Upload app.py

app.py

@@ -93,16 +93,31 @@ def chat_interaction(audio_input, history_state):
     if not history_state:
         history_state = [{"role": "system", "content": CONVERSATION_SYSTEM_PROMPT}]
 
-    history_state.append({"role": "user", "content": user_text})
+    history_state.append({"role": "user", "content": user_text, "display_content": user_text})
     
     user_turns = (len(history_state) - 1) // 2
     responses_remaining = 5 - user_turns
     
     if user_turns < 5:
         response = client.chat.completions.create(model="gpt-4o", messages=history_state, temperature=0.7)
-        ai_response = response.choices[0].message.content
-        history_state.append({"role": "assistant", "content": ai_response})
-        chat_display = [(history_state[i]['content'], history_state[i+1]['content']) for i in range(1, len(history_state), 2)]
+        ai_response_text = response.choices[0].message.content
+        
+        try:
+            tts = gTTS(text=ai_response_text, lang='en')
+            mp3_fp = io.BytesIO()
+            tts.write_to_fp(mp3_fp)
+            mp3_fp.seek(0)
+            audio_base64 = base64.b64encode(mp3_fp.read()).decode('utf-8')
+            audio_player = f'<audio src="data:audio/mpeg;base64,{audio_base64}" controls autoplay></audio>'
+            ai_display_content = f"{ai_response_text}<br>{audio_player}"
+        except Exception as e:
+            print(f"Error al generar TTS para la respuesta del chat: {e}")
+            ai_display_content = ai_response_text
+
+        history_state.append({"role": "assistant", "content": ai_response_text, "display_content": ai_display_content})
+
+        chat_display = [(msg['display_content'], None) if msg['role']=='user' else (None, msg['display_content']) for msg in history_state[1:]]
+
         return chat_display, history_state, f"Responses remaining: {responses_remaining}", gr.update(visible=False), gr.update(visible=False)
     else: # Turno 5: generar evaluación
         print("Generating final evaluation...")
@@ -115,15 +130,14 @@ def chat_interaction(audio_input, history_state):
             fb_es = result.get('feedback_es', {}); md_es = f"## Reporte Final (Nivel MCERL: {result.get('cefr_level', 'N/A')})\n### Fortalezas\n{fb_es.get('fortalezas', '')}\n### Áreas a Mejorar\n{fb_es.get('areas_a_mejorar', '')}\n### Retroalimentación por Palabra\n"
             for item in fb_es.get('feedback_por_palabra', []): md_es += f"- **{item['palabra']}**: {item['feedback']}\n"
             
-            chat_display = [(history_state[i]['content'], history_state[i+1]['content']) for i in range(1, len(history_state)-1, 2)]
-            chat_display.append((user_text, "Thank you! Your final report is now available on the right."))
+            chat_display = [(msg['display_content'], None) if msg['role']=='user' else (None, msg['display_content']) for msg in history_state[1:]]
+            chat_display[-1] = (chat_display[-1][0], "Thank you! Your final report is now available on the right.")
             
             # --- CAMBIO CLAVE: Reiniciamos el historial para la siguiente conversación ---
             return chat_display, [], "Conversation finished!", gr.update(value=md_en, visible=True), gr.update(value=md_es, visible=True)
         except Exception as e:
             print(f"Error parsing final report: {e}")
-            chat_display = [(history_state[i]['content'], history_state[i+1]['content']) for i in range(1, len(history_state)-1, 2)]
-            return chat_display, [], "Error!", gr.update(value="Error generating report.", visible=True), gr.update(visible=False)
+            return history_state[1:], [], "Error!", gr.update(value="Error generating report.", visible=True), gr.update(visible=False)
 
 def run_sentence_evaluation(audio_input, reference_transcript):
     if not api_key_found: raise gr.Error("OpenAI API key not found.")
@@ -202,7 +216,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                 inputs=[],
                 outputs=[audio_in_chat]
             )
-            
+
         # --- PESTAÑA 2: EVALUACIÓN POR FRASE ---
         with gr.TabItem("Evaluación por Frase"):
             TONGUE_TWISTERS = ["Peter Piper picked a peck of pickled peppers.", "She sells seashells by the seashore.", "How much wood would a woodchuck chuck if a woodchuck could chuck wood?", "Betty Botter bought some butter but she said the butter’s bitter.", "A proper copper coffee pot."]