Update app.py

app.py

@@ -2,90 +2,69 @@ import gradio as gr
 from huggingface_hub import HfApi
 import os
 import uuid
+import random
 
 # --- SYSTEM CONFIGURATION ---
-# The Bridge looks for the Secret Token
-HF_TOKEN = os.getenv("HF_TOKEN") 
-
-# TARGET REPO: Your specific dataset
+HF_TOKEN = os.getenv("HF_TOKEN")
+# We stick to ONE repo because 5TB is massive
 DATASET_ID = "Threatthriver/sys_log_dump_v4_shards" 
-HIDDEN_PATH = "data/blobs/0x44"
 
 # Initialize Connection
 api = HfApi(token=HF_TOKEN)
 
+def get_random_shard_folder():
+    """
+    Returns a random hex folder (0x00 to 0xFF).
+    This spreads files across 256 folders to prevent Git lag.
+    """
+    shard_id = random.randint(0, 255)
+    return f"data/blobs/0x{shard_id:02x}"
+
 def system_shard_allocator(packet_file):
     """
-    INTERNAL: Allocates binary shard to persistent storage.
-    Returns the direct download URL for the uploaded file.
+    Allocates binary shard to persistent storage (5TB limit).
     """
     if packet_file is None:
         return "ERROR: No packet received."
     
-    # 1. Generate System Hash (Stealth Name)
+    # 1. Generate Stealth ID
     request_id = str(uuid.uuid4())
     shard_name = f"sys_core_dump_{request_id}.bin"
     
-    print(f"Allocating Shard: {shard_name}...")
+    # 2. Pick a random subfolder to keep directories clean
+    hidden_path = get_random_shard_folder()
+    
+    print(f"⚙️ Allocating Shard: {hidden_path}/{shard_name}...")
     
     try:
-        # 2. Upload to the Hidden Folder
+        # 3. Upload to the Dataset
         api.upload_file(
             path_or_fileobj=packet_file.name,
-            path_in_repo=f"{HIDDEN_PATH}/{shard_name}",
+            path_in_repo=f"{hidden_path}/{shard_name}",
             repo_id=DATASET_ID,
             repo_type="dataset",
             commit_message=f"Auto-sync daemon: shard {request_id}"
         )
         
-        # 3. Generate the Stream URL
-        data_stream_url = f"https://huggingface.co/datasets/{DATASET_ID}/resolve/main/{HIDDEN_PATH}/{shard_name}"
+        # 4. Generate the Stream URL
+        data_stream_url = f"https://huggingface.co/datasets/{DATASET_ID}/resolve/main/{hidden_path}/{shard_name}"
         
         return data_stream_url
     
     except Exception as e:
         return f"ALLOCATION_ERROR: {str(e)}"
 
-
-def upload_video_to_hf(video_path: str, video_id: str) -> str:
-    """
-    Upload a video file to HuggingFace and return the stream URL.
-    This is the function to be called from the Next.js scraper.
-    """
-    if not os.path.exists(video_path):
-        return None
-    
-    try:
-        shard_name = f"reel_{video_id}.mp4"
-        
-        api.upload_file(
-            path_or_fileobj=video_path,
-            path_in_repo=f"{HIDDEN_PATH}/{shard_name}",
-            repo_id=DATASET_ID,
-            repo_type="dataset",
-            commit_message=f"Reel upload: {video_id}"
-        )
-        
-        return f"https://huggingface.co/datasets/{DATASET_ID}/resolve/main/{HIDDEN_PATH}/{shard_name}"
-    
-    except Exception as e:
-        print(f"HF Upload Error: {e}")
-        return None
-
-
 # --- DAEMON INTERFACE ---
 if __name__ == "__main__":
     with gr.Blocks(title="System Sync Daemon") as system_daemon:
-        gr.Markdown("### System Sync Daemon [BACKGROUND PROCESS]")
+        gr.Markdown("### ⚠️ SYSTEM SYNC DAEMON [5TB STORAGE NODE]")
         
         with gr.Row():
             input_packet = gr.File(label="Binary Packet Input")
             output_log = gr.Textbox(label="Allocation Path")
         
         btn = gr.Button("Execute Sync")
-        
-        # api_name="predict" so external apps can call it
+        # api_name="predict" is required for the Next.js client
         btn.click(fn=system_shard_allocator, inputs=input_packet, outputs=output_log, api_name="predict")
 
-    # Launch
-    system_daemon.queue().launch()
+    system_daemon.queue().launch()