Teknium
39975613b1
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.
86 lines
3.1 KiB
Python
86 lines
3.1 KiB
Python
#!/usr/bin/env python3
|
|
|
|
import unittest
|
|
from unittest.mock import patch
|
|
|
|
from tools.skills_hub import BrowseShSource, SkillMeta, SkillBundle
|
|
|
|
|
|
# Catalog shape mirrors the real ``GET https://browse.sh/api/skills`` response:
|
|
# ``slug`` is ``<hostname>/<task-id>`` and ``name`` is the task name.
|
|
SAMPLE_CATALOG = [
|
|
{
|
|
"slug": "airbnb.com/search-listings-ddgioa",
|
|
"name": "search-listings",
|
|
"title": "Airbnb Search Listings",
|
|
"description": "Search and browse Airbnb listings by location and dates.",
|
|
"hostname": "airbnb.com",
|
|
"category": "travel",
|
|
"tags": ["travel", "accommodation"],
|
|
"sourceUrl": "https://github.com/browserbase/browse.sh/blob/main/skills/airbnb.com/search-listings-ddgioa/SKILL.md",
|
|
"recommendedMethod": "stagehand",
|
|
"proxies": False,
|
|
"installCount": 42,
|
|
},
|
|
{
|
|
"slug": "amazon.com/search-products-xyz",
|
|
"name": "search-products",
|
|
"title": "Amazon Product Search",
|
|
"description": "Search for products on Amazon.",
|
|
"hostname": "amazon.com",
|
|
"category": "shopping",
|
|
"tags": ["shopping", "ecommerce"],
|
|
"sourceUrl": "https://github.com/browserbase/browse.sh/blob/main/skills/amazon.com/search-products-xyz/SKILL.md",
|
|
"recommendedMethod": "stagehand",
|
|
"proxies": False,
|
|
"installCount": 99,
|
|
},
|
|
]
|
|
|
|
|
|
class _MockResponse:
|
|
def __init__(self, status_code=200, json_data=None, text="", headers=None):
|
|
self.status_code = status_code
|
|
self._json_data = json_data
|
|
self.text = text
|
|
self.headers = headers or {}
|
|
|
|
def json(self):
|
|
return self._json_data
|
|
|
|
|
|
class TestBrowseShSource(unittest.TestCase):
|
|
def setUp(self):
|
|
self.src = BrowseShSource()
|
|
|
|
def test_source_id(self):
|
|
self.assertEqual(self.src.source_id(), "browse-sh")
|
|
|
|
@patch.object(BrowseShSource, "_fetch_catalog", return_value=SAMPLE_CATALOG)
|
|
def test_search_returns_results(self, _mock_catalog):
|
|
results = self.src.search("airbnb", limit=10)
|
|
self.assertGreaterEqual(len(results), 1)
|
|
meta = results[0]
|
|
self.assertIsInstance(meta, SkillMeta)
|
|
self.assertEqual(meta.name, "search-listings")
|
|
self.assertEqual(meta.source, "browse-sh")
|
|
self.assertEqual(meta.trust_level, "community")
|
|
self.assertEqual(meta.identifier, "browse-sh/airbnb.com/search-listings-ddgioa")
|
|
self.assertIn("travel", meta.tags)
|
|
|
|
|
|
@patch.object(BrowseShSource, "_fetch_catalog", return_value=SAMPLE_CATALOG)
|
|
def test_inspect_returns_meta(self, _mock_catalog):
|
|
meta = self.src.inspect("browse-sh/airbnb.com/search-listings-ddgioa")
|
|
self.assertIsNotNone(meta)
|
|
self.assertIsInstance(meta, SkillMeta)
|
|
self.assertEqual(meta.name, "search-listings")
|
|
self.assertEqual(meta.identifier, "browse-sh/airbnb.com/search-listings-ddgioa")
|
|
self.assertEqual(meta.extra["hostname"], "airbnb.com")
|
|
self.assertEqual(meta.extra["category"], "travel")
|
|
self.assertEqual(meta.extra["install_count"], 42)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|