llama-stack-mirror/.github/workflows/integration-auth-tests.yml
Ashwin Bharambe 39f33f7f12
feat(cherry-pick): fixes for 0.3.1 release (#3998)
## Summary

Cherry-picks 5 critical fixes from main to the release-0.3.x branch for
the v0.3.1 release, plus CI workflow updates.

**Note**: This recreates the cherry-picks from the closed PR #3991, now
targeting the renamed `release-0.3.x` branch (previously
`release-0.3.x-maint`).

## Commits

1. **2c56a8560** - fix(context): prevent provider data leak between
streaming requests (#3924)
- **CRITICAL SECURITY FIX**: Prevents provider credentials from leaking
between requests
   - Fixed import path for 0.3.0 compatibility

2. **ddd32b187** - fix(inference): enable routing of models with
provider_data alone (#3928)
   - Enables routing for fully qualified model IDs with provider_data
   - Resolved merge conflicts, adapted for 0.3.0 structure

3. **f7c2973aa** - fix: Avoid BadRequestError due to invalid max_tokens
(#3667)
- Fixes failures with Gemini and other providers that reject
max_tokens=0
   - Non-breaking API change

4. **d7f9da616** - fix(responses): sync conversation before yielding
terminal events in streaming (#3888)
- Ensures conversation sync executes even when streaming consumers break
early

5. **0ffa8658b** - fix(logging): ensure logs go to stderr, loggers obey
levels (#3885)
   - Fixes logging infrastructure

6. **75b49cb3c** - ci: support release branches and match client branch
(#3990)
   - Updates CI workflows to support release-X.Y.x branches
- Matches client branch from llama-stack-client-python for release
testing
   - Fixes artifact name collisions

## Adaptations for 0.3.0

- Fixed import paths: `llama_stack.core.telemetry.tracing` →
`llama_stack.providers.utils.telemetry.tracing`
- Fixed import paths: `llama_stack.core.telemetry.telemetry` →
`llama_stack.apis.telemetry`
- Changed `self.telemetry_enabled` → `self.telemetry` (0.3.0 attribute
name)
- Removed `rerank()` method that doesn't exist in 0.3.0

## Testing

All imports verified and tests should pass once CI is set up.
2025-10-30 21:51:42 -07:00

160 lines
6.3 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/**'
- 'llama_stack/**'
- '!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@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
- 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/run.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: $run_dir/sql_store.db
stores:
metadata:
namespace: registry
backend: kv_default
inference:
table_name: inference_store
backend: sql_default
conversations:
table_name: openai_conversations
backend: sql_default
server:
port: 8321
EOF
yq eval '.server.auth.provider_config.type = "${{ matrix.auth-provider }}"' -i $run_dir/run.yaml
yq eval '.server.auth.provider_config.tls_cafile = "${{ env.KUBERNETES_CA_CERT_PATH }}"' -i $run_dir/run.yaml
yq eval '.server.auth.provider_config.issuer = "${{ env.KUBERNETES_ISSUER }}"' -i $run_dir/run.yaml
yq eval '.server.auth.provider_config.audience = "${{ env.KUBERNETES_AUDIENCE }}"' -i $run_dir/run.yaml
yq eval '.server.auth.provider_config.jwks.uri = "${{ env.KUBERNETES_API_SERVER_URL }}"' -i $run_dir/run.yaml
yq eval '.server.auth.provider_config.jwks.token = "${{ env.TOKEN }}"' -i $run_dir/run.yaml
cat $run_dir/run.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/run.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: |
echo "Testing /v1/version without token (should succeed)..."
if curl -s -L -o /dev/null -w "%{http_code}" http://127.0.0.1:8321/v1/version | grep -q "200"; then
echo "/v1/version accessible without token (200)"
else
echo "/v1/version returned non-200 status without token"
exit 1
fi
echo "Testing /v1/providers without token (should fail with 401)..."
if curl -s -L -o /dev/null -w "%{http_code}" http://127.0.0.1:8321/v1/providers | grep -q "401"; then
echo "/v1/providers blocked without token (401)"
else
echo "/v1/providers did not return 401 without token"
exit 1
fi
echo "Testing /v1/providers with valid token (should succeed)..."
curl -s -L -H "Authorization: Bearer $(cat llama-stack-auth-token)" http://127.0.0.1:8321/v1/providers | jq
if [ $? -eq 0 ]; then
echo "/v1/providers accessible with valid token"
else
echo "/v1/providers failed with valid token"
exit 1
fi