fixes found and rooted out along the way:
- tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls
  (DEFAULT_CONFIG smart-approval leaked in) — pinned approval
  mode=manual via autouse fixture: 17.4s → 0.4s.
- test_model_switch_custom_providers.py / test_user_providers_model_switch.py
  silently probed live provider catalogs (~2s/test) — stubbed
  cached_provider_model_ids/provider_model_ids/fetch_api_models.
- test_telegram_noise_filter.py: 15-platform copy-paste matrix over
  shared gateway.run logic → 3 representative platforms (55s → 3.9s).
- test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on
  MagicMock agents — interrupt.side_effect now clears _running_agents
  (22s → 1.0s).
- test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x
  (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps
  patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait
  5s → 0.5s.
- test_telegram_init_deadline.py: loop-block margin restored to 1.0s
  with rationale comment — the watchdog-dump assertion needs the loop
  blocked well past deadline+grace under parallel load (flaked once in
  the 40-worker verification run at a 0.2s margin).

Verification: full hermetic suite via scripts/run_tests.sh —
2,438 files, 21,718 tests passed, 0 failed, 293.9s wall.
Suite totals vs original baseline: 46,820 → 19,757 test functions
(−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
2026-07-29 13:39:40 -07:00

89 lines
2.5 KiB
Python

"""Regression tests for model-forwarded web-search result objects."""
import json
import pytest
from agent import web_search_registry
from agent.web_search_provider import WebSearchProvider
from tools import web_tools
class _FakeExtractProvider(WebSearchProvider):
def __init__(self) -> None:
self.received_urls: list[str] = []
@property
def name(self) -> str:
return "dict-url-test"
@property
def display_name(self) -> str:
return "Dict URL Test"
def is_available(self) -> bool:
return True
def supports_extract(self) -> bool:
return True
async def extract(self, urls, **kwargs):
self.received_urls.extend(urls)
return [
{"url": url, "title": "", "content": "ok"}
for url in urls
]
@pytest.fixture
def extract_provider(monkeypatch):
with web_search_registry._lock:
previous = dict(web_search_registry._providers)
web_search_registry._providers.clear()
provider = _FakeExtractProvider()
web_search_registry.register_provider(provider)
monkeypatch.setattr(web_tools, "_ensure_web_plugins_loaded", lambda: None)
monkeypatch.setattr(
web_tools,
"_load_web_config",
lambda: {"extract_backend": provider.name},
)
async def _safe(_url):
return True
monkeypatch.setattr(web_tools, "async_is_safe_url", _safe)
yield provider
with web_search_registry._lock:
web_search_registry._providers.clear()
web_search_registry._providers.update(previous)
@pytest.mark.asyncio
async def test_web_extract_dispatches_urls_from_search_result_objects(extract_provider):
result = json.loads(await web_tools.web_extract_tool([
{"url": "https://example.com/a", "title": "A"},
{"href": "https://example.org/b"},
]))
assert extract_provider.received_urls == [
"https://example.com/a",
"https://example.org/b",
]
assert [entry["url"] for entry in result["results"]] == extract_provider.received_urls
def test_web_extract_registry_dispatch_accepts_search_result_objects(
extract_provider,
):
"""The model-facing registry path preserves object URLs through dispatch."""
raw = web_tools.registry.dispatch("web_extract", {
"urls": [{"url": "https://example.net/from-registry", "title": "R"}],
})
assert isinstance(raw, str)
result = json.loads(raw)
assert extract_provider.received_urls == ["https://example.net/from-registry"]
assert result["results"][0]["url"] == "https://example.net/from-registry"