Record code-trace calibration and canary gates

runs/frontier-code-trace-v0/summarize_calibration.py

@@ -0,0 +1,88 @@
+#!/usr/bin/env python3
+"""Compact code-trace Frontier rho calibration into a reviewable artifact."""
+
+from __future__ import annotations
+
+import argparse
+import hashlib
+import json
+import re
+from pathlib import Path
+
+
+CELL_RE = re.compile(r"r(?P<rho>[0-9p]+)-tp(?P<tp>[24])-v3")
+ATTENTION_FLAG = "--random_forrest_execution_time_predictor_config_atten_input_file"
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--sim-root", type=Path, required=True)
+    parser.add_argument("--profile-manifest", type=Path, required=True)
+    parser.add_argument("--output", type=Path, required=True)
+    return parser.parse_args()
+
+
+def sha256(path: Path) -> str:
+    digest = hashlib.sha256()
+    with path.open("rb") as stream:
+        for chunk in iter(lambda: stream.read(1024 * 1024), b""):
+            digest.update(chunk)
+    return digest.hexdigest()
+
+
+def main() -> None:
+    args = parse_args()
+    profile = json.loads(args.profile_manifest.read_text())
+    expected_profile_sha = profile["output_sha256"]
+    cells = []
+    for root in sorted(args.sim_root.iterdir()):
+        match = CELL_RE.fullmatch(root.name)
+        if match is None or not (root / "summary.json").is_file():
+            continue
+        manifest = json.loads((root / "manifest.json").read_text())
+        observed_profile_sha = manifest.get("attention_profile_sha256")
+        if observed_profile_sha is None:
+            argv = manifest["argv"]
+            profile_path = Path(argv[argv.index(ATTENTION_FLAG) + 1])
+            observed_profile_sha = sha256(profile_path)
+        if observed_profile_sha != expected_profile_sha:
+            raise ValueError(
+                f"{root}: attention profile {observed_profile_sha} "
+                f"!= profile-v6 {expected_profile_sha}"
+            )
+        summary = json.loads((root / "summary.json").read_text())
+        drain_fraction = (
+            summary["drain"]["tail_after_last_arrival_s"] / summary["duration_s"]
+        )
+        cells.append(
+            {
+                "topology": f"tp{match.group('tp')}_mns16",
+                "rho": float(match.group("rho").replace("p", ".")),
+                "requests": summary["requests"],
+                "offered_load": summary["offered_load"],
+                "waiting_ms": summary["latency_ms"]["waiting"],
+                "ttft_ms": summary["latency_ms"]["ttft"],
+                "tpot_ms": summary["latency_ms"]["tpot"],
+                "decode_batch": summary["decode_batch"],
+                "drain_tail_s": summary["drain"]["tail_after_last_arrival_s"],
+                "drain_fraction": drain_fraction,
+                "subcritical_gate": drain_fraction <= 0.1,
+                "prefix_cache_hit_ratio": summary["prefix_cache"]["hit_ratio"],
+                "trace_sha256": manifest["trace_sha256"],
+            }
+        )
+    if not cells:
+        raise ValueError(f"no completed v3 calibration cells below {args.sim_root}")
+    payload = {
+        "schema": "frontier-code-trace-calibration-summary-v1",
+        "attention_profile_sha256": expected_profile_sha,
+        "subcritical_rule": "drain tail <= 10% of the 3660s arrival window",
+        "cells": cells,
+    }
+    args.output.parent.mkdir(parents=True, exist_ok=True)
+    args.output.write_text(json.dumps(payload, indent=2, sort_keys=True) + "\n")
+    print(json.dumps({"cells": len(cells), "output": str(args.output)}, sort_keys=True))
+
+
+if __name__ == "__main__":
+    main()