Fix async telemetry coverage audit

runs/action-aware-v0/analyze_pilot.py

@@ -138,6 +138,37 @@ def binding_summary(
     }
 
 
+def telemetry_coverage(
+    records: list[Mapping[str, Any]], *, start_ns: int, end_ns: int
+) -> tuple[dict[str, float], bool]:
+    if not records:
+        raise ValueError("telemetry coverage requires records")
+    submit_gaps = [
+        (int(right["submit_mono_ns"]) - int(left["submit_mono_ns"])) / 1e9
+        for left, right in zip(records, records[1:], strict=False)
+    ]
+    uncovered_gaps = [
+        max(
+            0,
+            int(right["submit_mono_ns"]) - int(left["complete_mono_ns"]),
+        )
+        / 1e9
+        for left, right in zip(records, records[1:], strict=False)
+    ]
+    coverage = {
+        "start_gap_s": (int(records[0]["submit_mono_ns"]) - start_ns) / 1e9,
+        "end_gap_s": (end_ns - int(records[-1]["submit_mono_ns"])) / 1e9,
+        "max_internal_submit_gap_s": max(submit_gaps, default=0.0),
+        "max_uncovered_gap_s": max(uncovered_gaps, default=0.0),
+    }
+    covered = (
+        0.0 <= coverage["start_gap_s"] <= 1.0
+        and 0.0 <= coverage["end_gap_s"] <= 1.0
+        and 0.0 <= coverage["max_uncovered_gap_s"] <= 1.0
+    )
+    return coverage, covered
+
+
 def request_summary(path: Path, expected_count: int) -> dict[str, Any]:
     rows = load_jsonl(path)
     if len(rows) != expected_count:
@@ -222,17 +253,8 @@ def analyze_run(
     ]
     if not full_records:
         raise ValueError(f"no telemetry records in measured window: {result_path}")
-    gaps = [
+    coverage, invariants["telemetry_coverage"] = telemetry_coverage(
-        (int(right["submit_mono_ns"]) - int(left["submit_mono_ns"])) / 1e9
+        full_records, start_ns=start_ns, end_ns=arrival_end_ns
-        for left, right in zip(full_records, full_records[1:], strict=False)
-    ]
-    coverage = {
-        "start_gap_s": (int(full_records[0]["submit_mono_ns"]) - start_ns) / 1e9,
-        "end_gap_s": (arrival_end_ns - int(full_records[-1]["submit_mono_ns"])) / 1e9,
-        "max_internal_gap_s": max(gaps, default=0.0),
-    }
-    invariants["telemetry_coverage"] = all(
-        0.0 <= value <= 1.0 for value in coverage.values()
     )
     binding = binding_summary(
         full_records, mns=int(config["mns"]), mbbt=int(config["mbbt"])

runs/action-aware-v0/test_pilot.py

@@ -81,6 +81,25 @@ def main() -> None:
     assert summary["waiting_unresolved_count"] == 1
     assert summary["waiting_count"] == 4
 
+    # A per-step stream may have a submit gap above one second when the
+    # preceding model execution itself spans that interval.  Such a gap is
+    # covered telemetry, not a dropped-record interval.
+    asynchronous = [
+        {"submit_mono_ns": 0, "complete_mono_ns": 1_200_000_000},
+        {"submit_mono_ns": 1_100_000_000, "complete_mono_ns": 1_300_000_000},
+    ]
+    coverage, covered = analysis.telemetry_coverage(
+        asynchronous, start_ns=0, end_ns=1_100_000_000
+    )
+    assert coverage["max_internal_submit_gap_s"] == 1.1
+    assert coverage["max_uncovered_gap_s"] == 0.0
+    assert covered
+    missing = copy.deepcopy(asynchronous)
+    missing[0]["complete_mono_ns"] = 0
+    assert not analysis.telemetry_coverage(
+        missing, start_ns=0, end_ns=1_100_000_000
+    )[1]
+
     manifest = {
         "repetitions": {str(index): {} for index in (1, 2, 3)},
         "regimes": {