Update app.py

app.py

@@ -1,5 +1,6 @@
 import os
 import logging
+import spaces
 import gradio as gr
 from huggingface_hub import InferenceClient
 
@@ -13,6 +14,12 @@ SYSTEM_PROMPT = (
 )
 
 
+# Required by ZeroGPU: at least one @spaces.GPU function must exist at startup.
+@spaces.GPU
+def _gpu_placeholder():
+    return "ok"
+
+
 def chat(message, history):
     if not message or not message.strip():
         yield "Please enter a message."
@@ -24,38 +31,23 @@ def chat(message, history):
         yield "Configuration error: HF_TOKEN is missing from Space Secrets."
         return
 
-    messages = [
-        {"role": "system", "content": SYSTEM_PROMPT}
-    ]
+    messages = [{"role": "system", "content": SYSTEM_PROMPT}]
 
-    # Preserve previous conversation turns.
     for item in history or []:
         if not isinstance(item, dict):
             continue
-
         role = item.get("role")
         content = item.get("content")
-
         if role in ("user", "assistant") and isinstance(content, str):
-            messages.append({
-                "role": role,
-                "content": content,
-            })
+            messages.append({"role": role, "content": content})
 
-    messages.append({
-        "role": "user",
-        "content": message.strip(),
-    })
+    messages.append({"role": "user", "content": message.strip()})
 
     answer = ""
 
     try:
         logging.info("Starting inference request for %s", MODEL_ID)
-
-        client = InferenceClient(
-            model=MODEL_ID,
-            token=token,
-        )
+        client = InferenceClient(model=MODEL_ID, token=token)
 
         stream = client.chat.completions.create(
             messages=messages,
@@ -67,9 +59,7 @@ def chat(message, history):
         for chunk in stream:
             if not chunk.choices:
                 continue
-
             content = chunk.choices[0].delta.content
-
             if isinstance(content, str) and content:
                 answer += content
                 yield answer
@@ -84,6 +74,7 @@ def chat(message, history):
 
 demo = gr.ChatInterface(
     fn=chat,
+    type="messages",
     title="🧠 Tony-Flash",
     description="Chat with DeepSeek V4 Flash",
     textbox=gr.Textbox(
@@ -93,9 +84,4 @@ demo = gr.ChatInterface(
 )
 
 if __name__ == "__main__":
-    demo.queue().launch(
-        server_name="0.0.0.0",
-        server_port=7860,
-        show_error=True,
-        ssr_mode=False,
-    )
+    demo.queue().launch(show_error=True, ssr_mode=False)