Fix Lexi native prompt framing and Gradio 6 history

app.py

@@ -21,24 +21,72 @@ model = AutoModelForCausalLM.from_pretrained(
 model.eval()
 print("Model ready.")
 
+
+def extract_text(content):
+    if content is None:
+        return ""
+
+    if isinstance(content, str):
+        return content
+
+    if isinstance(content, list):
+        parts = []
+
+        for block in content:
+            text = extract_text(block)
+
+            if text:
+                parts.append(text)
+
+        return "\n".join(parts)
+
+    if isinstance(content, dict):
+        if content.get("type") == "text":
+            return extract_text(content.get("text"))
+
+        if "text" in content:
+            return extract_text(content["text"])
+
+        if "content" in content:
+            return extract_text(content["content"])
+
+    return ""
+
+
 @spaces.GPU(duration=120)
 def chat(message, history):
-    messages = []
+
+    # Lexi V2 expects a system turn to exist.
+    # "." is the model author's recommended effectively-empty value.
+    messages = [
+        {
+            "role": "system",
+            "content": "."
+        }
+    ]
 
     for item in history or []:
-        if isinstance(item, dict):
-            role = item.get("role")
-            content = item.get("content")
+        if not isinstance(item, dict):
+            continue
+
+        role = item.get("role")
+
+        if role not in ("user", "assistant"):
+            continue
 
-            if role in ("user", "assistant") and content is not None:
-                messages.append({
-                    "role": role,
-                    "content": str(content)
-                })
+        text = extract_text(item.get("content"))
+
+        if text:
+            messages.append({
+                "role": role,
+                "content": text
+            })
+
+    user_text = extract_text(message)
 
     messages.append({
         "role": "user",
-        "content": str(message)
+        "content": user_text
     })
 
     inputs = tokenizer.apply_chat_template(
@@ -68,6 +116,7 @@ def chat(message, history):
         )
 
     prompt_length = inputs["input_ids"].shape[-1]
+
     new_tokens = output[0, prompt_length:]
 
     response = tokenizer.decode(
@@ -77,10 +126,11 @@ def chat(message, history):
 
     return response.strip()
 
+
 demo = gr.ChatInterface(
     fn=chat,
     title="Lexi 8B — OBLITERATED",
-    description="Raw model — temp 1.0 / top-p 1.0 / 4000 max tokens",
+    description="Native Lexi framing • temp 1.0 • top-p 1.0 • 4000 max tokens",
 )
 
 demo.launch()