Fix webhook starvation and isolate scheduled job failures for v0.1.2 [skip ci]

tests/test_extensions.py

@@ -373,3 +373,30 @@ def test_ai_layout_sends_metadata_only_and_validates_response(
     assert b"test-ai-secret" not in calls[0]["body"]
     assert image.getvalue() not in calls[0]["body"]
     assert calls[0]["headers"]["Authorization"] == "Bearer test-ai-secret"
+
+
+def test_webhook_matching_event_after_unrelated_backlog(client, service, monkeypatch):
+    import json
+
+    service.settings.image_url_hosts.append("example.com")
+    response = client.post(
+        "/api/v1/webhooks",
+        json={
+            "callback_url": "https://example.com/events",
+            "event_types": ["operation.failed"],
+        },
+    )
+    assert response.status_code == 201
+    for _ in range(500):
+        service.db.event("display.changed", {})
+    service.db.event("operation.failed", {"operation_id": "expected"})
+    sent = []
+    monkeypatch.setattr(
+        service.assets, "fetch_url", lambda url, **kwargs: sent.append(kwargs) or b""
+    )
+    service.webhooks.tick()
+    service.webhooks.last = 0
+    service.webhooks.tick()
+    assert len(sent) == 1
+    assert json.loads(sent[0]["body"])["data"] == {"operation_id": "expected"}
+    assert len(service.db.all("SELECT * FROM webhook_deliveries")) == 1

tests/test_scheduler.py

@@ -93,3 +93,58 @@ def test_worker_checks_late_sync_before_due_tasks(app, service, monkeypatch):
     monkeypatch.setattr(service, "process_one", lambda: False)
     scheduler.run()
     assert calls[:2] == ["sync", "tick"]
+
+
+def test_blocked_job_keeps_retry_slot_without_blocking_worker(
+    app, service, monkeypatch
+):
+    scheduler = app.state.scheduler
+    service.registry.drivers["other-room"] = service.registry.get("living-room")
+    jobs = []
+    for device in ("living-room", "other-room"):
+        jobs.append(
+            scheduler.save_job(
+                JobInput(
+                    name=device,
+                    device_id=device,
+                    schedule={"type": "daily", "time": "07:00"},
+                    source={"type": "restore"},
+                )
+            )
+        )
+    current = datetime.now(UTC)
+    due = (current - timedelta(seconds=2)).isoformat()
+    service.db.execute("UPDATE jobs SET next_run=?", (due,))
+    unknown = service.submit("display", {}, "living-room", "test", "unknown")
+    service.db.execute(
+        "UPDATE operations SET status='UNKNOWN',write_started=1 WHERE id=?", (unknown,)
+    )
+    queued = service.submit("render", {}, "living-room", "test", "render")
+    calls = []
+    monkeypatch.setattr(service, "sync", lambda: None)
+    monkeypatch.setattr(service, "expire", lambda: calls.append("expire"))
+    monkeypatch.setattr(service.cloud_library, "sweep", lambda: None)
+    monkeypatch.setattr(service.local_retention, "sweep", lambda: None)
+
+    def process():
+        calls.append("process")
+        assert service.operation(queued)["status"] == "QUEUED"
+        scheduler.stop_event.set()
+        return False
+
+    monkeypatch.setattr(service, "process_one", process)
+    monkeypatch.setattr(
+        scheduler.stop_event, "wait", lambda timeout: scheduler.stop_event.set()
+    )
+    scheduler.run()
+    assert calls == ["expire", "process"]
+    blocked = service.db.one("SELECT * FROM jobs WHERE id=?", (jobs[0]["id"],))
+    assert blocked["next_run"] == due
+    assert blocked["last_run"] is None
+    assert len(service.db.all("SELECT * FROM job_runs")) == 1
+    assert service.db.one("SELECT * FROM job_runs")["job_id"] == jobs[1]["id"]
+    scheduler.tick(current + timedelta(minutes=6))
+    assert (
+        service.db.one("SELECT * FROM jobs WHERE id=?", (jobs[0]["id"],))["last_result"]
+        == "SKIPPED_OVERDUE"
+    )