fix chat history for speaking

vibe_bot/main.py

@@ -288,9 +288,18 @@ async def speak(ctx, *, message: str):
         system_prompt_edit = f"{system_prompt}\nKeep your responses under 2-3 sentences."
 
         try:
+            db = get_database()
+            context = db.get_conversation_context(
+                user_id=str(ctx.author.id), current_message=text_to_speak, max_context=5
+            )
+
+            prompts = [{"role": "user", "content": text_to_speak}]
+            if context:
+                prompts = context + prompts
+
             bot_response = llama_wrapper.chat_completion_with_history(
                 system_prompt=system_prompt_edit,
-                prompts=[{"role": "user", "content": text_to_speak}],
+                prompts=prompts,
                 openai_url=CHAT_ENDPOINT,
                 openai_api_key=CHAT_ENDPOINT_KEY,
                 model=CHAT_MODEL,
@@ -301,6 +310,24 @@ async def speak(ctx, *, message: str):
                 await ctx.send(f"❌ **{bot_name}** failed to generate a response.")
                 return
 
+            db.add_message(
+                message_id=f"{ctx.message.id}",
+                user_id=str(ctx.author.id),
+                username=ctx.author.name,
+                content=f"User: {text_to_speak}",
+                channel_id=str(ctx.channel.id),
+                guild_id=str(ctx.guild.id) if ctx.guild else None,
+            )
+
+            db.add_message(
+                message_id=f"{ctx.message.id}_response",
+                user_id=str(bot.user.id),
+                username=bot.user.name,
+                content=f"Bot: {bot_response}",
+                channel_id=str(ctx.channel.id),
+                guild_id=str(ctx.guild.id) if ctx.guild else None,
+            )
+
             await ctx.send(f"🔊 Generating speech for **{bot_name}**...")
             audio_buffer = tts_engine.generate_audio(bot_response, voice=TTS_VOICE, speed=TTS_SPEED)