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

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>

scripts/build_skills_index.py

@@ -272,8 +272,9 @@ def main():
     # (well above current catalog size) lets the full catalog land in the
     # index instead of being truncated at an arbitrary build-time limit.
     SOURCE_LIMITS = {
-        # ClawHub had 49,698+ skills as of May 2026; 200k leaves headroom.
-        "clawhub": 200_000,
+        # 0 = unbounded catalog walk (max_items=0 in ClawHubSource). A positive
+        # limit bounds the walk and also enables the interactive 12s budget.
+        "clawhub": 0,
         "lobehub": 100_000,
         "browse-sh": 5_000,
         "claude-marketplace": 5_000,

tests/tools/test_skills_hub_clawhub.py

@@ -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")

tools/skills_hub.py

@@ -2279,12 +2279,20 @@ class ClawHubSource(SkillSource):
         # terminates well before this on `nextCursor` going None — the cap is
         # a safety rail against an infinite-cursor loop.
         max_pages = 750
-        deadline = time.monotonic() + self.CATALOG_WALK_BUDGET_SECONDS
+        # Wall-clock budget is for interactive browse (max_items > 0) only.
+        # The offline index builder passes max_items=0 and must walk the full
+        # catalog — a 12s cap there ships ~3k skills and trips the deploy
+        # health floor (20k).
+        deadline = (
+            time.monotonic() + self.CATALOG_WALK_BUDGET_SECONDS
+            if max_items > 0
+            else None
+        )
         hit_deadline = False
         hit_max_items = False
 
         for _ in range(max_pages):
-            if time.monotonic() > deadline:
+            if deadline is not None and time.monotonic() > deadline:
                 hit_deadline = True
                 break
             params: Dict[str, Any] = {"limit": 200}