include/kpn/diagnostics.hpp

@@ -157,6 +157,16 @@ struct NodeSnapshot {
     double      cpu_util_pct;       // exec_ms / (exec_ms + blocked_ms) * 100
     double      queue_wait_ms{0};   // PoolNode: cumulative time spent in pool queue
 
+    // Cumulative wall time inside fire_once. Unlike ema_exec_ms this is a true
+    // sum, so it is the field to use for "share of the run spent in this node".
+    // Note it still includes time parked pushing into a full output channel;
+    // total_cpu_ms is the part that backpressure cannot inflate.
+    //
+    // Declared before the two bools below because every node type initialises
+    // this aggregate positionally, and all of them supply total_exec_ms as the
+    // element after queue_wait_ms.
+    double      total_exec_ms{0};
+
     // Live scheduling state, for observing the AR-004 invariant "a node never
     // sleeps with a wake outstanding". The invariant was previously asserted in
     // comments but invisible at runtime, so a lost wake could only be found in a
@@ -169,11 +179,6 @@ struct NodeSnapshot {
     //   queued=1 while nothing running  -> submitted but never scheduled
     bool        queued{false};
     bool        wake_pending{false};
-    // Cumulative wall time inside fire_once. Unlike ema_exec_ms this is a true
-    // sum, so it is the field to use for "share of the run spent in this node".
-    // Note it still includes time parked pushing into a full output channel;
-    // total_cpu_ms is the part that backpressure cannot inflate.
-    double      total_exec_ms{0};
 };
 
 // ── Pool statistics + snapshot ────────────────────────────────────────────────

tests/test_pool_node.cpp

@@ -478,3 +478,49 @@ TEST_CASE("per-node and network overflow callbacks both fire independently", "[p
     REQUIRE(per_node.load() == 0);
     REQUIRE(network.load() == 0);
 }
+
+// Regression: NodeSnapshot's fields must line up with what nodes initialise.
+//
+// The snapshot is an aggregate that every node type fills positionally, and
+// a8cfe73 appended queued/wake_pending/total_exec_ms to it in an order no call
+// site used: each node supplies total_exec_ms as the element straight after
+// queue_wait_ms, but the struct declared the two bools there. So the exec total
+// landed in `queued`, `queued` landed in `wake_pending`, and `wake_pending`
+// landed in total_exec_ms. The compiler said so (-Wnarrowing, bool to double,
+// once per node instantiation) and the build carried on.
+//
+// It matters more than a cosmetic mix-up: these three fields exist to diagnose a
+// wedge, and a wedged pipeline reported total_exec_ms as 0 or 1 and `queued` as
+// "did this node ever run". Reading them would have pointed at the wrong node.
+//
+// Asserted against ema_exec_ms because that field is independently computed and
+// was already correct: a true sum over several frames cannot be below the
+// exponentially-weighted average of the same samples.
+TEST_CASE("node snapshot fields line up with the values nodes supply",
+          "[pool_node][diagnostics]") {
+    auto pool = std::make_shared<ThreadPool>(1);
+    pool->start();
+
+    auto node = make_pool_node<double_it>(pool, 64);
+    Channel<int> out(64);
+    node.set_output_channel<0>(&out);
+    node.start();
+
+    for (int i = 0; i < 8; ++i) node.input_channel<0>().push(i);
+    std::this_thread::sleep_for(std::chrono::milliseconds(100));
+
+    auto snap = node.node_snapshot("n", 1.0);
+    node.stop();
+    pool->stop();
+
+    INFO("frames=" << snap.frames_processed
+         << " ema=" << snap.ema_exec_ms
+         << " total=" << snap.total_exec_ms);
+    REQUIRE(snap.frames_processed == 8);
+    // The mis-ordered aggregate put wake_pending here, so this was 0.0 or 1.0.
+    CHECK(snap.total_exec_ms >= snap.ema_exec_ms);
+    // ...and the exec total here, which is non-zero, so `queued` read true for
+    // any node that had ever run — including one asleep with nothing to do.
+    CHECK_FALSE(snap.queued);
+    CHECK_FALSE(snap.wake_pending);
+}