feat: implement automatic payload candidate retry mechanism in AIPlanner for improved LM Studio compatibility

tests/test_ai_planner_lmstudio_compat.py

@@ -4,14 +4,28 @@ from ai_planner import AIPlanner
 
 
 class TestAIPlannerLMStudioCompat(unittest.TestCase):
-    def test_build_chat_payload_includes_input_for_responses_compat(self):
+    def test_build_chat_payload_has_legacy_chat_keys(self):
         payload = AIPlanner._build_chat_payload("hello")
 
         self.assertIn("messages", payload)
-        self.assertIn("input", payload)
-        self.assertEqual(payload["input"], "hello")
+        self.assertIn("options", payload)
         self.assertEqual(payload["messages"][1]["content"], "hello")
 
+    def test_build_input_only_payload_has_minimal_keys(self):
+        payload = AIPlanner._build_input_only_payload("hello")
+
+        self.assertIn("input", payload)
+        self.assertNotIn("messages", payload)
+        self.assertEqual(payload["stream"], False)
+        self.assertIn("hello", payload["input"])
+
+    def test_payload_candidates_order(self):
+        payloads = AIPlanner._build_payload_candidates("hello")
+        self.assertEqual(len(payloads), 2)
+        self.assertIn("messages", payloads[0])
+        self.assertIn("input", payloads[1])
+        self.assertNotIn("messages", payloads[1])
+
     def test_extract_response_content_supports_message_content(self):
         data = {
             "message": {