[python] fix last token fetch logic #5133

	name: Continuous

	on:
	pull_request:
	paths-ignore:
	- "**.md"
	- "**.ipynb"
	- "**.json"
	- "**.html"
	- "**.js"
	- "**.css"
	workflow_dispatch:

	jobs:
	build:
	runs-on: ${{ matrix.os }}
	strategy:
	matrix:
	os: [ubuntu-latest, windows-latest, macos-latest]
	include:
	- os: ubuntu-latest
	format: true
	steps:
	- uses: actions/checkout@v4
	- name: Set up JDK 17
	uses: actions/setup-java@v4
	with:
	distribution: 'corretto'
	java-version: 17
	- name: Set up Python3
	uses: actions/setup-python@v5
	with:
	python-version: '3.11'
	- name: install Python Dependencies
	run: pip3 install "numpy<2" yapf
	# Enable gradle cache: https://github.com/actions/cache/blob/master/examples.md#java---gradle
	- uses: actions/cache@v4
	with:
	path: ~/.gradle/caches
	key: ${{ runner.os }}-gradle-${{ hashFiles('*/.gradle*') }}
	restore-keys: \|
	${{ runner.os }}-gradle-
	- name: Test repo formatting
	if: ${{ matrix.format }}
	run: ./gradlew verifyPython
	- name: Build with Gradle
	run: ./gradlew --refresh-dependencies build :jacoco:testCodeCoverageReport --stacktrace
	- name: Upload test results
	uses: actions/upload-artifact@v4
	if: always()
	with:
	name: serving-${{ matrix.os }}
	path: \|
	awscurl/build/reports
	benchmark/build/reports
	serving/build/reports
	wlm/build/reports
	engines/python/build/reports

Provide feedback