Merge pull request #1400 from NousResearch/hermes/hermes-45b79a59-clawhub-search

fix: harden ClawHub skill search exact matches

tests/tools/test_skills_hub_clawhub.py

@@ -3,7 +3,7 @@
 import unittest
 from unittest.mock import patch
 
-from tools.skills_hub import ClawHubSource
+from tools.skills_hub import ClawHubSource, SkillMeta
 
 
 class _MockResponse:
@@ -22,21 +22,31 @@ class TestClawHubSource(unittest.TestCase):
 
     @patch("tools.skills_hub._write_index_cache")
     @patch("tools.skills_hub._read_index_cache", return_value=None)
+    @patch.object(ClawHubSource, "_load_catalog_index", return_value=[])
     @patch("tools.skills_hub.httpx.get")
-    def test_search_uses_new_endpoint_and_parses_items(self, mock_get, _mock_read_cache, _mock_write_cache):
-        mock_get.return_value = _MockResponse(
-            status_code=200,
-            json_data={
-                "items": [
-                    {
-                        "slug": "caldav-calendar",
-                        "displayName": "CalDAV Calendar",
-                        "summary": "Calendar integration",
-                        "tags": ["calendar", "productivity"],
-                    }
-                ]
-            },
-        )
+    def test_search_uses_listing_endpoint_as_fallback(
+        self, mock_get, _mock_load_catalog, _mock_read_cache, _mock_write_cache
+    ):
+        def side_effect(url, *args, **kwargs):
+            if url.endswith("/skills"):
+                return _MockResponse(
+                    status_code=200,
+                    json_data={
+                        "items": [
+                            {
+                                "slug": "caldav-calendar",
+                                "displayName": "CalDAV Calendar",
+                                "summary": "Calendar integration",
+                                "tags": ["calendar", "productivity"],
+                            }
+                        ]
+                    },
+                )
+            if url.endswith("/skills/caldav"):
+                return _MockResponse(status_code=404, json_data={})
+            return _MockResponse(status_code=404, json_data={})
+
+        mock_get.side_effect = side_effect
 
         results = self.src.search("caldav", limit=5)
 
@@ -45,11 +55,112 @@ class TestClawHubSource(unittest.TestCase):
         self.assertEqual(results[0].name, "CalDAV Calendar")
         self.assertEqual(results[0].description, "Calendar integration")
 
-        mock_get.assert_called_once()
-        args, kwargs = mock_get.call_args
+        self.assertGreaterEqual(mock_get.call_count, 2)
+        args, kwargs = mock_get.call_args_list[0]
         self.assertTrue(args[0].endswith("/skills"))
         self.assertEqual(kwargs["params"], {"search": "caldav", "limit": 5})
 
+    @patch("tools.skills_hub._write_index_cache")
+    @patch("tools.skills_hub._read_index_cache", return_value=None)
+    @patch.object(
+        ClawHubSource,
+        "_load_catalog_index",
+        return_value=[],
+    )
+    @patch("tools.skills_hub.httpx.get")
+    def test_search_falls_back_to_exact_slug_when_search_results_are_irrelevant(
+        self, mock_get, _mock_load_catalog, _mock_read_cache, _mock_write_cache
+    ):
+        def side_effect(url, *args, **kwargs):
+            if url.endswith("/skills"):
+                return _MockResponse(
+                    status_code=200,
+                    json_data={
+                        "items": [
+                            {
+                                "slug": "apple-music-dj",
+                                "displayName": "Apple Music DJ",
+                                "summary": "Unrelated result",
+                            }
+                        ]
+                    },
+                )
+            if url.endswith("/skills/self-improving-agent"):
+                return _MockResponse(
+                    status_code=200,
+                    json_data={
+                        "skill": {
+                            "slug": "self-improving-agent",
+                            "displayName": "self-improving-agent",
+                            "summary": "Captures learnings and errors for continuous improvement.",
+                            "tags": {"latest": "3.0.2", "automation": "3.0.2"},
+                        },
+                        "latestVersion": {"version": "3.0.2"},
+                    },
+                )
+            return _MockResponse(status_code=404, json_data={})
+
+        mock_get.side_effect = side_effect
+
+        results = self.src.search("self-improving-agent", limit=5)
+
+        self.assertEqual(len(results), 1)
+        self.assertEqual(results[0].identifier, "self-improving-agent")
+        self.assertEqual(results[0].name, "self-improving-agent")
+        self.assertIn("continuous improvement", results[0].description)
+
+    @patch("tools.skills_hub.httpx.get")
+    def test_search_repairs_poisoned_cache_with_exact_slug_lookup(self, mock_get):
+        mock_get.return_value = _MockResponse(
+            status_code=200,
+            json_data={
+                "skill": {
+                    "slug": "self-improving-agent",
+                    "displayName": "self-improving-agent",
+                    "summary": "Captures learnings and errors for continuous improvement.",
+                    "tags": {"latest": "3.0.2", "automation": "3.0.2"},
+                },
+                "latestVersion": {"version": "3.0.2"},
+            },
+        )
+
+        poisoned = [
+            SkillMeta(
+                name="Apple Music DJ",
+                description="Unrelated cached result",
+                source="clawhub",
+                identifier="apple-music-dj",
+                trust_level="community",
+                tags=[],
+            )
+        ]
+        results = self.src._finalize_search_results("self-improving-agent", poisoned, 5)
+
+        self.assertEqual(len(results), 1)
+        self.assertEqual(results[0].identifier, "self-improving-agent")
+        mock_get.assert_called_once()
+        self.assertTrue(mock_get.call_args.args[0].endswith("/skills/self-improving-agent"))
+
+    @patch.object(
+        ClawHubSource,
+        "_exact_slug_meta",
+        return_value=SkillMeta(
+            name="self-improving-agent",
+            description="Captures learnings and errors for continuous improvement.",
+            source="clawhub",
+            identifier="self-improving-agent",
+            trust_level="community",
+            tags=["automation"],
+        ),
+    )
+    def test_search_matches_space_separated_query_to_hyphenated_slug(
+        self, _mock_exact_slug
+    ):
+        results = self.src.search("self improving", limit=5)
+
+        self.assertEqual(len(results), 1)
+        self.assertEqual(results[0].identifier, "self-improving-agent")
+
     @patch("tools.skills_hub.httpx.get")
     def test_inspect_maps_display_name_and_summary(self, mock_get):
         mock_get.return_value = _MockResponse(
@@ -69,6 +180,29 @@ class TestClawHubSource(unittest.TestCase):
         self.assertEqual(meta.description, "Calendar integration")
         self.assertEqual(meta.identifier, "caldav-calendar")
 
+    @patch("tools.skills_hub.httpx.get")
+    def test_inspect_handles_nested_skill_payload(self, mock_get):
+        mock_get.return_value = _MockResponse(
+            status_code=200,
+            json_data={
+                "skill": {
+                    "slug": "self-improving-agent",
+                    "displayName": "self-improving-agent",
+                    "summary": "Captures learnings and errors for continuous improvement.",
+                    "tags": {"latest": "3.0.2", "automation": "3.0.2"},
+                },
+                "latestVersion": {"version": "3.0.2"},
+            },
+        )
+
+        meta = self.src.inspect("self-improving-agent")
+
+        self.assertIsNotNone(meta)
+        self.assertEqual(meta.name, "self-improving-agent")
+        self.assertIn("continuous improvement", meta.description)
+        self.assertEqual(meta.identifier, "self-improving-agent")
+        self.assertEqual(meta.tags, ["automation"])
+
     @patch("tools.skills_hub.httpx.get")
     def test_fetch_resolves_latest_version_and_downloads_raw_files(self, mock_get):
         def side_effect(url, *args, **kwargs):