fix(runtime): make plugin and box connectors resilient

This commit is contained in:
Junyan Qin
2026-07-21 18:41:22 +08:00
parent 1765c43262
commit 998b76d53a
15 changed files with 699 additions and 236 deletions
+12 -4
View File
@@ -139,7 +139,8 @@ spec:
cpu: "1000m"
# Liveness probe to restart container if it becomes unresponsive
livenessProbe:
tcpSocket:
httpGet:
path: /healthz
port: 5400
initialDelaySeconds: 30
periodSeconds: 10
@@ -147,7 +148,8 @@ spec:
failureThreshold: 3
# Readiness probe to know when container is ready to accept traffic
readinessProbe:
tcpSocket:
httpGet:
path: /healthz
port: 5400
initialDelaySeconds: 10
periodSeconds: 5
@@ -265,14 +267,16 @@ spec:
memory: "1Gi"
cpu: "1000m"
livenessProbe:
tcpSocket:
httpGet:
path: /healthz
port: 5410
initialDelaySeconds: 20
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 3
readinessProbe:
tcpSocket:
httpGet:
path: /healthz
port: 5410
initialDelaySeconds: 10
periodSeconds: 5
@@ -319,6 +323,10 @@ metadata:
app: langbot
spec:
replicas: 1
# Plugin Runtime has a single active LangBot control owner. Recreate avoids
# two LangBot pods fighting over that connection during a rolling update.
strategy:
type: Recreate
selector:
matchLabels:
app: langbot