Residual from STATE-WP-0091: pending pods in capacity evidence.

RCLUSTER-WP-0015 proposed. 105m remaining is not cluster admission.

Assistant: grok
Assistant-Session: 01a09dc1-b21e-77e1-919e-fcad2f82b267

workplans/RCLUSTER-WP-0015-state-hub-surge-headroom.md

@@ -0,0 +1,34 @@
+---
+id: RCLUSTER-WP-0015
+type: workplan
+title: "Keep node remaining CPU honest for State Hub surge and pending demand"
+domain: financials
+repo: railiance-cluster
+status: proposed
+owner: codex
+topic_slug: railiance
+origin: residual
+origin_ref: STATE-WP-0091
+created: "2026-09-14"
+updated: "2026-09-14"
+related: [RCLUSTER-WP-0014, STATE-WP-0091, CUST-WP-0071]
+---
+
+Residual from STATE-WP-0091. State Hub now refuses promotion when remaining
+CPU cannot cover its 100m API surge, and when unrelated pending pods would
+eat the 5m sliver above 105m. Cluster observation must keep publishing
+allocatable, allocated, **and pending-unrelated** demand. 105m remaining is
+not capacity admission for factory or other zero-request workloads.
+
+## Include pending pods in capacity observations
+
+```task
+id: RCLUSTER-WP-0015-T01
+status: todo
+priority: high
+```
+
+Extend `tools/observe_cluster_resources.py` / `make cluster-observe` so the
+published observation names pending unscheduled pods and their requests.
+State Hub's preflight already consumes that shape. Do not treat residual
+millicores as a scheduling guarantee.