feat: wire hybrid provider into CLI

tests/unit/test_ollama_provider.py

@@ -26,6 +26,14 @@ class _OllamaHandler(BaseHTTPRequestHandler):
         self.end_headers()
         self.wfile.write(body)
 
+    def do_GET(self) -> None:
+        body = json.dumps({"models": [{"name": "test-model"}]}).encode()
+        self.send_response(200)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(body)))
+        self.end_headers()
+        self.wfile.write(body)
+
     def log_message(self, format: str, *args: object) -> None:
         return
 
@@ -42,6 +50,7 @@ class OllamaProviderTests(unittest.TestCase):
                 2,
             )
             response = provider.chat([ChatMessage("user", "Hallo")])
+            status = provider.probe()
         finally:
             server.shutdown()
             server.server_close()
@@ -50,6 +59,8 @@ class OllamaProviderTests(unittest.TestCase):
         self.assertEqual(response, "Lokale Antwort")
         self.assertEqual(_OllamaHandler.request_payload["model"], "test-model")
         self.assertFalse(_OllamaHandler.request_payload["stream"])
+        self.assertTrue(status.reachable)
+        self.assertTrue(status.model_available)
 
 
 if __name__ == "__main__":