feat: add live endpoint benchmark runner

tests/test_performance_contract.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import json
+from unittest.mock import MagicMock, patch
 
 from meshnet_node.performance_contract import (
     BENCHMARK_SCHEMA_VERSION,
@@ -10,6 +11,7 @@ from meshnet_node.performance_contract import (
     SCHEMA_VERSION,
     main,
     run_performance_benchmark,
+    run_real_model_endpoint_benchmark,
 )
 
 
@@ -165,3 +167,37 @@ def test_contract_cli_writes_benchmark_report(tmp_path, capsys):
     output = capsys.readouterr().out
     assert str(contract_out) in output
     assert str(benchmark_out) in output
+
+
+def test_real_model_endpoint_benchmark_uses_lane_specific_endpoints_and_shared_schema():
+    """The live client path fans out to one endpoint per CPU/GPU lane.
+
+    Tags: performance, benchmark, live
+    """
+    response = MagicMock()
+    response.read.return_value = json.dumps({"choices": [{"message": {"content": "mesh activation"}}]}).encode()
+    response.headers.get.return_value = "lane-session"
+    response.__enter__.return_value = response
+
+    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",
+    }
+
+    with patch("meshnet_node.performance_contract.urllib.request.urlopen", return_value=response) as urlopen:
+        report = run_real_model_endpoint_benchmark(endpoints=endpoints, model="deepseek-ai/DeepSeek-V2-Lite-Chat")
+
+    assert report["source"] == "real-model-endpoints"
+    assert report["model_target"] == DEFAULT_CONTRACT.model_target.to_dict()
+    assert set(report["comparisons"]) == {"cpu", "gpu"}
+    assert urlopen.call_count == len(endpoints)
+    called_urls = [call.args[0].full_url for call in urlopen.call_args_list]
+    assert called_urls == [f"{url}/v1/chat/completions" for url in endpoints.values()]
+    for lane in report["lanes"]:
+        assert lane["results"][0]["metrics"]["decode_tok_per_sec"] > 0
+        assert lane["results"][0]["metrics"]["ttft_ms"] > 0
+        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"