include/kpn/channel.hpp

@@ -58,6 +58,18 @@ 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.

include/kpn/pool_node.hpp

@@ -473,6 +473,14 @@ private:
             auto t2   = clock_t::now();
             // blocked_time = 0 for pool nodes (we don't block waiting for inputs)
             stats_.record_exec(duration_t(t2 - t1), duration_t::zero(), cpu0, cpu1);
+        } catch (const ChannelEmptyError&) {
+            // Not an error: there was simply nothing to take. Release and wait
+            // to be woken again. fire_once checks readiness before it gets
+            // here, and this node is the sole consumer of its inputs, so this
+            // is unreachable today — it exists so that if the check is ever
+            // weakened the cost is a wasted firing rather than a dead node.
+            finish_firing();
+            return;
         } catch (const ChannelClosedError&) {
             fire_callbacks(closed_callbacks_);
             self_stop();
@@ -512,8 +520,16 @@ private:
     std::tuple_element_t<I, args_tuple> pop_one() {
         auto& ch = *std::get<I>(input_channels_);
         std::tuple_element_t<I, args_tuple> val;
-        if (!ch.try_pop_now(val))
+        if (!ch.try_pop_now(val)) {
+            // try_pop_now returns false for "nothing available", which covers
+            // two very different situations. A closed channel means upstream is
+            // finished and this node should stop. An open one means only that
+            // nothing is here at this instant — and treating that as closed
+            // kills a live node, which then disables its own inputs and outputs
+            // and takes the rest of the pipeline with it.
+            if (ch.is_accepting()) throw ChannelEmptyError{};
             throw ChannelClosedError{};
+        }
         return val;
     }
 
@@ -980,6 +996,14 @@ private:
             auto cpu1 = NodeStats::cpu_now();
             auto t2   = clock_t::now();
             stats_.record_exec(duration_t(t2 - t1), duration_t::zero(), cpu0, cpu1);
+        } catch (const ChannelEmptyError&) {
+            // Not an error: there was simply nothing to take. Release and wait
+            // to be woken again. fire_once checks readiness before it gets
+            // here, and this node is the sole consumer of its inputs, so this
+            // is unreachable today — it exists so that if the check is ever
+            // weakened the cost is a wasted firing rather than a dead node.
+            finish_firing();
+            return;
         } catch (const ChannelClosedError&) {
             fire_callbacks(closed_callbacks_);
             self_stop();
@@ -1014,7 +1038,16 @@ private:
     std::tuple_element_t<I, args_tuple> pop_one() {
         auto& ch = *std::get<I>(input_channels_);
         std::tuple_element_t<I, args_tuple> val;
-        if (!ch.try_pop_now(val)) throw ChannelClosedError{};
+        if (!ch.try_pop_now(val)) {
+            // try_pop_now returns false for "nothing available", which covers
+            // two very different situations. A closed channel means upstream is
+            // finished and this node should stop. An open one means only that
+            // nothing is here at this instant — and treating that as closed
+            // kills a live node, which then disables its own inputs and outputs
+            // and takes the rest of the pipeline with it.
+            if (ch.is_accepting()) throw ChannelEmptyError{};
+            throw ChannelClosedError{};
+        }
         return val;
     }
 

tests/test_pool_node.cpp

@@ -602,3 +602,69 @@ TEST_CASE("a twice-parked value keeps its payload", "[pool_node][backpressure]")
     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();
+}