mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-16 22:19:26 +00:00
Some checks failed
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Integration Tests (Replay) / generate-matrix (push) Successful in 3s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 4s
Test Llama Stack Build / generate-matrix (push) Failing after 3s
Test Llama Stack Build / build (push) Has been skipped
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Test llama stack list-deps / generate-matrix (push) Failing after 3s
Test llama stack list-deps / list-deps (push) Has been skipped
API Conformance Tests / check-schema-compatibility (push) Successful in 11s
Python Package Build Test / build (3.13) (push) Successful in 19s
Python Package Build Test / build (3.12) (push) Successful in 23s
Test Llama Stack Build / build-single-provider (push) Successful in 33s
Test llama stack list-deps / show-single-provider (push) Successful in 36s
Test llama stack list-deps / list-deps-from-config (push) Successful in 44s
Vector IO Integration Tests / test-matrix (push) Failing after 57s
Test External API and Providers / test-external (venv) (push) Failing after 1m37s
Unit Tests / unit-tests (3.12) (push) Failing after 1m56s
UI Tests / ui-tests (22) (push) Successful in 2m2s
Unit Tests / unit-tests (3.13) (push) Failing after 2m35s
Pre-commit / pre-commit (22) (push) Successful in 3m16s
Test Llama Stack Build / build-custom-container-distribution (push) Successful in 3m34s
Test Llama Stack Build / build-ubi9-container-distribution (push) Successful in 3m59s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 4m30s
# What does this PR do? the build.yaml is only used in the following ways: 1. list-deps 2. distribution code-gen since `llama stack build` no longer exists, I found myself asking "why do we need two different files for list-deps and run"? Removing the BuildConfig and altering the usage of the DistributionTemplate in llama stack list-deps is the first step in removing the build yaml entirely. Removing the BuildConfig and build.yaml cuts the files users need to maintain in half, and allows us to focus on the stability of _just_ the run.yaml This PR removes the build.yaml, BuildConfig datatype, and its usage throughout the codebase. Users are now expected to point to run.yaml files when running list-deps, and our codebase automatically uses these types now for things like `get_provider_registry`. **Additionally, two renames: `StackRunConfig` -> `StackConfig` and `run.yaml` -> `config.yaml`.** The build.yaml made sense for when we were managing the build process for the user and actually _producing_ a run.yaml _from_ the build.yaml, but now that we are simply just getting the provider registry and listing the deps, switching to config.yaml simplifies the scope here greatly. ## Test Plan existing list-deps usage should work in the tests. --------- Signed-off-by: Charlie Doern <cdoern@redhat.com>
176 lines
6.9 KiB
YAML
176 lines
6.9 KiB
YAML
name: Integration Auth Tests
|
|
|
|
run-name: Run the integration test suite with Kubernetes authentication
|
|
|
|
on:
|
|
push:
|
|
branches:
|
|
- main
|
|
- 'release-[0-9]+.[0-9]+.x'
|
|
pull_request:
|
|
branches:
|
|
- main
|
|
- 'release-[0-9]+.[0-9]+.x'
|
|
paths:
|
|
- 'distributions/**'
|
|
- 'src/llama_stack/**'
|
|
- '!src/llama_stack_ui/**'
|
|
- 'tests/integration/**'
|
|
- 'uv.lock'
|
|
- 'pyproject.toml'
|
|
- 'requirements.txt'
|
|
- '.github/workflows/integration-auth-tests.yml' # This workflow
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
test-matrix:
|
|
runs-on: ubuntu-latest
|
|
strategy:
|
|
matrix:
|
|
auth-provider: [oauth2_token]
|
|
fail-fast: false # we want to run all tests regardless of failure
|
|
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
|
|
|
|
- name: Install dependencies
|
|
uses: ./.github/actions/setup-runner
|
|
|
|
- name: Install minikube
|
|
if: ${{ matrix.auth-provider == 'kubernetes' }}
|
|
uses: medyagh/setup-minikube@e3c7f79eb1e997eabccc536a6cf318a2b0fe19d9 # v0.0.20
|
|
|
|
- name: Start minikube
|
|
if: ${{ matrix.auth-provider == 'oauth2_token' }}
|
|
run: |
|
|
minikube start
|
|
kubectl get pods -A
|
|
|
|
- name: Configure Kube Auth
|
|
if: ${{ matrix.auth-provider == 'oauth2_token' }}
|
|
run: |
|
|
kubectl create namespace llama-stack
|
|
kubectl create serviceaccount llama-stack-auth -n llama-stack
|
|
kubectl create token llama-stack-auth -n llama-stack > llama-stack-auth-token
|
|
|
|
- name: Set Kubernetes Config
|
|
if: ${{ matrix.auth-provider == 'oauth2_token' }}
|
|
run: |
|
|
echo "KUBERNETES_API_SERVER_URL=$(kubectl get --raw /.well-known/openid-configuration| jq -r .jwks_uri)" >> $GITHUB_ENV
|
|
echo "KUBERNETES_CA_CERT_PATH=$(kubectl config view --minify -o jsonpath='{.clusters[0].cluster.certificate-authority}')" >> $GITHUB_ENV
|
|
echo "KUBERNETES_ISSUER=$(kubectl get --raw /.well-known/openid-configuration| jq -r .issuer)" >> $GITHUB_ENV
|
|
echo "KUBERNETES_AUDIENCE=$(kubectl create token llama-stack-auth -n llama-stack --duration=1h | cut -d. -f2 | base64 -d | jq -r '.aud[0]')" >> $GITHUB_ENV
|
|
echo "TOKEN=$(cat llama-stack-auth-token)" >> $GITHUB_ENV
|
|
|
|
- name: Set Kube Auth Config and run server
|
|
env:
|
|
INFERENCE_MODEL: "meta-llama/Llama-3.2-3B-Instruct"
|
|
if: ${{ matrix.auth-provider == 'oauth2_token' }}
|
|
run: |
|
|
run_dir=$(mktemp -d)
|
|
cat <<EOF > $run_dir/config.yaml
|
|
version: '2'
|
|
image_name: kube
|
|
apis: []
|
|
providers: {}
|
|
storage:
|
|
backends:
|
|
kv_default:
|
|
type: kv_sqlite
|
|
db_path: $run_dir/kvstore.db
|
|
sql_default:
|
|
type: sql_sqlite
|
|
db_path: $run_dir/sql_store.db
|
|
stores:
|
|
metadata:
|
|
namespace: registry
|
|
backend: kv_default
|
|
inference:
|
|
table_name: inference_store
|
|
backend: sql_default
|
|
conversations:
|
|
table_name: openai_conversations
|
|
backend: sql_default
|
|
prompts:
|
|
namespace: prompts
|
|
backend: kv_default
|
|
server:
|
|
port: 8321
|
|
EOF
|
|
yq eval '.server.auth.provider_config.type = "${{ matrix.auth-provider }}"' -i $run_dir/config.yaml
|
|
yq eval '.server.auth.provider_config.tls_cafile = "${{ env.KUBERNETES_CA_CERT_PATH }}"' -i $run_dir/config.yaml
|
|
yq eval '.server.auth.provider_config.issuer = "${{ env.KUBERNETES_ISSUER }}"' -i $run_dir/config.yaml
|
|
yq eval '.server.auth.provider_config.audience = "${{ env.KUBERNETES_AUDIENCE }}"' -i $run_dir/config.yaml
|
|
yq eval '.server.auth.provider_config.jwks.uri = "${{ env.KUBERNETES_API_SERVER_URL }}"' -i $run_dir/config.yaml
|
|
yq eval '.server.auth.provider_config.jwks.token = "${{ env.TOKEN }}"' -i $run_dir/config.yaml
|
|
cat $run_dir/config.yaml
|
|
|
|
# avoid line breaks in the server log, especially because we grep it below.
|
|
export LLAMA_STACK_LOG_WIDTH=200
|
|
nohup uv run llama stack run $run_dir/config.yaml > server.log 2>&1 &
|
|
|
|
- name: Wait for Llama Stack server to be ready
|
|
run: |
|
|
echo "Waiting for Llama Stack server..."
|
|
for i in {1..30}; do
|
|
# Note: /v1/health does not require authentication
|
|
if curl -s -L http://localhost:8321/v1/health | grep -q "OK"; then
|
|
echo "Llama Stack server is up!"
|
|
if grep -q "Enabling authentication with provider: ${{ matrix.auth-provider }}" server.log; then
|
|
echo "Llama Stack server is configured to use ${{ matrix.auth-provider }} auth"
|
|
exit 0
|
|
else
|
|
echo "Llama Stack server is not configured to use ${{ matrix.auth-provider }} auth"
|
|
cat server.log
|
|
exit 1
|
|
fi
|
|
fi
|
|
sleep 1
|
|
done
|
|
echo "Llama Stack server failed to start"
|
|
cat server.log
|
|
exit 1
|
|
|
|
- name: Test auth
|
|
run: |
|
|
# Function to test API endpoint with authentication
|
|
# Usage: test_endpoint <curl_args> <user_token_file> <expected_status> [output_file]
|
|
test_endpoint() {
|
|
local curl_args="$1"
|
|
local user_token_file=$2
|
|
local expected_status=$3
|
|
local output_file=${4:-/dev/null}
|
|
|
|
local status
|
|
local extra_curl_args=(-s -L -o "$output_file" -w "%{http_code}")
|
|
|
|
if [ "$user_token_file" != "none" ]; then
|
|
extra_curl_args+=(-H "Authorization: Bearer $(cat $user_token_file)")
|
|
fi
|
|
|
|
set -x
|
|
status=$(curl $curl_args "${extra_curl_args[@]}")
|
|
set +x
|
|
|
|
if [ "$status" = "$expected_status" ]; then
|
|
echo " ✓ Status: $status (expected $expected_status)"
|
|
return 0
|
|
else
|
|
echo " ✗ Status: $status (expected $expected_status)"
|
|
exit 1
|
|
fi
|
|
}
|
|
|
|
echo "Testing /v1/version without token (should succeed)..."
|
|
test_endpoint "http://127.0.0.1:8321/v1/version" "none" "200" || exit 1
|
|
|
|
echo "Testing /v1/providers without token (should fail with 401)..."
|
|
test_endpoint "http://127.0.0.1:8321/v1/providers" "none" "401" || exit 1
|
|
|
|
echo "Testing /v1/providers with valid token (should succeed)..."
|
|
test_endpoint "http://127.0.0.1:8321/v1/providers" "llama-stack-auth-token" "200" "providers.json" || exit 1
|
|
cat providers.json | jq . > /dev/null && echo " ✓ Valid JSON response"
|