Improve retrieval of deep workspace evidence

SovereignAI-Starter/tests/test_knowledge.py

@@ -133,6 +133,49 @@ class KnowledgeIndexTests(unittest.TestCase):
         self.assertEqual(results[0]["path"], "docs/guide.md")
         self.assertIn("Whisper", str(results[0]["text"]))
 
+    def test_skill_permission_query_retrieves_allowed_tools_identifier(self) -> None:
+        self._index(
+            "if tool_name not in selected_skill.allowed_tools: "
+            "raise PermissionError('tool is not allowed')"
+        )
+
+        results = self._search(
+            "How is a tool call blocked when it is outside the selected skill permissions?"
+        )
+
+        self.assertTrue(results)
+        self.assertIn("allowed_tools", str(results[0]["text"]))
+
+    def test_search_clamps_global_and_per_document_result_limits(self) -> None:
+        with patch.object(knowledge.database, "DATABASE_PATH", self.database):
+            for index in range(5):
+                relative_path = f"docs/repeated-{index}.md"
+                text = "sharedphrase " * 220
+                path = self.workspace / relative_path
+                path.parent.mkdir(parents=True, exist_ok=True)
+                path.write_text(text, encoding="utf-8")
+                knowledge.index_document(
+                    user_id="local-user",
+                    workspace_path=self.workspace,
+                    relative_path=relative_path,
+                    text=text,
+                    content_hash=hashlib.sha256(text.encode("utf-8")).hexdigest(),
+                )
+
+            results = knowledge.search(
+                "sharedphrase",
+                user_id="local-user",
+                workspace_path=self.workspace,
+                limit=100,
+            )
+
+        self.assertEqual(len(results), knowledge.MAX_SEARCH_RESULTS)
+        for path in {str(item["path"]) for item in results}:
+            self.assertLessEqual(
+                sum(item["path"] == path for item in results),
+                knowledge.MAX_CHUNKS_PER_DOCUMENT,
+            )
+
     def test_chunking_preserves_overlap_for_boundary_context(self) -> None:
         text = "a" * (knowledge.CHUNK_SIZE - 2) + " boundaryphrase " + "b" * 80
         chunks = knowledge._chunks(text)