Claim only what the cascade pool can run

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01UytviPMJbXzD8P84nLvXcq
2026-08-25 18:33:28 +02:00
parent 68711e2ee7
commit df22475f54
2 changed files with 77 additions and 4 deletions
@@ -333,3 +333,56 @@ def test_work_in_flight_is_touched_until_it_finishes(monkeypatch):
    finally:
        release.set()
        service.stop()
+
+
+def test_no_more_is_claimed_than_the_pool_can_run():
+    """A backlog belongs in the queue, not inside the process.
+
+    Claiming ahead of the pool used to leave every waiting item counted as a
+    busy cascade and holding its journal entry open, so four cascade threads
+    reported hundreds in flight on an engine that was merely behind.
+    """
+    release = threading.Event()
+
+    def slow(reading, params):
+        release.wait(5)
+        return {"doubled": reading * 2}
+
+    source = Node(
+        f=lambda params: None,
+        provides=[MessageSpec(name="reading", dtype=DType.FLOAT)],
+        name="source",
+    )
+    consumer = Node(
+        f=slow,
+        requires=[MessageSpec(name="reading", dtype=DType.FLOAT)],
+        provides=[MessageSpec(name="doubled", dtype=DType.FLOAT)],
+        name="consumer",
+    )
+    source.assign_flow("f", "source")
+    consumer.assign_flow("f", "consumer")
+
+    queue = MemoryWorkQueue()
+    pipeline = Pipeline(nodes=[source, consumer], state=MemoryState(), work_queue=queue)
+    service = ExecutionService(queue)
+    service.bind(pipeline)
+    service.start()
+    try:
+        for i in range(40):
+            queue.add(
+                WorkItem(
+                    kind="cascade",
+                    node="f.source",
+                    flow="f",
+                    outputs={"f.reading": float(i)},
+                )
+            )
+        time.sleep(0.5)
+
+        stats = service.stats()
+        assert stats["cascades_busy"] <= executor.MAX_CASCADES
+        # And the journal entries of what is only waiting are still free.
+        assert stats["pending"] <= executor.MAX_CASCADES
+    finally:
+        release.set()
+        service.stop()