fix: apply lossless push in PoolObjectNode too

PoolNode and PoolObjectNode each have their own push_one_out(). The previous commit only reached PoolNode's copy, so ObjectNode-based pipelines — the common case — still dropped on overflow with lossless enabled. Verified end to end: a 2300-frame source now reports exactly 2300 frames at every stage, where it previously delivered 774 to the second node. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
feat: opt-in lossless (blocking) output for nodes and fanouts
2026-07-25 23:12:51 +02:00 · 2026-07-25 23:03:56 +02:00
27 changed files with 267 additions and 2869 deletions
@@ -27,6 +27,3 @@ Thumbs.db
 # Claude Code local settings
 .claude/settings.local.json
 include/kpn/ort_cache/
 build-tsan/
 build-*/
@@ -7,78 +7,12 @@
 #include <array>
 #include <atomic>
 #include <chrono>
 #include <functional>
 #include <memory>
 #include <thread>
 namespace kpn {
 // ── Lossless single-output delivery ───────────────────────────────────────────
 //
 // Shared by RouterNode and FilterNode, which each deliver a value to exactly one
 // channel. Both previously did
 //
 //     try { ch->push(val); } catch (const ChannelOverflowError&) {}
 //
 // which discards the value whenever the consumer is behind. 6595e6e made node
 // outputs lossless, 28e0667 stopped them parking a worker, and a8cfe73 did the
 // same for FanoutNode — these two were in none of them, and were the last
 // remaining users of the throwing push() on a data path.
 //
 // A dropped item does not degrade a downstream result, it silently changes one.
 // Worse, a dropped *sentinel* wedges the pipeline outright: EOF is what tells
 // every downstream node to shut down, and there is nothing after it to retry.
 // A filter that passes EOF by predicate but drops it by backpressure is a
 // pipeline that never terminates.
 //
 // So sentinels go out-of-band via push_sentinel (a dedicated slot that consumes
 // no ring capacity and cannot overflow), and everything else is retried until
 // taken. Like FanoutNode and unlike a pool node, these own a private thread, so
 // waiting here costs no scheduler worker and needs no space-callback park.
 // stop_flag_ is rechecked every pass so teardown cannot hang on a full output.
 //
 // `parked` receives the time spent waiting, which the caller charges to blocked
 // rather than exec — a parked node is idle, and charging it to exec reports the
 // node as busy exactly when it is the one being held up.
 //
 // Returns false if stopped with the value undelivered.
 template<typename T>
 bool deliver_one(Channel<T>* ch, T& val, const std::atomic<bool>& stop_flag,
                 duration_t& parked) {
    if (is_sentinel_value(val)) {
        ch->push_sentinel(std::move(val));
        return true;
    }
    const auto park_from = clock_t::now();
    for (;;) {
        switch (ch->try_push(val)) {
            case Channel<T>::PushResult::Taken:
                parked = duration_t(clock_t::now() - park_from);
                return true;
            case Channel<T>::PushResult::Closed:
                // Nobody is listening any more; the channel has recorded the
                // drop. Retrying would spin until teardown noticed.
                parked = duration_t(clock_t::now() - park_from);
                return false;
            case Channel<T>::PushResult::Full:
                break;                       // fall through to the retry logic
        }
        if (stop_flag.load(std::memory_order_relaxed)) {
            // Teardown with work in hand and the output still full. One last
            // throwing push, purely so the channel's own stats record the
            // overflow — the point of the lossless path is that a loss is never
            // invisible, and a silent return here would reintroduce exactly the
            // hole this function exists to close.
            try { ch->push(std::move(val)); }
            catch (const ChannelOverflowError&) {}
            parked = duration_t(clock_t::now() - park_from);
            return false;
        }
        std::this_thread::sleep_for(std::chrono::microseconds(50));
    }
 }
 // ── RouterNode ────────────────────────────────────────────────────────────────
 //
 // Reads one item and pushes it to exactly one of N output channels, chosen by
@@ -192,20 +126,15 @@ private:
                auto        t1  = clock_t::now();
                auto        cpu0 = NodeStats::cpu_now();
                // An out-of-range selector still drops by design (documented on
                // the class): the item was routed nowhere, not lost to a full
                // channel. Only the latter is what deliver_one exists to stop.
                std::size_t idx = selector_(val);
-                duration_t  parked{0};
+                if (idx < N && out_channels_[idx]) {
-                bool        delivered = true;
+                    try { out_channels_[idx]->push(val); }
-                if (idx < N && out_channels_[idx])
+                    catch (const ChannelOverflowError&) {}
-                    delivered = deliver_one(out_channels_[idx], val, stop_flag_, parked);
+                }
                auto cpu1 = NodeStats::cpu_now();
                auto t2   = clock_t::now();
-                stats_.record_exec(duration_t(t2 - t1) - parked,
+                stats_.record_exec(duration_t(t2 - t1), duration_t(t1 - t0), cpu0, cpu1);
                                   duration_t(t1 - t0) + parked, cpu0, cpu1);
                if (!delivered) break;
            } catch (const ChannelClosedError&) {
                break;
            }
@@ -332,19 +261,12 @@ private:
                auto t1  = clock_t::now();
                auto cpu0 = NodeStats::cpu_now();
                // A value the predicate rejects is dropped by design and is not
                // counted as a processed frame. One it accepts is now delivered
                // losslessly — including a sentinel, which a filter typically
                // passes unconditionally so downstream can shut down, and which
                // the old throwing push discarded whenever the output was full.
                if (pred_(val) && out_ch_) {
-                    duration_t parked{0};
+                    try { out_ch_->push(val); }
-                    const bool delivered = deliver_one(out_ch_, val, stop_flag_, parked);
+                    catch (const ChannelOverflowError&) {}
                    auto cpu1 = NodeStats::cpu_now();
                    auto t2   = clock_t::now();
-                    stats_.record_exec(duration_t(t2 - t1) - parked,
+                    stats_.record_exec(duration_t(t2 - t1), duration_t(t1 - t0), cpu0, cpu1);
                                       duration_t(t1 - t0) + parked, cpu0, cpu1);
                    if (!delivered) break;
                }
            } catch (const ChannelClosedError&) {
                break;
@@ -58,18 +58,6 @@ public:
    ChannelClosedError() : std::runtime_error("channel closed") {}
 };
 // Nothing available *right now* on a channel that is still open. Distinct from
 // ChannelClosedError, which means upstream is finished and never coming back.
 //
 // Conflating the two is expensive in one direction only: a consumer that reads
 // "empty" as "closed" stops a live node permanently, and because a stopping
 // node disables its own inputs and outputs, one benign empty read takes the
 // rest of the pipeline with it. The reverse costs nothing.
 class ChannelEmptyError : public std::runtime_error {
 public:
    ChannelEmptyError() : std::runtime_error("channel empty") {}
 };
 // ── CPU pause hint ────────────────────────────────────────────────────────────
 // Signals the CPU that this is a spin-wait loop, improving HT sibling throughput
 // and preventing branch-predictor thrash on x86. Falls back to a compiler barrier.
@@ -148,55 +136,6 @@ public:
            push_callback_();
    }
    /// Called when a pop frees a slot in a previously-full ring.
    ///
    /// The mirror of `set_push_callback`, and it exists for the same reason:
    /// a producer must be able to *park* rather than spin. Without it the only
    /// lossless option is `push_blocking`, which sleeps inside the caller's
    /// thread — and when that thread is a scheduler worker, parking it starves
    /// every node pinned to it (see the hold-and-wait note on push_sentinel).
    void set_space_callback(std::function<void()> cb) { space_callback_ = std::move(cb); }
    /// True when a push would currently succeed. Used to close the lost-wakeup
    /// race: a producer that parks must re-check after clearing its queued flag,
    /// because a space_callback fired in between would otherwise be swallowed.
    bool has_space() const {
        return tail_.load(std::memory_order_relaxed) -
               head_.load(std::memory_order_acquire) < capacity_;
    }
    /// Outcome of a non-blocking push.
    ///
    /// try_push used to return bool, and returned *true* for a closed channel —
    /// so "delivered" and "discarded because nobody is listening" were the same
    /// answer. Both mean "stop trying", which is why the callers were correct,
    /// but neither they nor the producer's own accounting could tell a value
    /// that arrived from one that was thrown away. Only the channel's drop
    /// counter knew.
    enum class PushResult { Taken, Full, Closed };
    /// Non-blocking, lossless push. Returns Full when the ring is full, having
    /// changed nothing — the caller keeps the value and retries when woken.
    PushResult try_push(T& value) {
        if (!accepting_.load(std::memory_order_acquire)) {
            stats_.record_drop();
            return PushResult::Closed;
        }
        const std::size_t t = tail_.load(std::memory_order_relaxed);
        const std::size_t h = head_.load(std::memory_order_acquire);
        if (t - h >= capacity_) return PushResult::Full;
        const std::size_t data_bytes = ChannelDataSize<T>::bytes(value);
        const bool was_empty = (t == h);
        buf_[t & ring_mask_] = make_storage(std::move(value));
        tail_.store(t + 1, std::memory_order_release);
        stats_.record_push(t - h + 1, data_bytes);
        wake_.fetch_add(1, std::memory_order_release);
        wake_.notify_one();
        if (was_empty && push_callback_) push_callback_();
        return PushResult::Taken;
    }
    // Lossless push with BACKPRESSURE: if the ring is full, wait for the consumer to
    // drain instead of dropping (the throwing push()) — the producer just runs slower.
    // Use when every value must be delivered (e.g. replaying a dump for scoring, where
@@ -239,37 +178,12 @@ public:
    // preserving ordering (EOF arrives after all data pushed before it).
    //
    // Only the sole producer may call it (SPSC contract, same as push()).
-    //
+    // Returns false if the channel is already disabled (token discarded —
-    // The slot holds exactly one undelivered token. A second offered before the
+    // teardown is in progress, so the sentinel is moot).
-    // first is taken is refused, not queued and not overwritten: two control
+    bool push_sentinel(T value) {
    // tokens on one channel means the stream ended twice, which is a caller
    // protocol error rather than backpressure, and silently coalescing them
    // would hide it.
    /// Outcome of offering a sentinel. SlotBusy is a protocol error, not
    /// backpressure: it means a second control token was offered while the
    /// first was still undelivered, and a channel carries at most one.
    enum class SentinelResult { Taken, Closed, SlotBusy };
    /// Non-consuming form. `value` is left untouched unless the result is
    /// Taken, so a refused token is still the caller's to report.
    SentinelResult try_push_sentinel(T& value) {
        if (!accepting_.load(std::memory_order_acquire)) {
            stats_.record_drop();
-            return SentinelResult::Closed;
+            return false;
        }
        // Refuse rather than overwrite. Overwriting lost the first token
        // silently, and worse, wrote eof_value_ while the consumer could be
        // moving the previous one out of it — a data race on the storage, which
        // for a shared_ptr payload is a torn refcount rather than a stale read.
        //
        // Checking here is what makes the slot a correct SPSC handshake: the
        // producer is the only writer of eof_value_ and the only one that sets
        // has_eof_, the consumer is the only one that clears it, so observing
        // false here means the consumer has finished with the storage and will
        // not touch it again until this store publishes the next token.
        if (has_eof_.load(std::memory_order_acquire)) {
            stats_.record_drop();
            return SentinelResult::SlotBusy;
        }
        eof_value_ = make_storage(std::move(value));
        has_eof_.store(true, std::memory_order_release);
@@ -278,13 +192,7 @@ public:
        wake_.fetch_add(1, std::memory_order_release);
        wake_.notify_one();
        if (push_callback_) push_callback_();
-        return SentinelResult::Taken;
+        return true;
    }
    /// Consuming convenience form. Returns false when the token was not stored,
    /// whether because the channel is closed or because one is already pending.
    bool push_sentinel(T value) {
        return try_push_sentinel(value) == SentinelResult::Taken;
    }
    // Blocking pop. Returns when an item is available.
@@ -340,8 +248,6 @@ public:
                throw ChannelClosedError{};
            T value = extract(std::move(buf_[h & ring_mask_]));
            head_.store(h + 1, std::memory_order_release);
            // A slot just freed: wake any producer parked on this channel.
            if (t - h >= capacity_ && space_callback_) space_callback_();
            stats_.record_pop();
            return value;
        }
@@ -363,15 +269,11 @@ public:
    // so pool nodes — which pop only via this path — still receive the token.
    bool try_pop_now(T& out) {
        const std::size_t h = head_.load(std::memory_order_relaxed);
-        const std::size_t t = tail_.load(std::memory_order_acquire);
+        if (h == tail_.load(std::memory_order_acquire))
        if (h == t)
            return take_sentinel(out);
        out = extract(std::move(buf_[h & ring_mask_]));
        head_.store(h + 1, std::memory_order_release);
        stats_.record_pop();
        // Pool nodes pop only through here, so this is where a parked producer
        // gets woken: the ring was full, and it no longer is.
        if (t - h >= capacity_ && space_callback_) space_callback_();
        return true;
    }
@@ -395,15 +297,9 @@ public:
    // Ring occupancy, derived lazily from indices — no separate counter on the
    // hot path. Excludes any out-of-band sentinel (that lives outside the ring).
    // head_ is loaded first, deliberately. Both indices only ever increase, so
    // reading head_ before tail_ can at worst under-report a concurrent push;
    // the other order can read a head_ that has advanced past the tail_ already
    // sampled, and the unsigned difference then wraps to ~2^64. A caller
    // polling "is this channel empty yet" against that value never terminates.
    std::size_t size() const {
-        const std::size_t h = head_.load(std::memory_order_relaxed);
+        return tail_.load(std::memory_order_relaxed)
-        const std::size_t t = tail_.load(std::memory_order_acquire);
+             - head_.load(std::memory_order_relaxed);
        return t - h;
    }
    // A pending out-of-band sentinel (EOF) counts as consumable work here even
@@ -420,9 +316,8 @@ public:
    const ChannelStats& stats() const { return stats_; }
    ChannelSnapshot snapshot(const std::string& name) const {
-        // head_ before tail_, for the reason given on size().
+        const std::size_t t = tail_.load(std::memory_order_relaxed);
        const std::size_t h = head_.load(std::memory_order_relaxed);
        const std::size_t t = tail_.load(std::memory_order_acquire);
        return {
            name,
            capacity_,
@@ -457,24 +352,6 @@ private:
    // delivered after every value pushed before it.
    bool take_sentinel(T& out) {
        if (!has_eof_.load(std::memory_order_acquire)) return false;
        // Re-check emptiness *after* observing has_eof_, not before.
        //
        // Callers check the ring is empty and then call this, but the producer
        // can push a value and publish the sentinel in the window between those
        // two steps — so the sentinel would be delivered with a real value still
        // queued behind it, breaking the "sentinel is strictly last" contract
        // that downstream teardown depends on. a0c4bf5 closed the variant where
        // the caller's emptiness check used a stale tail_ snapshot; this is the
        // one where the check is fresh but simply too early.
        //
        // Checking here is what makes it sound: the producer publishes the
        // sentinel with a release store *after* its ring pushes, so a consumer
        // that has observed has_eof_ has also observed every tail_ advance
        // before it. If the ring is non-empty now, those values genuinely
        // precede the sentinel and must be delivered first.
        if (head_.load(std::memory_order_relaxed)
                != tail_.load(std::memory_order_acquire))
            return false;
        out = extract(std::move(eof_value_));
        has_eof_.store(false, std::memory_order_release);
        stats_.record_pop();
@@ -486,7 +363,6 @@ private:
    std::size_t                     ring_mask_;
    std::unique_ptr<storage_type[]> buf_;
    std::function<void()>           push_callback_;
    std::function<void()> space_callback_;
    ChannelStats                    stats_;
    // Out-of-band sentinel (EOF): stored outside the ring so its delivery never
@@ -51,14 +51,6 @@ struct NodeStats {
    std::atomic<int64_t> max_exec_us{0};
    std::atomic<int64_t> total_blocked_us{0};
    // Cumulative wall time inside fire_once, summed over every invocation.
    // The EMA above cannot be turned into a total: it is exponentially
    // weighted, so frames * ema_exec_us tracks the tail of the run rather than
    // the whole of it, and on a workload whose per-frame cost varies (a face
    // detector on a film: crowd scenes then empty landscapes) the two differ by
    // a lot. Answering "how much time went into this node" needs a real sum.
    std::atomic<int64_t> total_exec_us{0};
    // Thread CPU time — actual CPU consumed by this node's thread,
    // measured via CLOCK_THREAD_CPUTIME_ID. Excludes time sleeping or
    // blocked on mutexes/channels. Sampled once per frame.
@@ -97,7 +89,6 @@ struct NodeStats {
        frames_processed.fetch_add(1, std::memory_order_relaxed);
        int64_t us = static_cast<int64_t>(exec_time.count() * 1000.0);
        total_exec_us.fetch_add(us, std::memory_order_relaxed);
        uint64_t n = frames_processed.load(std::memory_order_relaxed);
        int64_t prev = ema_exec_us.load(std::memory_order_relaxed);
@@ -156,29 +147,6 @@ struct NodeSnapshot {
    double      total_cpu_ms;       // cumulative CPU time consumed by this node's thread
    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
    // debugger — and this bug does not reproduce under one (it needs full speed).
    // Two atomic loads at snapshot time, nothing on the hot path.
    //
    // Read them together with the node's channel fill:
    //   queued=0, wake=1                -> wake recorded and never consumed
    //   queued=0, wake=0, input full    -> wake never generated at all
    //   queued=1 while nothing running  -> submitted but never scheduled
    bool        queued{false};
    bool        wake_pending{false};
 };
 // ── Pool statistics + snapshot ────────────────────────────────────────────────
@@ -220,11 +188,6 @@ struct ResourceSnapshot {
 struct IResourceProbe {
    virtual ~IResourceProbe() = default;
    virtual ResourceSnapshot snapshot(const std::string& name) const = 0;
    /// Release every thread waiting for the resource, so teardown is not held
    /// up by one. A network calls this on the resources registered with it when
    /// it halts; default no-op for probes with nothing to wake.
    virtual void close() {}
 };
 } // namespace kpn
@@ -7,10 +7,8 @@
 #include <array>
 #include <atomic>
 #include <chrono>
 #include <iostream>
 #include <memory>
 #include <optional>
 #include <thread>
 #include <tuple>
 #include <utility>
@@ -80,9 +78,7 @@ public:
                blocked_ms,
                elapsed_s > 0 ? frames / elapsed_s : 0.0,
                stats_.total_cpu_us.load(std::memory_order_relaxed) / 1000.0,
-                total_ms > 0 ? 100.0 * exec_ms / total_ms : 0.0,
+                total_ms > 0 ? 100.0 * exec_ms / total_ms : 0.0};
                0.0,  // queue_wait_ms — fanout is not pool-scheduled
                stats_.total_exec_us.load(std::memory_order_relaxed) / 1000.0};
    }
    // ── Port access ───────────────────────────────────────────────────────────
@@ -119,80 +115,17 @@ public:
        out_channels_[I] = ch;
    }
    // Lossless fanout: block until each consumer drains rather than dropping.
    void set_lossless_output(bool on) override { lossless_ = on; }
    // Opt a single output back out of blocking.  Needed when one branch may
    // stall indefinitely — a display tap nobody is servicing, say — since
    // blocking on it would apply backpressure to every other branch too.
    void set_lossy_output(std::size_t i, bool lossy = true) {
        if (i < N) lossy_out_[i] = lossy;
    }
 private:
    // Deliver `val` to every connected output, losslessly.
    //
    // Previously a full output cost the value: push() threw and the exception was
    // swallowed per output. A dropped item does not degrade a downstream result,
    // it silently changes one, and the consumer cannot tell it happened — so the
    // fanout waits instead, and the producer upstream runs slower.
    //
    // Unlike a pool node, a fanout owns a private thread, so waiting here costs
    // no scheduler worker and needs no space-callback park; a bounded retry is
    // enough. `stop_flag_` is re-checked every pass so teardown cannot hang on a
    // full output regardless of the order the network stops its nodes in.
    //
    // Outputs are retried independently, so a full output never delays delivery
    // to one with room. Note what that does *not* buy: the next input is not
    // popped until every output has accepted the current item, so one branch can
    // never run ahead of another by more than the slower branch's buffering.
    //
    // **That bound is a precondition on any topology where the branches rejoin.**
    // If a consumer on branch B blocks waiting for something branch A computes,
    // B's buffering must exceed the lead A needs, or the two wedge — B waiting on
    // A, A starved because the fanout is holding an item B will not take. Making
    // the fanout lossless is what puts that precondition on the topology; while
    // it dropped, the question could not arise.
    //
    // `parked` receives the time spent waiting on a full output, which the caller
    // charges to blocked rather than exec.
    //
    // Returns false if stopped with the value undelivered.
    bool deliver(const T& val, duration_t& parked) {
        std::array<std::optional<T>, N> pending;
        std::size_t outstanding = 0;
        for (std::size_t i = 0; i < N; ++i)
            if (out_channels_[i]) { pending[i].emplace(val); ++outstanding; }
        bool first_pass = true;
        auto park_from  = clock_t::now();
        for (;;) {
            for (std::size_t i = 0; i < N; ++i) {
                if (!pending[i]) continue;
                // Taken or Closed both mean "stop trying" — delivered, or gone
                // with the drop recorded. Only Full is worth another pass.
                if (out_channels_[i]->try_push(*pending[i])
                        != Channel<T>::PushResult::Full) {
                    pending[i].reset();
                    --outstanding;
                }
            }
            if (first_pass) { park_from = clock_t::now(); first_pass = false; }
            if (outstanding == 0) {
                parked = duration_t(clock_t::now() - park_from);
                return true;
            }
            if (stop_flag_.load(std::memory_order_relaxed)) {
                // Teardown with work in hand. One last throwing push per
                // outstanding output, purely so the channel's own stats record
                // the loss (drop if it is disabled, overflow if it is merely
                // full). The whole point of the lossless path is that a loss is
                // never invisible, and a silent `return` here would reintroduce
                // exactly the hole this function exists to close.
                for (std::size_t i = 0; i < N; ++i) {
                    if (!pending[i]) continue;
                    try { out_channels_[i]->push(std::move(*pending[i])); }
                    catch (const ChannelOverflowError&) {}
                }
                parked = duration_t(clock_t::now() - park_from);
                return false;
            }
            std::this_thread::sleep_for(std::chrono::microseconds(50));
        }
    }
    void run_loop() {
        while (!stop_flag_.load(std::memory_order_relaxed)) {
            try {
@@ -201,17 +134,27 @@ private:
                auto t1  = clock_t::now();
                auto cpu0 = NodeStats::cpu_now();
-                duration_t parked{0};
+                for (std::size_t i = 0; i < N; ++i) {
-                const bool delivered = deliver(val, parked);
+                    if (out_channels_[i]) {
                        // Lossless: block until this consumer drains.  Note the
                        // branches differ in more than blocking — the dropping
                        // path discards per-output independently and silently,
                        // so a slow consumer on one branch costs frames on that
                        // branch only, with no diagnostic.  That is the right
                        // default for display taps but hides frame loss from
                        // analysis branches.
                        if (lossless_ && !lossy_out_[i])
                            out_channels_[i]->push_blocking(val);
                        else {
                            try { out_channels_[i]->push(val); }
                            catch (const ChannelOverflowError&) {}  // drop independently
                        }
                    }
                }
                auto cpu1 = NodeStats::cpu_now();
                auto t2   = clock_t::now();
-                // Time spent waiting on a full output is *blocked*, not exec: a
+                stats_.record_exec(duration_t(t2 - t1), duration_t(t1 - t0), cpu0, cpu1);
                // parked fanout is idle, and charging it to exec would report the
                // node as busy exactly when it is the one being held up.
                stats_.record_exec(duration_t(t2 - t1) - parked,
                                   duration_t(t1 - t0) + parked, cpu0, cpu1);
                if (!delivered) break;
            } catch (const ChannelClosedError&) {
                break;
            }
@@ -220,6 +163,8 @@ private:
    std::string                 name_;
    std::size_t                 fifo_capacity_;
    bool                        lossless_{false};
    std::array<bool, N>         lossy_out_{};   // per-output opt-out of blocking
    std::shared_ptr<Channel<T>> input_ch_;
    std::array<Channel<T>*, N>  out_channels_{};
    std::atomic<bool>           stop_flag_{false};
@@ -22,23 +22,6 @@ enum class NodeEvent { Overflow, Closed };
 struct INode {
    virtual ~INode()       = default;
    // Install channel callbacks, without starting anything.
    //
    // A node's push/space callbacks live in std::function members on channels
    // it shares with its neighbours, and a neighbour that is already running
    // reads them on its own thread. Writing one while the pipeline runs is a
    // data race on the std::function — ThreadSanitizer reports it, and the
    // consequence in the field was the missed startup wake a8cfe73 had to
    // patch around.
    //
    // So a network calls prepare() on every node before it calls start() on
    // any of them: all the writes happen while nothing is running, and once a
    // node is live the callbacks are read-only. start() calls prepare() itself
    // if it has not been called, so standalone nodes still work; it is
    // idempotent, and the network relies on that.
    virtual void prepare() {}
    virtual void start()   = 0;
    virtual void stop()    = 0;
    virtual bool running() const = 0;
@@ -51,17 +34,13 @@ struct INode {
    virtual void set_network_overflow_callback(NodeEventCallback) {}
    virtual void set_network_closed_callback(NodeEventCallback)   {}
    // Network-level error listener. Consulted when a node's function throws
    // and no per-node handler resolved it. Without this the exception is
    // discarded and the failure is only visible as a Closed event, which says
    // a node stopped but not why — the difference between a diagnosis and a
    // guess. Same contract as NodeErrorHandler: true to continue, false to
    // stop the node.
    virtual void set_network_error_callback(NodeErrorHandler) {}
    // halt(): alias for stop() — immediate, discards in-flight work.
    virtual void halt() { stop(); }
    // Opt into lossless (blocking) output for nodes that support it.  Default
    // is a no-op so node types with no output channels ignore it.
    virtual void set_lossless_output(bool) {}
    // shutdown(): graceful drain before stopping. Base implementation falls
    // back to stop(). Network and StaticNetwork override with topo-ordered drain.
    virtual void shutdown() { stop(); }
@@ -104,7 +104,6 @@ public:
            stats_.total_cpu_us.load(std::memory_order_relaxed) / 1000.0,
            total_ms > 0 ? 100.0 : 0.0,
            qwait_ms,
            stats_.total_exec_us.load(std::memory_order_relaxed) / 1000.0,
        };
    }
@@ -90,8 +90,6 @@ public:
            elapsed_s > 0 ? frames / elapsed_s : 0.0,
            stats_.total_cpu_us.load(std::memory_order_relaxed) / 1000.0,
            total_ms > 0 ? 100.0 * exec_ms / total_ms : 0.0,
            0.0,  // queue_wait_ms — main-thread node is not pool-scheduled
            stats_.total_exec_us.load(std::memory_order_relaxed) / 1000.0,
        };
    }
@@ -8,10 +8,8 @@
 #include <memory>
 #endif
 #include <condition_variable>
 #include <functional>
 #include <iomanip>
 #include <mutex>
 #include <iostream>
 #include <map>
 #include <set>
@@ -41,15 +39,8 @@ public:
 class Network : public INode {
 public:
-    /// Application-level error listener. Receives the exception any node's
+    using ErrorHandler =
-    /// function throws, after that node's own handler (if any) declined it.
+        std::function<void(std::string_view node_name, std::exception_ptr)>;
    /// Return true to skip the failed invocation and keep the node running,
    /// false to let it stop.
    ///
    /// Same type as StaticNetwork's, deliberately: this used to be a void
    /// signature, which could not express the keep-running decision and, more
    /// to the point, was never delivered anywhere.
    using ErrorHandler = NodeErrorHandler;
    using DiagnosticsHandler =
        std::function<void(const std::vector<NodeSnapshot>&,
                           const std::vector<ChannelSnapshot>&)>;
@@ -100,7 +91,6 @@ public:
                            + " → " + dst_name + ":" + std::to_string(DstIdx);
        channel_probes_.push_back(
            std::make_unique<ChannelProbe<out_t>>(in_ch, ch_name));
        channel_src_names_.push_back(src_name);
        adj_[src_name].push_back(dst_name);
        return *this;
@@ -144,17 +134,6 @@ public:
    void start() override {
        start_time_ = clock_t::now();
        // Deliver the listener to the nodes. Without this the handler was
        // stored and never read: a node's exception was discarded at the node
        // boundary and the only surviving evidence was a Closed event, which
        // says a node stopped but not why. StaticNetwork has always done this;
        // Network accepted the handler and silently dropped it.
        if (error_handler_)
            for (auto& name : topo_)
                nodes_.at(name)->set_network_error_callback(error_handler_);
        // Callbacks first, everywhere, before anything runs — see INode::prepare.
        for (auto& name : topo_)
            nodes_.at(name)->prepare();
        for (auto& name : topo_)
            nodes_.at(name)->start();
        start_watchdog();
@@ -231,11 +210,6 @@ public:
        watchdog_interval_ = interval;
    }
    /// How long shutdown() waits for one node's outputs to drain before giving
    /// up on them and stopping the next layer anyway.
    void set_drain_timeout(std::chrono::milliseconds t) { drain_timeout_ = t; }
    /// Must be called before start(); the handler is delivered to nodes there.
    void set_error_handler(ErrorHandler h)             { error_handler_  = std::move(h); }
    void set_diagnostics_handler(DiagnosticsHandler h) { diag_handler_  = std::move(h); }
    void set_event_handler(EventHandler h)             { event_handler_  = std::move(h); }
@@ -393,46 +367,19 @@ private:
        return true;
    }
-    /// Wait for the channels fed by `name` to empty, or give up.
+    void drain_output_channels(const std::string& /*name*/) const {
-    ///
+        // Poll all channel probes until none report non-zero fill.
-    /// This took a node name and ignored it, polling *every* channel in the
+        // A short sleep prevents busy-spin; 1 ms is fine for drain purposes.
-    /// graph instead — so shutdown() waited for the whole network to be idle
+        bool any_full = true;
-    /// before stopping each successive layer. With no deadline either, anything
+        while (any_full) {
-    /// wedged downstream turned a graceful shutdown into the hang it exists to
+            any_full = false;
-    /// avoid.
+            for (auto& probe : channel_probes_) {
-    ///
+                auto snap = probe->snapshot();
-    /// Two bounds, because they fail differently. The deadline covers a
+                if (snap.current_fill > 0) { any_full = true; break; }
-    /// consumer that has stopped consuming, where fill never changes and
+            }
-    /// waiting cannot help. The no-progress counter covers one that is merely
+            if (any_full)
    /// slow: it keeps waiting while the queue is shrinking, so a slow drain is
    /// not cut short just for taking a while.
    void drain_output_channels(const std::string& name) const {
        const auto deadline = clock_t::now() + drain_timeout_;
        std::size_t last_fill = static_cast<std::size_t>(-1);
        int         stalls    = 0;
        auto fill_of = [&] {
            std::size_t fill = 0;
            for (std::size_t i = 0; i < channel_probes_.size(); ++i)
                if (channel_src_names_[i] == name)
                    fill += channel_probes_[i]->snapshot().current_fill;
            return fill;
        };
        for (;;) {
            const std::size_t fill = fill_of();
            if (fill == 0) return;
            if (fill >= last_fill) { if (++stalls > 100) break; }
            else                   { stalls = 0; }
            last_fill = fill;
            if (clock_t::now() >= deadline) break;
                std::this_thread::sleep_for(std::chrono::milliseconds(1));
        }
        if (const std::size_t left = fill_of())
            std::cerr << "[kpn] shutdown: '" << name << "' still has " << left
                      << " queued item(s) its consumer did not take; "
                         "they are discarded\n";
    }
    // ── Cycle detection / topological sort ───────────────────────────────────
@@ -451,20 +398,9 @@ private:
    void start_watchdog() {
        watchdog_ = std::jthread([this](std::stop_token tok) {
            // Interruptible wait, not sleep_for. request_stop() cannot wake a
            // sleeping thread, so stop_watchdog()'s join blocked for up to a
            // full interval — three seconds by default, and unbounded for
            // anyone who set a long one to keep the periodic report quiet.
            // Every teardown paid it.
            std::mutex                  m;
            std::condition_variable_any cv;
            while (!tok.stop_requested()) {
-                {
+                std::this_thread::sleep_for(watchdog_interval_);
-                    std::unique_lock lk(m);
+                if (tok.stop_requested()) break;
                    if (cv.wait_for(lk, tok, watchdog_interval_,
                                    [&tok] { return tok.stop_requested(); }))
                        break;
                }
                auto s = collect_snapshots();
                check_hung_nodes();
@@ -508,10 +444,6 @@ private:
    std::map<std::string, std::string>                     exposed_outputs_;
    std::set<std::pair<std::string, std::size_t>>          connected_outputs_;
    std::vector<std::unique_ptr<IChannelProbe>>            channel_probes_;
    /// Name of the node feeding each probe, parallel to channel_probes_.
    /// shutdown() drains a node's own outputs, so it has to know which they are.
    std::vector<std::string>                               channel_src_names_;
    std::chrono::milliseconds                              drain_timeout_{5000};
    std::vector<std::pair<std::string, IPoolProbe*>>       pool_probes_;
    ErrorHandler                                           error_handler_;
    DiagnosticsHandler                                     diag_handler_;
@@ -5,7 +5,6 @@
 #include <functional>
 #include <memory>
 #include <mutex>
 #include <shared_mutex>
 #include <optional>
 #include <queue>
 #include <thread>
@@ -63,30 +62,18 @@ public:
    }
    void stop() override {
        // Close the pool to new work before touching anything, and do it under
        // the lifecycle lock so no submit() is midway through indexing queues_.
        {
            std::unique_lock lk(lifecycle_mx_);
        stopped_.store(true, std::memory_order_seq_cst);
        }
        for (auto& q : queues_) {
            std::lock_guard lock(q->mx);
            std::size_t discarded = q->pq.size();
            while (!q->pq.empty()) q->pq.pop();
            total_.fetch_sub(discarded, std::memory_order_relaxed);
            queued_.fetch_sub(discarded, std::memory_order_relaxed);
        }
        // Lock cv_mx_ before notifying so the stop signal can't be lost in the
        // gap between a worker's predicate check and its wait() (see submit()).
        { std::lock_guard<std::mutex> lk(cv_mx_); }
        cv_.notify_all();
        // Join without the lock: a worker's task may call submit(), which takes
        // it shared, and holding it here would deadlock against that.
        for (auto& t : workers_) if (t.joinable()) t.join();
        // Destroying the queues is what submit() must never race. By now
        // stopped_ is published, so any submit() that acquires the lock after
        // this point returns without touching them.
        std::unique_lock lk(lifecycle_mx_);
        workers_.clear();
        queues_.clear();
    }
@@ -99,22 +86,6 @@ public:
    }
    void submit(std::function<void()> task, float priority = 0.5f) override {
        // A submission can arrive after this pool has been stopped, and did so
        // by an ordinary route: a node's space callback fires from whichever
        // thread drained the channel, which belongs to the *consumer*. Stop the
        // producer first — as a sources-first shutdown does — and the consumer
        // keeps draining its backlog, firing the producer's space callback into
        // a pool whose stop() has already run queues_.clear(). submit() then
        // indexed an empty vector: a segfault, reproducible about 12 runs in 20.
        //
        // The shared lock is what makes the check meaningful. Reading stopped_
        // alone leaves the window between the read and the indexing, which is
        // precisely where stop() clears the vector.
        std::shared_lock lk(lifecycle_mx_);
        if (stopped_.load(std::memory_order_acquire) || queues_.empty()) {
            rejected_.fetch_add(1, std::memory_order_relaxed);
            return;
        }
        std::size_t target = next_.fetch_add(1, std::memory_order_relaxed) % thread_count_;
        {
            std::lock_guard lock(queues_[target]->mx);
@@ -122,7 +93,6 @@ public:
                {std::move(task), priority, seq_.fetch_add(1, std::memory_order_relaxed)});
        }
        total_.fetch_add(1, std::memory_order_relaxed);
        queued_.fetch_add(1, std::memory_order_relaxed);
        submitted_.fetch_add(1, std::memory_order_relaxed);
        // Synchronize with worker_loop's predicate evaluation: taking cv_mx_
        // here guarantees a worker is either before its predicate check (and
@@ -135,16 +105,14 @@ public:
    std::size_t thread_count() const { return thread_count_; }
    /// Submissions dropped because the pool was stopped. See rejected_.
    uint64_t rejected() const { return rejected_.load(std::memory_order_relaxed); }
    // ── IPoolProbe ────────────────────────────────────────────────────────────
    PoolSnapshot snapshot(const std::string& name) const override {
        std::size_t a = active_.load(std::memory_order_relaxed);
        std::size_t t = total_.load(std::memory_order_relaxed);
        return {
            name, thread_count_,
-            queued_.load(std::memory_order_relaxed),   // queued (exact)
+            t > a ? t - a : 0,   // queued (approximate)
            a,                    // executing
            submitted_.load(std::memory_order_relaxed),
            completed_.load(std::memory_order_relaxed),
@@ -174,7 +142,6 @@ private:
        if (q.pq.empty()) return std::nullopt;
        auto fn = std::move(const_cast<Task&>(q.pq.top()).fn);
        q.pq.pop();
        queued_.fetch_sub(1, std::memory_order_relaxed);
        return fn;
    }
@@ -215,13 +182,10 @@ private:
            std::unique_lock lock(cv_mx_);
            cv_.wait(lock, [this] {
                return stopped_.load(std::memory_order_seq_cst)
-                    || queued_.load(std::memory_order_relaxed) > 0;
+                    || total_.load(std::memory_order_relaxed) > 0;
            });
            // Exit on queued_, not total_: waiting for total_ to reach zero
            // meant waiting for someone else's task to finish, which this
            // worker cannot help with and would spin through until it did.
            if (stopped_.load(std::memory_order_seq_cst)
-                && queued_.load(std::memory_order_relaxed) == 0)
+                && total_.load(std::memory_order_relaxed) == 0)
                return;
        }
    }
@@ -230,36 +194,17 @@ private:
    std::vector<std::unique_ptr<WorkerQueue>>  queues_;
    std::vector<std::thread>                   workers_;
    /// Guards the lifetime of queues_/workers_ against a concurrent submit().
    /// Shared by submit, exclusive by stop, so submissions still run in
    /// parallel with each other.
    mutable std::shared_mutex lifecycle_mx_;
    std::mutex              cv_mx_;
    std::condition_variable cv_;
    std::mutex              drain_mx_;
    std::condition_variable drain_cv_;
    std::atomic<bool>     stopped_{true};
-    std::atomic<size_t>   total_{0};      // queued + executing (drain() waits on this)
+    std::atomic<size_t>   total_{0};      // queued + executing
    /// Queued only — never counts a task that is already executing.
    ///
    /// The wait predicate used total_, which includes running tasks, so while
    /// any one task ran every *other* worker's predicate was true: wait()
    /// returned instantly and the worker spun through try_pop / try_steal /
    /// wait at full speed, try_lock-ing every peer queue on each pass. One slow
    /// task therefore pinned every other core and contended the very mutexes
    /// the working thread needed. Sleeping requires "no work is *waiting*",
    /// which is this.
    std::atomic<size_t>   queued_{0};     // waiting to run
    std::atomic<size_t>   active_{0};     // executing only (for snapshot)
    std::atomic<size_t>   next_{0};       // round-robin submit cursor
    std::atomic<uint64_t> seq_{0};        // tie-break for equal-priority tasks
    std::atomic<uint64_t> submitted_{0};
    /// Submissions refused because the pool was already stopped. Not an error —
    /// teardown races are expected — but silence here would hide a node that
    /// keeps trying to run after its pool is gone.
    std::atomic<uint64_t> rejected_{0};
    std::atomic<uint64_t> completed_{0};
 };
@@ -14,18 +14,6 @@ namespace kpn {
 template<typename T> class Channel; // forward declaration for acquire_balanced
 /// Thrown by a pending acquire() when the resource is closed underneath it.
 ///
 /// acquire() blocks on a condition variable with no timeout and no stop
 /// condition, so a node parked there ignored teardown entirely: the worker
 /// never returned, the pool's join never completed, and shutdown hung on a
 /// resource nobody was going to release. Closing the resource turns that into
 /// an exception the node's normal error path already handles.
 class ResourceClosedError : public std::runtime_error {
 public:
    ResourceClosedError() : std::runtime_error("shared resource closed") {}
 };
 // ── SharedResource ────────────────────────────────────────────────────────────
 //
 // Wraps an exclusive resource (e.g. an ONNX session, a CUDA stream) and
@@ -84,7 +72,6 @@ public:
    template<typename PriorityFn>
    Guard acquire(PriorityFn&& fn) {
        std::unique_lock lock(mutex_);
        if (closed_) throw ResourceClosedError{};
        if (!held_) {
            held_ = true;
            acq_.fetch_add(1, std::memory_order_relaxed);
@@ -96,46 +83,18 @@ public:
        current_waiters_.store(waiters_.size(), std::memory_order_relaxed);
        auto t0 = w.wait_start;
-        // Woken either by release() handing over ownership, or by close()
+        w.cv.wait(lock, [&w] { return w.ready; });
        // giving up on the wait entirely.
        w.cv.wait(lock, [&w] { return w.ready || w.closed; });
        int64_t wait_us = std::chrono::duration_cast<std::chrono::microseconds>(
            clock_t::now() - t0).count();
        waiters_.erase(std::find(waiters_.begin(), waiters_.end(), &w));
        current_waiters_.store(waiters_.size(), std::memory_order_relaxed);
        acq_.fetch_add(1, std::memory_order_relaxed);
        total_wait_us_.fetch_add(static_cast<uint64_t>(wait_us > 0 ? wait_us : 0),
                                 std::memory_order_relaxed);
        // Closed without being handed ownership: no Guard, so nothing to
        // release, and held_ is left exactly as close() found it.
        if (!w.ready) throw ResourceClosedError{};
        acq_.fetch_add(1, std::memory_order_relaxed);
        return Guard(this);
    }
    /// Wake every waiter and refuse further acquisitions.
    ///
    /// Teardown is the whole point: a node parked in acquire() is not
    /// observing stop flags, so without this the only way out is for whoever
    /// holds the resource to release it — which, if that node is also being
    /// stopped, may never happen. Idempotent, and safe to call from any thread.
    void close() override {
        std::lock_guard lock(mutex_);
        closed_ = true;
        for (Waiter* w : waiters_) {
            w->closed = true;
            w->cv.notify_one();
        }
    }
    /// Reopen after a close(). For reuse across runs; not needed for teardown.
    void reopen() {
        std::lock_guard lock(mutex_);
        closed_ = false;
    }
    // Acquire with no priority (all waiters treated equally, order is fair-ish).
    Guard acquire() {
        return acquire([] { return 0.5f; });
@@ -173,10 +132,7 @@ public:
 private:
    void release() {
        std::unique_lock lock(mutex_);
-        // Hand over only to a waiter that is still waiting. A closed one is on
+        if (waiters_.empty()) {
        // its way out and will not take ownership, so treating it as the next
        // holder would leave held_ true with nobody holding it.
        if (closed_ || waiters_.empty()) {
            held_ = false;
            return;
        }
@@ -206,8 +162,7 @@ private:
        std::function<float()>  priority_fn;
        clock_t::time_point     wait_start;
        std::condition_variable cv;
-        bool                    ready{false};   // handed ownership by release()
+        bool                    ready{false};
        bool                    closed{false};  // woken by close() instead
        Waiter(std::function<float()> fn, clock_t::time_point t)
            : priority_fn(std::move(fn)), wait_start(t) {}
@@ -217,7 +172,6 @@ private:
    T                        resource_;
    bool                     held_{false};
    bool                     closed_{false};
    mutable std::mutex       mutex_;
    std::vector<Waiter*>     waiters_;
    std::atomic<uint64_t>    acq_{0};
@@ -98,15 +98,13 @@ public:
                  std::vector<INode*>        fanout_ptrs,
                  std::vector<std::string>   user_node_names,
                  std::vector<std::string>   fanout_node_names,
-                  std::vector<std::unique_ptr<IChannelProbe>> channel_probes,
+                  std::vector<std::unique_ptr<IChannelProbe>> channel_probes)
                  std::vector<std::string>   channel_src_names)
        : fanouts_(std::move(fanouts))
        , user_nodes_topo_(std::move(user_nodes_topo))
        , fanout_nodes_ptr_(std::move(fanout_ptrs))
        , user_node_names_(std::move(user_node_names))
        , fanout_node_names_(std::move(fanout_node_names))
        , channel_probes_(std::move(channel_probes))
        , channel_src_names_(std::move(channel_src_names))
    {}
    ~StaticNetwork() override { stop(); }
@@ -124,19 +122,6 @@ public:
                    [this, n](auto ts) { event_handler_(n, NodeEvent::Closed, ts); });
            }
        }
        if (error_handler_) {
            for (auto* node : user_nodes_topo_)
                node->set_network_error_callback(error_handler_);
        }
        // Install every node's channel callbacks before starting any of them.
        // Those callbacks are std::function members on channels shared with
        // neighbours; a neighbour that is already running reads them from its
        // own thread, so writing one after the pipeline is live is a data race
        // (ThreadSanitizer reports it on any multi-node network). Doing all the
        // writes here, while nothing runs, makes them read-only thereafter.
        for (auto* n : user_nodes_topo_)  n->prepare();
        for (auto* n : fanout_nodes_ptr_) n->prepare();
        for (auto* n : user_nodes_topo_)  n->start();
        for (auto* n : fanout_nodes_ptr_) n->start();
 #ifdef KPN_WEB_DEBUG
@@ -160,11 +145,6 @@ public:
 #ifdef KPN_WEB_DEBUG
        if (web_server_) web_server_->stop();
 #endif
        // Release anything parked on a shared resource first. A node blocked in
        // acquire() is not watching stop flags, so stopping it would wait on a
        // handover that may never come — its holder is being stopped too.
        for (auto& [rname, probe] : resource_probes_) { (void)rname; probe->close(); }
        for (auto it = fanout_nodes_ptr_.rbegin(); it != fanout_nodes_ptr_.rend(); ++it)
            (*it)->stop();
        for (auto it = user_nodes_topo_.rbegin(); it != user_nodes_topo_.rend(); ++it)
@@ -178,12 +158,11 @@ public:
 #ifdef KPN_WEB_DEBUG
        if (web_server_) web_server_->stop();
 #endif
        for (auto& [rname, probe] : resource_probes_) { (void)rname; probe->close(); }
        // user_nodes_topo_ is already in sources-first order.
        // Stop each node and drain its output channels before moving on.
-        for (std::size_t i = 0; i < user_nodes_topo_.size(); ++i) {
+        for (auto* n : user_nodes_topo_) {
-            user_nodes_topo_[i]->stop();
+            n->stop();
-            drain_outputs_of(user_node_names_[i]);
+            drain_all_channels();
        }
        for (auto* n : fanout_nodes_ptr_) n->stop();
    }
@@ -202,18 +181,6 @@ public:
    void set_event_handler(EventHandler h) { event_handler_ = std::move(h); }
    /// How long shutdown() waits for one node's outputs to drain before giving
    /// up on them and stopping the next layer anyway.
    void set_drain_timeout(std::chrono::milliseconds t) { drain_timeout_ = t; }
    /// Application-level error listener. Receives the exception any node's
    /// function throws, after that node's own handler (if any) declined it.
    /// Return true to skip the failed invocation and keep the node running,
    /// false to let it stop. Without a listener the exception is discarded
    /// and only a Closed event survives, which reports that a node stopped
    /// but not why.
    void set_error_handler(NodeErrorHandler h) { error_handler_ = std::move(h); }
 #ifdef KPN_WEB_DEBUG
    void set_web_debug_port(uint16_t port) { web_debug_port_ = port; }
    // Called by DebugHub::register_network() so the hub owns the debug server.
@@ -252,6 +219,24 @@ public:
    FanoutStorage& fanouts_storage() { return *fanouts_; }
    // Make every node in this network push losslessly (block until the consumer
    // drains) instead of dropping on a full channel.  Includes the fanout nodes
    // make_network() inserts automatically, which is the part user code cannot
    // reach: they are unnamed, and they drop silently per-output, so a network
    // whose own nodes are all lossless can still lose items at a fanout.
    //
    // Only safe when every consumer eventually drains.  A branch that can stall
    // indefinitely — a display node nobody is servicing, say — will block the
    // whole pipeline through backpressure.  Call before start().
    void set_lossless(bool on = true) {
        for (auto* n : user_nodes_topo_)  if (n) n->set_lossless_output(on);
        for (auto* n : fanout_nodes_ptr_) if (n) n->set_lossless_output(on);
    }
    // Block until every channel is empty.  Useful before stop() so work already
    // in flight completes rather than being discarded at teardown.
    void drain() const { drain_all_channels(); }
 private:
    struct Snapshots {
        std::vector<NodeSnapshot>     nodes;
@@ -286,50 +271,16 @@ private:
        return {std::move(nodes), std::move(channels), std::move(resources), std::move(pools), elapsed_s};
    }
-    /// Wait for the channels fed by `src` to empty, or give up.
+    void drain_all_channels() const {
-    ///
+        bool any_full = true;
-    /// This was an unbounded `while (anything anywhere is non-empty)` poll over
+        while (any_full) {
-    /// *every* channel in the graph, which made shutdown() wait for the whole
+            any_full = false;
-    /// network to be idle before stopping each successive layer, and wait
+            for (auto& probe : channel_probes_) {
-    /// forever if anything downstream was wedged — turning a graceful shutdown
+                if (probe->snapshot().current_fill > 0) { any_full = true; break; }
-    /// into the hang it exists to avoid.
+            }
-    ///
+            if (any_full)
    /// Two bounds, because they fail differently. The deadline covers a
    /// consumer that has stopped consuming: fill never changes and no amount of
    /// waiting helps. The no-progress counter covers a consumer that is merely
    /// slow — it keeps waiting as long as the queue is shrinking, so a slow
    /// drain is not cut short just for exceeding a fixed time.
    ///
    /// Giving up is reported rather than silent: undrained data at this point
    /// means values are about to be discarded by the stop that follows.
    void drain_outputs_of(const std::string& src) const {
        const auto deadline = clock_t::now() + drain_timeout_;
        std::size_t last_fill = static_cast<std::size_t>(-1);
        int         stalls    = 0;
        for (;;) {
            std::size_t fill = 0;
            for (std::size_t i = 0; i < channel_probes_.size(); ++i)
                if (channel_src_names_[i] == src)
                    fill += channel_probes_[i]->snapshot().current_fill;
            if (fill == 0) return;
            if (fill >= last_fill) { if (++stalls > 100) break; }
            else                   { stalls = 0; }
            last_fill = fill;
            if (clock_t::now() >= deadline) break;
                std::this_thread::sleep_for(std::chrono::milliseconds(1));
        }
        std::size_t left = 0;
        for (std::size_t i = 0; i < channel_probes_.size(); ++i)
            if (channel_src_names_[i] == src)
                left += channel_probes_[i]->snapshot().current_fill;
        if (left)
            std::cerr << "[kpn] shutdown: '" << src << "' still has " << left
                      << " queued item(s) its consumer did not take; "
                         "they are discarded\n";
    }
    std::string                                         name_;
@@ -340,14 +291,9 @@ private:
    std::vector<std::string>                            user_node_names_;
    std::vector<std::string>                            fanout_node_names_;
    std::vector<std::unique_ptr<IChannelProbe>>         channel_probes_;
    /// Display name of the node feeding each probe, parallel to channel_probes_.
    /// shutdown() drains a node's own outputs, so it has to know which they are.
    std::vector<std::string>                            channel_src_names_;
    std::chrono::milliseconds                           drain_timeout_{5000};
    std::vector<std::pair<std::string, IResourceProbe*>> resource_probes_;
    std::vector<std::pair<std::string, IPoolProbe*>>     pool_probes_;
    EventHandler                                        event_handler_;
    NodeErrorHandler                                    error_handler_;
    clock_t::time_point                                 start_time_;
 #ifdef KPN_WEB_DEBUG
    uint16_t                                            web_debug_port_{9090};
@@ -380,6 +326,29 @@ auto make_network(Edges&&... edges) {
    // 4. Construct owned fanout storage on the heap (FanoutNode has jthread — not moveable)
    auto fanout_storage = std::make_unique<FanoutSto>();
    // 5. Collect unique user node pointers + their display names, in edge-declaration order
    std::vector<INode*>      user_node_ptrs;
    std::vector<std::string> user_node_names;
    auto collect = [&](auto& e) {
        using SrcT = std::decay_t<decltype(e.src)>;
        using DstT = std::decay_t<decltype(e.dst)>;
        auto* s = static_cast<INode*>(&e.src);
        auto* d = static_cast<INode*>(&e.dst);
        if (std::find(user_node_ptrs.begin(), user_node_ptrs.end(), s) == user_node_ptrs.end()) {
            auto sname = node_display_name<SrcT>();
            user_node_ptrs.push_back(s);
            user_node_names.push_back(sname);
            s->set_name(sname);
        }
        if (std::find(user_node_ptrs.begin(), user_node_ptrs.end(), d) == user_node_ptrs.end()) {
            auto dname = node_display_name<DstT>();
            user_node_ptrs.push_back(d);
            user_node_names.push_back(dname);
            d->set_name(dname);
        }
    };
    (collect(edges), ...);
    // 5. Wire all expanded SimpleEdges.
    //    find_node<NodeT>: searches fanout storage then user edge pack, returns NodeT*.
    //    Uses if constexpr in a fold so mismatched types never reach assignment.
@@ -404,38 +373,6 @@ auto make_network(Edges&&... edges) {
        return ptr;
    };
    // 5. Collect user node pointers + display names in *topological* order.
    //
    // Topo is computed above for the cycle check and used to be discarded,
    // while this vector was filled in edge-declaration order — and then named
    // user_nodes_topo_ and relied upon as if it were sorted. halt() stops in
    // its reverse, and shutdown() walks it forwards stopping each node and
    // draining its outputs before the next, which is only a graceful drain if
    // the order really is sources-first. It held for every network in the tree
    // because edges happen to be declared in pipeline order, and would have
    // broken silently for one that was not.
    //
    // Fanout nodes appear in Topo too; they are skipped here because they are
    // owned separately, in fanout_storage.
    std::vector<INode*>      user_node_ptrs;
    std::vector<std::string> user_node_names;
    [&]<typename... Ns>(tmp::TypeList<Ns...>) {
        ([&]<typename NodeT>() {
            if constexpr (!requires { NodeT::is_fanout_node; }) {
                if (auto* p = find_node.template operator()<NodeT>()) {
                    auto* n = static_cast<INode*>(p);
                    if (std::find(user_node_ptrs.begin(), user_node_ptrs.end(), n)
                            == user_node_ptrs.end()) {
                        auto nm = node_display_name<NodeT>();
                        user_node_ptrs.push_back(n);
                        user_node_names.push_back(nm);
                        n->set_name(nm);
                    }
                }
            }
        }.template operator()<Ns>(), ...);
    }(typename Topo::topo{});
    // Pre-pass: build fanout_id → source display name map so fanout nodes
    // can be named after the node feeding them (e.g. "capture_fanout").
    std::map<std::size_t, std::string> fanout_src_name;
@@ -460,7 +397,6 @@ auto make_network(Edges&&... edges) {
    };
    std::vector<std::unique_ptr<IChannelProbe>> channel_probes;
    std::vector<std::string>                    channel_src_names;
    auto wire_one = [&]<typename SE>(SE) {
        using SrcNode = typename SE::src_node_t;
@@ -478,7 +414,6 @@ auto make_network(Edges&&... edges) {
                                + " \xe2\x86\x92 "  // UTF-8 →
                                + node_name.template operator()<DstNode>() + ":" + std::to_string(DstIdx);
            channel_probes.push_back(std::make_unique<ChannelProbe<out_t>>(ch, ch_name));
            channel_src_names.push_back(node_name.template operator()<SrcNode>());
        }
    };
@@ -506,8 +441,7 @@ auto make_network(Edges&&... edges) {
               std::move(fanout_ptrs),
               std::move(user_node_names),
               std::move(fanout_node_names),
-               std::move(channel_probes),
+               std::move(channel_probes));
               std::move(channel_src_names));
 }
 } // namespace kpn
@@ -1,101 +0,0 @@
 #pragma once
 #include <atomic>
 namespace kpn {
 // ── SubmitGate ────────────────────────────────────────────────────────────────
 //
 // Decides, for one node, whether a wake must turn into a scheduler submission.
 // Exactly one firing of a node may be in flight at a time, and a wake that
 // arrives while one is already in flight must not be lost — it has to be
 // honoured when that firing finishes, or the node sleeps holding work.
 //
 // 9c5ce5f wrote this as two independent atomics: queued_ said a firing was in
 // flight, wake_pending_ recorded a wake that arrived during one. That cannot be
 // made correct, because the release side has to read and write both, and a wake
 // can land between the two operations:
 //
 //   producer (try_submit)              worker (release_and_recheck)
 //   ------------------------           ----------------------------
 //   CAS reads queued_ == true, fails
 //                                      queued_.store(false)
 //                                      wake_pending_.exchange(false) -> false
 //   wake_pending_.store(true)
 //
 // End state: queued_ false, wake_pending_ true, nothing running and nothing
 // scheduled. The node sleeps with a wake outstanding, which is precisely the
 // invariant that commit set out to establish. It is not a memory-ordering
 // subtlety — the interleaving above holds under seq_cst.
 //
 // It survived because every caller happened to follow release_and_recheck()
 // with a level re-check (on_input_ready(), or outputs_have_space() on the
 // parked path), which rediscovers the state a lost wake would have signalled.
 // That is a property of the call sites, not of the mechanism, and any new early
 // return that forgets the re-check turns it back into a hang.
 //
 // One atomic with three states makes the race unrepresentable: "idle" and "wake
 // outstanding" are the same variable, so no interleaving can produce both.
 //
 //   Idle       nothing in flight
 //   Queued     a firing is in flight or queued; no wake since it was claimed
 //   QueuedWake a firing is in flight or queued, and a wake arrived meanwhile
 //
 class SubmitGate {
 public:
    /// Register a wake. Returns true when the caller must submit the node;
    /// false when a firing is already in flight and the wake has been recorded
    /// against it instead.
    bool claim() noexcept {
        int cur = state_.load(std::memory_order_acquire);
        for (;;) {
            if (cur == kIdle) {
                if (state_.compare_exchange_weak(cur, kQueued,
                        std::memory_order_acq_rel, std::memory_order_acquire))
                    return true;
            } else if (cur == kQueued) {
                if (state_.compare_exchange_weak(cur, kQueuedWake,
                        std::memory_order_acq_rel, std::memory_order_acquire))
                    return false;
            } else {
                return false;            // a wake is already recorded
            }
        }
    }
    /// End the in-flight firing. Returns true when a wake arrived during it and
    /// the caller must submit again — in which case the gate stays claimed, so
    /// the node is handed straight from one firing to the next and is never
    /// momentarily idle with work outstanding. Returns false when the node is
    /// now idle.
    bool release() noexcept {
        int cur = state_.load(std::memory_order_acquire);
        for (;;) {
            if (cur == kQueuedWake) {
                if (state_.compare_exchange_weak(cur, kQueued,
                        std::memory_order_acq_rel, std::memory_order_acquire))
                    return true;
            } else {
                // kQueued, or kIdle if a stop already forced the gate down.
                if (state_.compare_exchange_weak(cur, kIdle,
                        std::memory_order_acq_rel, std::memory_order_acquire))
                    return false;
            }
        }
    }
    /// Drop the claim and any recorded wake. For stop paths only: honouring a
    /// wake there would resubmit a dead node.
    void force_idle() noexcept { state_.store(kIdle, std::memory_order_release); }
    bool queued()       const noexcept { return state_.load(std::memory_order_relaxed) != kIdle; }
    bool wake_pending() const noexcept { return state_.load(std::memory_order_relaxed) == kQueuedWake; }
 private:
    static constexpr int kIdle       = 0;
    static constexpr int kQueued     = 1;
    static constexpr int kQueuedWake = 2;
    std::atomic<int> state_{kIdle};
 };
 } // namespace kpn
@@ -97,41 +97,4 @@ struct repeat_tuple<T, N, std::index_sequence<Is...>> {
 template<typename T, std::size_t N>
 using repeat_tuple_t = typename repeat_tuple<T, N>::type;
 // ── Sentinel detection ────────────────────────────────────────────────────────
 // A value is a "sentinel" (must-deliver control token, e.g. EOF) if its type
 // carries a bool-convertible eof flag — either directly (`v.eof`, as on a raw
 // source Frame) or nested one level under a `.source` member (`v.source.eof`,
 // as on message types that wrap the originating Frame). Sentinels are delivered
 // losslessly and non-blockingly via Channel::push_sentinel() instead of the
 // throwing push(), so backpressure can never drop the token that unblocks
 // downstream teardown.
 //
 // Types with neither shape are never treated as sentinels — both traits are
 // SFINAE-safe and the runtime check compiles away to `false` for them, so this
 // stays a no-op for pipelines that don't use an eof convention.
 //
 // Lives here rather than in pool_node.hpp because every node type that forwards
 // values needs it, not just the pool-scheduled ones. FilterNode and RouterNode
 // not having it is what let an EOF token be dropped on a full output.
 template<typename T, typename = void>
 struct has_eof_field : std::false_type {};
 template<typename T>
 struct has_eof_field<T, std::void_t<decltype(static_cast<bool>(std::declval<const T&>().eof))>>
    : std::true_type {};
 template<typename T, typename = void>
 struct has_source_eof_field : std::false_type {};
 template<typename T>
 struct has_source_eof_field<T,
    std::void_t<decltype(static_cast<bool>(std::declval<const T&>().source.eof))>>
    : std::true_type {};
 template<typename T>
 constexpr bool is_sentinel_value(const T& v) {
    if constexpr (has_eof_field<T>::value)             return static_cast<bool>(v.eof);
    else if constexpr (has_source_eof_field<T>::value) return static_cast<bool>(v.source.eof);
    else                                               return false;
 }
 } // namespace kpn
@@ -162,7 +162,6 @@ public:
    // ── INode ─────────────────────────────────────────────────────────────────
    void prepare() override { node_.prepare(); }
    void start() override { node_.start(); }
    void stop()  override { node_.stop(); }
    bool running() const override { return node_.running(); }
@@ -65,11 +65,6 @@ static std::string to_json(const std::vector<NodeSnapshot>& nodes,
          << ",\"fps\":"          << n.throughput_fps
          << ",\"total_cpu_ms\":" << n.total_cpu_ms
          << ",\"cpu_util_pct\":" << n.cpu_util_pct
          // Scheduling state — lets a WEDGED pipeline be interrogated over HTTP
          // without a debugger, which matters because the lost-wake bug does not
          // reproduce under one. See NodeSnapshot for how to read the pair.
          << ",\"queued\":"       << (n.queued ? "true" : "false")
          << ",\"wake_pending\":" << (n.wake_pending ? "true" : "false")
          << "}";
    }
    o << "],\"edges\":[";
@@ -34,9 +34,7 @@ add_executable(kpn_tests
    test_static_network.cpp
    test_shared_resource.cpp
    test_pool_node.cpp
    test_backpressure_deadlock.cpp
    test_scheduler.cpp
    test_submit_gate.cpp
 )
 target_link_libraries(kpn_tests PRIVATE
@@ -1,421 +0,0 @@
 // Regression: a blocking push must not park a pool worker.
 //
 // Node outputs use push_blocking so a full channel costs time rather than data
 // (a dropped frame does not degrade a downstream result, it silently changes
 // one). But push_blocking sleeps *inside* fire_once, which runs on a pool
 // worker — and nodes are pinned to workers by index. Park enough workers in
 // that retry loop and there is nobody left to run the consumer that would drain
 // the channel, so the whole chain wedges.
 //
 // This is the failure channel.hpp:174 already warns about for sentinels
 // ("a blocking push would park that thread and stop it draining its own input,
 // cascading into a hold-and-wait deadlock under backpressure"). The warning
 // applies to data pushes too.
 //
 // Observed in the field as an intermittent hang: frame_source, camera_pos,
 // face_detector and face_aligner all asleep in push_blocking at once.
 #include <catch2/catch_test_macros.hpp>
 #include <kpn/kpn.hpp>
 #include <atomic>
 #include <chrono>
 #include <thread>
 namespace {
 struct Produce {
    static constexpr std::string_view label() { return "produce"; }
    int n{0};
    int operator()() { return n++; }
 };
 struct Relay {
    static constexpr std::string_view label() { return "relay"; }
    int operator()(int v) { return v; }
 };
 // Deliberately slower than the producer, so the channels between them fill.
 struct SlowSink {
    static constexpr std::string_view label() { return "slow_sink"; }
    std::atomic<int>* seen;
    void operator()(int) {
        std::this_thread::sleep_for(std::chrono::milliseconds(2));
        seen->fetch_add(1, std::memory_order_relaxed);
    }
 };
 }  // namespace
 TEST_CASE("a saturated chain keeps draining", "[backpressure][deadlock]") {
    std::atomic<int> seen{0};
    Produce  p_fn;
    Relay    r1_fn, r2_fn, r3_fn;
    SlowSink s_fn{&seen};
    // Small channels so they saturate immediately, and a chain longer than a
    // modest pool — the shape that starves workers.
    kpn::ObjectNode<Produce,  kpn::in<>,        kpn::out<"a">, "produce",   0> p (p_fn,  2);
    kpn::ObjectNode<Relay,    kpn::in<"a">,     kpn::out<"b">, "relay1",    0> r1(r1_fn, 2);
    kpn::ObjectNode<Relay,    kpn::in<"b">,     kpn::out<"c">, "relay2",    0> r2(r2_fn, 2);
    kpn::ObjectNode<Relay,    kpn::in<"c">,     kpn::out<"d">, "relay3",    0> r3(r3_fn, 2);
    kpn::ObjectNode<SlowSink, kpn::in<"d">,     kpn::out<>,    "slow_sink", 0> s (s_fn,  2);
    auto net = kpn::make_network(
        kpn::edge(p.output<"a">(),  r1.input<"a">()),
        kpn::edge(r1.output<"b">(), r2.input<"b">()),
        kpn::edge(r2.output<"c">(), r3.input<"c">()),
        kpn::edge(r3.output<"d">(), s.input<"d">())
    );
    net.start();
    // The sink is the slowest stage at 2 ms/item, so 40 items is ~80 ms of real
    // work. Anything approaching the timeout means the chain stopped draining
    // rather than merely running slowly.
    const auto deadline = std::chrono::steady_clock::now() + std::chrono::seconds(20);
    while (seen.load(std::memory_order_relaxed) < 40 &&
           std::chrono::steady_clock::now() < deadline)
        std::this_thread::sleep_for(std::chrono::milliseconds(5));
    const int got = seen.load(std::memory_order_relaxed);
    net.stop();
    INFO("items drained: " << got << " of 40");
    CHECK(got >= 40);
 }
 // Regression: a saturated chain must never stall.
 //
 // push_outputs parks from two places: the retry at the top of fire_once, and
 // the ordinary push after the node function returns. Both release the worker,
 // so both face the same lost wakeup — a space callback firing while queued_ is
 // still up is swallowed by try_submit's CAS. Only the retry path re-checked for
 // space afterwards. The normal path fell through to on_input_ready(), which
 // resubmits only if inputs are ready — and the firing that just parked had
 // consumed its input, so they are not.
 //
 // The strand is permanent under saturation: the node holds its value, its
 // consumer waits for exactly that value, and its producer fills the node's
 // input channel and parks too. Nothing moves again.
 //
 // The test above cannot catch it — 40 items drain before any strand occurs.
 // This one runs the chain saturated and watches for progress to *freeze*, which
 // is the signature of the deadlock. It deliberately does not assert a total:
 // capacity-1 channels are slow, and "slow" must never be reported as "wedged".
 namespace {
 struct FreeRun {
    static constexpr std::string_view label() { return "free_run"; }
    int n{0};
    int operator()() { return n++; }
 };
 struct CountingSink {
    static constexpr std::string_view label() { return "counting_sink"; }
    std::atomic<int>* seen;
    void operator()(int) { seen->fetch_add(1, std::memory_order_relaxed); }
 };
 }  // namespace
 TEST_CASE("a saturated chain never stalls", "[backpressure][deadlock]") {
    std::atomic<int> seen{0};
    FreeRun      p_fn;
    Relay        r1_fn, r2_fn;
    CountingSink s_fn{&seen};
    // Capacity 1 everywhere: every push contends, so the park path is taken
    // constantly and the race window is sampled millions of times.
    kpn::ObjectNode<FreeRun,      kpn::in<>,     kpn::out<"a">, "free_run", 0> p (p_fn,  1);
    kpn::ObjectNode<Relay,        kpn::in<"a">,  kpn::out<"b">, "relay1",   0> r1(r1_fn, 1);
    kpn::ObjectNode<Relay,        kpn::in<"b">,  kpn::out<"c">, "relay2",   0> r2(r2_fn, 1);
    kpn::ObjectNode<CountingSink, kpn::in<"c">,  kpn::out<>,    "sink",     0> s (s_fn,  1);
    auto net = kpn::make_network(
        kpn::edge(p.output<"a">(),  r1.input<"a">()),
        kpn::edge(r1.output<"b">(), r2.input<"b">()),
        kpn::edge(r2.output<"c">(), s.input<"c">())
    );
    net.start();
    // A live chain moves thousands of items a second, so 3 s with no movement
    // at all is a wedge, not a slow patch. Sampling for 25 s gives the race
    // ample opportunity: the pipeline hit it roughly twice in 30 runs.
    const auto  giveup    = std::chrono::steady_clock::now() + std::chrono::seconds(25);
    int         last      = 0;
    auto        last_move = std::chrono::steady_clock::now();
    bool        stalled   = false;
    int         stall_at  = 0;
    while (std::chrono::steady_clock::now() < giveup) {
        std::this_thread::sleep_for(std::chrono::milliseconds(100));
        const int now_seen = seen.load(std::memory_order_relaxed);
        if (now_seen != last) {
            last      = now_seen;
            last_move = std::chrono::steady_clock::now();
        } else if (std::chrono::steady_clock::now() - last_move >
                   std::chrono::seconds(3)) {
            stalled  = true;
            stall_at = now_seen;
            break;
        }
    }
    net.stop();
    INFO("chain stalled after " << stall_at << " items");
    CHECK_FALSE(stalled);
    // Guard against the test passing because nothing ever ran.
    CHECK(last > 1000);
 }
 // Regression: a node must not start with a wake already outstanding.
 //
 // 9c5ce5f established the invariant for the running pipeline — a node never
 // sleeps with a wake it dropped. start() broke the same invariant before the
 // pipeline was even running:
 //
 //     enable_inputs(...);          // channel goes live here
 //     stop_flag_.store(false);
 //     queued_.store(false);
 //     register_callbacks(...);     // push callback installed here
 //
 // StaticNetwork starts nodes sources-first, so an upstream node is already
 // firing into this one during that gap. A push landing there is accepted by the
 // ring but wakes nobody: Channel::push invokes push_callback_ only on the
 // empty→non-empty transition, and at that instant the callback is null. Every
 // later push sees a non-empty ring and stays silent. The node is never
 // submitted, and since a sink has no outputs there is no space callback to
 // rescue it either.
 //
 // The signature is distinctive: **zero** items delivered, not a stall partway.
 // The chain reads as wedged from the first frame. Under `ctest -j4` on a loaded
 // machine it reproduced 7 times in 24, and never once in 10 unloaded runs —
 // contention widens the window between those two statements. That is almost
 // certainly the "rare hang, ~1 run in 20 at a 300 s timeout" 28e0667 recorded as
 // known-incomplete.
 //
 // This test needs no contention: it constructs the state the race leaves behind
 // directly, by enabling the input and pushing before start() is ever called.
 namespace {
 int passthrough(int x) { return x; }
 }  // namespace
 TEST_CASE("a node started with data already queued still fires",
          "[backpressure][startup]") {
    auto pool = std::make_shared<kpn::ThreadPool>(2);
    pool->start();
    auto node = kpn::make_pool_node<passthrough>(pool, 8);
    kpn::Channel<int> out_ch(8);
    node.set_output_channel<0>(&out_ch);
    // The missed edge: the channel is live and already holds a value, but no
    // callback was installed when it arrived, so the wake has been and gone.
    node.input_channel<0>().enable();
    node.input_channel<0>().push(21);
    node.start();
    // Bounded wait — a plain pop() would hang rather than fail on a regression.
    const auto deadline = std::chrono::steady_clock::now() + std::chrono::seconds(5);
    while (out_ch.size() == 0 && std::chrono::steady_clock::now() < deadline)
        std::this_thread::sleep_for(std::chrono::milliseconds(5));
    const bool delivered = out_ch.size() > 0;
    const int  got       = delivered ? out_ch.pop() : -1;
    node.stop();
    pool->stop();
    INFO("value delivered: " << got);
    REQUIRE(delivered);
    CHECK(got == 21);
 }
 // Regression: a fanout absorbs an unequal pair of consumers by slowing, not by
 // dropping.
 //
 // 6595e6e made node outputs lossless and 28e0667 stopped them parking a worker,
 // but FanoutNode was in neither: it kept `catch (ChannelOverflowError&) {}` per
 // output, so whichever branch fell behind lost items — silently, and by an
 // amount that depended on timing. Two runs of the same input could therefore
 // disagree, which is fatal for a fixture the rest of the suite is scored
 // against.
 //
 // The two assertions are the two halves of the requirement:
 //   - no gaps: the slow branch receives *every* item, not most of them;
 //   - bounded lead: the fast branch is throttled to the slow one rather than
 //     racing ahead over a drain that is quietly discarding the difference.
 //
 // Either alone would pass on a broken implementation. A fanout that pushed only
 // to the slow branch has no gaps; one that dropped everything for the slow
 // branch keeps a bounded lead by never letting it fall behind.
 namespace {
 // Records the sequence it sees, so a dropped item shows up as a gap rather than
 // merely as a smaller total.
 struct SeqCheck {
    std::atomic<int>*  next_expected;
    std::atomic<bool>* saw_gap;
    int                delay_us{0};
    void record(int v) const {
        if (delay_us)
            std::this_thread::sleep_for(std::chrono::microseconds(delay_us));
        const int want = next_expected->load(std::memory_order_relaxed);
        if (v != want) saw_gap->store(true, std::memory_order_relaxed);
        else           next_expected->store(want + 1, std::memory_order_relaxed);
    }
 };
 struct FastBranch : SeqCheck {
    static constexpr std::string_view label() { return "fast_branch"; }
    void operator()(int v) { record(v); }
 };
 struct SlowBranch : SeqCheck {
    static constexpr std::string_view label() { return "slow_branch"; }
    void operator()(int v) { record(v); }
 };
 }  // namespace
 TEST_CASE("a fanout absorbs an unequal pair by slowing, not dropping",
          "[backpressure][fanout]") {
    std::atomic<int>  fast_next{0}, slow_next{0};
    std::atomic<bool> fast_gap{false}, slow_gap{false};
    FreeRun    p_fn;
    FastBranch fast_fn{{&fast_next, &fast_gap, 0}};
    SlowBranch slow_fn{{&slow_next, &slow_gap, 500}};   // 0.5 ms/item
    // Small channels so the slow branch saturates in the first few milliseconds
    // and stays saturated for the whole run.
    kpn::ObjectNode<FreeRun,    kpn::in<>,       kpn::out<"v">, "free_run", 0> p (p_fn,    8);
    kpn::ObjectNode<FastBranch, kpn::in<"fast">, kpn::out<>,    "fast",     0> fa(fast_fn, 8);
    kpn::ObjectNode<SlowBranch, kpn::in<"slow">, kpn::out<>,    "slow",     0> sl(slow_fn, 8);
    // Two edges from one output port: make_network auto-inserts FanoutNode<int,2>.
    auto net = kpn::make_network(
        kpn::edge(p.output<"v">(), fa.input<"fast">()),
        kpn::edge(p.output<"v">(), sl.input<"slow">())
    );
    net.start();
    std::this_thread::sleep_for(std::chrono::seconds(1));
    net.stop();
    const int fast_seen = fast_next.load(std::memory_order_relaxed);
    const int slow_seen = slow_next.load(std::memory_order_relaxed);
    INFO("fast branch " << fast_seen << " items, slow branch " << slow_seen);
    CHECK_FALSE(fast_gap.load(std::memory_order_relaxed));
    CHECK_FALSE(slow_gap.load(std::memory_order_relaxed));
    // Guard against passing because nothing ran: 1 s at 0.5 ms/item is ~2000.
    CHECK(slow_seen > 200);
    // The lead is bounded by the buffering between the two — the fanout's own
    // input, the two output channels, and one item in each node's hand. A
    // dropping fanout has no such bound: the fast branch runs at full speed and
    // the difference is the loss.
    CHECK(fast_seen - slow_seen < 200);
 }
 // Regression: a filter must not drop an EOF sentinel into a full output.
 //
 // RouterNode and FilterNode were the last nodes on a data path still using the
 // throwing push() and swallowing the result:
 //
 //     try { out_ch_->push(val); } catch (const ChannelOverflowError&) {}
 //
 // 6595e6e made node outputs lossless, 28e0667 stopped them parking a worker,
 // a8cfe73 did the same for FanoutNode. These two were in none of them.
 //
 // For ordinary values that is the familiar silent-loss problem. For a sentinel
 // it is a hang. EOF is what tells every downstream node to shut down, and
 // nothing comes after it to retry — so a filter that passes EOF by predicate
 // but drops it by backpressure produces a pipeline that never terminates. The
 // scene-actor-extraction decimator is exactly this shape: `if (f.eof) return
 // true;` in the predicate, feeding a chain whose slowest node is an ONNX
 // embedder, so the output is reliably full at the moment EOF arrives.
 //
 // The test forces that state rather than racing for it: the sink is slow enough
 // that the filter's output channel is saturated for the whole run, so EOF meets
 // a full ring with certainty.
 //
 // Both assertions are needed. `saw_eof` alone would pass on an implementation
 // that dropped every ordinary value and delivered only the sentinel; `count`
 // alone would pass on the broken one, which delivers plenty of values and loses
 // only the token that matters.
 namespace {
 struct EofFrame {
    int  seq{0};
    bool eof{false};
 };
 // EOF is emitted exactly once, as a real source does. Everything after it is a
 // filler frame the predicate rejects, which keeps the node alive without
 // re-offering the sentinel — a source that retried EOF would mask the bug,
 // since a later attempt could find the channel drained.
 struct EofSource {
    static constexpr std::string_view label() { return "eof_source"; }
    int  n{0};
    int  total{0};
    EofFrame operator()() {
        if (n > total) {
            std::this_thread::sleep_for(std::chrono::milliseconds(1));
            return {-1, false};          // filler: dropped by the predicate
        }
        EofFrame f{n, n == total};
        ++n;
        return f;
    }
 };
 struct EofSink {
    static constexpr std::string_view label() { return "eof_sink"; }
    std::atomic<int>*  count;
    std::atomic<bool>* saw_eof;
    void operator()(EofFrame f) {
        std::this_thread::sleep_for(std::chrono::microseconds(200));
        if (f.eof) saw_eof->store(true, std::memory_order_release);
        else       count->fetch_add(1, std::memory_order_relaxed);
    }
 };
 }  // namespace
 TEST_CASE("a filter delivers EOF into a saturated output", "[backpressure][filter]") {
    std::atomic<int>  count{0};
    std::atomic<bool> saw_eof{false};
    EofSource src_fn{0, 40};
    EofSink   sink_fn{&count, &saw_eof};
    // Every real frame passes the predicate, so the only thing between source
    // and sink is backpressure. Small channels keep the output saturated.
    auto filt = kpn::make_filter<EofFrame>(
        [](const EofFrame& f) { return f.seq >= 0; }, 4);
    kpn::ObjectNode<EofSource, kpn::in<>,      kpn::out<"f">, "eof_source", 0> s(src_fn,  4);
    kpn::ObjectNode<EofSink,   kpn::in<"f">,   kpn::out<>,    "eof_sink",   0> k(sink_fn, 4);
    auto net = kpn::make_network(
        kpn::edge(s.output<"f">(),      filt.input<0>()),
        kpn::edge(filt.output<0>(),     k.input<"f">())
    );
    net.start();
    // Generous relative to 41 frames at 200 us, and this is a liveness test:
    // the broken implementation never sets saw_eof no matter how long it runs.
    for (int i = 0; i < 200 && !saw_eof.load(std::memory_order_acquire); ++i)
        std::this_thread::sleep_for(std::chrono::milliseconds(10));
    net.stop();
    INFO("values delivered: " << count.load() << " of 40");
    CHECK(saw_eof.load(std::memory_order_acquire));
    CHECK(count.load(std::memory_order_relaxed) == 40);
 }
@@ -1,4 +1,3 @@
 #include <string>
 #include <catch2/catch_test_macros.hpp>
 #include <catch2/catch_approx.hpp>
 #include <kpn/channel.hpp>
@@ -239,87 +238,3 @@ TEST_CASE("try_pop_now delivers a pending sentinel once the ring is empty",
    REQUIRE(out == 99);
    REQUIRE_FALSE(ch.try_pop_now(out));   // nothing left
 }
 // Regression: the sentinel slot holds one token and refuses a second.
 //
 // push_sentinel used to write eof_value_ unconditionally. Offering a second
 // token before the first was taken therefore did two wrong things at once: it
 // lost the first silently — and a lost EOF wedges every downstream pop forever
 // — and it wrote the storage while the consumer could be moving the previous
 // value out of it. For the shared_ptr storage that non-trivial types use, that
 // is a torn refcount, not merely a stale read.
 //
 // Refusing is correct rather than queueing: two control tokens on one channel
 // means the stream ended twice, which is a caller protocol error. Coalescing
 // them would hide it, and there is no second value that could sensibly follow
 // the end of a stream.
 TEST_CASE("a second sentinel is refused, not swallowed", "[channel][sentinel]") {
    Channel<int> ch(4);
    REQUIRE(ch.push_sentinel(1));
    // Slot occupied: the first token is still undelivered.
    REQUIRE_FALSE(ch.push_sentinel(2));
    // The first survives intact — the overwrite is what used to lose it.
    int out = 0;
    REQUIRE(ch.try_pop_now(out));
    CHECK(out == 1);
    // And the slot is reusable once drained.
    REQUIRE(ch.push_sentinel(3));
    REQUIRE(ch.try_pop_now(out));
    CHECK(out == 3);
 }
 TEST_CASE("a refused sentinel is counted as a drop", "[channel][sentinel]") {
    // Visibility matters more here than for a dropped value: the refusal means
    // a control token went nowhere, and the only alternative to a counter is
    // for it to vanish.
    Channel<int> ch(4);
    REQUIRE(ch.push_sentinel(1));
    const auto before = ch.stats().drops.load();
    REQUIRE_FALSE(ch.push_sentinel(2));
    CHECK(ch.stats().drops.load() == before + 1);
 }
 TEST_CASE("try_push_sentinel leaves a refused value untouched", "[channel][sentinel]") {
    // The non-consuming form exists so a refused token is still the caller's to
    // report. The consuming push_sentinel cannot offer that, since the value is
    // already moved into its parameter.
    Channel<std::string> ch(4);
    std::string first = "eof-1", second = "eof-2";
    REQUIRE(ch.try_push_sentinel(first) == Channel<std::string>::SentinelResult::Taken);
    REQUIRE(ch.try_push_sentinel(second) == Channel<std::string>::SentinelResult::SlotBusy);
    CHECK(second == "eof-2");          // not moved from
    ch.disable();
    std::string third = "eof-3";
    CHECK(ch.try_push_sentinel(third) == Channel<std::string>::SentinelResult::Closed);
    CHECK(third == "eof-3");
 }
 // Regression: try_push must distinguish delivered from discarded.
 //
 // It returned bool, and returned *true* for a closed channel — so "the value
 // arrived" and "the value was thrown away because nobody is listening" were the
 // same answer. Every caller was nonetheless correct, because both cases mean
 // "stop trying"; but nothing above the channel could tell the two apart, and a
 // producer counting successful pushes counted discards among them. Only the
 // channel's own drop counter knew, and only if someone read the diagnostics.
 TEST_CASE("try_push distinguishes taken, full and closed", "[channel]") {
    Channel<int> ch(2);
    int v = 1;
    CHECK(ch.try_push(v) == Channel<int>::PushResult::Taken);
    CHECK(ch.try_push(v) == Channel<int>::PushResult::Taken);
    // Ring is full: the value is untouched and the caller keeps it.
    CHECK(ch.try_push(v) == Channel<int>::PushResult::Full);
    CHECK(v == 1);
    ch.disable();
    const auto drops_before = ch.stats().drops.load();
    CHECK(ch.try_push(v) == Channel<int>::PushResult::Closed);
    // Discarded, and recorded as such rather than reported as a delivery.
    CHECK(ch.stats().drops.load() == drops_before + 1);
 }
@@ -19,7 +19,6 @@
 // Channel<T> is SPSC: exactly one producer thread and one consumer thread per
 // channel. Every scenario below honours that contract.
 #include <string>
 #include <catch2/catch_test_macros.hpp>
 #include <atomic>
 #include <chrono>
@@ -280,51 +279,3 @@ TEST_CASE("SPSC: sentinel is strictly last, after every value (try_pop_now)",
        REQUIRE(ch.approx_size() == 0);
    }
 }
 // Contended: a producer offering sentinels while the consumer takes them.
 //
 // The old push_sentinel wrote eof_value_ with no regard for whether the
 // consumer was reading it, so a second offer racing a take was a data race on
 // the storage — for the shared_ptr form used by non-trivial types, on the
 // refcount. Under TSan the old code reports it; the handshake added alongside
 // this test makes the producer's write conditional on observing the slot free,
 // which is what serialises the two.
 //
 // Payload is a std::string so the storage is the shared_ptr path rather than
 // the trivially-copyable one, and each token carries its own identity so a torn
 // value shows up as a mismatch rather than as a plausible-looking result.
 TEST_CASE("SPSC: offering sentinels concurrently with takes is race-free",
          "[channel][stress][sentinel]") {
    constexpr int kRounds = 20000;
    Channel<std::string> ch(4);
    std::atomic<int> taken{0};
    std::atomic<bool> torn{false};
    std::atomic<bool> done{false};
    std::thread consumer([&] {
        std::string out;
        while (!done.load(std::memory_order_acquire) || ch.approx_size() > 0) {
            if (ch.try_pop_now(out)) {
                if (out.rfind("eof-", 0) != 0) torn.store(true, std::memory_order_relaxed);
                taken.fetch_add(1, std::memory_order_relaxed);
            }
        }
    });
    int accepted = 0;
    for (int i = 0; i < kRounds; ++i) {
        std::string tok = "eof-" + std::to_string(i);
        if (ch.try_push_sentinel(tok) == Channel<std::string>::SentinelResult::Taken)
            ++accepted;
    }
    done.store(true, std::memory_order_release);
    consumer.join();
    INFO("accepted " << accepted << " taken " << taken.load());
    CHECK_FALSE(torn.load(std::memory_order_relaxed));
    // Every accepted token must be delivered: the slot is refused while full,
    // so acceptance and delivery are one-to-one.
    CHECK(taken.load(std::memory_order_relaxed) == accepted);
    CHECK(accepted > 0);
 }
@@ -1,10 +1,6 @@
 #include <catch2/catch_test_macros.hpp>
 #include <kpn/kpn.hpp>
 #include <atomic>
 #include <chrono>
 #include <mutex>
 #include <stdexcept>
 #include <string>
 #include <thread>
 using namespace kpn;
@@ -58,93 +54,3 @@ TEST_CASE("stop disables input channels — producer push is silently dropped",
    in_ch.push(99);
    REQUIRE(in_ch.size() == 0);
 }
 // Regression: Network::set_error_handler must actually deliver the handler.
 //
 // The handler was stored in a member and never read. A node's exception was
 // discarded at the node boundary and the only surviving evidence was a Closed
 // event, which reports that a node stopped but not why — the difference between
 // a diagnosis and a guess. StaticNetwork has always wired this; Network
 // accepted the handler and silently dropped it, which is worse than not
 // offering the setter at all.
 //
 // The type changed with the fix. It was void(name, exception_ptr), which cannot
 // express the keep-running decision the node side needs, so it is now
 // NodeErrorHandler like StaticNetwork's.
 namespace {
 static int throwing_stage(int x) {
    if (x == 42) throw std::runtime_error("boom");
    return x;
 }
 }  // namespace
 TEST_CASE("network error handler receives the node's exception", "[network]") {
    auto src  = kpn::make_node<throwing_stage>(kpn::in<"v">{}, kpn::out<"w">{}, 8);
    kpn::Channel<int> out(8);
    src.set_output_channel<0>(&out);
    kpn::Network net;
    net.add("stage", src).build();
    std::atomic<int>  calls{0};
    std::string       seen_name;
    std::string       seen_what;
    std::mutex        mx;
    net.set_error_handler([&](std::string_view name, std::exception_ptr ep) {
        std::lock_guard lk(mx);
        seen_name = std::string(name);
        try { if (ep) std::rethrow_exception(ep); }
        catch (const std::exception& e) { seen_what = e.what(); }
        calls.fetch_add(1, std::memory_order_relaxed);
        return true;                       // handled: keep the node running
    });
    net.set_watchdog_interval(std::chrono::hours(1));   // keep the report quiet
    net.start();
    src.input_channel<0>().push(42);                    // throws
    std::this_thread::sleep_for(std::chrono::milliseconds(100));
    src.input_channel<0>().push(7);                     // must still be running
    const int passed = out.pop();
    net.stop();
    CHECK(calls.load(std::memory_order_relaxed) == 1);
    CHECK(seen_name == "stage");
    CHECK(seen_what == "boom");
    CHECK(passed == 7);
 }
 // Regression: stopping a network must not wait for the watchdog's next tick.
 //
 // The watchdog looped on std::this_thread::sleep_for(watchdog_interval_), and
 // request_stop() cannot wake a sleeping thread — so stop_watchdog()'s join
 // blocked until the current sleep expired. Every teardown paid up to a full
 // interval, three seconds by default, and a caller who set a long one to keep
 // the periodic report quiet got a stop() that looked like a hang. That is how
 // this was found: the error-handler case above set an hour.
 TEST_CASE("stopping a network does not wait for the watchdog interval", "[network]") {
    auto node = kpn::make_node<increment>(kpn::in<"v">{}, kpn::out<"w">{}, 4);
    kpn::Channel<int> out(4);
    node.set_output_channel<0>(&out);
    kpn::Network net;
    net.add("inc", node).build();
    net.set_watchdog_interval(std::chrono::hours(1));
    net.start();
    // Let the watchdog actually reach its wait. Without this the test races it:
    // stop_watchdog() runs before the thread has entered the loop, the token is
    // already set when it does, and it exits without ever waiting — which passes
    // against the bug as well as the fix.
    std::this_thread::sleep_for(std::chrono::milliseconds(100));
    const auto t0 = std::chrono::steady_clock::now();
    net.stop();
    const auto ms = std::chrono::duration_cast<std::chrono::milliseconds>(
        std::chrono::steady_clock::now() - t0).count();
    INFO("stop took " << ms << " ms");
    CHECK(ms < 2000);
 }
@@ -243,13 +243,7 @@ TEST_CASE("interrupt node: trigger after stop is ignored", "[interrupt_node]") {
 // ── Overflow callback ─────────────────────────────────────────────────────────
-// NOTE: output overflow is no longer reachable on the data path. A node whose
+TEST_CASE("pool node overflow callback fires on full output channel", "[pool_node][overflow]") {
 // output channel is full now PARKS — it keeps the value in a hidden one-slot
 // buffer, releases its scheduler worker, and is re-submitted when the consumer
 // frees a slot. The overflow callback survives for other producers (a direct
 // Channel::push by non-node code still throws), but a pool node cannot trigger
 // it, so these cases assert the stronger property instead: nothing is dropped.
 TEST_CASE("pool node parks instead of overflowing a full output", "[pool_node][overflow]") {
    auto pool = std::make_shared<ThreadPool>(2);
    pool->start();
@@ -270,13 +264,10 @@ TEST_CASE("pool node parks instead of overflowing a full output", "[pool_node][o
    node.stop();
    pool->stop();
-    // Parked, not overflowed: the value is still owned by the node.
+    REQUIRE(overflow_count.load() > 0);
    REQUIRE(overflow_count.load() == 0);
    // And it was never handed downstream, so nothing was lost or duplicated.
    REQUIRE(full_ch.size() == 1);
 }
-TEST_CASE("parking is per node, not shared", "[pool_node][overflow]") {
+TEST_CASE("pool node overflow callback is independent per instance", "[pool_node][overflow]") {
    auto pool = std::make_shared<ThreadPool>(2);
    pool->start();
@@ -305,10 +296,7 @@ TEST_CASE("parking is per node, not shared", "[pool_node][overflow]") {
    nodeB.stop();
    pool->stop();
-    // Neither overflows now: A parks on its full output, B runs normally. The
+    REQUIRE(a_overflows.load() > 0);
    // point of the case is unchanged — one node's backpressure must not leak
    // into another's callbacks.
    REQUIRE(a_overflows.load() == 0);
    REQUIRE(b_overflows.load() == 0);
 }
@@ -424,9 +412,7 @@ TEST_CASE("network_overflow_callback fires on overflow", "[pool_node][network]")
    node.stop();
    pool->stop();
-    // Parking replaced overflow on the data path, so the network callback no
+    REQUIRE(net_overflows.load() > 0);
    // longer fires for a pool node's own output. See the note above.
    REQUIRE(net_overflows.load() == 0);
 }
 TEST_CASE("network_closed_callback fires on crash", "[pool_node][network]") {
@@ -473,250 +459,6 @@ TEST_CASE("per-node and network overflow callbacks both fire independently", "[p
    node.stop();
    pool->stop();
-    // Both zero now: the node parks rather than overflowing. The case still
+    REQUIRE(per_node.load() > 0);
-    // guards that the two callbacks are wired independently.
+    REQUIRE(network.load() > 0);
    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);
 }
 // Regression: a value parked twice must keep its payload.
 //
 // push_outputs ends with
 //
 //     else pending_ = std::move(result);
 //
 // and the retry path calls it as push_outputs(std::move(*pending_), …), so on
 // that path `result` is the parked tuple itself. The assignment was therefore a
 // self-move-assignment. std::tuple's is elementwise, and libstdc++'s
 // std::vector does not guard against self-move: it swaps its data into a
 // temporary and leaves the vector empty. So the first park was clean (the
 // argument is a local temporary) and the second erased the payload.
 //
 // The value was still delivered, still in order, still counted — just empty.
 // Downstream cannot distinguish that from a frame on which the node genuinely
 // found nothing, which is why it never surfaced as an error: in
 // scene-actor-extraction it reads as "no faces in this frame" and the run
 // completes with a quietly wrong answer.
 //
 // Reaching it needs *two* outputs. With one, the only thing that resubmits a
 // parked node is that output's own space callback, which by definition fires
 // when there is room — so the retry always succeeds and never reassigns. With
 // two, output A draining resubmits the node while output B is still full: the
 // retry skips A (already delivered, tracked in pending_done_) and fails on B,
 // and that is the reassignment that eats B's payload.
 //
 // Driven through raw channels rather than consumer nodes so each step is
 // forced rather than raced: B is pre-filled and stays full for exactly as long
 // as the test wants it to.
 namespace {
 struct TwoPayloads {
    static constexpr std::string_view label() { return "two_payloads"; }
    std::tuple<std::vector<int>, std::vector<int>> operator()() {
        return {std::vector<int>(4, 1), std::vector<int>(4, 2)};
    }
 };
 }  // namespace
 TEST_CASE("a twice-parked value keeps its payload", "[pool_node][backpressure]") {
    auto pool = std::make_shared<ThreadPool>(2);
    pool->start();
    TwoPayloads fn;
    auto node = make_pool_node(fn, pool);
    // Both capacity 1. A must be *full* for its pop to signal space at all —
    // Channel fires the space callback only on the full->not-full edge, so a
    // roomy A would never resubmit the node and the retry would never happen.
    Channel<std::vector<int>> out_a(1), out_b(1);
    node.set_output_channel<0>(&out_a);
    node.set_output_channel<1>(&out_b);
    // B is full before the node ever runs, so the very first firing parks.
    out_b.push(std::vector<int>(4, 99));
    node.start();
    std::this_thread::sleep_for(std::chrono::milliseconds(50));
    // Draining A resubmits the node while B is still full: this is the retry
    // that reassigned the tuple to itself.
    (void)out_a.pop();
    std::this_thread::sleep_for(std::chrono::milliseconds(50));
    // Now let B through and collect what the node had been holding for it.
    (void)out_b.pop();                       // the pre-fill
    std::this_thread::sleep_for(std::chrono::milliseconds(50));
    std::vector<int> parked = out_b.pop();   // the value parked across two tries
    node.stop();
    pool->stop();
    INFO("parked payload size " << parked.size());
    CHECK(parked.size() == 4);
    if (parked.size() == 4) CHECK(parked[0] == 2);
 }
 // Regression: a node woken with nothing to read must not stop itself.
 //
 // pop_one reported an empty channel the same way it reported a closed one, by
 // throwing ChannelClosedError, and fire_once treats that as "upstream is
 // finished" and calls self_stop(). self_stop disables the node's own inputs
 // *and* outputs, so one benign empty read does not merely skip a frame — it
 // kills the node and, through the disabled channels, the rest of the pipeline.
 //
 // A node genuinely does get woken with empty inputs: a space callback fires
 // when its output drains, which has nothing to do with input arrival. fire_once
 // guards against it by checking readiness before popping, and that guard is
 // what this test pins. pop_one now also distinguishes the two cases, so if the
 // guard is ever weakened the cost is a wasted firing rather than a dead node.
 //
 // The sequence below reaches the guard deliberately. The output is capacity 1
 // so that draining it signals space at all — Channel fires the space callback
 // only on the full->not-full edge — and by the final pop the input is long
 // since consumed, so the resulting firing has nothing to read.
 namespace {
 struct CountingRelay {
    static constexpr std::string_view label() { return "counting_relay"; }
    std::atomic<int>* calls;
    int operator()(int v) { calls->fetch_add(1, std::memory_order_relaxed); return v; }
 };
 }  // namespace
 TEST_CASE("a node woken with empty inputs does not stop itself", "[pool_node]") {
    std::atomic<int>  calls{0};
    std::atomic<int>  closed{0};
    auto pool = std::make_shared<ThreadPool>(2);
    pool->start();
    CountingRelay fn{&calls};
    auto node = make_pool_node(fn, pool, 8);
    Channel<int> out(1);
    node.set_output_channel<0>(&out);
    node.set_closed_callback([&](auto) { closed.fetch_add(1, std::memory_order_relaxed); });
    out.push(99);                     // output full before the node runs
    node.start();
    node.input_channel<0>().push(1);  // fires, cannot deliver, parks
    std::this_thread::sleep_for(std::chrono::milliseconds(50));
    REQUIRE(out.pop() == 99);         // space -> retry delivers the parked value
    std::this_thread::sleep_for(std::chrono::milliseconds(50));
    REQUIRE(out.pop() == 1);          // space again -> fires with empty inputs
    std::this_thread::sleep_for(std::chrono::milliseconds(50));
    // That firing had nothing to read. The node must still be alive.
    CHECK(closed.load(std::memory_order_relaxed) == 0);
    CHECK(node.running());
    // And must still do its job when real input arrives.
    node.input_channel<0>().push(2);
    std::this_thread::sleep_for(std::chrono::milliseconds(50));
    CHECK(out.pop() == 2);
    CHECK(calls.load(std::memory_order_relaxed) == 2);
    node.stop();
    pool->stop();
 }
 // Regression: stop() must not return while a firing is still running.
 //
 // stop() set the flag, disabled the inputs and returned, leaving an executing
 // fire_once touching input_channels_, stats_ and pending_ while the caller went
 // on to destroy them. The old comment was explicit that callers wanting the
 // guarantee should call scheduler_->drain() first — but ~PoolNode calls stop(),
 // and a destructor cannot ask its caller to have done that.
 //
 // A node with a private pool survived by accident: Node::stop() calls
 // pool->stop(), which joins the worker. A node sharing a pool, which
 // make_pool_node exists to create, had nothing joining it at all, so its own
 // destructor raced the firing.
 //
 // Asserted through an observable side effect rather than by trying to catch the
 // use-after-free: if stop() returns before the node function has finished, the
 // flag it sets on the way out is still false.
 namespace {
 struct SlowFiring {
    static constexpr std::string_view label() { return "slow_firing"; }
    std::atomic<bool>* entered;
    std::atomic<bool>* finished;
    void operator()(int) {
        entered->store(true, std::memory_order_release);
        std::this_thread::sleep_for(std::chrono::milliseconds(200));
        finished->store(true, std::memory_order_release);
    }
 };
 }  // namespace
 TEST_CASE("stop waits for a firing already in flight", "[pool_node]") {
    std::atomic<bool> entered{false}, finished{false};
    auto pool = std::make_shared<ThreadPool>(2);
    pool->start();
    SlowFiring fn{&entered, &finished};
    auto node = make_pool_node(fn, pool, 4);
    node.start();
    node.input_channel<0>().push(1);
    // Stop only once the node is demonstrably inside its function.
    while (!entered.load(std::memory_order_acquire))
        std::this_thread::sleep_for(std::chrono::milliseconds(1));
    node.stop();
    CHECK(finished.load(std::memory_order_acquire));
    pool->stop();
 }
@@ -227,116 +227,3 @@ TEST_CASE("work stealing: tasks complete with more threads than initial queue ta
    REQUIRE(counter.load() == 4);
    pool.stop();
 }
 // Regression: submitting to a stopped pool must be a no-op, not a segfault.
 //
 // stop() ends with queues_.clear(), and submit() went straight to
 // queues_[target] with no check — so a submission arriving after stop indexed
 // an empty vector.
 //
 // This is not a contrived teardown ordering; it happens on a normal path. A
 // node's space callback fires from whichever thread drained the channel, and
 // that thread belongs to the *consumer*. Stop the producer first — which a
 // sources-first shutdown does by design — and the consumer keeps draining its
 // backlog, firing the producer's space callback into a pool that has already
 // been torn down. Before this fix the static-network shutdown case crashed
 // about 12 runs in 20.
 //
 // Checking stopped_ without the lock would not be enough: the window between
 // reading the flag and indexing the vector is exactly where clear() runs.
 TEST_CASE("submitting to a stopped pool is refused, not fatal", "[scheduler]") {
    ThreadPool pool(2);
    pool.start();
    pool.stop();
    std::atomic<int> ran{0};
    for (int i = 0; i < 10; ++i)
        pool.submit([&] { ran.fetch_add(1, std::memory_order_relaxed); });
    CHECK(ran.load(std::memory_order_relaxed) == 0);
    CHECK(pool.rejected() == 10);
 }
 TEST_CASE("submitting while the pool stops does not crash", "[scheduler]") {
    // The racing form of the case above: a producer thread submitting
    // continuously while stop() runs underneath it. Nothing is asserted about
    // how many tasks run — the point is that every submission either enqueues
    // or is refused, and none touches a destroyed queue.
    for (int rep = 0; rep < 20; ++rep) {
        ThreadPool pool(4);
        pool.start();
        std::atomic<bool> go{false};
        std::atomic<int>  ran{0};
        std::thread submitter([&] {
            while (!go.load(std::memory_order_acquire)) {}
            for (int i = 0; i < 2000; ++i)
                pool.submit([&] { ran.fetch_add(1, std::memory_order_relaxed); });
        });
        go.store(true, std::memory_order_release);
        std::this_thread::sleep_for(std::chrono::microseconds(200));
        pool.stop();
        submitter.join();
        // Everything submitted was either executed or refused; nothing vanished
        // into a queue that no longer existed.
        CHECK(pool.rejected() + pool.snapshot("p").tasks_completed <= 2000);
    }
 }
 // Regression: idle workers must sleep while another worker is busy.
 //
 // The wait predicate was `stopped_ || total_ > 0`, and total_ counts queued
 // *plus executing*. So while any one task ran, every other worker's predicate
 // was true: wait() returned immediately and the worker spun through try_pop,
 // try_steal and back to wait at full speed — try_lock-ing every peer queue on
 // each pass. One slow task pinned every other core and contended the very
 // mutexes the working thread needed to make progress.
 //
 // That is the shape of this pipeline's load exactly: a handful of nodes whose
 // work is tens of milliseconds of ONNX inference. It was latent only because
 // each node currently owns a private single-thread pool, where there is no
 // idle peer to spin. Any use of a shared pool — which make_pool_node exists
 // for — hits it immediately.
 //
 // Measured as CPU time rather than wall time, because the bug does not make
 // anything slower to finish; it makes seven cores burn while one works. A
 // sleeping task consumes no CPU, so with workers correctly asleep the whole
 // pool should account for almost none.
 TEST_CASE("idle workers do not spin while one task runs", "[scheduler]") {
    auto cpu_ms = [] {
        struct timespec ts{};
        clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &ts);
        return ts.tv_sec * 1000.0 + ts.tv_nsec / 1e6;
    };
    constexpr int kThreads = 8;
    constexpr int kWorkMs  = 300;
    ThreadPool pool(kThreads);
    pool.start();
    std::this_thread::sleep_for(20ms);      // let workers reach the wait
    const double before = cpu_ms();
    // One long task plus a trivial one per remaining worker. The trivial ones
    // matter: a worker that has never been woken stays blocked in wait() and
    // never re-evaluates the predicate, so the spin only appears once a worker
    // *finishes* something and re-enters the loop while a peer is still busy.
    // Submitting only the long task does not reproduce it.
    pool.submit([&] { std::this_thread::sleep_for(std::chrono::milliseconds(kWorkMs)); });
    for (int i = 0; i < kThreads - 1; ++i) pool.submit([] {});
    pool.drain();
    const double used = cpu_ms() - before;
    pool.stop();
    // Measured on this tree: 1991 ms of CPU with the total_ predicate against
    // 0.4 ms with queued_, and 19205 voluntary context switches against 10 —
    // roughly (kThreads - 1) cores burned for the duration of one sleeping
    // task. The threshold sits far from both so the case is not sensitive to
    // how loaded the machine is.
    INFO("cpu " << used << " ms over " << kWorkMs << " ms of sleeping work");
    CHECK(used < kWorkMs);
 }
@@ -237,51 +237,3 @@ TEST_CASE("make_shared_resource constructs with forwarded args", "[shared_resour
    auto g = res.acquire();
    REQUIRE(*g == "hello");
 }
 // Regression: a waiter must be releasable, or teardown waits on it forever.
 //
 // acquire() blocks on a condition variable whose predicate only becomes true
 // when release() hands over ownership. There was no timeout and no stop
 // condition, so a node parked there ignored teardown entirely: its worker never
 // returned, the pool's join never completed, and shutdown hung waiting for a
 // resource nobody was going to release — which is exactly the case when the
 // holder is being stopped too.
 //
 // close() turns that into an exception the node's existing error path already
 // handles, and networks now call it on registered resources before stopping any
 // node, for the same reason.
 TEST_CASE("closing a shared resource releases its waiters", "[shared_resource]") {
    SharedResource<int> res(42);
    auto holder = res.acquire();          // resource is now held
    std::atomic<bool> threw{false}, returned{false};
    std::thread waiter([&] {
        try {
            auto g = res.acquire();       // blocks: someone else holds it
            (void)g;
        } catch (const ResourceClosedError&) {
            threw.store(true, std::memory_order_release);
        }
        returned.store(true, std::memory_order_release);
    });
    // Let it park, then tear down without ever releasing the holder.
    std::this_thread::sleep_for(std::chrono::milliseconds(50));
    REQUIRE_FALSE(returned.load(std::memory_order_acquire));
    res.close();
    waiter.join();
    CHECK(threw.load(std::memory_order_acquire));
 }
 TEST_CASE("acquiring a closed resource fails immediately", "[shared_resource]") {
    SharedResource<int> res(7);
    res.close();
    CHECK_THROWS_AS(res.acquire(), ResourceClosedError);
    // Reusable across runs once reopened.
    res.reopen();
    CHECK_NOTHROW(res.acquire());
 }
@@ -271,164 +271,3 @@ TEST_CASE("static_network: fanout with labelled same-function consumers", "[stat
    REQUIRE(outB.pop() == 7);
    net.stop();
 }
 // Regression: shutdown() must return even when a consumer stopped consuming.
 //
 // The drain step was an unbounded `while (anything anywhere is non-empty)` poll
 // over *every* channel in the graph. Two defects in one loop: it waited for the
 // whole network to be idle before stopping each successive layer rather than
 // just the node it had stopped — the dynamic Network's version even took a node
 // name and ignored it — and it had no deadline, so anything wedged downstream
 // turned a graceful shutdown into the hang it exists to avoid.
 //
 // It could also fail to terminate with nothing wedged at all. current_fill came
 // from a snapshot that loaded tail_ before head_; a concurrent pop between the
 // two reads yields a head_ past the sampled tail_, and the unsigned difference
 // wraps to ~2^64. Any poll for "is it empty yet" against that value runs
 // forever. Both indices only ever increase, so loading head_ first can at worst
 // under-report a push, which this loop tolerates and a wrap does not.
 //
 // Here the sink never takes anything, so its input cannot drain and the only
 // correct outcome is to give up and say so. The bound asserted is deliberately
 // loose: the point is that it terminates, not how fast.
 namespace {
 struct DrainSource {
    static constexpr std::string_view label() { return "drain_source"; }
    int n{0};
    int operator()() {
        std::this_thread::sleep_for(std::chrono::microseconds(100));
        return n++;
    }
 };
 struct NeverConsumes {
    static constexpr std::string_view label() { return "never_consumes"; }
    std::atomic<bool>* wedged;
    void operator()(int) {
        // Blocks for the duration of the test: the input channel behind it
        // fills and stays full.
        while (!wedged->load(std::memory_order_acquire))
            std::this_thread::sleep_for(std::chrono::milliseconds(1));
    }
 };
 }  // namespace
 TEST_CASE("shutdown returns when a consumer has wedged", "[static_network][shutdown]") {
    std::atomic<bool> release{false};
    DrainSource   src_fn;
    NeverConsumes sink_fn{&release};
    kpn::ObjectNode<DrainSource,   kpn::in<>,    kpn::out<"v">, "drain_source",   0> s(src_fn,  4);
    kpn::ObjectNode<NeverConsumes, kpn::in<"v">, kpn::out<>,    "never_consumes", 0> k(sink_fn, 4);
    auto net = kpn::make_network(kpn::edge(s.output<"v">(), k.input<"v">()));
    net.set_drain_timeout(std::chrono::milliseconds(100));
    net.start();
    // Let the channel fill and the sink jam.
    std::this_thread::sleep_for(std::chrono::milliseconds(100));
    // Unjam the sink well after the drain timeout should have expired. Stopping
    // a node joins its worker, so a sink blocked forever would hang the test in
    // stop() rather than in the drain loop this case is about.
    std::thread unjam([&] {
        std::this_thread::sleep_for(std::chrono::milliseconds(800));
        release.store(true, std::memory_order_release);
    });
    const auto t0 = std::chrono::steady_clock::now();
    net.shutdown();
    const auto elapsed = std::chrono::steady_clock::now() - t0;
    unjam.join();
    const auto ms = std::chrono::duration_cast<std::chrono::milliseconds>(elapsed).count();
    INFO("shutdown took " << ms << " ms");
    CHECK(ms < 3000);   // unbounded before; one 100 ms drain timeout after
 }
 // Regression: node order must come from the topological sort, not from the
 // order the edges happened to be written in.
 //
 // make_network computes Topo for the cycle check and then dropped it, filling
 // the node vector in edge-declaration order — and named it user_nodes_topo_.
 // halt() stops in its reverse, and shutdown() walks it forwards stopping each
 // node and draining its outputs before moving to the next, which is a graceful
 // drain only if the order really is sources-first.
 //
 // Every network in this tree declares edges in pipeline order, so the two
 // coincided and nothing failed. This case declares them backwards, which is
 // legal and which make_network otherwise accepts silently.
 //
 // Asserted through shutdown() rather than by reading the order back, because
 // the order is private and the ordering is not the point — what it buys is.
 // A sources-first shutdown lets the values already in flight reach the sink;
 // stopping the sink first strands them, and the drain step then has nobody
 // left to take them.
 namespace {
 struct OrderSource {
    static constexpr std::string_view label() { return "order_source"; }
    std::atomic<int>* made;
    int operator()() {
        std::this_thread::sleep_for(std::chrono::microseconds(20));
        return made->fetch_add(1, std::memory_order_relaxed);
    }
 };
 // Deliberately slower than the source, so a deep backlog builds up in its input
 // channel. That backlog is what a sources-first shutdown preserves and a
 // sink-first one throws away, and it needs to be big enough that the difference
 // cannot be mistaken for one value in flight.
 struct OrderRelay {
    static constexpr std::string_view label() { return "order_relay"; }
    int operator()(int v) {
        std::this_thread::sleep_for(std::chrono::microseconds(300));
        return v;
    }
 };
 struct OrderSink {
    static constexpr std::string_view label() { return "order_sink"; }
    std::atomic<int>* seen;
    void operator()(int) { seen->fetch_add(1, std::memory_order_relaxed); }
 };
 }  // namespace
 TEST_CASE("edges declared out of order still start and stop sources-first",
          "[static_network][shutdown]") {
    std::atomic<int> seen{0}, made{0};
    OrderSource src_fn{&made};
    OrderRelay  relay_fn;
    OrderSink   sink_fn{&seen};
    kpn::ObjectNode<OrderSource, kpn::in<>,    kpn::out<"v">, "order_source", 0> s(src_fn,   8);
    kpn::ObjectNode<OrderRelay,  kpn::in<"v">, kpn::out<"w">, "order_relay",  0> r(relay_fn, 64);
    kpn::ObjectNode<OrderSink,   kpn::in<"w">, kpn::out<>,    "order_sink",   0> k(sink_fn,  64);
    // Sink edge first, source edge last — the reverse of pipeline order.
    auto net = kpn::make_network(
        kpn::edge(r.output<"w">(), k.input<"w">()),
        kpn::edge(s.output<"v">(), r.input<"v">())
    );
    net.start();
    std::this_thread::sleep_for(std::chrono::milliseconds(300));
    const int before = seen.load(std::memory_order_relaxed);
    REQUIRE(before > 0);              // the pipeline ran at all
    net.shutdown();
    // Sources stop first and each layer drains before the next stops, so the
    // backlog queued in front of the relay still reaches the sink. Stopping in
    // declaration order stops the relay first and discards all of it.
    const int after = seen.load(std::memory_order_relaxed);
    INFO("made " << made.load() << ", delivered " << before
         << " before shutdown, " << after << " after");
    CHECK(after - before >= 20);
 }
@@ -1,173 +0,0 @@
 // Regression: a node must never end up idle with a wake outstanding.
 //
 // 9c5ce5f established that invariant and implemented it as two independent
 // atomics — queued_ for "a firing is in flight", wake_pending_ for "a wake
 // arrived during one". Two variables cannot express it, because the release
 // side has to read and write both and a wake can land in between:
 //
 //   producer (try_submit)              worker (release_and_recheck)
 //   ------------------------           ----------------------------
 //   CAS reads queued_ == true, fails
 //                                      queued_.store(false)
 //                                      wake_pending_.exchange(false) -> false
 //   wake_pending_.store(true)
 //
 // queued_ false, wake_pending_ true, nothing running and nothing scheduled.
 // Not a memory-ordering subtlety: the interleaving holds under seq_cst.
 //
 // LegacyGate below is that protocol verbatim, with a hook between the failed
 // CAS and the wake_pending_ store so the interleaving can be forced rather than
 // waited for. That makes the loss deterministic and the test non-flaky, and it
 // keeps the defect on record now that the code implementing it is gone.
 //
 // A note on what is NOT tested here, because it would be misleading to imply
 // otherwise: there is no black-box, node-level test that fails before this fix
 // and passes after. Every call site of release_and_recheck() happens to follow
 // it with a level re-check — on_input_ready(), or outputs_have_space() on the
 // parked path — which rediscovers the state a lost wake would have signalled.
 // That masking is a property of the call sites, not of the mechanism, and the
 // point of the fix is that a future early return that forgets the re-check no
 // longer reintroduces a hang. The value is structural, so the tests are
 // structural: the state machine is pinned by contract, and the defect it
 // replaces is pinned by demonstration.
 #include <catch2/catch_test_macros.hpp>
 #include <kpn/submit_gate.hpp>
 #include <atomic>
 #include <functional>
 #include <thread>
 using namespace kpn;
 namespace {
 // The pre-fix protocol, with a seam at the point where the race lives.
 class LegacyGate {
 public:
    std::function<void()> before_recording_wake;
    bool claim() noexcept {
        bool expected = false;
        if (queued_.compare_exchange_strong(expected, true, std::memory_order_acq_rel))
            return true;
        if (before_recording_wake) before_recording_wake();
        wake_pending_.store(true, std::memory_order_release);
        return false;
    }
    bool release() noexcept {
        queued_.store(false, std::memory_order_release);
        if (wake_pending_.exchange(false, std::memory_order_acq_rel)) {
            bool expected = false;
            if (queued_.compare_exchange_strong(expected, true, std::memory_order_acq_rel))
                return true;
        }
        return false;
    }
    bool queued()       const noexcept { return queued_.load(std::memory_order_relaxed); }
    bool wake_pending() const noexcept { return wake_pending_.load(std::memory_order_relaxed); }
 private:
    std::atomic<bool> queued_{false};
    std::atomic<bool> wake_pending_{false};
 };
 }  // namespace
 TEST_CASE("the two-atomic gate loses a wake, deterministically", "[submit_gate]") {
    LegacyGate gate;
    bool resubmitted = true;
    REQUIRE(gate.claim());              // a firing is now in flight
    // Force the interleaving: the firing completes in the window between the
    // second wake's failed CAS and its record of that wake.
    gate.before_recording_wake = [&] { resubmitted = gate.release(); };
    const bool submitted = gate.claim();
    // The wake was neither submitted by the producer nor honoured by the
    // release. Nothing is scheduled, and nothing else will re-trigger it.
    CHECK_FALSE(submitted);
    CHECK_FALSE(resubmitted);
    CHECK_FALSE(gate.queued());
    CHECK(gate.wake_pending());         // recorded, and never to be consumed
 }
 TEST_CASE("submit gate: a wake during a firing is honoured", "[submit_gate]") {
    SubmitGate gate;
    REQUIRE(gate.claim());              // idle -> queued, caller submits
    REQUIRE(gate.queued());
    REQUIRE_FALSE(gate.wake_pending());
    REQUIRE_FALSE(gate.claim());        // second wake is recorded, not submitted
    REQUIRE(gate.wake_pending());
    REQUIRE(gate.release());            // and honoured when the firing ends
    // The gate stays claimed across the handover, so the node is never
    // momentarily idle while a submission for it is in flight. This is the
    // state the legacy gate could not represent.
    REQUIRE(gate.queued());
    REQUIRE_FALSE(gate.wake_pending());
    REQUIRE_FALSE(gate.release());      // no further wake: now idle
    REQUIRE_FALSE(gate.queued());
 }
 TEST_CASE("submit gate: repeated wakes collapse to one resubmission", "[submit_gate]") {
    // Collapsing is deliberate. A firing consumes one item and its caller then
    // re-checks the input level, so the gate only has to guarantee that at
    // least one more firing follows a wake, not one per wake.
    SubmitGate gate;
    REQUIRE(gate.claim());
    for (int i = 0; i < 10; ++i) REQUIRE_FALSE(gate.claim());
    REQUIRE(gate.release());
    REQUIRE_FALSE(gate.release());
 }
 TEST_CASE("submit gate: force_idle drops a recorded wake", "[submit_gate]") {
    // Stop paths use this deliberately — honouring a wake there would resubmit
    // a node that has already been told to stop.
    SubmitGate gate;
    REQUIRE(gate.claim());
    REQUIRE_FALSE(gate.claim());
    REQUIRE(gate.wake_pending());
    gate.force_idle();
    REQUIRE_FALSE(gate.queued());
    REQUIRE_FALSE(gate.wake_pending());
    REQUIRE(gate.claim());              // and the gate is reusable afterwards
 }
 TEST_CASE("submit gate: concurrent claim and release stay consistent", "[submit_gate]") {
    // Not a lost-wake test — see the header note. This is a TSan target and a
    // check that the CAS loops always terminate and always leave the gate in a
    // reachable state: exactly one party may hold the claim at a time, so the
    // count of claims granted must equal the count of releases that ended idle.
    SubmitGate gate;
    std::atomic<long> granted{0}, ended_idle{0};
    std::atomic<bool> stop{false};
    std::thread waker([&] {
        while (!stop.load(std::memory_order_relaxed))
            if (gate.claim()) granted.fetch_add(1, std::memory_order_relaxed);
    });
    std::thread worker([&] {
        while (!stop.load(std::memory_order_relaxed))
            if (gate.queued() && !gate.release())
                ended_idle.fetch_add(1, std::memory_order_relaxed);
    });
    std::this_thread::sleep_for(std::chrono::milliseconds(200));
    stop.store(true, std::memory_order_relaxed);
    waker.join();
    worker.join();
    // Drain whatever claim is outstanding so the two counts can be compared.
    while (gate.queued())
        if (!gate.release()) ended_idle.fetch_add(1, std::memory_order_relaxed);
    INFO("granted " << granted.load() << " ended idle " << ended_idle.load());
    REQUIRE(granted.load() > 0);
    CHECK(granted.load() == ended_idle.load());
 }