KrustyPlanet/hermes-agent
6
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix(skills): let ClawHub index build walk past the 12s browse budget (#44500)

Browse source 
The deploy-site skills index crawl was capped at ~3k ClawHub entries
because CATALOG_WALK_BUDGET_SECONDS applied to max_items=0 walks too.
Only enforce the wall-clock budget for bounded browse requests and pass
limit=0 from build_skills_index so CI walks the full catalog.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Austin Pickett 2026-06-11 18:03:11 -04:00 • committed by GitHub
parent 021ed69141
commit 2ee69d0579
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 33 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

22
tests/tools/test_skills_hub_clawhub.py
View file

@ -381,9 +381,10 @@ class TestClawHubSource(unittest.TestCase):
mock_get.side_effect = side_effect
# Force the deadline to be in the past immediately.
# Force the deadline to be in the past immediately. Budget only applies
# to bounded browse walks (max_items > 0), not the index builder path.
with patch.object(ClawHubSource, "CATALOG_WALK_BUDGET_SECONDS", -1):
results = self.src._load_catalog_index()
results = self.src._load_catalog_index(max_items=10)
# Walk broke well before the 750-page cap.
self.assertLess(page_calls["n"], 750)
@ -480,6 +481,23 @@ class TestClawHubCatalogWalkBounded(unittest.TestCase):
# Partial (bounded) walk must not be cached.
mock_write_cache.assert_not_called()
@patch("tools.skills_hub._write_index_cache")
@patch("tools.skills_hub._read_index_cache", return_value=None)
@patch("tools.skills_hub.httpx.get")
def test_max_items_zero_ignores_wall_clock_budget(
self, mock_get, _mock_read_cache, _mock_write_cache
):
"""Index builder path (max_items=0) must not truncate on the browse budget."""
page_calls = {"n": 0}
mock_get.side_effect = self._infinite_pages(page_calls)
with patch.object(ClawHubSource, "CATALOG_WALK_BUDGET_SECONDS", -1):
results = self.src._load_catalog_index(max_items=0)
# No budget -> walks until the 750-page safety cap, not ~14 pages in 12s.
self.assertEqual(page_calls["n"], 750)
self.assertEqual(len(results), 750)
@patch("tools.skills_hub._write_index_cache")
@patch("tools.skills_hub._read_index_cache", return_value=None)
@patch("tools.skills_hub.httpx.get")