updating Deep_Research models from Qwen3-235B to GLM-4.6

Modules/Deep_Research.py

@@ -418,7 +418,7 @@ def Deep_Research(
     def _invoke_chat(messages, provider: str, max_tokens: int, temp: float, top_p: float):
         client = InferenceClient(provider=provider, api_key=HF_TEXTGEN_TOKEN)
         return client.chat.completions.create(
-            model="Qwen/Qwen3-235B-A22B-Thinking-2507",
+            model="zai-org/GLM-4.6",
             messages=messages,
             max_tokens=max_tokens,
             temperature=temp,
@@ -492,7 +492,7 @@ def Deep_Research(
     except Exception:
         prompt_chars = -1
     print(f"[PIPELINE] Fetch complete: pages={len(pages)}, unique_urls={len(pages.keys())}, prompt_chars={prompt_chars}", flush=True)
-    print("[PIPELINE] Starting inference (provider=cerebras, model=Qwen/Qwen3-235B-A22B-Thinking-2507)", flush=True)
+    print("[PIPELINE] Starting inference (provider=cerebras, model=zai-org/GLM-4.6)", flush=True)
 
     try:
         print("[LLM] Attempt 1: provider=cerebras, max_tokens=32768", flush=True)