Initial vLLM agent strategy

tests/test_download_slot_policy.py

@@ -0,0 +1,12 @@
+from app.storage.db import connect
+from app.storage.repositories import Repository
+
+
+def test_active_self_download_count(tmp_path):
+    conn = connect(str(tmp_path / "state.db"))
+    repo = Repository(conn)
+    for i in range(8):
+        repo.upsert_download(f"owner/model-{i}", "HUGGING_FACE", "RUNNING", "self", True)
+    repo.upsert_download("owner/other", "HUGGING_FACE", "RUNNING", "others", False)
+    assert repo.count_active_self_downloads() == 8
+    conn.close()

tests/test_priority_order.py

@@ -0,0 +1,5 @@
+from app.domain.priorities import PRIORITY_BOUNTY, PRIORITY_PROMOTE, PRIORITY_OTHERS_DOWNLOADED, PRIORITY_SELF_DOWNLOAD
+
+
+def test_priority_order():
+    assert PRIORITY_BOUNTY < PRIORITY_PROMOTE < PRIORITY_OTHERS_DOWNLOADED < PRIORITY_SELF_DOWNLOAD

tests/test_strategy_id_payload.py

@@ -0,0 +1,21 @@
+from app.clients.modelhub import ModelHubClient
+from app.settings import Settings
+
+
+def test_strategy_id_payload_field_configurable():
+    settings = Settings(
+        auth_token="a", hf_token="h", contest_api_token="c", email="e", user_id="1",
+        contributors="u", strategy_id="sid", contest_task_strategy_field="strategy_id"
+    )
+    payload = ModelHubClient(settings).build_contest_payload("owner/model", "hygon_k100-ai", "cfg")
+    assert payload["strategy_id"] == "sid"
+    assert payload["taskType"] == "text-generation"
+
+
+def test_strategy_id_payload_can_disable_injection():
+    settings = Settings(
+        auth_token="a", hf_token="h", contest_api_token="c", email="e", user_id="1",
+        contributors="u", strategy_id="sid", inject_strategy_id=False
+    )
+    payload = ModelHubClient(settings).build_contest_payload("owner/model", "hygon_k100-ai", "cfg")
+    assert "strategyId" not in payload

tests/test_submit_result_mapping.py

@@ -0,0 +1,38 @@
+from app.clients.modelhub import ModelHubClient
+from app.settings import Settings
+
+
+class FakeResponse:
+    def __init__(self, body):
+        self.body = body
+    def json(self):
+        return self.body
+
+
+class FakeSession:
+    def __init__(self, body):
+        self.body = body
+    def post(self, *args, **kwargs):
+        return FakeResponse(self.body)
+
+
+def make_client(body):
+    settings = Settings(
+        auth_token="a", hf_token="h", contest_api_token="c", email="e", user_id="1",
+        contributors="u", strategy_id="s", submit_dry_run=False
+    )
+    client = ModelHubClient(settings)
+    client.session = FakeSession(body)
+    return client
+
+
+def test_submit_success_mapping():
+    assert make_client({"code": 0, "message": "ok"}).create_contest_task("m", "hygon_k100-ai", "cfg").result == "success"
+
+
+def test_submit_queue_full_mapping():
+    assert make_client({"code": 60007, "message": "full"}).create_contest_task("m", "hygon_k100-ai", "cfg").result == "queue_full"
+
+
+def test_submit_conflict_mapping():
+    assert make_client({"code": 40000, "message": "正在验证中"}).create_contest_task("m", "hygon_k100-ai", "cfg").result == "conflict"

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()