fix: configure default models for built-in Kilo Code agents

- code: ollama-cloud/qwen3-coder:480b (coding tasks)
- ask: qwen/qwen3.6-plus:free (codebase questions)
- plan: ollama-cloud/nemotron-3-super (task planning)
- debug: ollama-cloud/gpt-oss:20b (bug diagnostics)

This fixes the issue where default models were not set in Settings.

.kilo/kilo.jsonc

@@ -14,6 +14,22 @@
         "bash": "allow",
         "task": "allow"
       }
+    },
+    "code": {
+      "model": "ollama-cloud/qwen3-coder:480b",
+      "description": "Primary code writer. Full tool access for development tasks."
+    },
+    "ask": {
+      "model": "qwen/qwen3.6-plus:free",
+      "description": "Read-only Q&A agent for codebase questions."
+    },
+    "plan": {
+      "model": "ollama-cloud/nemotron-3-super",
+      "description": "Task planner. Creates detailed implementation plans."
+    },
+    "debug": {
+      "model": "ollama-cloud/gpt-oss:20b",
+      "description": "Bug diagnostics and troubleshooting."
     }
   }
 }