feat: add durable success-first modelhub agent

main.py

@@ -17,6 +17,7 @@ HOST = "0.0.0.0"
 PORT = int(os.getenv("PORT", "8080"))
 ROOT = Path(__file__).resolve().parent
 WORKER_SCRIPT = ROOT / "modelhub_submmit_api" / "poll_runner.py"
+READINESS_PATH = ROOT / ".modelhub_state" / "readiness.json"
 
 shutdown_requested = False
 worker: subprocess.Popen | None = None
@@ -53,6 +54,7 @@ def _worker_command() -> list[str]:
         "--post-cycle-cooldown-seconds",
         os.getenv("MODELHUB_AGENT_POST_CYCLE_COOLDOWN_SECONDS", "2"),
         "--skip-history-archive",
+        "--state-sync",
     ]
 
     daily_target = os.getenv("MODELHUB_AGENT_DAILY_TARGET", "").strip()
@@ -86,6 +88,14 @@ def _config() -> dict[str, object]:
     }
 
 
+def _readiness() -> dict[str, object]:
+    try:
+        payload = json.loads(READINESS_PATH.read_text(encoding="utf-8"))
+    except (FileNotFoundError, OSError, ValueError, TypeError):
+        return {"ready": False, "reason": "readiness_not_reported"}
+    return payload if isinstance(payload, dict) else {"ready": False, "reason": "readiness_invalid"}
+
+
 class Handler(BaseHTTPRequestHandler):
     def do_GET(self) -> None:
         if self.path == "/health":
@@ -98,6 +108,19 @@ class Handler(BaseHTTPRequestHandler):
             self._send_json({"status": "ok", "config": _config()})
             return
 
+        if self.path == "/ready":
+            readiness = _readiness()
+            status = 200 if readiness.get("ready") is True else 503
+            self._send_json(
+                {
+                    "status": "ready" if status == 200 else "not_ready",
+                    "readiness": readiness,
+                    "config": _config(),
+                },
+                status=status,
+            )
+            return
+
         if self.path == "/":
             self._send_json({"name": "modelhub-submmit-agent", "status": "running", "config": _config()})
             return