feat: configure 32k context for protocol generation

tests/test_direct_protocol.py

@@ -116,6 +116,7 @@ class GeneratorTests(unittest.TestCase):
         self.assertEqual(check.call_count, 1)
         self.assertEqual(call.call_count, 1)
         self.assertEqual(call.call_args.args[1], "qwen3.6:35B-A3B")
+        self.assertEqual(call.call_args.kwargs["num_ctx"], 32768)
         self.assertEqual(result.runtime_metadata["request_count"], 1)
         self.assertEqual(result.runtime_metadata["prompt_token_count"], 123)
         self.assertFalse(result.runtime_metadata["think"])
@@ -181,7 +182,7 @@ class OllamaTests(unittest.TestCase):
         with patch.object(ollama.requests, "post", return_value=response) as post:
             result = ollama.generate_once(
                 "http://localhost:11434",
-                "chosen:model",
+                "qwen3.8:27b",
                 "prompt",
                 timeout=30,
                 num_ctx=32768,
@@ -190,8 +191,9 @@ class OllamaTests(unittest.TestCase):
 
         self.assertEqual(post.call_count, 1)
         payload = post.call_args.kwargs["json"]
-        self.assertEqual(payload["model"], "chosen:model")
+        self.assertEqual(payload["model"], "qwen3.8:27b")
         self.assertEqual(payload["options"]["temperature"], 0.0)
+        self.assertEqual(payload["options"]["num_ctx"], 32768)
         self.assertFalse(payload["think"])
         self.assertFalse(payload["stream"])
         self.assertEqual(result.raw_response, raw)