Initial vLLM agent strategy

tests/test_task_granularity.py

@@ -0,0 +1,16 @@
+from app.scheduler.budget import Budget
+from app.scheduler.planner import Planner
+from app.storage.db import connect
+from app.storage.repositories import Repository
+
+
+def test_task_granularity_per_model_gpu(tmp_path):
+    conn = connect(str(tmp_path / "state.db"))
+    repo = Repository(conn)
+    repo.upsert_candidate("owner/model", "HUGGING_FACE", "manual_bounty", 0, True, target_gpu_aliases="k100,p800")
+    created = Planner(repo, Budget(repo, 2000), ["k100"]).materialize_tasks()
+    assert created == 2
+    rows = repo.due_tasks(("pending",), limit=10)
+    assert {row["gpu_type"] for row in rows} == {"hygon_k100-ai", "Kunlunxin_p-800"}
+    assert Planner(repo, Budget(repo, 2000), ["k100"]).materialize_tasks() == 0
+    conn.close()