Audit Frontier prefix-cache trace contract

runs/frontier-fidelity-envelope-v1/run_frontier_qwen30_exact_trace_surface.py

@@ -84,8 +84,21 @@ def percentile(values: list[float], fraction: float) -> float | None:
     return ordered[math.ceil(fraction * len(ordered)) - 1]
 
 
+def manifest_offered_rate(path: Path) -> tuple[float | None, str | None]:
+    manifest_path = path.with_name("manifest.json")
+    if not manifest_path.is_file():
+        return None, None
+    manifest = json.loads(manifest_path.read_text())
+    if manifest.get("public_csv") != str(path):
+        return None, None
+    rate = manifest.get("global_offered_request_rate")
+    if not isinstance(rate, (int, float)) or not math.isfinite(rate) or rate <= 0:
+        raise ValueError(f"invalid global_offered_request_rate in {manifest_path}")
+    return float(rate), str(manifest_path)
+
+
 def parse_trace(
-    specification: str, *, rate_contract: str = "trace-window"
+    specification: str, *, rate_contract: str = "trace-window", prefix_caching: bool
 ) -> dict[str, Any]:
     if "=" not in specification:
         raise ValueError(f"trace must be LABEL=PATH: {specification}")
@@ -114,7 +127,12 @@ def parse_trace(
     if any(right < left for left, right in zip(arrivals, arrivals[1:])):
         raise ValueError(f"arrival order drift in {path}")
     if rate_contract == "trace-window":
-        offered_request_rate = len(rows) / WINDOW_SECONDS
+        offered_request_rate, rate_manifest = manifest_offered_rate(path)
+        if offered_request_rate is None:
+            offered_request_rate = len(rows) / WINDOW_SECONDS
+            rate_source = "legacy_fixed_600_second_window"
+        else:
+            rate_source = f"manifest:{rate_manifest}"
     elif rate_contract == "uniform-spacing":
         if len(rows) < 2 or arrivals[-1] <= arrivals[0]:
             raise ValueError("uniform-spacing traces require at least two arrivals")
@@ -123,6 +141,7 @@ def parse_trace(
         if any(abs(value - expected_interval) > 1e-9 for value in intervals):
             raise ValueError(f"non-uniform fixed trace: {path}")
         offered_request_rate = 1.0 / expected_interval
+        rate_source = "uniform_spacing"
     else:
         raise ValueError(f"unknown rate contract: {rate_contract}")
     shapes = [
@@ -131,12 +150,22 @@ def parse_trace(
     ]
     if any(prefill <= 0 or decode <= 0 or prefill + decode > 40960 for prefill, decode in shapes):
         raise ValueError(f"out-of-contract shape in {path}")
+    if prefix_caching:
+        for index, (row, (prefill, _)) in enumerate(zip(rows, shapes, strict=True)):
+            block_ids = [value for value in row["block_hash_ids"].split("|") if value]
+            if len(block_ids) != prefill // 16:
+                raise ValueError(
+                    "Frontier prefix-cache trace must expose only complete "
+                    f"16-token blocks: row={index}, ISL={prefill}, "
+                    f"ids={len(block_ids)}, expected={prefill // 16}"
+                )
     return {
         "label": label,
         "path": path,
         "sha256": BASE.sha256(path),
         "requests": len(rows),
         "offered_request_rate": offered_request_rate,
+        "offered_request_rate_source": rate_source,
         "first_arrival_s": arrivals[0],
         "last_arrival_s": arrivals[-1],
         "shapes": shapes,
@@ -236,7 +265,11 @@ def main() -> None:
     if args.allreduce_csv is not None:
         args.allreduce_csv = args.allreduce_csv.resolve()
     traces = [
-        parse_trace(specification, rate_contract=args.rate_contract)
+        parse_trace(
+            specification,
+            rate_contract=args.rate_contract,
+            prefix_caching=args.prefix_caching,
+        )
         for specification in args.trace
     ]
     if len({trace["label"] for trace in traces}) != len(traces):