Update app.py

app.py

@@ -26,14 +26,34 @@ def load_llm():
     )
     return pipeline("text-generation", model=mod, tokenizer=tok, max_new_tokens=512)
 
+def check_token_access():
+    token = os.environ.get("HF_TOKEN", "")
+    if not token:
+        print("❌ No token found")
+        return
+    headers = {"Authorization": f"Bearer {token}"}
+    url = "https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/config.json"
+    try:
+        r = requests.get(url, headers=headers, timeout=10)
+        print(f"🔍 Token test response: {r.status_code}")
+        if r.status_code == 200:
+            print("✅ Token access confirmed for gated model.")
+        elif r.status_code == 403:
+            print("❌ 403 Forbidden: Token does not have access.")
+        else:
+            print("⚠️ Unexpected status:", r.status_code)
+    except Exception as e:
+        print("❌ Token check failed:", e)
+
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
 
-        print("ENV-HF_TOKEN-LEN", len(os.getenv("HF_TOKEN", "")), file=sys.stderr)
+        print("ENV-HF_TOKEN-LEN", len(hf_token), file=sys.stderr)
         print(smolagents.__version__)
+        check_token_access()
 
         # Local test
         # client = InferenceClient(