Expose workload traceback in Space health endpoint

space_runner.py

@@ -5,6 +5,7 @@ import signal
 import subprocess
 import sys
 import threading
+from collections import deque
 from http.server import BaseHTTPRequestHandler, HTTPServer
 
 
@@ -14,8 +15,16 @@ def main():
         print("No command provided to space_runner.py", flush=True)
         sys.exit(2)
 
-    # Start the long-running workload and forward logs to container stdout/stderr.
-    child = subprocess.Popen(cmd)
+    # Start workload with captured output so we can expose failure tracebacks.
+    child = subprocess.Popen(
+        cmd,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.STDOUT,
+        text=True,
+        bufsize=1,
+    )
+
+    recent_logs = deque(maxlen=400)
 
     state = {
         "status": "running",
@@ -24,9 +33,17 @@ def main():
         "command": cmd,
     }
 
+    def stream_output():
+        if child.stdout is None:
+            return
+        for line in child.stdout:
+            line = line.rstrip("\n")
+            recent_logs.append(line)
+            print(line, flush=True)
+
     class Handler(BaseHTTPRequestHandler):
         def do_GET(self):
-            payload = json.dumps(state).encode("utf-8")
+            payload = json.dumps({**state, "recent_logs": list(recent_logs)}).encode("utf-8")
             self.send_response(200)
             self.send_header("Content-Type", "application/json")
             self.send_header("Content-Length", str(len(payload)))
@@ -38,6 +55,9 @@ def main():
 
     server = HTTPServer(("0.0.0.0", int(os.environ.get("PORT", "7860"))), Handler)
 
+    log_thread = threading.Thread(target=stream_output, daemon=True)
+    log_thread.start()
+
     def wait_child():
         rc = child.wait()
         state["returncode"] = rc