feat: wire live benchmark CLI endpoints

tests/test_performance_contract.py

@@ -5,6 +5,8 @@ from __future__ import annotations
 import json
 from unittest.mock import MagicMock, patch
 
+import pytest
+
 from meshnet_node.performance_contract import (
     BENCHMARK_SCHEMA_VERSION,
     DEFAULT_CONTRACT,
@@ -201,3 +203,84 @@ def test_real_model_endpoint_benchmark_uses_lane_specific_endpoints_and_shared_s
         assert lane["output_tokens"] == ["mesh", "activation"]
     assert report["comparisons"]["cpu"]["gguf_lane"] == "llama-cpp-gguf-cpu"
     assert report["comparisons"]["gpu"]["gguf_lane"] == "llama-cpp-gguf-gpu"
+
+
+def test_contract_cli_runs_live_endpoint_benchmark(tmp_path, capsys):
+    """--live-endpoint mappings drive the live runner and write its report.
+
+    Tags: performance, benchmark, live, artifact
+    """
+    contract_out = tmp_path / "performance-contract.json"
+    live_out = tmp_path / "artifacts" / "live-benchmark-report.json"
+    endpoints = {
+        "transformers-safetensors-cpu": "http://cpu-safetensors",
+        "llama-cpp-gguf-cpu": "http://cpu-gguf",
+        "transformers-safetensors-gpu": "http://gpu-safetensors",
+        "llama-cpp-gguf-gpu": "http://gpu-gguf",
+    }
+    fake_report = {"schema_version": BENCHMARK_SCHEMA_VERSION, "source": "real-model-endpoints"}
+    argv = ["--json-out", str(contract_out), "--live-benchmark-out", str(live_out)]
+    for lane_id, url in endpoints.items():
+        argv += ["--live-endpoint", f"{lane_id}={url}"]
+
+    with patch(
+        "meshnet_node.performance_contract.run_real_model_endpoint_benchmark",
+        return_value=fake_report,
+    ) as runner:
+        assert main(argv) == 0
+
+    runner.assert_called_once_with(
+        endpoints,
+        model=DEFAULT_CONTRACT.model_target.safetensors_repo,
+        contract=DEFAULT_CONTRACT,
+    )
+    assert json.loads(live_out.read_text(encoding="utf-8")) == fake_report
+    output = capsys.readouterr().out
+    assert str(contract_out) in output
+    assert str(live_out) in output
+
+
+def test_contract_cli_passes_explicit_live_model(tmp_path):
+    """--live-model overrides the contract's safetensors repo default.
+
+    Tags: performance, benchmark, live
+    """
+    live_out = tmp_path / "live-benchmark-report.json"
+    argv = [
+        "--json-out", str(tmp_path / "performance-contract.json"),
+        "--live-benchmark-out", str(live_out),
+        "--live-endpoint", "transformers-safetensors-cpu=http://cpu-safetensors",
+        "--live-model", "local/DeepSeek-V2-Lite-Chat-Q2_K",
+    ]
+
+    with patch(
+        "meshnet_node.performance_contract.run_real_model_endpoint_benchmark",
+        return_value={},
+    ) as runner:
+        assert main(argv) == 0
+
+    assert runner.call_args.kwargs["model"] == "local/DeepSeek-V2-Lite-Chat-Q2_K"
+
+
+@pytest.mark.parametrize(
+    "argv",
+    [
+        ["--live-endpoint", "transformers-safetensors-cpu=http://cpu"],
+        ["--live-benchmark-out", "live-report.json"],
+        [
+            "--live-endpoint", "not-a-mapping",
+            "--live-benchmark-out", "live-report.json",
+        ],
+    ],
+    ids=["endpoint-without-out", "out-without-endpoint", "malformed-mapping"],
+)
+def test_contract_cli_rejects_incomplete_live_arguments(tmp_path, argv, capsys):
+    """Live flags must arrive as a consistent LANE_ID=URL + output-path set.
+
+    Tags: performance, benchmark, live, cli
+    """
+    with pytest.raises(SystemExit) as excinfo:
+        main(["--json-out", str(tmp_path / "performance-contract.json"), *argv])
+
+    assert excinfo.value.code == 2
+    assert "--live-" in capsys.readouterr().err