Update app.py

Take one management level t3 search like

app.py

@@ -1,69 +1,44 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
+from openai import OpenAI
+import os
+
+# The "Kernel" Configuration
+# Get your API key from Moonshot AI or OpenRouter
+API_KEY = os.getenv("KIMI_API_KEY") 
+BASE_URL = "https://api.moonshot.cn/v1" # Or your custom endpoint
+
+client = OpenAI(api_key=API_KEY, base_url=BASE_URL)
+
+def samaran_kernel_chat(message, history):
+    # 1. Prepare the Conversation Context
+    messages = [{"role": "system", "content": "You are the Samaran Kernel. Use <think> tags for deep reasoning. Be witty, technical, and precise."}]
+    for user_msg, ai_msg in history:
+        messages.append({"role": "user", "content": user_msg})
+        messages.append({"role": "assistant", "content": ai_msg})
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+    # 2. Call the Kimi K2 Engine
+    response = client.chat.completions.create(
+        model="moonshot-v1-32k", # Replace with k2-thinking if using private endpoint
+        messages=messages,
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+        temperature=0.6 # Recommended for Kimi K2 stability
+    )
+
+    partial_message = ""
+    for chunk in response:
+        if chunk.choices[0].delta.content:
+            partial_message += chunk.choices[0].delta.content
+            yield partial_message
+
+# 3. The T3-Style UI Interface
+view = gr.ChatInterface(
+    fn=samaran_kernel_chat,
+    title="Samaran Kernel T3 Chat",
+    description="Running on Kimi K2 Engine. Optimized for Deep Reasoning and Agentic Logic.",
+    theme="soft",
+    examples=["Explain the MoE architecture of Kimi K2.", "Draft a technical pitch for a new AI SaaS."]
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
 if __name__ == "__main__":
-    demo.launch()
+    view.launch()