Initial vLLM agent strategy

scripts/dry_run_plan.py

@@ -0,0 +1,31 @@
+from __future__ import annotations
+
+import argparse
+
+from app.scheduler.budget import Budget
+from app.scheduler.planner import Planner
+from app.settings import load_settings
+from app.storage.db import connect
+from app.storage.repositories import Repository
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--limit", type=int, default=50)
+    args = parser.parse_args()
+
+    settings = load_settings(require_secrets=False)
+    conn = connect(settings.db_path)
+    try:
+        repo = Repository(conn)
+        Planner(repo, Budget(repo, settings.max_user_tasks), settings.default_gpu_alias_list).materialize_tasks()
+        rows = repo.due_tasks(("pending", "ready_to_submit", "waiting_download", "queue_full_backoff"), limit=args.limit)
+        for row in rows:
+            print(f"#{row['id']} priority={row['priority']} status={row['status']} {row['model_id']} -> {row['gpu_type']} ({row['gpu_alias']})")
+        print(f"budget used={repo.count_budgeted_tasks()} max={settings.max_user_tasks}")
+    finally:
+        conn.close()
+
+
+if __name__ == "__main__":
+    main()