a cap-only lease reported as already expired (v0.4.35)

Found by exercising the new ceiling against a live orchestrator:

    max_pods=128  effective_max_pods=8  client_max_pods=8
    client_pods=0  client_lease_expires_in_s=0

The lease had 1800 s left and was the reason the fleet had stopped
growing at 8. `client_lease_expires_in_s` was gated on the FLOOR, which
is 0 for a cap-only lease -- "grow no further than 8, hold nothing warm",
which is what a client with a long tail of work asks for. It now reports
whichever half of the lease lasts longer.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KnfkxBpcZ1v6ypRFFyhrVM

codai/__init__.py

@@ -16,7 +16,7 @@
 
 # Canonical product version for CoderAI — single source of truth. Both the API
 # metadata and the admin web UI read from here.
-__version__ = "0.4.34"
+__version__ = "0.4.35"
 __tagline__ = "Complete orchestration, distribution and escalation of remotizable advanced inference."
 
 # Configure the CUDA caching allocator BEFORE torch is imported anywhere.

codai/api/runpod_worker.py

@@ -5805,8 +5805,15 @@ def pools_schedule_status() -> list:
             # The client lease, so a bill nobody expected has a visible cause.
             "client_scale_allowed": bool(getattr(cfg, "allow_client_scale", False)),
             "client_pods": pool.client_floor(),
+            # Whichever half of the lease lasts longer. Gated on the FLOOR
+            # alone, a cap-only lease -- "grow no further than 8, hold nothing
+            # warm" -- reported as already expired while it was still the
+            # reason the fleet had stopped growing.
             "client_lease_expires_in_s": max(
-                0, int(pool._client_floor_until - time.time())) if pool.client_floor() else 0,
+                0,
+                int(pool._client_floor_until - time.time()) if pool.client_floor() else 0,
+                int(getattr(pool, "_client_cap_until", 0.0) - time.time())
+                if pool.client_cap() else 0),
             # What the lease narrowed the card choice to, if anything: a pod on
             # an unexpected card should have a visible cause too, not only a
             # bill.

tests/test_runpod_client_pod_ceiling.py

@@ -252,6 +252,21 @@ def test_set_client_pods_forwards_it_for_both_ways_of_naming_a_pool():
         "both the live-pool branch and the by-model branch must pass it")
 
 
+def test_a_cap_only_lease_does_not_report_as_expired():
+    """Observed live on 2026-10-19: a lease with 1800 s of cap left reported
+    `client_lease_expires_in_s: 0`, because the field was gated on the FLOOR.
+    A fleet that stopped growing must say why, and for how much longer."""
+    import time as _t
+    p = _pool(max_pods=128, ttl=1800)
+    p.set_client_floor(0, max_pods=8)
+    left = max(0,
+               int(p._client_floor_until - _t.time()) if p.client_floor() else 0,
+               int(p._client_cap_until - _t.time()) if p.client_cap() else 0)
+    assert left > 1700, left
+    src = open("codai/api/runpod_worker.py").read()
+    assert 'if pool.client_cap() else 0)' in src
+
+
 def test_the_status_surface_reports_the_ceiling_in_force():
     """A fleet that stopped growing short of max_pods must say why."""
     src = inspect_source = open("codai/api/runpod_worker.py").read()