Proposed Changes - Replace the default model from `moonshotai/Kimi-K2.5` to `Qwen/Qwen3-32B`. - Remove the provider-specific `extra_body={"thinking": {"type": "disabled"}}` parameter. - Update inference examples to use a model that is currently supported through Hugging Face Inference Providers. - Improve out-of-the-box execution for users running the notebook on Colab or local environments.

unit1/dummy_agent_library.ipynb

@@ -52,7 +52,7 @@
         "except ImportError:\n",
         "    HF_TOKEN = os.environ.get(\"HF_TOKEN\")\n",
         "\n",
-        "client = InferenceClient(model=\"moonshotai/Kimi-K2.5\", token=HF_TOKEN)"
+        "client = InferenceClient(model=\"Qwen/Qwen3-32B\", token=HF_TOKEN)"
       ]
     },
     {
@@ -74,7 +74,6 @@
         "    ],\n",
         "    stream=False,\n",
         "    max_tokens=1024,\n",
-        "    extra_body={'thinking': {'type': 'disabled'}},\n",
         ")\n",
         "print(output.choices[0].message.content)"
       ]
@@ -183,7 +182,6 @@
         "    messages=messages,\n",
         "    stream=False,\n",
         "    max_tokens=200,\n",
-        "    extra_body={'thinking': {'type': 'disabled'}},\n",
         ")\n",
         "print(output.choices[0].message.content)"
       ]
@@ -210,7 +208,6 @@
         "    messages=messages,\n",
         "    max_tokens=150,\n",
         "    stop=[\"Observation:\"], # Let's stop before any actual function is called\n",
-        "    extra_body={'thinking': {'type': 'disabled'}},\n",
         ")\n",
         "\n",
         "print(output.choices[0].message.content)"
@@ -261,7 +258,6 @@
         "    messages=messages,\n",
         "    stream=False,\n",
         "    max_tokens=200,\n",
-        "    extra_body={'thinking': {'type': 'disabled'}},\n",
         ")\n",
         "\n",
         "print(output.choices[0].message.content)"