Update app.py

app.py

@@ -1,70 +1,131 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import requests
+import os
+from datetime import datetime
 
+# Configuração GLM-4.6
+HF_TOKEN = os.getenv("HF_TOKEN", "")
+MODEL_ID = "zai-org/GLM-4.6"
+API_URL = f"https://api-inference.huggingface.co/models/{MODEL_ID}"
 
-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")
+class CodeAgentGLM:
+    def __init__(self):
+        self.headers = {"Authorization": f"Bearer {HF_TOKEN}"}
+    
+    def generate_code(self, prompt, language="python", max_tokens=1024):
+        """Gera código usando GLM-4.6"""
+        full_prompt = f"""You are an expert code generation AI. Generate high-quality {language} code.
 
-    messages = [{"role": "system", "content": system_message}]
+Request: {prompt}
 
-    messages.extend(history)
+Provide only the code without explanations:"""
+        
+        payload = {
+            "inputs": full_prompt,
+            "parameters": {
+                "max_new_tokens": max_tokens,
+                "temperature": 0.3,
+                "top_p": 0.9,
+                "do_sample": True
+            }
+        }
+        
+        try:
+            response = requests.post(API_URL, headers=self.headers, json=payload, timeout=30)
+            if response.status_code == 200:
+                result = response.json()
+                if isinstance(result, list) and len(result) > 0:
+                    return result[0].get("generated_text", "").split("Provide only the code without explanations:")[-1].strip()
+            return f"Erro: {response.status_code}"
+        except Exception as e:
+            return f"Erro na chamada: {str(e)}"
+    
+    def explain_code(self, code):
+        """Explica código"""
+        prompt = f"Explique brevemente este código:\n\n{code}"
+        payload = {
+            "inputs": prompt,
+            "parameters": {"max_new_tokens": 500, "temperature": 0.5}
+        }
+        try:
+            response = requests.post(API_URL, headers=self.headers, json=payload)
+            if response.status_code == 200:
+                result = response.json()
+                return result[0].get("generated_text", "") if isinstance(result, list) else str(result)
+            return f"Erro: {response.status_code}"
+        except Exception as e:
+            return f"Erro: {str(e)}"
 
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        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,
-    type="messages",
-    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)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+agent = CodeAgentGLM()
 
+# Interface Gradio
+with gr.Blocks(title="GLM-4.6 Code Agent", theme=gr.themes.Soft()) as demo:
+    gr.Markdown("""
+    # 💻 GLM-4.6 Code Agent
+    **KILOcode Agent Integration** - Geração e explicação de código com GLM-4.6
+    
+    - 🚀 Segue padrões GPT
+    - 📚 Suporta 200K tokens de contexto
+    - 💪 Excelente em coding tasks
+    """)
+    
+    with gr.Tabs():
+        with gr.Tab("🔨 Code Generation"):
+            code_prompt = gr.Textbox(
+                label="📝 Descrição do código",
+                placeholder="Ex: Crie uma função que calcula fibonacci com memoização",
+                lines=3
+            )
+            
+            language = gr.Dropdown(
+                choices=["python", "javascript", "java", "cpp", "go", "rust"],
+                value="python",
+                label="🔤 Linguagem"
+            )
+            
+            max_tokens_slider = gr.Slider(
+                minimum=256,
+                maximum=2048,
+                value=1024,
+                step=256,
+                label="📏 Max tokens"
+            )
+            
+            generate_btn = gr.Button("Gerar Código", variant="primary")
+            code_output = gr.Code(language="python", label="💾 Código Gerado")
+            
+            def generate(prompt, lang, tokens):
+                return agent.generate_code(prompt, lang, tokens)
+            
+            generate_btn.click(generate, [code_prompt, language, max_tokens_slider], code_output)
+        
+        with gr.Tab("📖 Code Explanation"):
+            code_to_explain = gr.Code(
+                language="python",
+                label="Código para explicar",
+                lines=10
+            )
+            
+            explain_btn = gr.Button("Explicar", variant="primary")
+            explanation_output = gr.Textbox(label="Explicação", lines=6)
+            
+            explain_btn.click(agent.explain_code, code_to_explain, explanation_output)
+        
+        with gr.Tab("⚙️ Configuração"):
+            gr.Markdown("""
+            ## Configuração do KILOcode Agent
+            
+            ### Modelo: GLM-4.6
+            - **Tamanho**: 357B parâmetros
+            - **Contexto**: 200K tokens
+            - **Formato**: BF16
+            - **Performance**: ⭐⭐⭐⭐⭐ para coding
+            
+            ### Como usar com KILOcode:
+            1. Adicione seu HF_TOKEN nos secrets
+            2. Use os endpoints de geração e explicação
+            3. Suporta múltiplas linguagens de programação
+            """)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(share=True)