merge: distributed performance baseline benchmark

tests/test_route_session_benchmark.py

@@ -32,12 +32,18 @@ def test_matrix_reports_direct_relay_prefill_decode_and_machine_readable_metrics
         assert {"p50_latency_ms", "p95_latency_ms", "payload_bytes", "compression_ratio",
                 "connection_attempts", "p95_queue_wait_ms"} <= set(run["phases"]["decode"])
         sample = run["samples"][0]
+        assert sample["model_ms"] > 0
+        assert sample["encode_ms"] > 0
+        assert sample["activation_decode_ms"] > 0
         assert sample["framing_ms"] > 0
         assert sample["metadata_ms"] > 0
         assert sample["copy_allocation_ms"] > 0
         assert sample["copy_allocation_bytes"] >= sample["payload_bytes"]
+        assert sample["local_http_forwarding_ms"] > 0
         assert len(run["samples"]) == 1 + len(run["output_tokens"])
-        assert {"tokens_per_sec", "bytes_per_token", "compression_cpu_ms", "peak_buffered_bytes"} <= set(run["phases"]["decode"])
+        assert {"tokens_per_sec", "bytes_per_token", "compression_cpu_ms", "peak_buffered_bytes",
+                "model_execution_ms", "activation_encoding_ms", "activation_decoding_ms",
+                "local_http_forwarding_ms"} <= set(run["phases"]["decode"])
 
 
 def test_cached_sessions_reuse_one_connection_and_preserve_stub_tokens():
@@ -74,7 +80,10 @@ def test_cli_writes_json_artifact_and_human_summary(tmp_path, capsys):
     report = json.loads(output.read_text())
     assert report["schema_version"] == 1
     assert "Route Session benchmark" in capsys.readouterr().out
-    assert "relay" in format_summary(report)
+    summary = format_summary(report)
+    assert "relay" in summary
+    assert "model/encode/decode" in summary
+    assert "HTTP" in summary
 
 
 def test_performance_gate_checks_comparison_identity_session_and_cleanup():