Release - Lucia Training Platform v1.5

.github/workflows/build-all.yaml

@@ -4,9 +4,8 @@ permissions:
   contents: read
 
 on:
-  push:
-    branches: ["release/*"]
   pull_request:
+    types: [opened, reopened, closed]
     branches: ["release/*"]
   release:
     types: [published]
@@ -15,7 +14,7 @@ on:
       branch:
         description: 'The branch name or tag to run the workflow on'
         required: true
-        default: 'main'
+        default: 'dev'
         type: string
 
 env:
@@ -27,6 +26,7 @@ jobs:
     runs-on: [self-hosted, paicicd]
     timeout-minutes: 120
     environment: auto-test
+    if: github.event_name != 'pull_request' || ( github.event.action == 'opened' || github.event.action == 'reopened' || github.event.pull_request.merged == true)
     container:
       image: ubuntu:latest
       volumes:

.github/workflows/build-deploy-changes.yaml

@@ -5,8 +5,6 @@ permissions:
   contents: read
 
 on:
-  push:
-    branches: [main, dev, "release/*"]
   pull_request:
     branches: [main, dev, "release/*"]
 

contrib/kubespray/script/environment.sh

@@ -46,7 +46,7 @@ echo "Install sshpass"
 sudo apt-get -y install sshpass
 
 echo "Install kubespray's requirements and ansible is included"
-sudo apt-get -y remove python3-cryptography # avoid conflict with pip
+sudo apt-get -y remove python3-cryptography python3-cffi # avoid conflict with pip
 sudo python3 -m pip install -r ${HOME}/pai-deploy/kubespray/requirements.txt
 
 # workaround python3-apt issue

contrib/kubespray/script/requirements.txt

@@ -4,3 +4,4 @@ jinja2==3.1.4
 pyOpenSSL==24.1.0
 requests==2.32.3
 oauthlib==3.3.1
+cffi==2.0.0

docs/LuciaTrainingPlatform/blog/2026-02-06-release-1-5.md

@@ -0,0 +1,39 @@
+---
+slug: release-ltp-v1.5
+title: Releasing Lucia Training Platform v1.5
+author: Lucia Training Platform Team
+tags: [ltp, announcement, release]
+---
+
+We are pleased to announce the official release of **Lucia Training Platform v1.5.0**!
+
+## Lucia Training Platform v1.5.0 Release Notes
+
+This release focuses on platform stability improvements, deployment enhancements, hardware compatibility, and security updates.
+
+## Platform Features & Stability
+- Added feature to track user's historical jobs in non-existing virtual clusters including the job status and logs
+- Support for assigning custom job names
+- Update the workflow trigger conditions to make the workflow triggered and executed only when a pull request targeting main, dev or release/* branch is closed
+
+## Deployment & Hardware Support
+- Fixed kubespray deployment on bare metal when cffi package is installed by package manager
+- Fixed NUMA parsing in job exporter on GB200 hardware
+- Fixed job exporter compatibility issue on ARM nodes
+- Enhanced multi-architecture support across platform components
+
+## Security
+- Updated Kubernetes scheduler version to 1.33.1
+- Updated Go version to 1.24.9 for framework controller, hivedscheduler, and watchdog
+- Updated Node.js packages for alert-handler, job-status-change-notification, rest-server
+- Updated Python packages for cluster local storage, copilot-chat, and dashboard-data-backup
+- Updated RPM packages for database-controller
+- Updated Docker version for webportal-dind
+- Fixed security issues in multiple component dependencies
+- Fixed the module "logger" missing when running DCGM with higher versions
+
+## Storage & Infrastructure
+- Mounted SSH key pairs for cluster local storage
+- Enhanced cluster local storage security and stability
+- Fixed Docker pull problem after Docker version update
+

src/job-exporter/src/Moneo/src/worker/exporters/node_exporter.py

@@ -273,7 +273,7 @@ def get_core_numa_mapping(core_count):
     numa_mapping = {}
     lines = output.split('\n')
     for line in lines:
-        if 'node ' in line and 'cpus' in line:
+        if 'node ' in line and 'cpus' in line and not line.strip().endswith('cpus:'):
             current_numa_domain = int(re.search(r'node (\d+)', line).group(1))
             if ':' in line:
                 cpus_str = line.split(': ')[1].split()

src/rest-server/src/models/v2/job/k8s.js

@@ -23,7 +23,6 @@ const runtimeEnv = require('./runtime-env');
 const launcherConfig = require('@pai/config/launcher');
 const createError = require('@pai/utils/error');
 const protocolSecret = require('@pai/utils/protocolSecret');
-const userModel = require('@pai/models/v2/user');
 const tokenModel = require('@pai/models/token');
 const storageModel = require('@pai/models/v2/storage');
 const logger = require('@pai/config/logger');
@@ -1135,6 +1134,8 @@ const get = async (frameworkName, jobAttemptId) => {
 };
 
 const put = async (frameworkName, config, rawConfig) => {
+  // Lazy load to avoid circular dependency
+  const userModel = require('@pai/models/v2/user');
   const [userName] = frameworkName.split(/~(.+)/);
 
   const virtualCluster =

src/rest-server/src/models/v2/storage.js

@@ -18,7 +18,6 @@
 // module dependencies
 const status = require('statuses');
 const createError = require('@pai/utils/error');
-const user = require('@pai/models/v2/user');
 const secret = require('@pai/models/kubernetes/k8s-secret');
 const kubernetes = require('@pai/models/kubernetes/kubernetes');
 const logger = require('@pai/config/logger');
@@ -178,6 +177,9 @@ const convertVolumeDetail = async (pvc) => {
 };
 
 const list = async (userName, filterDefault = false) => {
+  // Lazy require to avoid circular dependency
+  const user = require('@pai/models/v2/user');
+
   let response;
   if (pvcCache.has('storageList')) {
     logger.info('Read persistant volume claim list from cache');
@@ -247,6 +249,9 @@ const list = async (userName, filterDefault = false) => {
 };
 
 const get = async (storageName, userName) => {
+  // Lazy require to avoid circular dependency
+  const user = require('@pai/models/v2/user');
+
   let response;
   if (pvcCache.has(storageName)) {
     logger.info(`Read persistant volume claim from cache: ${storageName}`);

src/rest-server/src/utils/manager/user/crudK8sSecret.js

@@ -20,7 +20,6 @@ const logger = require('@pai/config/logger');
 const groupModel = require('@pai/models/v2/group');
 const k8sModel = require('@pai/models/kubernetes/kubernetes');
 const { Mutex } = require('async-mutex');
-const { job } = require('@pai/models/v2/job');
 
 const USER_NAMESPACE = process.env.PAI_USER_NAMESPACE || 'pai-user-v2';
 
@@ -44,6 +43,9 @@ const cache = new Map();
 const readMutex = new Mutex();
 
 async function getHistoryVCs(name, grouplist, retrieveFromHistory=true) {
+  // Lazy require to avoid circular dependency
+  const { job } = require('@pai/models/v2/job');
+
   // Retrieve VC list from the user's job history
   let vcsFromJob = [];
   if (retrieveFromHistory) {