From d457e7f039ee2f0b1b655fca9535b4e33f35c05a Mon Sep 17 00:00:00 2001
From: teknium1 <127238744+teknium1@users.noreply.github.com>
Date: Fri, 18 Sep 2026 11:16:39 -0700
Subject: [PATCH] test(skills): seam the sitemap-shard retry test on the hub
 guarded GET

The shard fetch now routes through hub()._guarded_http_get (#114887), so a patch
on tools.skills_hub_skillssh._get_text intercepted nothing and the test reached
the live sitemap on CI. Patch tools.skills_hub._ssrf_safe_http_get like the
neighbouring guarded-GET test and model the dark shard as a 503.
---
 tests/tools/test_skills_hub.py | 18 ++++++++++++------
 tools/skills_hub_skillssh.py   |  2 +-
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/tests/tools/test_skills_hub.py b/tests/tools/test_skills_hub.py
index 32e759998f..b7631b4d73 100644
--- a/tests/tools/test_skills_hub.py
+++ b/tests/tools/test_skills_hub.py
@@ -258,23 +258,29 @@ class TestSkillsShSource:
     @patch("tools.skills_hub._write_index_cache")
     @patch("tools.skills_hub._read_index_cache", return_value=None)
     def test_sitemap_catalog_retries_failed_shard_and_never_caches_partial(
-        self, _mock_read_cache, mock_write_cache, _mock_sleep,
+        self, _mock_read_cache, mock_write_cache, _mock_sleep, monkeypatch,
     ):
         """A per-skill sitemap shard that keeps failing is a hole in the catalog, not an
         empty shard: retry it, and never publish the partial slice to the shared cache."""
+        monkeypatch.setattr("tools.skills_hub.is_safe_url", lambda _url: True)
+        monkeypatch.setattr("tools.skills_hub.check_website_access", lambda _url: None)
+        monkeypatch.setattr("tools.skills_hub_skillssh._cached_metas", lambda _key: None)
+        monkeypatch.setattr("tools.skills_hub_skillssh._cache_metas", lambda _key, _metas: None)
         index = ("<sitemapindex><sitemap><loc>https://www.skills.sh/sitemap-skills-0.xml</loc></sitemap>"
                  "<sitemap><loc>https://www.skills.sh/sitemap-skills-1.xml</loc></sitemap></sitemapindex>")
         shard0 = "<urlset><url><loc>https://www.skills.sh/o/r/skill-a</loc></url></urlset>"
         calls: List[str] = []
 
-        def fake_get_text(url, **kwargs):
+        def fake_get(url, *, timeout, headers=None):
             calls.append(url)
             if url.endswith("sitemap.xml"):
-                return index
-            return shard0 if url.endswith("sitemap-skills-0.xml") else None
+                return MagicMock(status_code=200, headers={}, text=index)
+            if url.endswith("sitemap-skills-0.xml"):
+                return MagicMock(status_code=200, headers={}, text=shard0)
+            return MagicMock(status_code=503, headers={}, text="")
 
-        with patch("tools.skills_hub_skillssh._get_text", side_effect=fake_get_text):
-            results = self._source()._sitemap_catalog(0)
+        monkeypatch.setattr("tools.skills_hub._ssrf_safe_http_get", fake_get)
+        results = self._source()._sitemap_catalog(0)
 
         assert [m.identifier for m in results] == ["skills-sh/o/r/skill-a"]
         assert calls.count("https://www.skills.sh/sitemap-skills-1.xml") == SkillSource.CATALOG_PAGE_RETRIES
diff --git a/tools/skills_hub_skillssh.py b/tools/skills_hub_skillssh.py
index a5cd8cd777..7a3fe96f3f 100644
--- a/tools/skills_hub_skillssh.py
+++ b/tools/skills_hub_skillssh.py
@@ -139,7 +139,7 @@ class SkillsShSource(SkillSource):
             return self._featured_skills(limit)
 
         # Step 2: collect canonical "owner/repo/skill" IDs from each sitemap. A shard
-        # ``_get_text`` returns None for is a hole, not an empty shard: retry it, and
+        # ``_xml`` returns None for is a hole, not an empty shard: retry it, and
         # if it stays dark return the partial slice without publishing it to the cache.
         seen, results, partial = set(), [], False
         for sitemap_url in skill_sitemap_urls: