Audit Frontier prefix-cache trace contract

runs/frontier-fidelity-envelope-v1/qwen30_exact_trace_client.py

@@ -21,6 +21,11 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument("--port", type=int, required=True)
     parser.add_argument("--requests-file", type=Path, required=True)
     parser.add_argument("--output", type=Path, required=True)
+    parser.add_argument(
+        "--served-model",
+        default=None,
+        help="Optional server-side model alias used only for HTTP routing.",
+    )
     parser.add_argument("--tpot-slo-ms", type=float, default=150.0)
     parser.add_argument("--timeout-seconds", type=float, default=1800.0)
     return parser.parse_args()
@@ -64,6 +69,7 @@ async def request_one(
     scheduled_at: float,
     benchmark_start: float,
     tpot_slo_ms: float,
+    served_model: str | None,
 ) -> dict[str, Any]:
     loop = asyncio.get_running_loop()
     delay = scheduled_at - loop.time()
@@ -81,6 +87,8 @@ async def request_one(
         "success": False,
     }
     body = dict(row["body"])
+    if served_model is not None:
+        body["model"] = served_model
     body.update(
         {
             "temperature": 0,
@@ -178,6 +186,7 @@ async def replay(args: argparse.Namespace, rows: list[dict[str, Any]]) -> list[d
                     scheduled_at=benchmark_start + float(row["arrived_at"]),
                     benchmark_start=benchmark_start,
                     tpot_slo_ms=args.tpot_slo_ms,
+                    served_model=args.served_model,
                 )
             )
             for row in rows
@@ -219,6 +228,7 @@ def main() -> None:
             "last_arrival_s": arrivals[-1],
             "arrival": "original_trace_timestamp_and_order",
             "input_output_prompt": "exact_source_values",
+            "served_model_alias": args.served_model,
             "ttft_slo": "1000ms + 1000ms * input_tokens / 8000",
             "tpot_slo_ms": args.tpot_slo_ms,
             "target_pass_rate": TARGET_PASS_RATE,