From e3d394864d5de4fff0d51bd822eac37ad302bf9c Mon Sep 17 00:00:00 2001
From: Julian Sommer <115516918+juliansommer@users.noreply.github.com>
Date: Wed, 26 Aug 2026 11:33:51 +1000
Subject: [PATCH] fix: propagate KV read errors when releasing an ECS
 reservation

releaseReservation returned nil for every kv.Get error, so a NATS
timeout or connection drop was reported as a successful release and the
stopped task's CPU/memory/GPU capacity leaked on that instance. Narrow
the nil return to jetstream.ErrKeyNotFound, matching the pattern already
used in service.go and task_stop.go, and return anything else.
---
 spinifex/handlers/ecs/instances.go | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/spinifex/handlers/ecs/instances.go b/spinifex/handlers/ecs/instances.go
index 533fdf1eb..e2d6970a5 100644
--- a/spinifex/handlers/ecs/instances.go
+++ b/spinifex/handlers/ecs/instances.go
@@ -3,6 +3,7 @@ package handlers_ecs
 import (
 	"context"
 	"encoding/json"
+	"errors"
 	"log/slog"
 	"slices"
 	"time"
@@ -359,8 +360,11 @@ func (s *Service) recordDeploymentFailure(ctx context.Context, kv jetstream.KeyV
 func (s *Service) releaseReservation(ctx context.Context, kv jetstream.KeyValue, cluster, instanceID, taskID string, cpu, mem, gpu int) error {
 	for range reservePlacementRetries {
 		entry, err := kv.Get(ctx, InstanceKey(cluster, instanceID))
+		if errors.Is(err, jetstream.ErrKeyNotFound) {
+			return nil
+		}
 		if err != nil {
-			return nil //nolint:nilerr // instance gone; nothing to release
+			return err
 		}
 		var rec InstanceRecord
 		if uerr := json.Unmarshal(entry.Value(), &rec); uerr != nil {