Add knowledge retrieval configuration to Assistant model and related components

- Introduce new fields for knowledge retrieval configuration in AssistantConfig and Assistant models, including mode, top_n, and score_threshold.
- Implement KnowledgeRetrievalConfig schema with validation for top_n.
- Update backend services and routes to handle knowledge retrieval settings.
- Enhance frontend components to support knowledge retrieval configuration, including a new dialog for advanced settings.
- Add tests for knowledge retrieval configuration validation and description generation.

backend/tests/test_knowledge.py

@@ -1,5 +1,8 @@
 import unittest
 
+from pydantic import ValidationError
+
+from schemas import KnowledgeRetrievalConfig
 from services.knowledge import extract_text, split_text
 
 
@@ -19,5 +22,22 @@ class KnowledgeTextTest(unittest.TestCase):
             extract_text("archive.zip", b"data")
 
 
+class KnowledgeRetrievalConfigTest(unittest.TestCase):
+    def test_accepts_unlimited_top_n_with_threshold(self):
+        config = KnowledgeRetrievalConfig.model_validate(
+            {"mode": "on_demand", "topN": -1, "scoreThreshold": 0.65}
+        )
+
+        self.assertEqual(config.top_n, -1)
+        self.assertEqual(
+            config.model_dump(by_alias=True),
+            {"mode": "on_demand", "topN": -1, "scoreThreshold": 0.65},
+        )
+
+    def test_rejects_zero_top_n(self):
+        with self.assertRaises(ValidationError):
+            KnowledgeRetrievalConfig(top_n=0)
+
+
 if __name__ == "__main__":
     unittest.main()