docs(conductor): Synchronize tech-stack and commit monitor script updates

scripts/cluster_status/nomad_client.py

@@ -1,6 +1,7 @@
 import subprocess
 import re
 import sys
+from datetime import datetime, timezone
 
 def get_node_map():
     """
@@ -31,7 +32,7 @@ def get_node_map():
 
 def get_job_allocations(job_id):
     """
-    Returns a list of all active allocations for a job with their IPs.
+    Returns a list of all active allocations for a job with their IPs and uptimes.
     """
     try:
         # 1. Get list of allocations
@@ -56,8 +57,10 @@ def get_job_allocations(job_id):
                     if any(p == "running" for p in parts[3:]):
                         alloc_ids.append(alloc_id)
         
-        # 2. For each allocation, get its IP
+        # 2. For each allocation, get its IP and Uptime
         allocations = []
+        now = datetime.now(timezone.utc)
+        
         for alloc_id in alloc_ids:
             res_alloc = subprocess.run(
                 ["nomad", "alloc", "status", alloc_id],
@@ -67,6 +70,7 @@ def get_job_allocations(job_id):
             node_name = ""
             ip = ""
             full_id = alloc_id
+            uptime = "N/A"
             
             for l in res_alloc.stdout.splitlines():
                 if l.startswith("ID") and "=" in l:
@@ -79,11 +83,32 @@ def get_job_allocations(job_id):
                     m = re.search(r"(\d+\.\d+\.\d+\.\d+):", l)
                     if m:
                         ip = m.group(1)
+                
+                # Extract Uptime from Started At
+                if "Started At" in l and "=" in l:
+                    # e.g. "Started At     = 2026-02-09T14:04:28Z"
+                    ts_str = l.split("=")[1].strip()
+                    if ts_str and ts_str != "N/A":
+                        try:
+                            # Parse ISO timestamp
+                            started_at = datetime.fromisoformat(ts_str.replace("Z", "+00:00"))
+                            duration = now - started_at
+                            # Format duration
+                            secs = int(duration.total_seconds())
+                            if secs < 60:
+                                uptime = f"{secs}s"
+                            elif secs < 3600:
+                                uptime = f"{secs//60}m{secs%60}s"
+                            else:
+                                uptime = f"{secs//3600}h{(secs%3600)//60}m"
+                        except Exception:
+                            uptime = ts_str
             
             allocations.append({
                 "id": full_id,
                 "node": node_name,
-                "ip": ip
+                "ip": ip,
+                "uptime": uptime
             })
             
         return allocations
@@ -183,4 +208,4 @@ def restart_allocation(alloc_id):
         return True
     except Exception as e:
         print(f"Error restarting allocation: {e}", file=sys.stderr)
-        return False
+        return False