From 6df0be81c9a20a52349e683eb4eb7f7181b0575c Mon Sep 17 00:00:00 2001
From: Platform Engineer <platform-engineer@rogi.casa>
Date: Tue, 21 Jul 2026 20:28:12 +0000
Subject: [PATCH] fix(platform): fix high-restart pods - prometheus
 nodeSelector, litellm resources, gitea-runner limits

- Prometheus: change nodeSelector from hardware=high-memory (nonexistent label) to kubernetes.io/arch: amd64
  Fixes OOMKilled cause - pod was being scheduled on wrong nodes.
- litellm-deployment: add resource limits (2Gi/500m requests, 4Gi/2000m limits) + pin image to v1.34.0
  Fixes OOMKilled cause - no resource limits were set.
- gitea-runner: pin image to v0.12.0 from :latest + add resource limits (512Mi/250m requests, 1Gi/500m limits)
  Addresses extreme restart count (281) caused by unbounded memory usage and rolling image updates.
---
 gitea/gitea.yaml                      | 9 ++++++++-
 monitoring/prometheus-deployment.yaml | 5 +++--
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/gitea/gitea.yaml b/gitea/gitea.yaml
index a20e27a..e0feee0 100644
--- a/gitea/gitea.yaml
+++ b/gitea/gitea.yaml
@@ -119,7 +119,14 @@ spec:
         kubernetes.io/arch: arm64
       containers:
       - name: gitea-runner
-        image: vegardit/gitea-act-runner:latest
+        image: vegardit/gitea-act-runner:v0.12.0
+        resources:
+          requests:
+            memory: "512Mi"
+            cpu: "250m"
+          limits:
+            memory: "1Gi"
+            cpu: "500m"
         env:
         - name: GITEA_INSTANCE_URL
           valueFrom:
diff --git a/monitoring/prometheus-deployment.yaml b/monitoring/prometheus-deployment.yaml
index 825ecf1..8f420b6 100644
--- a/monitoring/prometheus-deployment.yaml
+++ b/monitoring/prometheus-deployment.yaml
@@ -15,9 +15,10 @@ spec:
       labels:
         app: prometheus
     spec:
-      # Prevent scheduling on Raspberry Pi due to resource requirements (512Mi-1Gi memory, 500m-1000m CPU)
+      # Target the nucbox (amd64, 24Gi RAM) which is the only node with enough memory for Prometheus.
       nodeSelector:
-        hardware: high-memory
+        kubernetes.io/os: linux
+        kubernetes.io/arch: amd64
       serviceAccountName: prometheus
       containers:
         - name: prometheus